system

Abstract

Provide a system. A method for collecting usage data from a terminal; means for storing collected usage data; A means of analyzing accumulated usage data and selecting the optimal service plan for each customer; a means for notifying the customer of the selected service plan; a means to change the service plan with customer approval; A system including:

Description

[Technical Field]

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

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

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

[0004] In today's world, it is extremely important to provide optimal pricing plans to mobile subscribers with diverse needs. However, analyzing usage patterns and selecting the appropriate plan is a complicated and time-consuming process for customers, and many customers are unable to find the plan that best suits them. As a result, customers end up paying excessive fees and suffer disadvantages. Furthermore, managing a variety of pricing plans is complex for service providers, making it difficult to provide efficient services. Therefore, there is a need to automatically provide the optimal pricing plan based on customer usage patterns and improve customer satisfaction. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. A means for collecting usage data from a terminal is provided, thereby collecting data such as the customer's communication volume, call duration, and SMS usage volume. A means for storing the collected data is provided, thereby retaining past usage information. A means for analyzing the stored data and identifying the customer's usage patterns using a machine learning algorithm is provided. The present invention further includes a means for selecting an optimal service plan for the customer based on the analysis results and notifying the customer of the plan. A means for notifying the customer of the selected service plan details and the reasons for the selection is also provided. Finally, a system is provided that includes a means for automatically changing the service plan if the customer approves, thereby enabling the optimal rate plan to be provided to the customer simply and effectively. This eliminates the need for customers to select the optimal rate plan and allows them to use services without paying excessive fees.

[0006] "Device" means a communication device used by a mobile subscriber and is the means by which communication services such as data, voice, and SMS are accessed.

[0007] "Usage Data" refers to information such as data traffic, call minutes, and SMS usage generated when a customer uses mobile communications services.

[0008] "Collection means" refers to the processes and technical mechanisms for collecting usage data from devices, including the ability to obtain data accurately and regularly.

[0009] "Storage means" refers to the process of using a database or storage device to store collected usage data, including the ability to securely retain data for an extended period of time.

[0010] "Means of analysis" refers to the process of implementing algorithms and statistical methods to analyze customer usage patterns based on accumulated usage data.

[0011] A "machine learning algorithm" is an algorithm that makes predictions and classifications by learning patterns and rules from data, and automatically analyzes and predicts data.

[0012] "Means for selecting a service plan" refers to the process and technical mechanisms for automatically selecting the optimal pricing plan for a customer based on the analysis results.

[0013] "Notification means" means the processes and techniques used to communicate information about the selected service plan to the customer, including the generation and transmission of notification messages.

[0014] "Means for changing service plans upon approval" means the process and technical mechanisms for obtaining approval from customers and automatically updating rate plans based on that approval. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The system of the present invention automatically provides mobile subscribers with the most appropriate rate plan based on their usage. The system collects usage data from the terminal, stores and analyzes the collected data, selects the most appropriate rate plan, and notifies the customer. It also has the ability to automatically change plans with the customer's approval.

[0037] Data collection and storage

[0038] The system first collects usage data from the device. The device has the ability to record information such as data traffic, call time, and SMS usage, and this data is periodically sent to the server. The server stores the received data in a database. This allows for detailed records of each customer's usage status to be used for later analysis.

[0039] Data analysis

[0040] The server uses machine learning algorithms to analyze the accumulated data. Specifically, it analyzes customer usage patterns based on past usage data and predicts future usage. Based on the results of this analysis, it selects the optimal pricing plan for the customer. For example, if the average data usage over the past three months is within a certain range, it will propose the optimal data plan based on that.

[0041] Plan presentation and notification

[0042] The server notifies the terminal of the selected optimal rate plan. The notification message includes details of the proposed plan and the reasons for it, providing information to the customer in a transparent manner. The terminal receives this notification and displays it to the user.

[0043] Change plan

[0044] When the user receives the notification, they review the proposed plan and choose whether to accept it. If the user accepts the new plan, the device sends that information to the server. The server receives this approval information and updates the customer's settings, so the new pricing plan is automatically applied.

[0045] Specific examples

[0046] User C's scenario

[0047] 1. Data Collection

[0048] Device: User C's device records this month's data usage of 15GB, talk time of 120 minutes, and SMS usage of 5 messages.

[0049] Server: Stores data collected from devices in a database. This data is updated every 5 minutes.

[0050] 2. Data analysis

[0051] Server: Based on usage data from the past three months, it is analyzed that User C's average data usage is 16GB, talk time is 110 minutes, and SMS usage is 4. It also uses a machine learning algorithm to predict future usage.

[0052] 3. Plan presentation and notification

[0053] Server: Based on the analysis results, it determines that the "20GB data plan + 120 minutes call plan" is optimal. It generates a notification message and sends it to User C's device.

[0054] Device: Receives and displays a notification to the user, detailing the proposed plan and explaining the reasons for it.

[0055] 4. Change of plan

[0056] User: Check the notification and accept the proposed plan by selecting "Change" from the device settings screen.

[0057] Terminal: Sends authorization information to the server.

[0058] Server: Receives the approval information and updates User C's settings. Notifies the user that the new pricing plan has been applied.

[0059] In this way, the present invention can improve customer satisfaction by automatically selecting the most suitable rate plan based on the customer's usage status and providing it in real time.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] Device: Records usage data. When a user uses a mobile phone, the device records information such as data traffic, call duration, and number of SMS sent. This data is set to be updated periodically.

[0063] Step 2:

[0064] Device: Sends recorded usage data to the server. Data is transferred to the server at specific intervals (e.g., every 5 minutes). Data transmission uses encryption technology to ensure secure communication.

[0065] Step 3:

[0066] Server: Stores the received usage data in a database. Organizes the data for each customer and stores it for future analysis.

[0067] Step 4:

[0068] Server: Periodically analyzes the accumulated data. Machine learning algorithms are used to identify each customer's usage patterns based on past usage data. For example, the average data usage, call minutes, and SMS usage over the past three months are calculated.

[0069] Step 5:

[0070] Server: Based on the analysis results, the server selects the most suitable pricing plan for the customer. It considers usage data patterns and selects the most cost-effective plan from the list of plans.

[0071] Step 6:

[0072] Server: After selecting the best pricing plan, generate a notification message containing details of the recommended plan and the reasons for it.

[0073] Step 7:

[0074] Server: The generated notification message is sent to the client's terminal. The data is transferred in real time, and the user is notified immediately.

[0075] Step 8:

[0076] Device: Receives a notification and displays it to the user, who can see the plan details and reasons.

[0077] Step 9:

[0078] User: Check the notified plan and decide whether to accept it. If you accept it, select "Change" on the device settings screen.

[0079] Step 10:

[0080] Terminal: Sends the user's selection information to the server. A request is sent to the server requesting the application of the new plan.

[0081] Step 11:

[0082] Server: Updates the customer's subscription information based on the received request. The new pricing plan is applied immediately.

[0083] Step 12:

[0084] Server: Notifies the customer that the plan change was successful. Sends a notification message to the device to let the user know that the change is complete.

[0085] Step 13:

[0086] Device: Receives notification and displays to the user that the plan change was successful.

[0087] This detailed process flow allows customers to easily and quickly select and apply the rate plan that best suits their usage situation.

[0088] Example 1

[0089] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0090] This invention relates to a system that automatically provides mobile subscribers with the most appropriate rate plan based on their usage. Conventional methods involve manually collecting and analyzing usage data, making it difficult to provide customers with the most appropriate plan in real time. For this reason, there has been a need for a method to quickly and effectively provide rate plans that meet customer needs.

[0091] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0092] In this invention, the server includes means for collecting usage data from the terminal, means for storing the collected usage data, means for analyzing the stored usage data using a machine learning algorithm and selecting an optimal service plan for the customer, means for sending a notification to the customer including details of the selected service plan and the reasons for the selection, and means for automatically changing the service plan with the customer's approval. This makes it possible to provide an optimal rate plan in real time based on the customer's usage status and improve customer satisfaction.

[0093] A "terminal" is an electronic device used by a user that has the function of collecting usage data such as data communication, calls, and SMS, and communicating with a server.

[0094] "Usage data" refers to information such as data usage, call time, and SMS usage when a user uses a mobile service.

[0095] A "server" is a central processing unit that receives, stores, and analyzes data sent from terminals.

[0096] A "machine learning algorithm" is an algorithm that learns from past data and predicts future data and patterns.

[0097] "Notification" is the act of sending a server-generated message to a terminal to provide information to a user.

[0098] "Customer Approval" refers to the User receiving the notification reviewing the proposed service plan and taking the action of consenting or rejecting it.

[0099] "Service Plan" refers to the pricing structure and terms of use offered to a mobile subscriber, including data volume, talk time, number of SMS sent, etc.

[0100] "Automatically change" refers to the server programmatically updating the service plan without manual intervention after obtaining user approval.

[0101] The system of the present invention automatically provides the most suitable rate plan to a mobile subscriber based on their usage. The system collects usage data from the terminal, stores and analyzes the collected data on a server, selects the most suitable rate plan, and notifies the customer. Furthermore, the system also has the function of automatically changing plans with the customer's approval.

[0102] Hardware and software used

[0103] This system mainly uses the following hardware and software:

[0104] 1. Terminal

[0105] Hardware: Mobile devices such as smartphones and tablets.

[0106] Software: Applications for collecting usage data.

[0107] 2. Server

[0108] Hardware: Database servers, compute servers for running machine learning models.

[0109] Software: Database management systems, machine learning algorithms, notification services.

[0110] Specific processing flow

[0111] Data collection and storage

[0112] The device collects usage data in real time, such as the user's data traffic, call time, and SMS usage. This usage data is stored in the device's internal storage and periodically (for example, every five minutes) sent to the server. The server stores the received data in a database, recording each customer's usage status in detail. This data can then be used for later data analysis.

[0113] Data analysis

[0114] The server analyzes the accumulated usage data using machine learning algorithms. Based on past usage data, the server analyzes the customer's usage patterns and predicts future usage. For example, if the average data usage over the past three months is within a certain range, the server can suggest the optimal data plan based on that prediction. The machine learning models used are often run on cloud platforms.

[0115] Plan presentation and notification

[0116] The server selects the optimal pricing plan for the customer based on the results of the data analysis. It generates a notification message containing details of the selected pricing plan and the reasons for it, and sends it to the customer's device. The device receives this notification and displays it to the user. The notification clearly explains how the change in pricing plan will benefit the customer.

[0117] Change plan

[0118] The user checks the notification on the device and chooses whether to accept the proposed pricing plan. If accepted, the device sends the information to the server. The server receives the approval information and updates the customer's account settings to the new pricing plan. The new pricing plan is then immediately applied, and the server notifies the device again.

[0119] Specific examples

[0120] User C's scenario

[0121] 1. Data Collection

[0122] Device: User C's device records this month's data usage of 15GB, talk time of 120 minutes, and SMS usage of 5 messages.

[0123] Server: Stores data collected from devices in a database. This data is updated every 5 minutes.

[0124] 2. Data analysis

[0125] Server: Based on usage data from the past three months, it is analyzed that User C's average data usage is 16GB, talk time is 110 minutes, and SMS usage is 4. It also uses a machine learning algorithm to predict future usage.

[0126] 3. Plan presentation and notification

[0127] Server: Based on the analysis results, it determines that the "20GB data plan + 120 minutes call plan" is optimal. It generates a notification message and sends it to User C's device.

[0128] Device: Receives and displays a notification to the user, detailing the proposed plan and explaining the reasons for it.

[0129] 4. Change of plan

[0130] User: Check the notification and accept the proposed plan by selecting "Change" from the device settings screen.

[0131] Terminal: Sends authorization information to the server.

[0132] Server: Receives the approval information and updates User C's settings. Notifies the user that the new pricing plan has been applied.

[0133] Prompt Sentence Examples

[0134] "Please analyze and suggest the optimal pricing plan for User C based on usage data from the past three months."

[0135] As described above, the present invention can improve customer satisfaction by automatically selecting an optimal rate plan based on the customer's usage status and providing it in real time.

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

[0137] Step 1:

[0138] Data collection

[0139] Input: User data usage, call time, SMS usage

[0140] How it works: The device collects usage data in real time and stores it in storage.

[0141] Example: A device records the current amount of data traffic and updates it every 5 minutes.

[0142] Output: The latest usage data is saved on the device.

[0143] Step 2:

[0144] Data transmission

[0145] Input: Usage data stored on the device

[0146] How it works: The device periodically sends collected data to a server. The data is encrypted and transmitted securely.

[0147] Example: A device sends the latest usage data to a server every 5 minutes.

[0148] Output: Usage data arrives at the server and is received.

[0149] Step 3:

[0150] Data accumulation

[0151] Input: Usage data sent to the server

[0152] How it works: The server stores the data it receives in a database, organizing it by customer for quick access and analysis later.

[0153] Example: The server adds user C's data usage of 15 GB, talk time of 120 minutes, and SMS usage of 5 to the database.

[0154] Output: The latest usage data is saved in the database.

[0155] Step 4:

[0156] Data analysis

[0157] Input: Usage data stored in the database

[0158] How it works: The server analyzes the data using machine learning algorithms, analyzing customer usage patterns based on past data and predicting future usage.

[0159] Example: The server analyzes usage data from the past three months and predicts that User C's average data usage is 16 GB, talk time is 110 minutes, and SMS usage is 4.

[0160] Output: The analysis results in customer usage patterns and predictions of future usage.

[0161] Step 5:

[0162] Plan selection

[0163] Input: Results of data analysis

[0164] How it works: The server selects the optimal pricing plan for the customer based on the analysis results. This selection is made by comparing the usage forecast with the terms of existing pricing plans.

[0165] Example: The server determines that the "20GB data plan + 120 minutes call plan" is optimal for user C.

[0166] Output: Detailed information on the best pricing plan.

[0167] Step 6:

[0168] Plan Notification

[0169] Input: Details of the best rate plan

[0170] Operation: The server generates a notification message containing details of the selected rate plan and the reason for the selection, and sends it to the terminal.

[0171] Example: The server generates a message detailing the "20GB data plan + 120 minutes call plan" and the reason for the plan, and sends it to User C's device.

[0172] Output: A notification message arrives on the terminal.

[0173] Step 7:

[0174] User Authorization

[0175] Input: Notification message

[0176] How it works: The user sees the notification on their device and chooses whether to accept the proposed pricing plan.

[0177] Example: User C checks the notification and presses the "Change" button on the device to approve the proposed plan.

[0178] Output: The authorization information is entered into the terminal.

[0179] Step 8:

[0180] Change plan

[0181] Input: User authorization information

[0182] Operation: The device sends the authorization information to the server, which updates the customer's settings with the new rate plan, which then applies the new rate plan.

[0183] Example: The server receives user C's authorization information and updates user C's settings to "20GB data plan + 120 minutes call plan."

[0184] Output: The new pricing plan is applied and you are notified.

[0185] (Application example 1)

[0186] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0187] With conventional electronic payment services, users must analyze their own usage data and select the appropriate plan to suit their usage, which is time-consuming and laborious. Furthermore, users may not be able to determine the appropriate plan and end up paying excessive fees. Furthermore, there is a lack of a mechanism for flexibly changing plans based on the user's lifestyle and frequency of use, resulting in low user satisfaction.

[0188] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0189] In this invention, the server includes means for collecting usage data from the terminal, means for storing the collected usage data, means for analyzing the stored usage data and selecting an optimal service plan for the customer, means for notifying the customer of the selected service plan, means for changing the service plan with the customer's approval, means for identifying usage data for the electronic payment service and using a machine learning algorithm to predict an optimal rate plan based on the usage data, and means for notifying the user terminal of the selected rate plan and obtaining approval. This makes it possible to automatically propose an optimal rate plan based on the user's usage data and flexibly change the plan with approval.

[0190] "Terminal" refers to a computing device such as a mobile phone, smartphone, or tablet that an investor uses on a daily basis.

[0191] "Usage data" refers to information such as the amount of data used, the amount used, and the number of transactions when a user uses an electronic payment service.

[0192] "Storage means" refers to a recording device or database for storing collected usage data.

[0193] "Analytical means" refers to machine learning algorithms and analytics software that evaluate collected and stored usage data and extract patterns.

[0194] "Optimal service plan" refers to the most cost-effective plan selected based on the user's past and predicted usage.

[0195] "Means of notification" refers to the messaging system or application functionality used to communicate information about the selected service plan to the user.

[0196] "Means for changing service plans with approval" means the system's ability to automatically update service plans after obtaining user consent.

[0197] "Electronic Payment Services" refers to payment platforms and systems that enable online or offline payments, purchases and transactions.

[0198] A "machine learning algorithm" refers to a mathematical model or computational method for learning patterns from past data and predicting or classifying future data.

[0199] "User terminal" refers to a computing device (smartphone, tablet, etc.) operated by a user when using an electronic payment service.

[0200] Data collection

[0201] The server first collects usage data from the device. This data includes communication volume, usage amount, number of transactions, etc. This collection process is carried out periodically through the device's API (Application Programming Interface). Specifically, it collects usage information from electronic payment services accessed by smartphones and tablet devices.

[0202] Data accumulation

[0203] The collected usage data is stored in a database on the server. The database is constructed using SQLite, and the collected data is saved in the database. This data storage process records detailed usage information for each user.

[0204] Data analysis

[0205] The server uses a machine learning algorithm to analyze the accumulated data. Specifically, it uses a linear regression model from scikit-learn. It analyzes customer usage patterns based on past usage data and predicts future usage. During this process, it extracts and analyzes features from the usage data. Based on the results of this analysis, it selects the optimal pricing plan for each user.

[0206] Plan presentation and notification

[0207] After the optimal plan is selected, the server notifies the user via a messaging system, and the user receives details of the proposed plan and the reasons for its selection via an application on their smartphone or tablet. The notification message also includes an option for the user to approve the plan.

[0208] Change plan

[0209] If the user approves the proposed plan, the device sends the approval information to the server. The server automatically updates the pricing plan based on that information. This update process uses an API to appropriately change the database settings. Once the change is complete, the server notifies the user again, informing them that the new pricing plan has been applied.

[0210] Specific examples

[0211] User A's scenario

[0212] User A's device records a monthly transaction amount of 5,000 yen and 50 transactions. The server stores this information in a database and analyzes it using a linear regression model in scikit-learn. As a result, it determines that a "10% cashback plan for users who spend more than 5,000 yen per month" is optimal for User A. The server notifies User A's smartphone of the details of this plan and the reasons for it. When User A approves through the application, the server automatically changes the pricing plan and notifies User A again.

[0213] Prompt Sentence Examples

[0214] "Please suggest the best plan for a monthly electronic payment amount of 5,000 yen or more and 50 or more transactions."

[0215] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0216] Step 1:

[0217] The server collects usage data from the device. Specifically, it periodically obtains data such as communication volume, usage amount, and number of transactions through the API of the electronic payment service accessed by the smartphone or tablet device. The input is the API request from the device, and the output is the obtained usage data. This data is often received in JSON format.

[0218] Step 2:

[0219] The server stores the collected usage data in a database. Specifically, it parses the acquired JSON data and stores it in a database such as SQLite. At this time, the data is converted into an appropriate format and stored as a record for each customer. The input is the collected usage data, and the output is the data stored in the database.

[0220] Step 3:

[0221] The server analyzes the accumulated usage data. Specifically, it reads past usage data stored in the database and analyzes it using a linear regression model from scikit-learn. During the analysis, transaction amounts and number of transactions are used as features to predict future usage patterns. The input is the usage data obtained from the database, and the output is the analysis results (predicted usage patterns).

[0222] Step 4:

[0223] The server selects the optimal pricing plan. Based on the analysis results obtained by the machine learning algorithm, it determines the optimal plan for each user. Specifically, it compares the analysis results with existing pricing plans and selects the most appropriate plan. The input is the analysis results and existing pricing plan information, and the output is the selected optimal pricing plan.

[0224] Step 5:

[0225] The server notifies the user of the selected optimal plan via a messaging system, displaying details of the plan on the user's smartphone or tablet. The input is the selected plan and the user's contact information, and the output is a notification message sent to the user's device.

[0226] Step 6:

[0227] The user receives the notification and approves the plan. The user checks the details of the proposed plan on the user terminal and selects whether to approve or reject it. The input is the notification content displayed to the user, and the output is the user's selection of whether to approve or reject it.

[0228] Step 7:

[0229] The server receives the user's approval information and automatically changes the pricing plan. Specifically, it updates the database settings based on the approval information and applies the new pricing plan. The input is the user's approval information, and the output is the updated database settings and a final notification to the user's terminal.

[0230] This process will create a system in which the most suitable pricing plan is automatically proposed based on the user's usage data, and if the user approves it, the plan is automatically applied.

[0231] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0232] The system of the present invention automatically provides mobile subscribers with the most appropriate pricing plan based on their usage and emotional state. This system combines traditional usage data with an emotion engine that recognizes user emotions to provide a more personalized service.

[0233] Data collection and storage

[0234] First, the system collects usage data from the device. The device periodically records information such as data traffic, call time, and SMS usage, and sends it to the server. The server then stores the received data in a database, recording each customer's usage in detail. In addition, the device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state in real time, for example, from facial expressions and voice tones, and also sends this data to the server.

[0235] Data analysis

[0236] The server periodically analyzes usage data and emotion data. First, it uses a machine learning algorithm to identify each customer's usage patterns based on past usage data. For example, it calculates the average data volume, call time, and SMS usage over the past three months and predicts future usage. Next, it analyzes the emotion data using an emotion engine to understand the user's emotional state. This makes it possible to adjust the system, for example, by avoiding notifications at certain times or situations when the user's stress level is high.

[0237] Plan selection

[0238] Based on the analysis results, the server considers usage data and emotional data to select the optimal pricing plan for the customer. Not only does it select the optimal plan based on usage patterns, but it also considers the user's emotional state to provide a plan that is reasonably acceptable to the user.

[0239] Plan presentation and notification

[0240] The server then notifies the device of the optimal pricing plan that has been selected. The notification message includes details of the recommended plan and the reasons for its selection, providing information to the customer in a transparent manner. The timing and method of notification are also adjusted based on emotional data. For example, by selecting a time when the user is relaxed to send the notification, the likelihood of approval is increased.

[0241] Change plan

[0242] When the user receives the notification, they can review the proposed plan and choose whether to accept it. If the user accepts the new plan, the information is sent from the device to the server. The server receives the approval information and updates the customer's settings, so the new pricing plan is automatically applied.

[0243] Specific examples

[0244] User D's scenario

[0245] 1. Data Collection

[0246] Device: User D's device records 20GB of data traffic, 80 minutes of talk time, and 15 SMS messages this month. The emotion engine analyzes User D's emotional state in real time and records his stress level, relaxation state, etc.

[0247] Server: Collects usage data and emotion data from devices and stores them in a database.

[0248] 2. Data analysis

[0249] Server: Based on usage data from the past three months, the server analyzes that User D's average data usage is 18GB, talk time is 85 minutes, and SMS usage is 12 messages. It also uses a machine learning algorithm to predict future usage. At the same time, it analyzes emotion data and determines that User D's stress level tends to be higher in the morning.

[0250] 3. Plan selection

[0251] Server: Based on the analysis results, it determines that the "25GB Data Plan + 100 Minutes Call Plan" is optimal. It also takes into account emotional data and sends notifications during the day, avoiding the morning.

[0252] 4. Plan presentation and notification

[0253] Server: Generates a notification message of the optimal plan and sends it to User D's device. The notification contains details of the proposed plan and the reasons for it.

[0254] Terminal: Receives notifications and displays them to the user.

[0255] 5. Change of plan

[0256] User: Check the notification and accept the proposed plan. Select "Change" on the device settings screen.

[0257] Terminal: Sends authorization information to the server.

[0258] Server: Receives the approval information and updates User D's settings. The new pricing plan is applied immediately and the server notifies the user that the plan change was successful.

[0259] Device: Receives notifications and displays them to the user.

[0260] By taking into account both the user's usage and emotional state, the system can provide a more personalized and optimal pricing plan for the customer, thereby improving customer satisfaction and preventing excessive charges.

[0261] The processing flow will be explained below.

[0262] Step 1:

[0263] Device: Records usage data. When a user uses a mobile phone, the device records information such as data traffic, call duration, and number of SMS sent. This data is set to be updated periodically.

[0264] Step 2:

[0265] Device: Analyzes user emotions in real time. Records the user's emotional state (e.g., stress level, relaxation level) using an emotion engine that analyzes facial expressions, voice tone, text message content, etc.

[0266] Step 3:

[0267] Device: The recorded usage data and emotion data are sent to the server. The data is transferred to the server at specific intervals (e.g., every 5 minutes). Encryption technology is used for data transmission to ensure secure communication.

[0268] Step 4:

[0269] Server: Stores the received usage and sentiment data in a database. Organizes the data for each customer and stores it for future analysis.

[0270] Step 5:

[0271] Server: The accumulated data is periodically analyzed. First, a machine learning algorithm is used to identify each customer's usage pattern based on past usage data. For example, the average data usage over the past three months is calculated and future usage predictions are made.

[0272] Step 6:

[0273] Server: Next, the emotional data is analyzed to understand the user's emotional state. Specific emotional patterns, such as stress level or relaxation state, are extracted from the data.

[0274] Step 7:

[0275] Server: Selects the optimal plan for each customer based on usage data and emotional data. For example, a high-capacity data plan may be recommended for a user who uses the service frequently but is in a relaxed state.

[0276] Step 8:

[0277] Server: After selecting the optimal pricing plan, generate a notification message. The notification contains details of the recommended plan and the reasons for its selection. The timing and method of notification are also adjusted based on sentiment data.

[0278] Step 9:

[0279] Server: The server sends the generated notification message to the customer's device. It selects the optimal timing, such as sending the message during a time when the user is relaxed, taking into account emotional data.

[0280] Step 10:

[0281] Device: Receives a notification and displays it to the user, who can see the plan details and reasons.

[0282] Step 11:

[0283] User: Check the notified plan and decide whether to accept it. If you accept it, select "Change" on the device settings screen.

[0284] Step 12:

[0285] Terminal: Sends the user's selection information to the server. A request is sent to the server requesting the application of the new plan.

[0286] Step 13:

[0287] Server: Updates the customer's subscription information based on the received request. The new pricing plan is applied immediately.

[0288] Step 14:

[0289] Server: Notifies the customer that the plan change was successful. Sends a notification message to the device to let the user know that the change is complete.

[0290] Step 15:

[0291] Device: Receives notification and displays to the user that the plan change was successful.

[0292] This detailed process flow allows customers to easily and quickly select and apply the pricing plan that best suits their usage and emotional state.

[0293] Example 2

[0294] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0295] Conventional systems select service plans for customers based solely on usage data, making it difficult to provide personalized services that take into account the customer's emotional state and stress levels due to usage. Furthermore, notifications were not provided at the appropriate time, which could lead to lower customer satisfaction and increased stress due to unnecessary notifications. Furthermore, when customers approved a proposed plan, there was a lack of transparency regarding the plan contents and the reasons for selection, making it difficult to improve reliability.

[0296] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0297] In this invention, the server includes means for collecting usage data and emotion data from the terminal, means for storing the collected usage data and emotion data, means for analyzing the stored usage data and emotion data and selecting an optimal service plan for the customer, means for notifying the customer of the selected service plan, means for adjusting the timing and method of notification based on the customer's emotional state, and means for changing the service plan with the customer's approval. This makes it possible to provide personalized services that take the customer's emotional state into consideration and to notify them at an appropriate time, and improves the transparency of the plan contents and the reasons for selection, thereby enabling increased customer satisfaction and reliability.

[0298] A "terminal" is a device used by a user that has the function of recording and transmitting usage data such as data communication, calls, and SMS, and also collecting emotional data.

[0299] "Usage data" refers to information such as data traffic, call time, and SMS usage generated when a user uses a mobile service.

[0300] "Emotional data" refers to information indicating a user's emotional state (e.g., stress level, relaxation level) analyzed from their facial expressions and vocal tone.

[0301] "Server" refers to a central aggregation system that receives, stores, and analyzes usage data and emotion data sent from terminals.

[0302] The term "storing means" refers to a method or device for storing the received usage data and emotion data in a storage device such as a database.

[0303] "Means for analyzing" refers to methods and devices for analyzing accumulated usage and sentiment data and using machine learning algorithms to identify usage patterns.

[0304] The "means for selecting the optimal service plan" refers to a method or device for selecting the most suitable rate plan for a customer based on the analysis results.

[0305] The "notification means" refers to a method or device for transmitting information about the selected optimum service plan to the user's terminal and displaying it.

[0306] "Means for adjusting the timing and method of notification based on the emotional state" refers to a method or device for providing notification at the most appropriate timing and in the most appropriate manner, taking into account the user's emotional data.

[0307] "Means for changing the service plan upon approval" refers to a method or device for sending information to a server when a user approves a proposed service plan and immediately changing the service plan.

[0308] The system of the present invention automatically provides mobile subscribers with the most appropriate pricing plan based on their usage and emotional state. This system combines traditional usage data with an emotion engine that recognizes user emotions to provide a more personalized service.

[0309] Data collection and storage

[0310] First, the system collects usage and emotion data from the device. The device periodically records information such as data traffic, call duration, and SMS usage, and sends it to the server. The device is equipped with an emotion engine that recognizes the user's emotions, and analyzes the user's emotional state in real time from facial expressions and voice tones, and also sends this data to the server.

[0311] The server stores the received data in a database, recording each customer's usage and emotional state in detail. This is done using a database management system (DBMS), such as an open-source database like MySQL (registered trademark) or PostgreSQL.

[0312] Data analysis

[0313] The server periodically analyzes the accumulated usage and sentiment data. It uses machine learning algorithms to identify each customer's usage patterns based on past usage data and predict future usage. This can be done using machine learning libraries such as TENSORFLOW (registered trademark) and scikit-learn.

[0314] Emotional data is also analyzed by an emotion engine, and analysis is carried out taking into account the user's emotional state. For example, if a user's stress level is high during a particular time period or situation, it is possible to adjust notifications to avoid those times.

[0315] Plan selection

[0316] Based on the analysis results, the server selects the optimal plan for the customer, taking into account usage data and emotional data. Specifically, it selects the optimal plan based on data traffic, call time, and SMS usage, and provides a plan that the user can reasonably accept based on emotional data.

[0317] Plan presentation and notification

[0318] The server then notifies the device of the optimal pricing plan. The notification message includes details of the recommended plan and the reasons for its selection, providing information to the customer in a transparent manner. The timing and method of notifications are also adjusted based on emotional data. For example, notifications can be sent at times when the user is relaxed, increasing the likelihood of approval.

[0319] Change plan

[0320] When the user receives the notification, they can review the proposed plan and choose whether to accept it. If the user accepts the new plan, the information is sent from the device to the server. The server receives the approval information and updates the customer's settings, so the new pricing plan is automatically applied.

[0321] Specific examples

[0322] User D's scenario

[0323] As a specific example, the case of user D will be described.

[0324] 1. Data Collection

[0325] Device: User D's device records 20GB of data traffic, 80 minutes of talk time, and 15 SMS messages this month. The emotion engine analyzes User D's emotional state in real time and records his stress level, relaxation state, etc.

[0326] Server: Collects usage data and emotion data from devices and stores them in a database.

[0327] 2. Data analysis

[0328] Server: Based on usage data from the past three months, the server analyzes that User D's average data usage is 18GB, talk time is 85 minutes, and SMS usage is 12 messages. It also uses a machine learning algorithm to predict future usage. At the same time, it analyzes emotion data and determines that User D's stress level tends to be higher in the morning.

[0329] 3. Plan selection

[0330] Server: Based on the analysis results, it determines that the 25GB data plan + 100 minutes call plan is optimal. Taking into account the emotional data, it sends notifications during the day, avoiding the morning.

[0331] 4. Plan presentation and notification

[0332] Server: Generates a notification message of the optimal plan and sends it to User D's device. The notification contains details of the proposed plan and the reasons for it.

[0333] Terminal: Receives notifications and displays them to the user.

[0334] 5. Change of plan

[0335] User: Check the notification and accept the proposed plan. Select "Change" on the device settings screen.

[0336] Terminal: Sends authorization information to the server.

[0337] Server: Receives the approval information and updates User D's settings. The new pricing plan is applied immediately and the server notifies the user that the plan change was successful.

[0338] Device: Receives notifications and displays them to the user.

[0339] In this way, by taking into account the user's usage and emotional state, we can provide more personalized and optimal pricing plans, improving customer satisfaction and preventing excessive payment of fees.

[0340] Prompt Sentence Examples

[0341] Below are some example prompts to input into the generative AI model to illustrate how this system can be used.

[0342] A user has a mobile plan with a high data usage and relatively long talk time. Analysis by the emotion engine reveals that the user's stress level tends to be higher in the morning. Design a system to recommend the optimal plan for this user and send notifications at appropriate times taking into account the emotion data.

[0343] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0344] Step 1:

[0345] Data collection

[0346] Input: Data from on-device sensors and logs, user facial expressions and vocal tones

[0347] Specific operation: The device periodically records usage data such as data traffic, call time, and SMS usage. The emotion engine analyzes the user's emotional state (e.g., stress level, relaxation level) from their facial expressions and voice.

[0348] Output: Collected usage and sentiment data

[0349] Step 2:

[0350] Data transmission

[0351] Input: Collected usage and sentiment data

[0352] Specific operation: The device periodically sends the collected data to the server. At this time, the data is encrypted and sent securely.

[0353] Output: Usage and emotion data sent to the server

[0354] Step 3:

[0355] Data accumulation

[0356] Input: Usage data and emotion data received by the server

[0357] Specific operation: The server stores the received data in a database, where data is organized for each user and managed in an easily accessible format.

[0358] Output: Usage data and emotion data stored in a database

[0359] Step 4:

[0360] Data analysis

[0361] Input: Usage data and emotion data stored in a database

[0362] How it works: The server uses machine learning algorithms to analyze usage data and identify each customer's usage patterns. It also analyzes emotion data to understand patterns of emotional states (e.g., stress levels) during specific times and situations. The libraries used include TensorFlow and scikit-learn.

[0363] Output: Usage and sentiment patterns for each customer

[0364] Step 5:

[0365] Plan selection

[0366] Input: Usage patterns and emotion patterns

[0367] Specific operation: The server selects the optimal pricing plan for each customer based on their usage patterns. It also takes into account their emotional patterns and provides a plan that the user can reasonably accept.

[0368] Output: The optimal pricing plan selected

[0369] Step 6:

[0370] Notification generation

[0371] Input: Selected optimal pricing plan and sentiment patterns

[0372] Specific operation: The server generates a notification message of the optimal plan and sends it to the device at the optimal time based on the emotional pattern. The notification includes details of the recommended plan and the reasons for it.

[0373] Output: Notification message sent to the terminal

[0374] Step 7:

[0375] Notification display

[0376] Input: Notification message sent from the server

[0377] Specific operation: The terminal displays the received notification message to the user.

[0378] Output: Notification message displayed to the user

[0379] Step 8:

[0380] Plan Approval

[0381] Input: User confirmed notification message

[0382] Specific operation: The user checks the notification and selects "Change" on the device settings screen.

[0383] Output: Plan Approval Selection

[0384] Step 9:

[0385] Send approval information

[0386] Input: User selected plan approval information

[0387] Specific operation: The terminal sends the plan approval information to the server. The information is encrypted.

[0388] Output: Plan approval information sent to the server

[0389] Step 10:

[0390] Update settings

[0391] Input: Plan approval information sent to the server

[0392] What happens: The server receives the authorization information and updates the customer's settings to apply the new pricing plan.

[0393] Output: New pricing plan applied

[0394] Step 11:

[0395] Change Notification

[0396] Input: New pricing plan applied

[0397] Specific operation: The server notifies the terminal that the plan change was successful.

[0398] Output: Change notification messages sent to the terminal

[0399] Step 12:

[0400] Change result display

[0401] Input: Change notification message sent from the server

[0402] Specific behavior: The device receives the notification and displays it to the user.

[0403] Output: The change notification message displayed to the user

[0404] (Application example 2)

[0405] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0406] Current electronic payment services have difficulty offering plans and promotions that take into account a customer's usage status and spending patterns. Furthermore, notifications are sent without considering the customer's emotional state, so the information provided is not always timely or effective for the customer. As a result, customer satisfaction declines and it becomes difficult to provide optimal service.

[0407] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0408] In this invention, the server includes means for collecting usage data and emotional data from the terminal, means for storing the collected data, means for analyzing the stored data and selecting an optimal electronic payment plan and promotion for the customer, means for notifying the customer of the selected electronic payment plan and promotion, and means for changing the plan and promotion with the customer's approval, thereby enabling timely and effective service provision that takes into account the customer's spending patterns and emotional state.

[0409] "Terminal" means a device used by a User to input or collect Usage Data and Emotional Data.

[0410] "Usage data" refers to information related to electronic payments, such as a user's spending history and purchase details.

[0411] "Emotional Data" means data collected to describe a user's emotional state, including facial expressions and vocal tones.

[0412] "Storage" is the process of storing collected usage data and emotion data in a database.

[0413] "Analysis" is the process of analyzing accumulated data using machine learning algorithms and other methods to identify users' spending patterns and emotional states.

[0414] An "electronic payment plan" is a plan that includes fee plans and point rewards when a user uses electronic payment.

[0415] "Promotion" refers to an advertising campaign such as cashback or special offers offered to users.

[0416] "Notification" means the act of informing a User of the details of the selected Electronic Payment Plan or Promotion and the reasons for such selection.

[0417] "Acceptance" means the user's acceptance of a proposed plan or promotion.

[0418] "Modification" is the process of updating an electronic payment plan or promotion based on user approval.

[0419] The system that realizes this application example is mainly composed of a terminal, a server, and an emotion recognition engine. A specific implementation method is described below.

[0420] Hardware and Software Configuration

[0421] Hardware and software used:

[0422] 1. Device: This refers to the smartphone held by the user, and is the device that collects usage data and emotional data.

[0423] 2. Emotion recognition engine: For example, using the Microsoft® Azure® Emotion API, it analyzes the user's emotions from facial expressions and voice tones collected via the smartphone's camera and microphone.

[0424] 3. Server: Stores usage data and emotion data in a database (e.g., MySQL) and performs data analysis.

[0425] 4. Data analysis platform: Responsible for processing and analyzing large-scale data using Apache Spark (registered trademark) and other technologies.

[0426] 5. Machine learning algorithms: Using TensorFlow and other technologies, we analyze user usage patterns and sentiment data to select optimal e-payment plans and promotions.

[0427] Program processing

[0428] The system performs data processing and calculation as follows.

[0429] Data collection:

[0430] The device periodically records usage data such as the user's spending history and purchase details and sends it to the server. In addition, an emotion recognition engine analyzes the user's emotional state in real time and sends that data to the server.

[0431] Data accumulation:

[0432] The server stores the usage data and emotion data sent from the device in a database. The data is periodically updated and stored, so that the latest usage status and emotion state are always maintained.

[0433] Data Analysis:

[0434] The server analyzes the accumulated data using machine learning algorithms. It identifies the user's spending patterns from past usage data and predicts future usage. At the same time, it analyzes emotional data to understand the user's stress level and relaxation state.

[0435] Plan Selection and Notification:

[0436] Based on the analysis results, the server selects the most suitable electronic payment plan and promotion for the user, and the selected plan or promotion is notified to the terminal, adjusting the notification timing based on the user's emotional state.

[0437] Plan Change:

[0438] The user can review the notification and accept or reject the proposed plans and promotions. If accepted, the server uses that information to modify the plans and promotions and update the user's settings.

[0439] Specific examples

[0440] For example, if a user recently made a large purchase, the system will detect that spending data and store it in a database. At the same time, an emotion recognition engine will analyze the user's state of relaxation, and notify them of a specific cashback campaign at a time when they are relaxed, which is expected to increase approval rates. Furthermore, the system can predict a user's spending patterns from past data and provide them with the optimal electronic payment plan.

[0441] Prompt Sentence Examples

[0442] "Based on the spending data (50 items) and emotional data (50 items) from the past three months, please generate a code that analyzes the user's spending patterns and emotional state and suggests the optimal payment plan."

[0443] In this way, timely and effective service delivery can be achieved that takes into account the customer's spending patterns and emotional state.

[0444] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0445] Step 1:

[0446] Data collection

[0447] The device collects usage data such as the user's spending history and purchases, and simultaneously collects the user's emotional state by analyzing facial expressions and vocal tone using an emotion recognition engine.

[0448] Input: spending history, purchase details, facial expressions, voice tones

[0449] Data processing: Organize and structure the collected usage data and sentiment data.

[0450] Output: Structured usage and sentiment data

[0451] Step 2:

[0452] Data transmission

[0453] The device transmits the collected usage and emotion data to a server, either periodically or in real time.

[0454] Input: Structured usage data and sentiment data

[0455] Data Calculation: Convert the data into the appropriate format and send it to the server.

[0456] Output: Data sent to the server

[0457] Step 3:

[0458] Data accumulation

[0459] The server stores the usage data and emotion data sent from the terminal in a database.

[0460] Input: Submitted usage data and emotion data

[0461] Data processing: Record and save the received data in a database.

[0462] Output: Data stored in the database

[0463] Step 4:

[0464] Data analysis

[0465] The server analyzes the accumulated usage data and emotional data using machine learning algorithms to identify the user's spending patterns from past usage data and understand the user's emotional state from emotional data.

[0466] Input: Usage data and emotion data stored in a database

[0467] Data Computing: Data Analysis and Pattern Recognition with Machine Learning Models

[0468] Output: Analysis of user spending patterns and emotional state

[0469] Step 5:

[0470] Plan selection

[0471] The server selects the most suitable e-payment plan and promotion for the user based on the analysis results, and adjusts notifications to be sent at the appropriate time, taking into account emotional data.

[0472] Input: Analysis results (spending patterns and emotional state)

[0473] Data calculation: Selecting the best plan and promotion

[0474] Output: Selected electronic payment plans and promotions

[0475] Step 6:

[0476] notification

[0477] The server sends a notification message containing details of the selected electronic payment plan and promotion to the terminal, optimizing the timing of the notification based on the emotion data.

[0478] Input: Selected plan and promotion

[0479] Data calculation: Notification message generation and timing adjustment

[0480] Output: Notification message sent to the terminal

[0481] Step 7:

[0482] Change plan

[0483] The user reviews the notification and can accept or reject the proposed plan or promotion. If accepted, the device sends the information to the server, which then changes the plan or promotion and updates the user's settings.

[0484] Input: User approval / rejection

[0485] Data operation: Plan and promotion update processing

[0486] Output: Updated electronic payment plans and promotions

[0487] In this way, a system is realized that comprehensively analyzes the spending patterns and emotional state of customers and provides timely and effective electronic payment plans and promotions.

[0488] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0489] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0490] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0491] [Second embodiment]

[0492] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0493] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0494] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0495] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0496] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0497] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0498] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0499] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0500] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0501] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0502] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0503] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0504] The system of the present invention automatically provides mobile subscribers with the most appropriate rate plan based on their usage. The system collects usage data from the terminal, stores and analyzes the collected data, selects the most appropriate rate plan, and notifies the customer. It also has the ability to automatically change plans with the customer's approval.

[0505] Data collection and storage

[0506] The system first collects usage data from the device. The device has the ability to record information such as data traffic, call time, and SMS usage, and this data is periodically sent to the server. The server stores the received data in a database. This allows for detailed records of each customer's usage status to be used for later analysis.

[0507] Data analysis

[0508] The server uses machine learning algorithms to analyze the accumulated data. Specifically, it analyzes customer usage patterns based on past usage data and predicts future usage. Based on the results of this analysis, it selects the optimal pricing plan for the customer. For example, if the average data usage over the past three months is within a certain range, it will propose the optimal data plan based on that.

[0509] Plan presentation and notification

[0510] The server notifies the terminal of the selected optimal rate plan. The notification message includes details of the proposed plan and the reasons for it, providing information to the customer in a transparent manner. The terminal receives this notification and displays it to the user.

[0511] Change plan

[0512] When the user receives the notification, they review the proposed plan and choose whether to accept it. If the user accepts the new plan, the device sends that information to the server. The server receives this approval information and updates the customer's settings, so the new pricing plan is automatically applied.

[0513] Specific examples

[0514] User C's scenario

[0515] 1. Data Collection

[0516] Device: User C's device records this month's data usage of 15GB, talk time of 120 minutes, and SMS usage of 5 messages.

[0517] Server: Stores data collected from devices in a database. This data is updated every 5 minutes.

[0518] 2. Data analysis

[0519] Server: Based on usage data from the past three months, it is analyzed that User C's average data usage is 16GB, talk time is 110 minutes, and SMS usage is 4. It also uses a machine learning algorithm to predict future usage.

[0520] 3. Plan presentation and notification

[0521] Server: Based on the analysis results, it determines that the "20GB data plan + 120 minutes call plan" is optimal. It generates a notification message and sends it to User C's device.

[0522] Device: Receives and displays a notification to the user, detailing the proposed plan and explaining the reasons for it.

[0523] 4. Change of plan

[0524] User: Check the notification and accept the proposed plan by selecting "Change" from the device settings screen.

[0525] Terminal: Sends authorization information to the server.

[0526] Server: Receives the approval information and updates User C's settings. Notifies the user that the new pricing plan has been applied.

[0527] In this way, the present invention can improve customer satisfaction by automatically selecting the most suitable rate plan based on the customer's usage status and providing it in real time.

[0528] The processing flow will be explained below.

[0529] Step 1:

[0530] Device: Records usage data. When a user uses a mobile phone, the device records information such as data traffic, call duration, and number of SMS sent. This data is set to be updated periodically.

[0531] Step 2:

[0532] Device: Sends recorded usage data to the server. Data is transferred to the server at specific intervals (e.g., every 5 minutes). Data transmission uses encryption technology to ensure secure communication.

[0533] Step 3:

[0534] Server: Stores the received usage data in a database. Organizes the data for each customer and stores it for future analysis.

[0535] Step 4:

[0536] Server: Periodically analyzes the accumulated data. Machine learning algorithms are used to identify each customer's usage patterns based on past usage data. For example, the average data usage, call minutes, and SMS usage over the past three months are calculated.

[0537] Step 5:

[0538] Server: Based on the analysis results, the server selects the most suitable pricing plan for the customer. It considers usage data patterns and selects the most cost-effective plan from the list of plans.

[0539] Step 6:

[0540] Server: After selecting the best pricing plan, generate a notification message containing details of the recommended plan and the reasons for it.

[0541] Step 7:

[0542] Server: The generated notification message is sent to the client's terminal. The data is transferred in real time, and the user is notified immediately.

[0543] Step 8:

[0544] Device: Receives a notification and displays it to the user, who can see the plan details and reasons.

[0545] Step 9:

[0546] User: Check the notified plan and decide whether to accept it. If you accept it, select "Change" on the device settings screen.

[0547] Step 10:

[0548] Terminal: Sends the user's selection information to the server. A request is sent to the server requesting the application of the new plan.

[0549] Step 11:

[0550] Server: Updates the customer's subscription information based on the received request. The new pricing plan is applied immediately.

[0551] Step 12:

[0552] Server: Notifies the customer that the plan change was successful. Sends a notification message to the device to let the user know that the change is complete.

[0553] Step 13:

[0554] Device: Receives notification and displays to the user that the plan change was successful.

[0555] This detailed process flow allows customers to easily and quickly select and apply the rate plan that best suits their usage situation.

[0556] Example 1

[0557] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0558] This invention relates to a system that automatically provides mobile subscribers with the most appropriate rate plan based on their usage. Conventional methods involve manually collecting and analyzing usage data, making it difficult to provide customers with the most appropriate plan in real time. For this reason, there has been a need for a method to quickly and effectively provide rate plans that meet customer needs.

[0559] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0560] In this invention, the server includes means for collecting usage data from the terminal, means for storing the collected usage data, means for analyzing the stored usage data using a machine learning algorithm and selecting an optimal service plan for the customer, means for sending a notification to the customer including details of the selected service plan and the reasons for the selection, and means for automatically changing the service plan with the customer's approval. This makes it possible to provide an optimal rate plan in real time based on the customer's usage status and improve customer satisfaction.

[0561] A "terminal" is an electronic device used by a user that has the function of collecting usage data such as data communication, calls, and SMS, and communicating with a server.

[0562] "Usage data" refers to information such as data usage, call time, and SMS usage when a user uses a mobile service.

[0563] A "server" is a central processing unit that receives, stores, and analyzes data sent from terminals.

[0564] A "machine learning algorithm" is an algorithm that learns from past data and predicts future data and patterns.

[0565] "Notification" is the act of sending a server-generated message to a terminal to provide information to a user.

[0566] "Customer Approval" refers to the User receiving the notification reviewing the proposed service plan and taking the action of consenting or rejecting it.

[0567] "Service Plan" refers to the pricing structure and terms of use offered to a mobile subscriber, including data volume, talk time, number of SMS sent, etc.

[0568] "Automatically change" refers to the server programmatically updating the service plan without manual intervention after obtaining user approval.

[0569] The system of the present invention automatically provides the most suitable rate plan to a mobile subscriber based on their usage. The system collects usage data from the terminal, stores and analyzes the collected data on a server, selects the most suitable rate plan, and notifies the customer. Furthermore, the system also has the function of automatically changing plans with the customer's approval.

[0570] Hardware and software used

[0571] This system mainly uses the following hardware and software:

[0572] 1. Terminal

[0573] Hardware: Mobile devices such as smartphones and tablets.

[0574] Software: Applications for collecting usage data.

[0575] 2. Server

[0576] Hardware: Database servers, compute servers for running machine learning models.

[0577] Software: Database management systems, machine learning algorithms, notification services.

[0578] Specific processing flow

[0579] Data collection and storage

[0580] The device collects usage data in real time, such as the user's data traffic, call time, and SMS usage. This usage data is stored in the device's internal storage and periodically (for example, every five minutes) sent to the server. The server stores the received data in a database, recording each customer's usage status in detail. This data can then be used for later data analysis.

[0581] Data analysis

[0582] The server analyzes the accumulated usage data using machine learning algorithms. Based on past usage data, the server analyzes the customer's usage patterns and predicts future usage. For example, if the average data usage over the past three months is within a certain range, the server can suggest the optimal data plan based on that prediction. The machine learning models used are often run on cloud platforms.

[0583] Plan presentation and notification

[0584] The server selects the optimal pricing plan for the customer based on the results of the data analysis. It generates a notification message containing details of the selected pricing plan and the reasons for it, and sends it to the customer's device. The device receives this notification and displays it to the user. The notification clearly explains how the change in pricing plan will benefit the customer.

[0585] Change plan

[0586] The user checks the notification on the device and chooses whether to accept the proposed pricing plan. If accepted, the device sends the information to the server. The server receives the approval information and updates the customer's account settings to the new pricing plan. The new pricing plan is then immediately applied, and the server notifies the device again.

[0587] Specific examples

[0588] User C's scenario

[0589] 1. Data Collection

[0590] Device: User C's device records this month's data usage of 15GB, talk time of 120 minutes, and SMS usage of 5 messages.

[0591] Server: Stores data collected from devices in a database. This data is updated every 5 minutes.

[0592] 2. Data analysis

[0593] Server: Based on usage data from the past three months, it is analyzed that User C's average data usage is 16GB, talk time is 110 minutes, and SMS usage is 4. It also uses a machine learning algorithm to predict future usage.

[0594] 3. Plan presentation and notification

[0595] Server: Based on the analysis results, it determines that the "20GB data plan + 120 minutes call plan" is optimal. It generates a notification message and sends it to User C's device.

[0596] Device: Receives and displays a notification to the user, detailing the proposed plan and explaining the reasons for it.

[0597] 4. Change of plan

[0598] User: Check the notification and accept the proposed plan by selecting "Change" from the device settings screen.

[0599] Terminal: Sends authorization information to the server.

[0600] Server: Receives the approval information and updates User C's settings. Notifies the user that the new pricing plan has been applied.

[0601] Prompt Sentence Examples

[0602] "Please analyze and suggest the optimal pricing plan for User C based on usage data from the past three months."

[0603] As described above, the present invention can improve customer satisfaction by automatically selecting an optimal rate plan based on the customer's usage status and providing it in real time.

[0604] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0605] Step 1:

[0606] Data collection

[0607] Input: User data usage, call time, SMS usage

[0608] How it works: The device collects usage data in real time and stores it in storage.

[0609] Example: A device records the current amount of data traffic and updates it every 5 minutes.

[0610] Output: The latest usage data is saved on the device.

[0611] Step 2:

[0612] Data transmission

[0613] Input: Usage data stored on the device

[0614] How it works: The device periodically sends collected data to a server. The data is encrypted and transmitted securely.

[0615] Example: A device sends the latest usage data to a server every 5 minutes.

[0616] Output: Usage data arrives at the server and is received.

[0617] Step 3:

[0618] Data accumulation

[0619] Input: Usage data sent to the server

[0620] How it works: The server stores the data it receives in a database, organizing it by customer for quick access and analysis later.

[0621] Example: The server adds user C's data usage of 15 GB, talk time of 120 minutes, and SMS usage of 5 to the database.

[0622] Output: The latest usage data is saved in the database.

[0623] Step 4:

[0624] Data analysis

[0625] Input: Usage data stored in the database

[0626] How it works: The server analyzes the data using machine learning algorithms, analyzing customer usage patterns based on past data and predicting future usage.

[0627] Example: The server analyzes usage data from the past three months and predicts that User C's average data usage is 16 GB, talk time is 110 minutes, and SMS usage is 4.

[0628] Output: The analysis results in customer usage patterns and predictions of future usage.

[0629] Step 5:

[0630] Plan selection

[0631] Input: Results of data analysis

[0632] How it works: The server selects the optimal pricing plan for the customer based on the analysis results. This selection is made by comparing the usage forecast with the terms of existing pricing plans.

[0633] Example: The server determines that the "20GB data plan + 120 minutes call plan" is optimal for user C.

[0634] Output: Detailed information on the best pricing plan.

[0635] Step 6:

[0636] Plan Notification

[0637] Input: Details of the best rate plan

[0638] Operation: The server generates a notification message containing details of the selected rate plan and the reason for the selection, and sends it to the terminal.

[0639] Example: The server generates a message detailing the "20GB data plan + 120 minutes call plan" and the reason for the plan, and sends it to User C's device.

[0640] Output: A notification message arrives on the terminal.

[0641] Step 7:

[0642] User Authorization

[0643] Input: Notification message

[0644] How it works: The user sees the notification on their device and chooses whether to accept the proposed pricing plan.

[0645] Example: User C checks the notification and presses the "Change" button on the device to approve the proposed plan.

[0646] Output: The authorization information is entered into the terminal.

[0647] Step 8:

[0648] Change plan

[0649] Input: User authorization information

[0650] Operation: The device sends the authorization information to the server, which updates the customer's settings with the new rate plan, which then applies the new rate plan.

[0651] Example: The server receives user C's authorization information and updates user C's settings to "20GB data plan + 120 minutes call plan."

[0652] Output: The new pricing plan is applied and you are notified.

[0653] (Application example 1)

[0654] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0655] With conventional electronic payment services, users must analyze their own usage data and select the appropriate plan to suit their usage, which is time-consuming and laborious. Furthermore, users may not be able to determine the appropriate plan and end up paying excessive fees. Furthermore, there is a lack of a mechanism for flexibly changing plans based on the user's lifestyle and frequency of use, resulting in low user satisfaction.

[0656] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0657] In this invention, the server includes means for collecting usage data from the terminal, means for storing the collected usage data, means for analyzing the stored usage data and selecting an optimal service plan for the customer, means for notifying the customer of the selected service plan, means for changing the service plan with the customer's approval, means for identifying usage data for the electronic payment service and using a machine learning algorithm to predict an optimal rate plan based on the usage data, and means for notifying the user terminal of the selected rate plan and obtaining approval. This makes it possible to automatically propose an optimal rate plan based on the user's usage data and flexibly change the plan with approval.

[0658] "Terminal" refers to a computing device such as a mobile phone, smartphone, or tablet that an investor uses on a daily basis.

[0659] "Usage data" refers to information such as the amount of data used, the amount used, and the number of transactions when a user uses an electronic payment service.

[0660] "Storage means" refers to a recording device or database for storing collected usage data.

[0661] "Analytical means" refers to machine learning algorithms and analytics software that evaluate collected and stored usage data and extract patterns.

[0662] "Optimal service plan" refers to the most cost-effective plan selected based on the user's past and predicted usage.

[0663] "Means of notification" refers to the messaging system or application functionality used to communicate information about the selected service plan to the user.

[0664] "Means for changing service plans with approval" means the system's ability to automatically update service plans after obtaining user consent.

[0665] "Electronic Payment Services" refers to payment platforms and systems that enable online or offline payments, purchases and transactions.

[0666] A "machine learning algorithm" refers to a mathematical model or computational method for learning patterns from past data and predicting or classifying future data.

[0667] "User terminal" refers to a computing device (smartphone, tablet, etc.) operated by a user when using an electronic payment service.

[0668] Data collection

[0669] The server first collects usage data from the device. This data includes communication volume, usage amount, number of transactions, etc. This collection process is carried out periodically through the device's API (Application Programming Interface). Specifically, it collects usage information from electronic payment services accessed by smartphones and tablet devices.

[0670] Data accumulation

[0671] The collected usage data is stored in a database on the server. The database is constructed using SQLite, and the collected data is saved in the database. This data storage process records detailed usage information for each user.

[0672] Data analysis

[0673] The server uses a machine learning algorithm to analyze the accumulated data. Specifically, it uses a linear regression model from scikit-learn. It analyzes customer usage patterns based on past usage data and predicts future usage. During this process, it extracts and analyzes features from the usage data. Based on the results of this analysis, it selects the optimal pricing plan for each user.

[0674] Plan presentation and notification

[0675] After the optimal plan is selected, the server notifies the user via a messaging system, and the user receives details of the proposed plan and the reasons for its selection via an application on their smartphone or tablet. The notification message also includes an option for the user to approve the plan.

[0676] Change plan

[0677] If the user approves the proposed plan, the device sends the approval information to the server. The server automatically updates the pricing plan based on that information. This update process uses an API to appropriately change the database settings. Once the change is complete, the server notifies the user again, informing them that the new pricing plan has been applied.

[0678] Specific examples

[0679] User A's scenario

[0680] User A's device records a monthly transaction amount of 5,000 yen and 50 transactions. The server stores this information in a database and analyzes it using a linear regression model in scikit-learn. As a result, it determines that a "10% cashback plan for users who spend more than 5,000 yen per month" is optimal for User A. The server notifies User A's smartphone of the details of this plan and the reasons for it. When User A approves through the application, the server automatically changes the pricing plan and notifies User A again.

[0681] Prompt Sentence Examples

[0682] "Please suggest the best plan for a monthly electronic payment amount of 5,000 yen or more and 50 or more transactions."

[0683] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0684] Step 1:

[0685] The server collects usage data from the device. Specifically, it periodically obtains data such as communication volume, usage amount, and number of transactions through the API of the electronic payment service accessed by the smartphone or tablet device. The input is the API request from the device, and the output is the obtained usage data. This data is often received in JSON format.

[0686] Step 2:

[0687] The server stores the collected usage data in a database. Specifically, it parses the acquired JSON data and stores it in a database such as SQLite. At this time, the data is converted into an appropriate format and stored as a record for each customer. The input is the collected usage data, and the output is the data stored in the database.

[0688] Step 3:

[0689] The server analyzes the accumulated usage data. Specifically, it reads past usage data stored in the database and analyzes it using a linear regression model from scikit-learn. During the analysis, transaction amounts and number of transactions are used as features to predict future usage patterns. The input is the usage data obtained from the database, and the output is the analysis results (predicted usage patterns).

[0690] Step 4:

[0691] The server selects the optimal pricing plan. Based on the analysis results obtained by the machine learning algorithm, it determines the optimal plan for each user. Specifically, it compares the analysis results with existing pricing plans and selects the most appropriate plan. The input is the analysis results and existing pricing plan information, and the output is the selected optimal pricing plan.

[0692] Step 5:

[0693] The server notifies the user of the selected optimal plan via a messaging system, displaying details of the plan on the user's smartphone or tablet. The input is the selected plan and the user's contact information, and the output is a notification message sent to the user's device.

[0694] Step 6:

[0695] The user receives the notification and approves the plan. The user checks the details of the proposed plan on the user terminal and selects whether to approve or reject it. The input is the notification content displayed to the user, and the output is the user's selection of whether to approve or reject it.

[0696] Step 7:

[0697] The server receives the user's approval information and automatically changes the pricing plan. Specifically, it updates the database settings based on the approval information and applies the new pricing plan. The input is the user's approval information, and the output is the updated database settings and a final notification to the user's terminal.

[0698] This process will create a system in which the most suitable pricing plan is automatically proposed based on the user's usage data, and if the user approves it, the plan is automatically applied.

[0699] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0700] The system of the present invention automatically provides mobile subscribers with the most appropriate pricing plan based on their usage and emotional state. This system combines traditional usage data with an emotion engine that recognizes user emotions to provide a more personalized service.

[0701] Data collection and storage

[0702] First, the system collects usage data from the device. The device periodically records information such as data traffic, call time, and SMS usage, and sends it to the server. The server then stores the received data in a database, recording each customer's usage in detail. In addition, the device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state in real time, for example, from facial expressions and voice tones, and also sends this data to the server.

[0703] Data analysis

[0704] The server periodically analyzes usage data and emotion data. First, it uses a machine learning algorithm to identify each customer's usage patterns based on past usage data. For example, it calculates the average data volume, call time, and SMS usage over the past three months and predicts future usage. Next, it analyzes the emotion data using an emotion engine to understand the user's emotional state. This makes it possible to adjust the system, for example, by avoiding notifications at certain times or situations when the user's stress level is high.

[0705] Plan selection

[0706] Based on the analysis results, the server considers usage data and emotional data to select the optimal pricing plan for the customer. Not only does it select the optimal plan based on usage patterns, but it also considers the user's emotional state to provide a plan that is reasonably acceptable to the user.

[0707] Plan presentation and notification

[0708] The server then notifies the device of the optimal pricing plan that has been selected. The notification message includes details of the recommended plan and the reasons for its selection, providing information to the customer in a transparent manner. The timing and method of notification are also adjusted based on emotional data. For example, by selecting a time when the user is relaxed to send the notification, the likelihood of approval is increased.

[0709] Change plan

[0710] When the user receives the notification, they can review the proposed plan and choose whether to accept it. If the user accepts the new plan, the information is sent from the device to the server. The server receives the approval information and updates the customer's settings, so the new pricing plan is automatically applied.

[0711] Specific examples

[0712] User D's scenario

[0713] 1. Data Collection

[0714] Device: User D's device records 20GB of data traffic, 80 minutes of talk time, and 15 SMS messages this month. The emotion engine analyzes User D's emotional state in real time and records his stress level, relaxation state, etc.

[0715] Server: Collects usage data and emotion data from devices and stores them in a database.

[0716] 2. Data analysis

[0717] Server: Based on usage data from the past three months, the server analyzes that User D's average data usage is 18GB, talk time is 85 minutes, and SMS usage is 12 messages. It also uses a machine learning algorithm to predict future usage. At the same time, it analyzes emotion data and determines that User D's stress level tends to be higher in the morning.

[0718] 3. Plan selection

[0719] Server: Based on the analysis results, it determines that the "25GB Data Plan + 100 Minutes Call Plan" is optimal. It also takes into account emotional data and sends notifications during the day, avoiding the morning.

[0720] 4. Plan presentation and notification

[0721] Server: Generates a notification message of the optimal plan and sends it to User D's device. The notification contains details of the proposed plan and the reasons for it.

[0722] Terminal: Receives notifications and displays them to the user.

[0723] 5. Change of plan

[0724] User: Check the notification and accept the proposed plan. Select "Change" on the device settings screen.

[0725] Terminal: Sends authorization information to the server.

[0726] Server: Receives the approval information and updates User D's settings. The new pricing plan is applied immediately and the server notifies the user that the plan change was successful.

[0727] Device: Receives notifications and displays them to the user.

[0728] By taking into account both the user's usage and emotional state, the system can provide a more personalized and optimal pricing plan for the customer, thereby improving customer satisfaction and preventing excessive charges.

[0729] The processing flow will be explained below.

[0730] Step 1:

[0731] Device: Records usage data. When a user uses a mobile phone, the device records information such as data traffic, call duration, and number of SMS sent. This data is set to be updated periodically.

[0732] Step 2:

[0733] Device: Analyzes user emotions in real time. Records the user's emotional state (e.g., stress level, relaxation level) using an emotion engine that analyzes facial expressions, voice tone, text message content, etc.

[0734] Step 3:

[0735] Device: The recorded usage data and emotion data are sent to the server. The data is transferred to the server at specific intervals (e.g., every 5 minutes). Encryption technology is used for data transmission to ensure secure communication.

[0736] Step 4:

[0737] Server: Stores the received usage and sentiment data in a database. Organizes the data for each customer and stores it for future analysis.

[0738] Step 5:

[0739] Server: The accumulated data is periodically analyzed. First, a machine learning algorithm is used to identify each customer's usage pattern based on past usage data. For example, the average data usage over the past three months is calculated and future usage predictions are made.

[0740] Step 6:

[0741] Server: Next, the emotional data is analyzed to understand the user's emotional state. Specific emotional patterns, such as stress level or relaxation state, are extracted from the data.

[0742] Step 7:

[0743] Server: Selects the optimal plan for each customer based on usage data and emotional data. For example, a high-capacity data plan may be recommended for a user who uses the service frequently but is in a relaxed state.

[0744] Step 8:

[0745] Server: After selecting the optimal pricing plan, generate a notification message. The notification contains details of the recommended plan and the reasons for its selection. The timing and method of notification are also adjusted based on sentiment data.

[0746] Step 9:

[0747] Server: The server sends the generated notification message to the customer's device. It selects the optimal timing, such as sending the message during a time when the user is relaxed, taking into account emotional data.

[0748] Step 10:

[0749] Device: Receives a notification and displays it to the user, who can see the plan details and reasons.

[0750] Step 11:

[0751] User: Check the notified plan and decide whether to accept it. If you accept it, select "Change" on the device settings screen.

[0752] Step 12:

[0753] Terminal: Sends the user's selection information to the server. A request is sent to the server requesting the application of the new plan.

[0754] Step 13:

[0755] Server: Updates the customer's subscription information based on the received request. The new pricing plan is applied immediately.

[0756] Step 14:

[0757] Server: Notifies the customer that the plan change was successful. Sends a notification message to the device to let the user know that the change is complete.

[0758] Step 15:

[0759] Device: Receives notification and displays to the user that the plan change was successful.

[0760] This detailed process flow allows customers to easily and quickly select and apply the pricing plan that best suits their usage and emotional state.

[0761] Example 2

[0762] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0763] Conventional systems select service plans for customers based solely on usage data, making it difficult to provide personalized services that take into account the customer's emotional state and stress levels due to usage. Furthermore, notifications were not provided at the appropriate time, which could lead to lower customer satisfaction and increased stress due to unnecessary notifications. Furthermore, when customers approved a proposed plan, there was a lack of transparency regarding the plan contents and the reasons for selection, making it difficult to improve reliability.

[0764] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0765] In this invention, the server includes means for collecting usage data and emotion data from the terminal, means for storing the collected usage data and emotion data, means for analyzing the stored usage data and emotion data and selecting an optimal service plan for the customer, means for notifying the customer of the selected service plan, means for adjusting the timing and method of notification based on the customer's emotional state, and means for changing the service plan with the customer's approval. This makes it possible to provide personalized services that take the customer's emotional state into consideration and to notify them at an appropriate time, and improves the transparency of the plan contents and the reasons for selection, thereby enabling increased customer satisfaction and reliability.

[0766] A "terminal" is a device used by a user that has the function of recording and transmitting usage data such as data communication, calls, and SMS, and also collecting emotional data.

[0767] "Usage data" refers to information such as data traffic, call time, and SMS usage generated when a user uses a mobile service.

[0768] "Emotional data" refers to information indicating a user's emotional state (e.g., stress level, relaxation level) analyzed from their facial expressions and vocal tone.

[0769] "Server" refers to a central aggregation system that receives, stores, and analyzes usage data and emotion data sent from terminals.

[0770] The term "storing means" refers to a method or device for storing the received usage data and emotion data in a storage device such as a database.

[0771] "Means for analyzing" refers to methods and devices for analyzing accumulated usage and sentiment data and using machine learning algorithms to identify usage patterns.

[0772] The "means for selecting the optimal service plan" refers to a method or device for selecting the most suitable rate plan for a customer based on the analysis results.

[0773] The "notification means" refers to a method or device for transmitting information about the selected optimum service plan to the user's terminal and displaying it.

[0774] "Means for adjusting the timing and method of notification based on the emotional state" refers to a method or device for providing notification at the most appropriate timing and in the most appropriate manner, taking into account the user's emotional data.

[0775] "Means for changing the service plan upon approval" refers to a method or device for sending information to a server when a user approves a proposed service plan and immediately changing the service plan.

[0776] The system of the present invention automatically provides mobile subscribers with the most appropriate pricing plan based on their usage and emotional state. This system combines traditional usage data with an emotion engine that recognizes user emotions to provide a more personalized service.

[0777] Data collection and storage

[0778] First, the system collects usage and emotion data from the device. The device periodically records information such as data traffic, call duration, and SMS usage, and sends it to the server. The device is equipped with an emotion engine that recognizes the user's emotions, and analyzes the user's emotional state in real time from facial expressions and voice tones, and also sends this data to the server.

[0779] The server stores the received data in a database, recording each customer's usage and emotional state in detail. This is done using a database management system (DBMS), such as an open-source database like MySQL or PostgreSQL.

[0780] Data analysis

[0781] The server periodically analyzes the accumulated usage and sentiment data, and uses machine learning algorithms to identify each customer's usage patterns based on past usage data and make future usage predictions. This can be done using machine learning libraries such as TensorFlow and scikit-learn.

[0782] Emotional data is also analyzed by an emotion engine, and analysis is carried out taking into account the user's emotional state. For example, if a user's stress level is high during a particular time period or situation, it is possible to adjust notifications to avoid those times.

[0783] Plan selection

[0784] Based on the analysis results, the server selects the optimal plan for the customer, taking into account usage data and emotional data. Specifically, it selects the optimal plan based on data traffic, call time, and SMS usage, and provides a plan that the user can reasonably accept based on emotional data.

[0785] Plan presentation and notification

[0786] The server then notifies the device of the optimal pricing plan. The notification message includes details of the recommended plan and the reasons for its selection, providing information to the customer in a transparent manner. The timing and method of notifications are also adjusted based on emotional data. For example, notifications can be sent at times when the user is relaxed, increasing the likelihood of approval.

[0787] Change plan

[0788] When the user receives the notification, they can review the proposed plan and choose whether to accept it. If the user accepts the new plan, the information is sent from the device to the server. The server receives the approval information and updates the customer's settings, so the new pricing plan is automatically applied.

[0789] Specific examples

[0790] User D's scenario

[0791] As a specific example, the case of user D will be described.

[0792] 1. Data Collection

[0793] Device: User D's device records 20GB of data traffic, 80 minutes of talk time, and 15 SMS messages this month. The emotion engine analyzes User D's emotional state in real time and records his stress level, relaxation state, etc.

[0794] Server: Collects usage data and emotion data from devices and stores them in a database.

[0795] 2. Data analysis

[0796] Server: Based on usage data from the past three months, the server analyzes that User D's average data usage is 18GB, talk time is 85 minutes, and SMS usage is 12 messages. It also uses a machine learning algorithm to predict future usage. At the same time, it analyzes emotion data and determines that User D's stress level tends to be higher in the morning.

[0797] 3. Plan selection

[0798] Server: Based on the analysis results, it determines that the 25GB data plan + 100 minutes call plan is optimal. Taking into account the emotional data, it sends notifications during the day, avoiding the morning.

[0799] 4. Plan presentation and notification

[0800] Server: Generates a notification message of the optimal plan and sends it to User D's device. The notification contains details of the proposed plan and the reasons for it.

[0801] Terminal: Receives notifications and displays them to the user.

[0802] 5. Change of plan

[0803] User: Check the notification and accept the proposed plan. Select "Change" on the device settings screen.

[0804] Terminal: Sends authorization information to the server.

[0805] Server: Receives the approval information and updates User D's settings. The new pricing plan is applied immediately and the server notifies the user that the plan change was successful.

[0806] Device: Receives notifications and displays them to the user.

[0807] In this way, by taking into account the user's usage and emotional state, we can provide more personalized and optimal pricing plans, improving customer satisfaction and preventing excessive payment of fees.

[0808] Prompt Sentence Examples

[0809] Below are some example prompts to input into the generative AI model to illustrate how this system can be used.

[0810] A user has a mobile plan with a high data usage and relatively long talk time. Analysis by the emotion engine reveals that the user's stress level tends to be higher in the morning. Design a system to recommend the optimal plan for this user and send notifications at appropriate times taking into account the emotion data.

[0811] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0812] Step 1:

[0813] Data collection

[0814] Input: Data from on-device sensors and logs, user facial expressions and vocal tones

[0815] Specific operation: The device periodically records usage data such as data traffic, call time, and SMS usage. The emotion engine analyzes the user's emotional state (e.g., stress level, relaxation level) from their facial expressions and voice.

[0816] Output: Collected usage and sentiment data

[0817] Step 2:

[0818] Data transmission

[0819] Input: Collected usage and sentiment data

[0820] Specific operation: The device periodically sends the collected data to the server. At this time, the data is encrypted and sent securely.

[0821] Output: Usage and emotion data sent to the server

[0822] Step 3:

[0823] Data accumulation

[0824] Input: Usage data and emotion data received by the server

[0825] Specific operation: The server stores the received data in a database, where data is organized for each user and managed in an easily accessible format.

[0826] Output: Usage data and emotion data stored in a database

[0827] Step 4:

[0828] Data analysis

[0829] Input: Usage data and emotion data stored in a database

[0830] How it works: The server uses machine learning algorithms to analyze usage data and identify each customer's usage patterns. It also analyzes emotion data to understand patterns of emotional states (e.g., stress levels) during specific times and situations. The libraries used include TensorFlow and scikit-learn.

[0831] Output: Usage and sentiment patterns for each customer

[0832] Step 5:

[0833] Plan selection

[0834] Input: Usage patterns and emotion patterns

[0835] Specific operation: The server selects the optimal pricing plan for each customer based on their usage patterns. It also takes into account their emotional patterns and provides a plan that the user can reasonably accept.

[0836] Output: The optimal pricing plan selected

[0837] Step 6:

[0838] Notification generation

[0839] Input: Selected optimal pricing plan and sentiment patterns

[0840] Specific operation: The server generates a notification message of the optimal plan and sends it to the device at the optimal time based on the emotional pattern. The notification includes details of the recommended plan and the reasons for it.

[0841] Output: Notification message sent to the terminal

[0842] Step 7:

[0843] Notification display

[0844] Input: Notification message sent from the server

[0845] Specific operation: The terminal displays the received notification message to the user.

[0846] Output: Notification message displayed to the user

[0847] Step 8:

[0848] Plan Approval

[0849] Input: User confirmed notification message

[0850] Specific operation: The user checks the notification and selects "Change" on the device settings screen.

[0851] Output: Plan Approval Selection

[0852] Step 9:

[0853] Send approval information

[0854] Input: User selected plan approval information

[0855] Specific operation: The terminal sends the plan approval information to the server. The information is encrypted.

[0856] Output: Plan approval information sent to the server

[0857] Step 10:

[0858] Update settings

[0859] Input: Plan approval information sent to the server

[0860] What happens: The server receives the authorization information and updates the customer's settings to apply the new pricing plan.

[0861] Output: New pricing plan applied

[0862] Step 11:

[0863] Change Notification

[0864] Input: New pricing plan applied

[0865] Specific operation: The server notifies the terminal that the plan change was successful.

[0866] Output: Change notification messages sent to the terminal

[0867] Step 12:

[0868] Change result display

[0869] Input: Change notification message sent from the server

[0870] Specific behavior: The device receives the notification and displays it to the user.

[0871] Output: The change notification message displayed to the user

[0872] (Application example 2)

[0873] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0874] Current electronic payment services have difficulty offering plans and promotions that take into account a customer's usage status and spending patterns. Furthermore, notifications are sent without considering the customer's emotional state, so the information provided is not always timely or effective for the customer. As a result, customer satisfaction declines and it becomes difficult to provide optimal service.

[0875] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0876] In this invention, the server includes means for collecting usage data and emotional data from the terminal, means for storing the collected data, means for analyzing the stored data and selecting an optimal electronic payment plan and promotion for the customer, means for notifying the customer of the selected electronic payment plan and promotion, and means for changing the plan and promotion with the customer's approval, thereby enabling timely and effective service provision that takes into account the customer's spending patterns and emotional state.

[0877] "Terminal" means a device used by a User to input or collect Usage Data and Emotional Data.

[0878] "Usage data" refers to information related to electronic payments, such as a user's spending history and purchase details.

[0879] "Emotional Data" means data collected to describe a user's emotional state, including facial expressions and vocal tones.

[0880] "Storage" is the process of storing collected usage data and emotion data in a database.

[0881] "Analysis" is the process of analyzing accumulated data using machine learning algorithms and other methods to identify users' spending patterns and emotional states.

[0882] An "electronic payment plan" is a plan that includes fee plans and point rewards when a user uses electronic payment.

[0883] "Promotion" refers to an advertising campaign such as cashback or special offers offered to users.

[0884] "Notification" means the act of informing a User of the details of the selected Electronic Payment Plan or Promotion and the reasons for such selection.

[0885] "Acceptance" means the user's acceptance of a proposed plan or promotion.

[0886] "Modification" is the process of updating an electronic payment plan or promotion based on user approval.

[0887] The system that realizes this application example is mainly composed of a terminal, a server, and an emotion recognition engine. A specific implementation method is described below.

[0888] Hardware and Software Configuration

[0889] Hardware and software used:

[0890] 1. Device: This refers to the smartphone held by the user, and is the device that collects usage data and emotional data.

[0891] 2. Emotion recognition engine: For example, using the Microsoft Azure Emotion API to analyze a user's emotions from facial expressions and voice tones collected via a smartphone's camera and microphone.

[0892] 3. Server: Stores usage data and emotion data in a database (e.g., MySQL) and performs data analysis.

[0893] 4. Data analysis platform: Responsible for processing and analyzing large-scale data using Apache Spark and other technologies.

[0894] 5. Machine learning algorithms: Using TensorFlow and other technologies, we analyze user usage patterns and sentiment data to select optimal e-payment plans and promotions.

[0895] Program processing

[0896] The system performs data processing and calculation as follows.

[0897] Data collection:

[0898] The device periodically records usage data such as the user's spending history and purchase details and sends it to the server. In addition, an emotion recognition engine analyzes the user's emotional state in real time and sends that data to the server.

[0899] Data accumulation:

[0900] The server stores the usage data and emotion data sent from the device in a database. The data is periodically updated and stored, so that the latest usage status and emotion state are always maintained.

[0901] Data Analysis:

[0902] The server analyzes the accumulated data using machine learning algorithms. It identifies the user's spending patterns from past usage data and predicts future usage. At the same time, it analyzes emotional data to understand the user's stress level and relaxation state.

[0903] Plan Selection and Notification:

[0904] Based on the analysis results, the server selects the most suitable electronic payment plan and promotion for the user, and the selected plan or promotion is notified to the terminal, adjusting the notification timing based on the user's emotional state.

[0905] Plan Change:

[0906] The user can review the notification and accept or reject the proposed plans and promotions. If accepted, the server uses that information to modify the plans and promotions and update the user's settings.

[0907] Specific examples

[0908] For example, if a user recently made a large purchase, the system will detect that spending data and store it in a database. At the same time, an emotion recognition engine will analyze the user's state of relaxation, and notify them of a specific cashback campaign at a time when they are relaxed, which is expected to increase approval rates. Furthermore, the system can predict a user's spending patterns from past data and provide them with the optimal electronic payment plan.

[0909] Prompt Sentence Examples

[0910] "Based on the spending data (50 items) and emotional data (50 items) from the past three months, please generate a code that analyzes the user's spending patterns and emotional state and suggests the optimal payment plan."

[0911] In this way, timely and effective service delivery can be achieved that takes into account the customer's spending patterns and emotional state.

[0912] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0913] Step 1:

[0914] Data collection

[0915] The device collects usage data such as the user's spending history and purchases, and simultaneously collects the user's emotional state by analyzing facial expressions and vocal tone using an emotion recognition engine.

[0916] Input: spending history, purchase details, facial expressions, voice tones

[0917] Data processing: Organize and structure the collected usage data and sentiment data.

[0918] Output: Structured usage and sentiment data

[0919] Step 2:

[0920] Data transmission

[0921] The device transmits the collected usage and emotion data to a server, either periodically or in real time.

[0922] Input: Structured usage data and sentiment data

[0923] Data Calculation: Convert the data into the appropriate format and send it to the server.

[0924] Output: Data sent to the server

[0925] Step 3:

[0926] Data accumulation

[0927] The server stores the usage data and emotion data sent from the terminal in a database.

[0928] Input: Submitted usage data and emotion data

[0929] Data processing: Record and save the received data in a database.

[0930] Output: Data stored in the database

[0931] Step 4:

[0932] Data analysis

[0933] The server analyzes the accumulated usage data and emotional data using machine learning algorithms to identify the user's spending patterns from past usage data and understand the user's emotional state from emotional data.

[0934] Input: Usage data and emotion data stored in a database

[0935] Data Computing: Data Analysis and Pattern Recognition with Machine Learning Models

[0936] Output: Analysis of user spending patterns and emotional state

[0937] Step 5:

[0938] Plan selection

[0939] The server selects the most suitable e-payment plan and promotion for the user based on the analysis results, and adjusts notifications to be sent at the appropriate time, taking into account emotional data.

[0940] Input: Analysis results (spending patterns and emotional state)

[0941] Data calculation: Selecting the best plan and promotion

[0942] Output: Selected electronic payment plans and promotions

[0943] Step 6:

[0944] notification

[0945] The server sends a notification message containing details of the selected electronic payment plan and promotion to the terminal, optimizing the timing of the notification based on the emotion data.

[0946] Input: Selected plan and promotion

[0947] Data calculation: Notification message generation and timing adjustment

[0948] Output: Notification message sent to the terminal

[0949] Step 7:

[0950] Change plan

[0951] The user reviews the notification and can accept or reject the proposed plan or promotion. If accepted, the device sends the information to the server, which then changes the plan or promotion and updates the user's settings.

[0952] Input: User approval / rejection

[0953] Data operation: Plan and promotion update processing

[0954] Output: Updated electronic payment plans and promotions

[0955] In this way, a system is realized that comprehensively analyzes the spending patterns and emotional state of customers and provides timely and effective electronic payment plans and promotions.

[0956] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0957] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0958] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0959] [Third embodiment]

[0960] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0961] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0962] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0963] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0964] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0965] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0966] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0967] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0968] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0969] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0970] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0971] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0972] The system of the present invention automatically provides mobile subscribers with the most appropriate rate plan based on their usage. The system collects usage data from the terminal, stores and analyzes the collected data, selects the most appropriate rate plan, and notifies the customer. It also has the ability to automatically change plans with the customer's approval.

[0973] Data collection and storage

[0974] The system first collects usage data from the device. The device has the ability to record information such as data traffic, call time, and SMS usage, and this data is periodically sent to the server. The server stores the received data in a database. This allows for detailed records of each customer's usage status to be used for later analysis.

[0975] Data analysis

[0976] The server uses machine learning algorithms to analyze the accumulated data. Specifically, it analyzes customer usage patterns based on past usage data and predicts future usage. Based on the results of this analysis, it selects the optimal pricing plan for the customer. For example, if the average data usage over the past three months is within a certain range, it will propose the optimal data plan based on that.

[0977] Plan presentation and notification

[0978] The server notifies the terminal of the selected optimal rate plan. The notification message includes details of the proposed plan and the reasons for it, providing information to the customer in a transparent manner. The terminal receives this notification and displays it to the user.

[0979] Change plan

[0980] When the user receives the notification, they review the proposed plan and choose whether to accept it. If the user accepts the new plan, the device sends that information to the server. The server receives this approval information and updates the customer's settings, so the new pricing plan is automatically applied.

[0981] Specific examples

[0982] User C's scenario

[0983] 1. Data Collection

[0984] Device: User C's device records this month's data usage of 15GB, talk time of 120 minutes, and SMS usage of 5 messages.

[0985] Server: Stores data collected from devices in a database. This data is updated every 5 minutes.

[0986] 2. Data analysis

[0987] Server: Based on usage data from the past three months, it is analyzed that User C's average data usage is 16GB, talk time is 110 minutes, and SMS usage is 4. It also uses a machine learning algorithm to predict future usage.

[0988] 3. Plan presentation and notification

[0989] Server: Based on the analysis results, it determines that the "20GB data plan + 120 minutes call plan" is optimal. It generates a notification message and sends it to User C's device.

[0990] Device: Receives and displays a notification to the user, detailing the proposed plan and explaining the reasons for it.

[0991] 4. Change of plan

[0992] User: Check the notification and accept the proposed plan by selecting "Change" from the device settings screen.

[0993] Terminal: Sends authorization information to the server.

[0994] Server: Receives the approval information and updates User C's settings. Notifies the user that the new pricing plan has been applied.

[0995] In this way, the present invention can improve customer satisfaction by automatically selecting the most suitable rate plan based on the customer's usage status and providing it in real time.

[0996] The processing flow will be explained below.

[0997] Step 1:

[0998] Device: Records usage data. When a user uses a mobile phone, the device records information such as data traffic, call duration, and number of SMS sent. This data is set to be updated periodically.

[0999] Step 2:

[1000] Device: Sends recorded usage data to the server. Data is transferred to the server at specific intervals (e.g., every 5 minutes). Data transmission uses encryption technology to ensure secure communication.

[1001] Step 3:

[1002] Server: Stores the received usage data in a database. Organizes the data for each customer and stores it for future analysis.

[1003] Step 4:

[1004] Server: Periodically analyzes the accumulated data. Machine learning algorithms are used to identify each customer's usage patterns based on past usage data. For example, the average data usage, call minutes, and SMS usage over the past three months are calculated.

[1005] Step 5:

[1006] Server: Based on the analysis results, the server selects the most suitable pricing plan for the customer. It considers usage data patterns and selects the most cost-effective plan from the list of plans.

[1007] Step 6:

[1008] Server: After selecting the best pricing plan, generate a notification message containing details of the recommended plan and the reasons for it.

[1009] Step 7:

[1010] Server: The generated notification message is sent to the client's terminal. The data is transferred in real time, and the user is notified immediately.

[1011] Step 8:

[1012] Device: Receives a notification and displays it to the user, who can see the plan details and reasons.

[1013] Step 9:

[1014] User: Check the notified plan and decide whether to accept it. If you accept it, select "Change" on the device settings screen.

[1015] Step 10:

[1016] Terminal: Sends the user's selection information to the server. A request is sent to the server requesting the application of the new plan.

[1017] Step 11:

[1018] Server: Updates the customer's subscription information based on the received request. The new pricing plan is applied immediately.

[1019] Step 12:

[1020] Server: Notifies the customer that the plan change was successful. Sends a notification message to the device to let the user know that the change is complete.

[1021] Step 13:

[1022] Device: Receives notification and displays to the user that the plan change was successful.

[1023] This detailed process flow allows customers to easily and quickly select and apply the rate plan that best suits their usage situation.

[1024] Example 1

[1025] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1026] This invention relates to a system that automatically provides mobile subscribers with the most appropriate rate plan based on their usage. Conventional methods involve manually collecting and analyzing usage data, making it difficult to provide customers with the most appropriate plan in real time. For this reason, there has been a need for a method to quickly and effectively provide rate plans that meet customer needs.

[1027] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1028] In this invention, the server includes means for collecting usage data from the terminal, means for storing the collected usage data, means for analyzing the stored usage data using a machine learning algorithm and selecting an optimal service plan for the customer, means for sending a notification to the customer including details of the selected service plan and the reasons for the selection, and means for automatically changing the service plan with the customer's approval. This makes it possible to provide an optimal rate plan in real time based on the customer's usage status and improve customer satisfaction.

[1029] A "terminal" is an electronic device used by a user that has the function of collecting usage data such as data communication, calls, and SMS, and communicating with a server.

[1030] "Usage data" refers to information such as data usage, call time, and SMS usage when a user uses a mobile service.

[1031] A "server" is a central processing unit that receives, stores, and analyzes data sent from terminals.

[1032] A "machine learning algorithm" is an algorithm that learns from past data and predicts future data and patterns.

[1033] "Notification" is the act of sending a server-generated message to a terminal to provide information to a user.

[1034] "Customer Approval" refers to the User receiving the notification reviewing the proposed service plan and taking the action of consenting or rejecting it.

[1035] "Service Plan" refers to the pricing structure and terms of use offered to a mobile subscriber, including data volume, talk time, number of SMS sent, etc.

[1036] "Automatically change" refers to the server programmatically updating the service plan without manual intervention after obtaining user approval.

[1037] The system of the present invention automatically provides the most suitable rate plan to a mobile subscriber based on their usage. The system collects usage data from the terminal, stores and analyzes the collected data on a server, selects the most suitable rate plan, and notifies the customer. Furthermore, the system also has the function of automatically changing plans with the customer's approval.

[1038] Hardware and software used

[1039] This system mainly uses the following hardware and software:

[1040] 1. Terminal

[1041] Hardware: Mobile devices such as smartphones and tablets.

[1042] Software: Applications for collecting usage data.

[1043] 2. Server

[1044] Hardware: Database servers, compute servers for running machine learning models.

[1045] Software: Database management systems, machine learning algorithms, notification services.

[1046] Specific processing flow

[1047] Data collection and storage

[1048] The device collects usage data in real time, such as the user's data traffic, call time, and SMS usage. This usage data is stored in the device's internal storage and periodically (for example, every five minutes) sent to the server. The server stores the received data in a database, recording each customer's usage status in detail. This data can then be used for later data analysis.

[1049] Data analysis

[1050] The server analyzes the accumulated usage data using machine learning algorithms. Based on past usage data, the server analyzes the customer's usage patterns and predicts future usage. For example, if the average data usage over the past three months is within a certain range, the server can suggest the optimal data plan based on that prediction. The machine learning models used are often run on cloud platforms.

[1051] Plan presentation and notification

[1052] The server selects the optimal pricing plan for the customer based on the results of the data analysis. It generates a notification message containing details of the selected pricing plan and the reasons for it, and sends it to the customer's device. The device receives this notification and displays it to the user. The notification clearly explains how the change in pricing plan will benefit the customer.

[1053] Change plan

[1054] The user checks the notification on the device and chooses whether to accept the proposed pricing plan. If accepted, the device sends the information to the server. The server receives the approval information and updates the customer's account settings to the new pricing plan. The new pricing plan is then immediately applied, and the server notifies the device again.

[1055] Specific examples

[1056] User C's scenario

[1057] 1. Data Collection

[1058] Device: User C's device records this month's data usage of 15GB, talk time of 120 minutes, and SMS usage of 5 messages.

[1059] Server: Stores data collected from devices in a database. This data is updated every 5 minutes.

[1060] 2. Data analysis

[1061] Server: Based on usage data from the past three months, it is analyzed that User C's average data usage is 16GB, talk time is 110 minutes, and SMS usage is 4. It also uses a machine learning algorithm to predict future usage.

[1062] 3. Plan presentation and notification

[1063] Server: Based on the analysis results, it determines that the "20GB data plan + 120 minutes call plan" is optimal. It generates a notification message and sends it to User C's device.

[1064] Device: Receives and displays a notification to the user, detailing the proposed plan and explaining the reasons for it.

[1065] 4. Change of plan

[1066] User: Check the notification and accept the proposed plan by selecting "Change" from the device settings screen.

[1067] Terminal: Sends authorization information to the server.

[1068] Server: Receives the approval information and updates User C's settings. Notifies the user that the new pricing plan has been applied.

[1069] Prompt Sentence Examples

[1070] "Please analyze and suggest the optimal pricing plan for User C based on usage data from the past three months."

[1071] As described above, the present invention can improve customer satisfaction by automatically selecting an optimal rate plan based on the customer's usage status and providing it in real time.

[1072] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1073] Step 1:

[1074] Data collection

[1075] Input: User data usage, call time, SMS usage

[1076] How it works: The device collects usage data in real time and stores it in storage.

[1077] Example: A device records the current amount of data traffic and updates it every 5 minutes.

[1078] Output: The latest usage data is saved on the device.

[1079] Step 2:

[1080] Data transmission

[1081] Input: Usage data stored on the device

[1082] How it works: The device periodically sends collected data to a server. The data is encrypted and transmitted securely.

[1083] Example: A device sends the latest usage data to a server every 5 minutes.

[1084] Output: Usage data arrives at the server and is received.

[1085] Step 3:

[1086] Data accumulation

[1087] Input: Usage data sent to the server

[1088] How it works: The server stores the data it receives in a database, organizing it by customer for quick access and analysis later.

[1089] Example: The server adds user C's data usage of 15 GB, talk time of 120 minutes, and SMS usage of 5 to the database.

[1090] Output: The latest usage data is saved in the database.

[1091] Step 4:

[1092] Data analysis

[1093] Input: Usage data stored in the database

[1094] How it works: The server analyzes the data using machine learning algorithms, analyzing customer usage patterns based on past data and predicting future usage.

[1095] Example: The server analyzes usage data from the past three months and predicts that User C's average data usage is 16 GB, talk time is 110 minutes, and SMS usage is 4.

[1096] Output: The analysis results in customer usage patterns and predictions of future usage.

[1097] Step 5:

[1098] Plan selection

[1099] Input: Results of data analysis

[1100] How it works: The server selects the optimal pricing plan for the customer based on the analysis results. This selection is made by comparing the usage forecast with the terms of existing pricing plans.

[1101] Example: The server determines that the "20GB data plan + 120 minutes call plan" is optimal for user C.

[1102] Output: Detailed information on the best pricing plan.

[1103] Step 6:

[1104] Plan Notification

[1105] Input: Details of the best rate plan

[1106] Operation: The server generates a notification message containing details of the selected rate plan and the reason for the selection, and sends it to the terminal.

[1107] Example: The server generates a message detailing the "20GB data plan + 120 minutes call plan" and the reason for the plan, and sends it to User C's device.

[1108] Output: A notification message arrives on the terminal.

[1109] Step 7:

[1110] User Authorization

[1111] Input: Notification message

[1112] How it works: The user sees the notification on their device and chooses whether to accept the proposed pricing plan.

[1113] Example: User C checks the notification and presses the "Change" button on the device to approve the proposed plan.

[1114] Output: The authorization information is entered into the terminal.

[1115] Step 8:

[1116] Change plan

[1117] Input: User authorization information

[1118] Operation: The device sends the authorization information to the server, which updates the customer's settings with the new rate plan, which then applies the new rate plan.

[1119] Example: The server receives user C's authorization information and updates user C's settings to "20GB data plan + 120 minutes call plan."

[1120] Output: The new pricing plan is applied and you are notified.

[1121] (Application example 1)

[1122] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1123] With conventional electronic payment services, users must analyze their own usage data and select the appropriate plan to suit their usage, which is time-consuming and laborious. Furthermore, users may not be able to determine the appropriate plan and end up paying excessive fees. Furthermore, there is a lack of a mechanism for flexibly changing plans based on the user's lifestyle and frequency of use, resulting in low user satisfaction.

[1124] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1125] In this invention, the server includes means for collecting usage data from the terminal, means for storing the collected usage data, means for analyzing the stored usage data and selecting an optimal service plan for the customer, means for notifying the customer of the selected service plan, means for changing the service plan with the customer's approval, means for identifying usage data for the electronic payment service and using a machine learning algorithm to predict an optimal rate plan based on the usage data, and means for notifying the user terminal of the selected rate plan and obtaining approval. This makes it possible to automatically propose an optimal rate plan based on the user's usage data and flexibly change the plan with approval.

[1126] "Terminal" refers to a computing device such as a mobile phone, smartphone, or tablet that an investor uses on a daily basis.

[1127] "Usage data" refers to information such as the amount of data used, the amount used, and the number of transactions when a user uses an electronic payment service.

[1128] "Storage means" refers to a recording device or database for storing collected usage data.

[1129] "Analytical means" refers to machine learning algorithms and analytics software that evaluate collected and stored usage data and extract patterns.

[1130] "Optimal service plan" refers to the most cost-effective plan selected based on the user's past and predicted usage.

[1131] "Means of notification" refers to the messaging system or application functionality used to communicate information about the selected service plan to the user.

[1132] "Means for changing service plans with approval" means the system's ability to automatically update service plans after obtaining user consent.

[1133] "Electronic Payment Services" refers to payment platforms and systems that enable online or offline payments, purchases and transactions.

[1134] A "machine learning algorithm" refers to a mathematical model or computational method for learning patterns from past data and predicting or classifying future data.

[1135] "User terminal" refers to a computing device (smartphone, tablet, etc.) operated by a user when using an electronic payment service.

[1136] Data collection

[1137] The server first collects usage data from the device. This data includes communication volume, usage amount, number of transactions, etc. This collection process is carried out periodically through the device's API (Application Programming Interface). Specifically, it collects usage information from electronic payment services accessed by smartphones and tablet devices.

[1138] Data accumulation

[1139] The collected usage data is stored in a database on the server. The database is constructed using SQLite, and the collected data is saved in the database. This data storage process records detailed usage information for each user.

[1140] Data analysis

[1141] The server uses a machine learning algorithm to analyze the accumulated data. Specifically, it uses a linear regression model from scikit-learn. It analyzes customer usage patterns based on past usage data and predicts future usage. During this process, it extracts and analyzes features from the usage data. Based on the results of this analysis, it selects the optimal pricing plan for each user.

[1142] Plan presentation and notification

[1143] After the optimal plan is selected, the server notifies the user via a messaging system, and the user receives details of the proposed plan and the reasons for its selection via an application on their smartphone or tablet. The notification message also includes an option for the user to approve the plan.

[1144] Change plan

[1145] If the user approves the proposed plan, the device sends the approval information to the server. The server automatically updates the pricing plan based on that information. This update process uses an API to appropriately change the database settings. Once the change is complete, the server notifies the user again, informing them that the new pricing plan has been applied.

[1146] Specific examples

[1147] User A's scenario

[1148] User A's device records a monthly transaction amount of 5,000 yen and 50 transactions. The server stores this information in a database and analyzes it using a linear regression model in scikit-learn. As a result, it determines that a "10% cashback plan for users who spend more than 5,000 yen per month" is optimal for User A. The server notifies User A's smartphone of the details of this plan and the reasons for it. When User A approves through the application, the server automatically changes the pricing plan and notifies User A again.

[1149] Prompt Sentence Examples

[1150] "Please suggest the best plan for a monthly electronic payment amount of 5,000 yen or more and 50 or more transactions."

[1151] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1152] Step 1:

[1153] The server collects usage data from the device. Specifically, it periodically obtains data such as communication volume, usage amount, and number of transactions through the API of the electronic payment service accessed by the smartphone or tablet device. The input is the API request from the device, and the output is the obtained usage data. This data is often received in JSON format.

[1154] Step 2:

[1155] The server stores the collected usage data in a database. Specifically, it parses the acquired JSON data and stores it in a database such as SQLite. At this time, the data is converted into an appropriate format and stored as a record for each customer. The input is the collected usage data, and the output is the data stored in the database.

[1156] Step 3:

[1157] The server analyzes the accumulated usage data. Specifically, it reads past usage data stored in the database and analyzes it using a linear regression model from scikit-learn. During the analysis, transaction amounts and number of transactions are used as features to predict future usage patterns. The input is the usage data obtained from the database, and the output is the analysis results (predicted usage patterns).

[1158] Step 4:

[1159] The server selects the optimal pricing plan. Based on the analysis results obtained by the machine learning algorithm, it determines the optimal plan for each user. Specifically, it compares the analysis results with existing pricing plans and selects the most appropriate plan. The input is the analysis results and existing pricing plan information, and the output is the selected optimal pricing plan.

[1160] Step 5:

[1161] The server notifies the user of the selected optimal plan via a messaging system, displaying details of the plan on the user's smartphone or tablet. The input is the selected plan and the user's contact information, and the output is a notification message sent to the user's device.

[1162] Step 6:

[1163] The user receives the notification and approves the plan. The user checks the details of the proposed plan on the user terminal and selects whether to approve or reject it. The input is the notification content displayed to the user, and the output is the user's selection of whether to approve or reject it.

[1164] Step 7:

[1165] The server receives the user's approval information and automatically changes the pricing plan. Specifically, it updates the database settings based on the approval information and applies the new pricing plan. The input is the user's approval information, and the output is the updated database settings and a final notification to the user's terminal.

[1166] This process will create a system in which the most suitable pricing plan is automatically proposed based on the user's usage data, and if the user approves it, the plan is automatically applied.

[1167] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1168] The system of the present invention automatically provides mobile subscribers with the most appropriate pricing plan based on their usage and emotional state. This system combines traditional usage data with an emotion engine that recognizes user emotions to provide a more personalized service.

[1169] Data collection and storage

[1170] First, the system collects usage data from the device. The device periodically records information such as data traffic, call time, and SMS usage, and sends it to the server. The server then stores the received data in a database, recording each customer's usage in detail. In addition, the device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state in real time, for example, from facial expressions and voice tones, and also sends this data to the server.

[1171] Data analysis

[1172] The server periodically analyzes usage data and emotion data. First, it uses a machine learning algorithm to identify each customer's usage patterns based on past usage data. For example, it calculates the average data volume, call time, and SMS usage over the past three months and predicts future usage. Next, it analyzes the emotion data using an emotion engine to understand the user's emotional state. This makes it possible to adjust the system, for example, by avoiding notifications at certain times or situations when the user's stress level is high.

[1173] Plan selection

[1174] Based on the analysis results, the server considers usage data and emotional data to select the optimal pricing plan for the customer. Not only does it select the optimal plan based on usage patterns, but it also considers the user's emotional state to provide a plan that is reasonably acceptable to the user.

[1175] Plan presentation and notification

[1176] The server then notifies the device of the optimal pricing plan that has been selected. The notification message includes details of the recommended plan and the reasons for its selection, providing information to the customer in a transparent manner. The timing and method of notification are also adjusted based on emotional data. For example, by selecting a time when the user is relaxed to send the notification, the likelihood of approval is increased.

[1177] Change plan

[1178] When the user receives the notification, they can review the proposed plan and choose whether to accept it. If the user accepts the new plan, the information is sent from the device to the server. The server receives the approval information and updates the customer's settings, so the new pricing plan is automatically applied.

[1179] Specific examples

[1180] User D's scenario

[1181] 1. Data Collection

[1182] Device: User D's device records 20GB of data traffic, 80 minutes of talk time, and 15 SMS messages this month. The emotion engine analyzes User D's emotional state in real time and records his stress level, relaxation state, etc.

[1183] Server: Collects usage data and emotion data from devices and stores them in a database.

[1184] 2. Data analysis

[1185] Server: Based on usage data from the past three months, the server analyzes that User D's average data usage is 18GB, talk time is 85 minutes, and SMS usage is 12 messages. It also uses a machine learning algorithm to predict future usage. At the same time, it analyzes emotion data and determines that User D's stress level tends to be higher in the morning.

[1186] 3. Plan selection

[1187] Server: Based on the analysis results, it determines that the "25GB Data Plan + 100 Minutes Call Plan" is optimal. It also takes into account emotional data and sends notifications during the day, avoiding the morning.

[1188] 4. Plan presentation and notification

[1189] Server: Generates a notification message of the optimal plan and sends it to User D's device. The notification contains details of the proposed plan and the reasons for it.

[1190] Terminal: Receives notifications and displays them to the user.

[1191] 5. Change of plan

[1192] User: Check the notification and accept the proposed plan. Select "Change" on the device settings screen.

[1193] Terminal: Sends authorization information to the server.

[1194] Server: Receives the approval information and updates User D's settings. The new pricing plan is applied immediately and the server notifies the user that the plan change was successful.

[1195] Device: Receives notifications and displays them to the user.

[1196] By taking into account both the user's usage and emotional state, the system can provide a more personalized and optimal pricing plan for the customer, thereby improving customer satisfaction and preventing excessive charges.

[1197] The processing flow will be explained below.

[1198] Step 1:

[1199] Device: Records usage data. When a user uses a mobile phone, the device records information such as data traffic, call duration, and number of SMS sent. This data is set to be updated periodically.

[1200] Step 2:

[1201] Device: Analyzes user emotions in real time. Records the user's emotional state (e.g., stress level, relaxation level) using an emotion engine that analyzes facial expressions, voice tone, text message content, etc.

[1202] Step 3:

[1203] Device: The recorded usage data and emotion data are sent to the server. The data is transferred to the server at specific intervals (e.g., every 5 minutes). Encryption technology is used for data transmission to ensure secure communication.

[1204] Step 4:

[1205] Server: Stores the received usage and sentiment data in a database. Organizes the data for each customer and stores it for future analysis.

[1206] Step 5:

[1207] Server: The accumulated data is periodically analyzed. First, a machine learning algorithm is used to identify each customer's usage pattern based on past usage data. For example, the average data usage over the past three months is calculated and future usage predictions are made.

[1208] Step 6:

[1209] Server: Next, the emotional data is analyzed to understand the user's emotional state. Specific emotional patterns, such as stress level or relaxation state, are extracted from the data.

[1210] Step 7:

[1211] Server: Selects the optimal plan for each customer based on usage data and emotional data. For example, a high-capacity data plan may be recommended for a user who uses the service frequently but is in a relaxed state.

[1212] Step 8:

[1213] Server: After selecting the optimal pricing plan, generate a notification message. The notification contains details of the recommended plan and the reasons for its selection. The timing and method of notification are also adjusted based on sentiment data.

[1214] Step 9:

[1215] Server: The server sends the generated notification message to the customer's device. It selects the optimal timing, such as sending the message during a time when the user is relaxed, taking into account emotional data.

[1216] Step 10:

[1217] Device: Receives a notification and displays it to the user, who can see the plan details and reasons.

[1218] Step 11:

[1219] User: Check the notified plan and decide whether to accept it. If you accept it, select "Change" on the device settings screen.

[1220] Step 12:

[1221] Terminal: Sends the user's selection information to the server. A request is sent to the server requesting the application of the new plan.

[1222] Step 13:

[1223] Server: Updates the customer's subscription information based on the received request. The new pricing plan is applied immediately.

[1224] Step 14:

[1225] Server: Notifies the customer that the plan change was successful. Sends a notification message to the device to let the user know that the change is complete.

[1226] Step 15:

[1227] Device: Receives notification and displays to the user that the plan change was successful.

[1228] This detailed process flow allows customers to easily and quickly select and apply the pricing plan that best suits their usage and emotional state.

[1229] Example 2

[1230] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1231] Conventional systems select service plans for customers based solely on usage data, making it difficult to provide personalized services that take into account the customer's emotional state and stress levels due to usage. Furthermore, notifications were not provided at the appropriate time, which could lead to lower customer satisfaction and increased stress due to unnecessary notifications. Furthermore, when customers approved a proposed plan, there was a lack of transparency regarding the plan contents and the reasons for selection, making it difficult to improve reliability.

[1232] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1233] In this invention, the server includes means for collecting usage data and emotion data from the terminal, means for storing the collected usage data and emotion data, means for analyzing the stored usage data and emotion data and selecting an optimal service plan for the customer, means for notifying the customer of the selected service plan, means for adjusting the timing and method of notification based on the customer's emotional state, and means for changing the service plan with the customer's approval. This makes it possible to provide personalized services that take the customer's emotional state into consideration and to notify them at an appropriate time, and improves the transparency of the plan contents and the reasons for selection, thereby enabling increased customer satisfaction and reliability.

[1234] A "terminal" is a device used by a user that has the function of recording and transmitting usage data such as data communication, calls, and SMS, and also collecting emotional data.

[1235] "Usage data" refers to information such as data traffic, call time, and SMS usage generated when a user uses a mobile service.

[1236] "Emotional data" refers to information indicating a user's emotional state (e.g., stress level, relaxation level) analyzed from their facial expressions and vocal tone.

[1237] "Server" refers to a central aggregation system that receives, stores, and analyzes usage data and emotion data sent from terminals.

[1238] The term "storing means" refers to a method or device for storing the received usage data and emotion data in a storage device such as a database.

[1239] "Means for analyzing" refers to methods and devices for analyzing accumulated usage and sentiment data and using machine learning algorithms to identify usage patterns.

[1240] The "means for selecting the optimal service plan" refers to a method or device for selecting the most suitable rate plan for a customer based on the analysis results.

[1241] The "notification means" refers to a method or device for transmitting information about the selected optimum service plan to the user's terminal and displaying it.

[1242] "Means for adjusting the timing and method of notification based on the emotional state" refers to a method or device for providing notification at the most appropriate timing and in the most appropriate manner, taking into account the user's emotional data.

[1243] "Means for changing the service plan upon approval" refers to a method or device for sending information to a server when a user approves a proposed service plan and immediately changing the service plan.

[1244] The system of the present invention automatically provides mobile subscribers with the most appropriate pricing plan based on their usage and emotional state. This system combines traditional usage data with an emotion engine that recognizes user emotions to provide a more personalized service.

[1245] Data collection and storage

[1246] First, the system collects usage and emotion data from the device. The device periodically records information such as data traffic, call duration, and SMS usage, and sends it to the server. The device is equipped with an emotion engine that recognizes the user's emotions, and analyzes the user's emotional state in real time from facial expressions and voice tones, and also sends this data to the server.

[1247] The server stores the received data in a database, recording each customer's usage and emotional state in detail. This is done using a database management system (DBMS), such as an open-source database like MySQL or PostgreSQL.

[1248] Data analysis

[1249] The server periodically analyzes the accumulated usage and sentiment data, and uses machine learning algorithms to identify each customer's usage patterns based on past usage data and make future usage predictions. This can be done using machine learning libraries such as TensorFlow and scikit-learn.

[1250] Emotional data is also analyzed by an emotion engine, and analysis is carried out taking into account the user's emotional state. For example, if a user's stress level is high during a particular time period or situation, it is possible to adjust notifications to avoid those times.

[1251] Plan selection

[1252] Based on the analysis results, the server selects the optimal plan for the customer, taking into account usage data and emotional data. Specifically, it selects the optimal plan based on data traffic, call time, and SMS usage, and provides a plan that the user can reasonably accept based on emotional data.

[1253] Plan presentation and notification

[1254] The server then notifies the device of the optimal pricing plan. The notification message includes details of the recommended plan and the reasons for its selection, providing information to the customer in a transparent manner. The timing and method of notifications are also adjusted based on emotional data. For example, notifications can be sent at times when the user is relaxed, increasing the likelihood of approval.

[1255] Change plan

[1256] When the user receives the notification, they can review the proposed plan and choose whether to accept it. If the user accepts the new plan, the information is sent from the device to the server. The server receives the approval information and updates the customer's settings, so the new pricing plan is automatically applied.

[1257] Specific examples

[1258] User D's scenario

[1259] As a specific example, the case of user D will be described.

[1260] 1. Data Collection

[1261] Device: User D's device records 20GB of data traffic, 80 minutes of talk time, and 15 SMS messages this month. The emotion engine analyzes User D's emotional state in real time and records his stress level, relaxation state, etc.

[1262] Server: Collects usage data and emotion data from devices and stores them in a database.

[1263] 2. Data analysis

[1264] Server: Based on usage data from the past three months, the server analyzes that User D's average data usage is 18GB, talk time is 85 minutes, and SMS usage is 12 messages. It also uses a machine learning algorithm to predict future usage. At the same time, it analyzes emotion data and determines that User D's stress level tends to be higher in the morning.

[1265] 3. Plan selection

[1266] Server: Based on the analysis results, it determines that the 25GB data plan + 100 minutes call plan is optimal. Taking into account the emotional data, it sends notifications during the day, avoiding the morning.

[1267] 4. Plan presentation and notification

[1268] Server: Generates a notification message of the optimal plan and sends it to User D's device. The notification contains details of the proposed plan and the reasons for it.

[1269] Terminal: Receives notifications and displays them to the user.

[1270] 5. Change of plan

[1271] User: Check the notification and accept the proposed plan. Select "Change" on the device settings screen.

[1272] Terminal: Sends authorization information to the server.

[1273] Server: Receives the approval information and updates User D's settings. The new pricing plan is applied immediately and the server notifies the user that the plan change was successful.

[1274] Device: Receives notifications and displays them to the user.

[1275] In this way, by taking into account the user's usage and emotional state, we can provide more personalized and optimal pricing plans, improving customer satisfaction and preventing excessive payment of fees.

[1276] Prompt Sentence Examples

[1277] Below are some example prompts to input into the generative AI model to illustrate how this system can be used.

[1278] A user has a mobile plan with a high data usage and relatively long talk time. Analysis by the emotion engine reveals that the user's stress level tends to be higher in the morning. Design a system to recommend the optimal plan for this user and send notifications at appropriate times taking into account the emotion data.

[1279] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1280] Step 1:

[1281] Data collection

[1282] Input: Data from on-device sensors and logs, user facial expressions and vocal tones

[1283] Specific operation: The device periodically records usage data such as data traffic, call time, and SMS usage. The emotion engine analyzes the user's emotional state (e.g., stress level, relaxation level) from their facial expressions and voice.

[1284] Output: Collected usage and sentiment data

[1285] Step 2:

[1286] Data transmission

[1287] Input: Collected usage and sentiment data

[1288] Specific operation: The device periodically sends the collected data to the server. At this time, the data is encrypted and sent securely.

[1289] Output: Usage and emotion data sent to the server

[1290] Step 3:

[1291] Data accumulation

[1292] Input: Usage data and emotion data received by the server

[1293] Specific operation: The server stores the received data in a database, where data is organized for each user and managed in an easily accessible format.

[1294] Output: Usage data and emotion data stored in a database

[1295] Step 4:

[1296] Data analysis

[1297] Input: Usage data and emotion data stored in a database

[1298] How it works: The server uses machine learning algorithms to analyze usage data and identify each customer's usage patterns. It also analyzes emotion data to understand patterns of emotional states (e.g., stress levels) during specific times and situations. The libraries used include TensorFlow and scikit-learn.

[1299] Output: Usage and sentiment patterns for each customer

[1300] Step 5:

[1301] Plan selection

[1302] Input: Usage patterns and emotion patterns

[1303] Specific operation: The server selects the optimal pricing plan for each customer based on their usage patterns. It also takes into account their emotional patterns and provides a plan that the user can reasonably accept.

[1304] Output: The optimal pricing plan selected

[1305] Step 6:

[1306] Notification generation

[1307] Input: Selected optimal pricing plan and sentiment patterns

[1308] Specific operation: The server generates a notification message of the optimal plan and sends it to the device at the optimal time based on the emotional pattern. The notification includes details of the recommended plan and the reasons for it.

[1309] Output: Notification message sent to the terminal

[1310] Step 7:

[1311] Notification display

[1312] Input: Notification message sent from the server

[1313] Specific operation: The terminal displays the received notification message to the user.

[1314] Output: Notification message displayed to the user

[1315] Step 8:

[1316] Plan Approval

[1317] Input: User confirmed notification message

[1318] Specific operation: The user checks the notification and selects "Change" on the device settings screen.

[1319] Output: Plan Approval Selection

[1320] Step 9:

[1321] Send approval information

[1322] Input: User selected plan approval information

[1323] Specific operation: The terminal sends the plan approval information to the server. The information is encrypted.

[1324] Output: Plan approval information sent to the server

[1325] Step 10:

[1326] Update settings

[1327] Input: Plan approval information sent to the server

[1328] What happens: The server receives the authorization information and updates the customer's settings to apply the new pricing plan.

[1329] Output: New pricing plan applied

[1330] Step 11:

[1331] Change Notification

[1332] Input: New pricing plan applied

[1333] Specific operation: The server notifies the terminal that the plan change was successful.

[1334] Output: Change notification messages sent to the terminal

[1335] Step 12:

[1336] Change result display

[1337] Input: Change notification message sent from the server

[1338] Specific behavior: The device receives the notification and displays it to the user.

[1339] Output: The change notification message displayed to the user

[1340] (Application example 2)

[1341] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1342] Current electronic payment services have difficulty offering plans and promotions that take into account a customer's usage status and spending patterns. Furthermore, notifications are sent without considering the customer's emotional state, so the information provided is not always timely or effective for the customer. As a result, customer satisfaction declines and it becomes difficult to provide optimal service.

[1343] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1344] In this invention, the server includes means for collecting usage data and emotional data from the terminal, means for storing the collected data, means for analyzing the stored data and selecting an optimal electronic payment plan and promotion for the customer, means for notifying the customer of the selected electronic payment plan and promotion, and means for changing the plan and promotion with the customer's approval, thereby enabling timely and effective service provision that takes into account the customer's spending patterns and emotional state.

[1345] "Terminal" means a device used by a User to input or collect Usage Data and Emotional Data.

[1346] "Usage data" refers to information related to electronic payments, such as a user's spending history and purchase details.

[1347] "Emotional Data" means data collected to describe a user's emotional state, including facial expressions and vocal tones.

[1348] "Storage" is the process of storing collected usage data and emotion data in a database.

[1349] "Analysis" is the process of analyzing accumulated data using machine learning algorithms and other methods to identify users' spending patterns and emotional states.

[1350] An "electronic payment plan" is a plan that includes fee plans and point rewards when a user uses electronic payment.

[1351] "Promotion" refers to an advertising campaign such as cashback or special offers offered to users.

[1352] "Notification" means the act of informing a User of the details of the selected Electronic Payment Plan or Promotion and the reasons for such selection.

[1353] "Acceptance" means the user's acceptance of a proposed plan or promotion.

[1354] "Modification" is the process of updating an electronic payment plan or promotion based on user approval.

[1355] The system that realizes this application example is mainly composed of a terminal, a server, and an emotion recognition engine. A specific implementation method is described below.

[1356] Hardware and Software Configuration

[1357] Hardware and software used:

[1358] 1. Device: This refers to the smartphone held by the user, and is the device that collects usage data and emotional data.

[1359] 2. Emotion recognition engine: For example, using the Microsoft Azure Emotion API to analyze a user's emotions from facial expressions and voice tones collected via a smartphone's camera and microphone.

[1360] 3. Server: Stores usage data and emotion data in a database (e.g., MySQL) and performs data analysis.

[1361] 4. Data analysis platform: Responsible for processing and analyzing large-scale data using Apache Spark and other technologies.

[1362] 5. Machine learning algorithms: Using TensorFlow and other technologies, we analyze user usage patterns and sentiment data to select optimal e-payment plans and promotions.

[1363] Program processing

[1364] The system performs data processing and calculation as follows.

[1365] Data collection:

[1366] The device periodically records usage data such as the user's spending history and purchase details and sends it to the server. In addition, an emotion recognition engine analyzes the user's emotional state in real time and sends that data to the server.

[1367] Data accumulation:

[1368] The server stores the usage data and emotion data sent from the device in a database. The data is periodically updated and stored, so that the latest usage status and emotion state are always maintained.

[1369] Data Analysis:

[1370] The server analyzes the accumulated data using machine learning algorithms. It identifies the user's spending patterns from past usage data and predicts future usage. At the same time, it analyzes emotional data to understand the user's stress level and relaxation state.

[1371] Plan Selection and Notification:

[1372] Based on the analysis results, the server selects the most suitable electronic payment plan and promotion for the user, and the selected plan or promotion is notified to the terminal, adjusting the notification timing based on the user's emotional state.

[1373] Plan Change:

[1374] The user can review the notification and accept or reject the proposed plans and promotions. If accepted, the server uses that information to modify the plans and promotions and update the user's settings.

[1375] Specific examples

[1376] For example, if a user recently made a large purchase, the system will detect that spending data and store it in a database. At the same time, an emotion recognition engine will analyze the user's state of relaxation, and notify them of a specific cashback campaign at a time when they are relaxed, which is expected to increase approval rates. Furthermore, the system can predict a user's spending patterns from past data and provide them with the optimal electronic payment plan.

[1377] Prompt Sentence Examples

[1378] "Based on the spending data (50 items) and emotional data (50 items) from the past three months, please generate a code that analyzes the user's spending patterns and emotional state and suggests the optimal payment plan."

[1379] In this way, timely and effective service delivery can be achieved that takes into account the customer's spending patterns and emotional state.

[1380] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1381] Step 1:

[1382] Data collection

[1383] The device collects usage data such as the user's spending history and purchases, and simultaneously collects the user's emotional state by analyzing facial expressions and vocal tone using an emotion recognition engine.

[1384] Input: spending history, purchase details, facial expressions, voice tones

[1385] Data processing: Organize and structure the collected usage data and sentiment data.

[1386] Output: Structured usage and sentiment data

[1387] Step 2:

[1388] Data transmission

[1389] The device transmits the collected usage and emotion data to a server, either periodically or in real time.

[1390] Input: Structured usage data and sentiment data

[1391] Data Calculation: Convert the data into the appropriate format and send it to the server.

[1392] Output: Data sent to the server

[1393] Step 3:

[1394] Data accumulation

[1395] The server stores the usage data and emotion data sent from the terminal in a database.

[1396] Input: Submitted usage data and emotion data

[1397] Data processing: Record and save the received data in a database.

[1398] Output: Data stored in the database

[1399] Step 4:

[1400] Data analysis

[1401] The server analyzes the accumulated usage data and emotional data using machine learning algorithms to identify the user's spending patterns from past usage data and understand the user's emotional state from emotional data.

[1402] Input: Usage data and emotion data stored in a database

[1403] Data Computing: Data Analysis and Pattern Recognition with Machine Learning Models

[1404] Output: Analysis of user spending patterns and emotional state

[1405] Step 5:

[1406] Plan selection

[1407] The server selects the most suitable e-payment plan and promotion for the user based on the analysis results, and adjusts notifications to be sent at the appropriate time, taking into account emotional data.

[1408] Input: Analysis results (spending patterns and emotional state)

[1409] Data calculation: Selecting the best plan and promotion

[1410] Output: Selected electronic payment plans and promotions

[1411] Step 6:

[1412] notification

[1413] The server sends a notification message containing details of the selected electronic payment plan and promotion to the terminal, optimizing the timing of the notification based on the emotion data.

[1414] Input: Selected plan and promotion

[1415] Data calculation: Notification message generation and timing adjustment

[1416] Output: Notification message sent to the terminal

[1417] Step 7:

[1418] Change plan

[1419] The user reviews the notification and can accept or reject the proposed plan or promotion. If accepted, the device sends the information to the server, which then changes the plan or promotion and updates the user's settings.

[1420] Input: User approval / rejection

[1421] Data operation: Plan and promotion update processing

[1422] Output: Updated electronic payment plans and promotions

[1423] In this way, a system is realized that comprehensively analyzes the spending patterns and emotional state of customers and provides timely and effective electronic payment plans and promotions.

[1424] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1425] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1426] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1427] [Fourth embodiment]

[1428] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1429] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1430] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1431] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1432] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1433] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1434] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1435] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1436] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1437] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1438] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1439] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1440] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1441] The system of the present invention automatically provides mobile subscribers with the most appropriate rate plan based on their usage. The system collects usage data from the terminal, stores and analyzes the collected data, selects the most appropriate rate plan, and notifies the customer. It also has the ability to automatically change plans with the customer's approval.

[1442] Data collection and storage

[1443] The system first collects usage data from the device. The device has the ability to record information such as data traffic, call time, and SMS usage, and this data is periodically sent to the server. The server stores the received data in a database. This allows for detailed records of each customer's usage status to be used for later analysis.

[1444] Data analysis

[1445] The server uses machine learning algorithms to analyze the accumulated data. Specifically, it analyzes customer usage patterns based on past usage data and predicts future usage. Based on the results of this analysis, it selects the optimal pricing plan for the customer. For example, if the average data usage over the past three months is within a certain range, it will propose the optimal data plan based on that.

[1446] Plan presentation and notification

[1447] The server notifies the terminal of the selected optimal rate plan. The notification message includes details of the proposed plan and the reasons for it, providing information to the customer in a transparent manner. The terminal receives this notification and displays it to the user.

[1448] Change plan

[1449] When the user receives the notification, they review the proposed plan and choose whether to accept it. If the user accepts the new plan, the device sends that information to the server. The server receives this approval information and updates the customer's settings, so the new pricing plan is automatically applied.

[1450] Specific examples

[1451] User C's scenario

[1452] 1. Data Collection

[1453] Device: User C's device records this month's data usage of 15GB, talk time of 120 minutes, and SMS usage of 5 messages.

[1454] Server: Stores data collected from devices in a database. This data is updated every 5 minutes.

[1455] 2. Data analysis

[1456] Server: Based on usage data from the past three months, it is analyzed that User C's average data usage is 16GB, talk time is 110 minutes, and SMS usage is 4. It also uses a machine learning algorithm to predict future usage.

[1457] 3. Plan presentation and notification

[1458] Server: Based on the analysis results, it determines that the "20GB data plan + 120 minutes call plan" is optimal. It generates a notification message and sends it to User C's device.

[1459] Device: Receives and displays a notification to the user, detailing the proposed plan and explaining the reasons for it.

[1460] 4. Change of plan

[1461] User: Check the notification and accept the proposed plan by selecting "Change" from the device settings screen.

[1462] Terminal: Sends authorization information to the server.

[1463] Server: Receives the approval information and updates User C's settings. Notifies the user that the new pricing plan has been applied.

[1464] In this way, the present invention can improve customer satisfaction by automatically selecting the most suitable rate plan based on the customer's usage status and providing it in real time.

[1465] The processing flow will be explained below.

[1466] Step 1:

[1467] Device: Records usage data. When a user uses a mobile phone, the device records information such as data traffic, call duration, and number of SMS sent. This data is set to be updated periodically.

[1468] Step 2:

[1469] Device: Sends recorded usage data to the server. Data is transferred to the server at specific intervals (e.g., every 5 minutes). Data transmission uses encryption technology to ensure secure communication.

[1470] Step 3:

[1471] Server: Stores the received usage data in a database. Organizes the data for each customer and stores it for future analysis.

[1472] Step 4:

[1473] Server: Periodically analyzes the accumulated data. Machine learning algorithms are used to identify each customer's usage patterns based on past usage data. For example, the average data usage, call minutes, and SMS usage over the past three months are calculated.

[1474] Step 5:

[1475] Server: Based on the analysis results, the server selects the most suitable pricing plan for the customer. It considers usage data patterns and selects the most cost-effective plan from the list of plans.

[1476] Step 6:

[1477] Server: After selecting the best pricing plan, generate a notification message containing details of the recommended plan and the reasons for it.

[1478] Step 7:

[1479] Server: The generated notification message is sent to the client's terminal. The data is transferred in real time, and the user is notified immediately.

[1480] Step 8:

[1481] Device: Receives a notification and displays it to the user, who can see the plan details and reasons.

[1482] Step 9:

[1483] User: Check the notified plan and decide whether to accept it. If you accept it, select "Change" on the device settings screen.

[1484] Step 10:

[1485] Terminal: Sends the user's selection information to the server. A request is sent to the server requesting the application of the new plan.

[1486] Step 11:

[1487] Server: Updates the customer's subscription information based on the received request. The new pricing plan is applied immediately.

[1488] Step 12:

[1489] Server: Notifies the customer that the plan change was successful. Sends a notification message to the device to let the user know that the change is complete.

[1490] Step 13:

[1491] Device: Receives notification and displays to the user that the plan change was successful.

[1492] This detailed process flow allows customers to easily and quickly select and apply the rate plan that best suits their usage situation.

[1493] Example 1

[1494] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1495] This invention relates to a system that automatically provides mobile subscribers with the most appropriate rate plan based on their usage. Conventional methods involve manually collecting and analyzing usage data, making it difficult to provide customers with the most appropriate plan in real time. For this reason, there has been a need for a method to quickly and effectively provide rate plans that meet customer needs.

[1496] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1497] In this invention, the server includes means for collecting usage data from the terminal, means for storing the collected usage data, means for analyzing the stored usage data using a machine learning algorithm and selecting an optimal service plan for the customer, means for sending a notification to the customer including details of the selected service plan and the reasons for the selection, and means for automatically changing the service plan with the customer's approval. This makes it possible to provide an optimal rate plan in real time based on the customer's usage status and improve customer satisfaction.

[1498] A "terminal" is an electronic device used by a user that has the function of collecting usage data such as data communication, calls, and SMS, and communicating with a server.

[1499] "Usage data" refers to information such as data usage, call time, and SMS usage when a user uses a mobile service.

[1500] A "server" is a central processing unit that receives, stores, and analyzes data sent from terminals.

[1501] A "machine learning algorithm" is an algorithm that learns from past data and predicts future data and patterns.

[1502] "Notification" is the act of sending a server-generated message to a terminal to provide information to a user.

[1503] "Customer Approval" refers to the User receiving the notification reviewing the proposed service plan and taking the action of consenting or rejecting it.

[1504] "Service Plan" refers to the pricing structure and terms of use offered to a mobile subscriber, including data volume, talk time, number of SMS sent, etc.

[1505] "Automatically change" refers to the server programmatically updating the service plan without manual intervention after obtaining user approval.

[1506] The system of the present invention automatically provides the most suitable rate plan to a mobile subscriber based on their usage. The system collects usage data from the terminal, stores and analyzes the collected data on a server, selects the most suitable rate plan, and notifies the customer. Furthermore, the system also has the function of automatically changing plans with the customer's approval.

[1507] Hardware and software used

[1508] This system mainly uses the following hardware and software:

[1509] 1. Terminal

[1510] Hardware: Mobile devices such as smartphones and tablets.

[1511] Software: Applications for collecting usage data.

[1512] 2. Server

[1513] Hardware: Database servers, compute servers for running machine learning models.

[1514] Software: Database management systems, machine learning algorithms, notification services.

[1515] Specific processing flow

[1516] Data collection and storage

[1517] The device collects usage data in real time, such as the user's data traffic, call time, and SMS usage. This usage data is stored in the device's internal storage and periodically (for example, every five minutes) sent to the server. The server stores the received data in a database, recording each customer's usage status in detail. This data can then be used for later data analysis.

[1518] Data analysis

[1519] The server analyzes the accumulated usage data using machine learning algorithms. Based on past usage data, the server analyzes the customer's usage patterns and predicts future usage. For example, if the average data usage over the past three months is within a certain range, the server can suggest the optimal data plan based on that prediction. The machine learning models used are often run on cloud platforms.

[1520] Plan presentation and notification

[1521] The server selects the optimal pricing plan for the customer based on the results of the data analysis. It generates a notification message containing details of the selected pricing plan and the reasons for it, and sends it to the customer's device. The device receives this notification and displays it to the user. The notification clearly explains how the change in pricing plan will benefit the customer.

[1522] Change plan

[1523] The user checks the notification on the device and chooses whether to accept the proposed pricing plan. If accepted, the device sends the information to the server. The server receives the approval information and updates the customer's account settings to the new pricing plan. The new pricing plan is then immediately applied, and the server notifies the device again.

[1524] Specific examples

[1525] User C's scenario

[1526] 1. Data Collection

[1527] Device: User C's device records this month's data usage of 15GB, talk time of 120 minutes, and SMS usage of 5 messages.

[1528] Server: Stores data collected from devices in a database. This data is updated every 5 minutes.

[1529] 2. Data analysis

[1530] Server: Based on usage data from the past three months, it is analyzed that User C's average data usage is 16GB, talk time is 110 minutes, and SMS usage is 4. It also uses a machine learning algorithm to predict future usage.

[1531] 3. Plan presentation and notification

[1532] Server: Based on the analysis results, it determines that the "20GB data plan + 120 minutes call plan" is optimal. It generates a notification message and sends it to User C's device.

[1533] Device: Receives and displays a notification to the user, detailing the proposed plan and explaining the reasons for it.

[1534] 4. Change of plan

[1535] User: Check the notification and accept the proposed plan by selecting "Change" from the device settings screen.

[1536] Terminal: Sends authorization information to the server.

[1537] Server: Receives the approval information and updates User C's settings. Notifies the user that the new pricing plan has been applied.

[1538] Prompt Sentence Examples

[1539] "Please analyze and suggest the optimal pricing plan for User C based on usage data from the past three months."

[1540] As described above, the present invention can improve customer satisfaction by automatically selecting an optimal rate plan based on the customer's usage status and providing it in real time.

[1541] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1542] Step 1:

[1543] Data collection

[1544] Input: User data usage, call time, SMS usage

[1545] How it works: The device collects usage data in real time and stores it in storage.

[1546] Example: A device records the current amount of data traffic and updates it every 5 minutes.

[1547] Output: The latest usage data is saved on the device.

[1548] Step 2:

[1549] Data transmission

[1550] Input: Usage data stored on the device

[1551] How it works: The device periodically sends collected data to a server. The data is encrypted and transmitted securely.

[1552] Example: A device sends the latest usage data to a server every 5 minutes.

[1553] Output: Usage data arrives at the server and is received.

[1554] Step 3:

[1555] Data accumulation

[1556] Input: Usage data sent to the server

[1557] How it works: The server stores the data it receives in a database, organizing it by customer for quick access and analysis later.

[1558] Example: The server adds user C's data usage of 15 GB, talk time of 120 minutes, and SMS usage of 5 to the database.

[1559] Output: The latest usage data is saved in the database.

[1560] Step 4:

[1561] Data analysis

[1562] Input: Usage data stored in the database

[1563] How it works: The server analyzes the data using machine learning algorithms, analyzing customer usage patterns based on past data and predicting future usage.

[1564] Example: The server analyzes usage data from the past three months and predicts that User C's average data usage is 16 GB, talk time is 110 minutes, and SMS usage is 4.

[1565] Output: The analysis results in customer usage patterns and predictions of future usage.

[1566] Step 5:

[1567] Plan selection

[1568] Input: Results of data analysis

[1569] How it works: The server selects the optimal pricing plan for the customer based on the analysis results. This selection is made by comparing the usage forecast with the terms of existing pricing plans.

[1570] Example: The server determines that the "20GB data plan + 120 minutes call plan" is optimal for user C.

[1571] Output: Detailed information on the best pricing plan.

[1572] Step 6:

[1573] Plan Notification

[1574] Input: Details of the best rate plan

[1575] Operation: The server generates a notification message containing details of the selected rate plan and the reason for the selection, and sends it to the terminal.

[1576] Example: The server generates a message detailing the "20GB data plan + 120 minutes call plan" and the reason for the plan, and sends it to User C's device.

[1577] Output: A notification message arrives on the terminal.

[1578] Step 7:

[1579] User Authorization

[1580] Input: Notification message

[1581] How it works: The user sees the notification on their device and chooses whether to accept the proposed pricing plan.

[1582] Example: User C checks the notification and presses the "Change" button on the device to approve the proposed plan.

[1583] Output: The authorization information is entered into the terminal.

[1584] Step 8:

[1585] Change plan

[1586] Input: User authorization information

[1587] Operation: The device sends the authorization information to the server, which updates the customer's settings with the new rate plan, which then applies the new rate plan.

[1588] Example: The server receives user C's authorization information and updates user C's settings to "20GB data plan + 120 minutes call plan."

[1589] Output: The new pricing plan is applied and you are notified.

[1590] (Application example 1)

[1591] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1592] With conventional electronic payment services, users must analyze their own usage data and select the appropriate plan to suit their usage, which is time-consuming and laborious. Furthermore, users may not be able to determine the appropriate plan and end up paying excessive fees. Furthermore, there is a lack of a mechanism for flexibly changing plans based on the user's lifestyle and frequency of use, resulting in low user satisfaction.

[1593] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1594] In this invention, the server includes means for collecting usage data from the terminal, means for storing the collected usage data, means for analyzing the stored usage data and selecting an optimal service plan for the customer, means for notifying the customer of the selected service plan, means for changing the service plan with the customer's approval, means for identifying usage data for the electronic payment service and using a machine learning algorithm to predict an optimal rate plan based on the usage data, and means for notifying the user terminal of the selected rate plan and obtaining approval. This makes it possible to automatically propose an optimal rate plan based on the user's usage data and flexibly change the plan with approval.

[1595] "Terminal" refers to a computing device such as a mobile phone, smartphone, or tablet that an investor uses on a daily basis.

[1596] "Usage data" refers to information such as the amount of data used, the amount used, and the number of transactions when a user uses an electronic payment service.

[1597] "Storage means" refers to a recording device or database for storing collected usage data.

[1598] "Analytical means" refers to machine learning algorithms and analytics software that evaluate collected and stored usage data and extract patterns.

[1599] "Optimal service plan" refers to the most cost-effective plan selected based on the user's past and predicted usage.

[1600] "Means of notification" refers to the messaging system or application functionality used to communicate information about the selected service plan to the user.

[1601] "Means for changing service plans with approval" means the system's ability to automatically update service plans after obtaining user consent.

[1602] "Electronic Payment Services" refers to payment platforms and systems that enable online or offline payments, purchases and transactions.

[1603] A "machine learning algorithm" refers to a mathematical model or computational method for learning patterns from past data and predicting or classifying future data.

[1604] "User terminal" refers to a computing device (smartphone, tablet, etc.) operated by a user when using an electronic payment service.

[1605] Data collection

[1606] The server first collects usage data from the device. This data includes communication volume, usage amount, number of transactions, etc. This collection process is carried out periodically through the device's API (Application Programming Interface). Specifically, it collects usage information from electronic payment services accessed by smartphones and tablet devices.

[1607] Data accumulation

[1608] The collected usage data is stored in a database on the server. The database is constructed using SQLite, and the collected data is saved in the database. This data storage process records detailed usage information for each user.

[1609] Data analysis

[1610] The server uses a machine learning algorithm to analyze the accumulated data. Specifically, it uses a linear regression model from scikit-learn. It analyzes customer usage patterns based on past usage data and predicts future usage. During this process, it extracts and analyzes features from the usage data. Based on the results of this analysis, it selects the optimal pricing plan for each user.

[1611] Plan presentation and notification

[1612] After the optimal plan is selected, the server notifies the user via a messaging system, and the user receives details of the proposed plan and the reasons for its selection via an application on their smartphone or tablet. The notification message also includes an option for the user to approve the plan.

[1613] Change plan

[1614] If the user approves the proposed plan, the device sends the approval information to the server. The server automatically updates the pricing plan based on that information. This update process uses an API to appropriately change the database settings. Once the change is complete, the server notifies the user again, informing them that the new pricing plan has been applied.

[1615] Specific examples

[1616] User A's scenario

[1617] User A's device records a monthly transaction amount of 5,000 yen and 50 transactions. The server stores this information in a database and analyzes it using a linear regression model in scikit-learn. As a result, it determines that a "10% cashback plan for users who spend more than 5,000 yen per month" is optimal for User A. The server notifies User A's smartphone of the details of this plan and the reasons for it. When User A approves through the application, the server automatically changes the pricing plan and notifies User A again.

[1618] Prompt Sentence Examples

[1619] "Please suggest the best plan for a monthly electronic payment amount of 5,000 yen or more and 50 or more transactions."

[1620] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1621] Step 1:

[1622] The server collects usage data from the device. Specifically, it periodically obtains data such as communication volume, usage amount, and number of transactions through the API of the electronic payment service accessed by the smartphone or tablet device. The input is the API request from the device, and the output is the obtained usage data. This data is often received in JSON format.

[1623] Step 2:

[1624] The server stores the collected usage data in a database. Specifically, it parses the acquired JSON data and stores it in a database such as SQLite. At this time, the data is converted into an appropriate format and stored as a record for each customer. The input is the collected usage data, and the output is the data stored in the database.

[1625] Step 3:

[1626] The server analyzes the accumulated usage data. Specifically, it reads past usage data stored in the database and analyzes it using a linear regression model from scikit-learn. During the analysis, transaction amounts and number of transactions are used as features to predict future usage patterns. The input is the usage data obtained from the database, and the output is the analysis results (predicted usage patterns).

[1627] Step 4:

[1628] The server selects the optimal pricing plan. Based on the analysis results obtained by the machine learning algorithm, it determines the optimal plan for each user. Specifically, it compares the analysis results with existing pricing plans and selects the most appropriate plan. The input is the analysis results and existing pricing plan information, and the output is the selected optimal pricing plan.

[1629] Step 5:

[1630] The server notifies the user of the selected optimal plan via a messaging system, displaying details of the plan on the user's smartphone or tablet. The input is the selected plan and the user's contact information, and the output is a notification message sent to the user's device.

[1631] Step 6:

[1632] The user receives the notification and approves the plan. The user checks the details of the proposed plan on the user terminal and selects whether to approve or reject it. The input is the notification content displayed to the user, and the output is the user's selection of whether to approve or reject it.

[1633] Step 7:

[1634] The server receives the user's approval information and automatically changes the pricing plan. Specifically, it updates the database settings based on the approval information and applies the new pricing plan. The input is the user's approval information, and the output is the updated database settings and a final notification to the user's terminal.

[1635] This process will create a system in which the most suitable pricing plan is automatically proposed based on the user's usage data, and if the user approves it, the plan is automatically applied.

[1636] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1637] The system of the present invention automatically provides mobile subscribers with the most appropriate pricing plan based on their usage and emotional state. This system combines traditional usage data with an emotion engine that recognizes user emotions to provide a more personalized service.

[1638] Data collection and storage

[1639] First, the system collects usage data from the device. The device periodically records information such as data traffic, call time, and SMS usage, and sends it to the server. The server then stores the received data in a database, recording each customer's usage in detail. In addition, the device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state in real time, for example, from facial expressions and voice tones, and also sends this data to the server.

[1640] Data analysis

[1641] The server periodically analyzes usage data and emotion data. First, it uses a machine learning algorithm to identify each customer's usage patterns based on past usage data. For example, it calculates the average data volume, call time, and SMS usage over the past three months and predicts future usage. Next, it analyzes the emotion data using an emotion engine to understand the user's emotional state. This makes it possible to adjust the system, for example, by avoiding notifications at certain times or situations when the user's stress level is high.

[1642] Plan selection

[1643] Based on the analysis results, the server considers usage data and emotional data to select the optimal pricing plan for the customer. Not only does it select the optimal plan based on usage patterns, but it also considers the user's emotional state to provide a plan that is reasonably acceptable to the user.

[1644] Plan presentation and notification

[1645] The server then notifies the device of the optimal pricing plan that has been selected. The notification message includes details of the recommended plan and the reasons for its selection, providing information to the customer in a transparent manner. The timing and method of notification are also adjusted based on emotional data. For example, by selecting a time when the user is relaxed to send the notification, the likelihood of approval is increased.

[1646] Change plan

[1647] When the user receives the notification, they can review the proposed plan and choose whether to accept it. If the user accepts the new plan, the information is sent from the device to the server. The server receives the approval information and updates the customer's settings, so the new pricing plan is automatically applied.

[1648] Specific examples

[1649] User D's scenario

[1650] 1. Data Collection

[1651] Device: User D's device records 20GB of data traffic, 80 minutes of talk time, and 15 SMS messages this month. The emotion engine analyzes User D's emotional state in real time and records his stress level, relaxation state, etc.

[1652] Server: Collects usage data and emotion data from devices and stores them in a database.

[1653] 2. Data analysis

[1654] Server: Based on usage data from the past three months, the server analyzes that User D's average data usage is 18GB, talk time is 85 minutes, and SMS usage is 12 messages. It also uses a machine learning algorithm to predict future usage. At the same time, it analyzes emotion data and determines that User D's stress level tends to be higher in the morning.

[1655] 3. Plan selection

[1656] Server: Based on the analysis results, it determines that the "25GB Data Plan + 100 Minutes Call Plan" is optimal. It also takes into account emotional data and sends notifications during the day, avoiding the morning.

[1657] 4. Plan presentation and notification

[1658] Server: Generates a notification message of the optimal plan and sends it to User D's device. The notification contains details of the proposed plan and the reasons for it.

[1659] Terminal: Receives notifications and displays them to the user.

[1660] 5. Change of plan

[1661] User: Check the notification and accept the proposed plan. Select "Change" on the device settings screen.

[1662] Terminal: Sends authorization information to the server.

[1663] Server: Receives the approval information and updates User D's settings. The new pricing plan is applied immediately and the server notifies the user that the plan change was successful.

[1664] Device: Receives notifications and displays them to the user.

[1665] By taking into account both the user's usage and emotional state, the system can provide a more personalized and optimal pricing plan for the customer, thereby improving customer satisfaction and preventing excessive charges.

[1666] The processing flow will be explained below.

[1667] Step 1:

[1668] Device: Records usage data. When a user uses a mobile phone, the device records information such as data traffic, call duration, and number of SMS sent. This data is set to be updated periodically.

[1669] Step 2:

[1670] Device: Analyzes user emotions in real time. Records the user's emotional state (e.g., stress level, relaxation level) using an emotion engine that analyzes facial expressions, voice tone, text message content, etc.

[1671] Step 3:

[1672] Device: The recorded usage data and emotion data are sent to the server. The data is transferred to the server at specific intervals (e.g., every 5 minutes). Encryption technology is used for data transmission to ensure secure communication.

[1673] Step 4:

[1674] Server: Stores the received usage and sentiment data in a database. Organizes the data for each customer and stores it for future analysis.

[1675] Step 5:

[1676] Server: The accumulated data is periodically analyzed. First, a machine learning algorithm is used to identify each customer's usage pattern based on past usage data. For example, the average data usage over the past three months is calculated and future usage predictions are made.

[1677] Step 6:

[1678] Server: Next, the emotional data is analyzed to understand the user's emotional state. Specific emotional patterns, such as stress level or relaxation state, are extracted from the data.

[1679] Step 7:

[1680] Server: Selects the optimal plan for each customer based on usage data and emotional data. For example, a high-capacity data plan may be recommended for a user who uses the service frequently but is in a relaxed state.

[1681] Step 8:

[1682] Server: After selecting the optimal pricing plan, generate a notification message. The notification contains details of the recommended plan and the reasons for its selection. The timing and method of notification are also adjusted based on sentiment data.

[1683] Step 9:

[1684] Server: The server sends the generated notification message to the customer's device. It selects the optimal timing, such as sending the message during a time when the user is relaxed, taking into account emotional data.

[1685] Step 10:

[1686] Device: Receives a notification and displays it to the user, who can see the plan details and reasons.

[1687] Step 11:

[1688] User: Check the notified plan and decide whether to accept it. If you accept it, select "Change" on the device settings screen.

[1689] Step 12:

[1690] Terminal: Sends the user's selection information to the server. A request is sent to the server requesting the application of the new plan.

[1691] Step 13:

[1692] Server: Updates the customer's subscription information based on the received request. The new pricing plan is applied immediately.

[1693] Step 14:

[1694] Server: Notifies the customer that the plan change was successful. Sends a notification message to the device to let the user know that the change is complete.

[1695] Step 15:

[1696] Device: Receives notification and displays to the user that the plan change was successful.

[1697] This detailed process flow allows customers to easily and quickly select and apply the pricing plan that best suits their usage and emotional state.

[1698] Example 2

[1699] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1700] Conventional systems select service plans for customers based solely on usage data, making it difficult to provide personalized services that take into account the customer's emotional state and stress levels due to usage. Furthermore, notifications were not provided at the appropriate time, which could lead to lower customer satisfaction and increased stress due to unnecessary notifications. Furthermore, when customers approved a proposed plan, there was a lack of transparency regarding the plan contents and the reasons for selection, making it difficult to improve reliability.

[1701] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1702] In this invention, the server includes means for collecting usage data and emotion data from the terminal, means for storing the collected usage data and emotion data, means for analyzing the stored usage data and emotion data and selecting an optimal service plan for the customer, means for notifying the customer of the selected service plan, means for adjusting the timing and method of notification based on the customer's emotional state, and means for changing the service plan with the customer's approval. This makes it possible to provide personalized services that take the customer's emotional state into consideration and to notify them at an appropriate time, and improves the transparency of the plan contents and the reasons for selection, thereby enabling increased customer satisfaction and reliability.

[1703] A "terminal" is a device used by a user that has the function of recording and transmitting usage data such as data communication, calls, and SMS, and also collecting emotional data.

[1704] "Usage data" refers to information such as data traffic, call time, and SMS usage generated when a user uses a mobile service.

[1705] "Emotional data" refers to information indicating a user's emotional state (e.g., stress level, relaxation level) analyzed from their facial expressions and vocal tone.

[1706] "Server" refers to a central aggregation system that receives, stores, and analyzes usage data and emotion data sent from terminals.

[1707] The term "storing means" refers to a method or device for storing the received usage data and emotion data in a storage device such as a database.

[1708] "Means for analyzing" refers to methods and devices for analyzing accumulated usage and sentiment data and using machine learning algorithms to identify usage patterns.

[1709] The "means for selecting the optimal service plan" refers to a method or device for selecting the most suitable rate plan for a customer based on the analysis results.

[1710] The "notification means" refers to a method or device for transmitting information about the selected optimum service plan to the user's terminal and displaying it.

[1711] "Means for adjusting the timing and method of notification based on the emotional state" refers to a method or device for providing notification at the most appropriate timing and in the most appropriate manner, taking into account the user's emotional data.

[1712] "Means for changing the service plan upon approval" refers to a method or device for sending information to a server when a user approves a proposed service plan and immediately changing the service plan.

[1713] The system of the present invention automatically provides mobile subscribers with the most appropriate pricing plan based on their usage and emotional state. This system combines traditional usage data with an emotion engine that recognizes user emotions to provide a more personalized service.

[1714] Data collection and storage

[1715] First, the system collects usage and emotion data from the device. The device periodically records information such as data traffic, call duration, and SMS usage, and sends it to the server. The device is equipped with an emotion engine that recognizes the user's emotions, and analyzes the user's emotional state in real time from facial expressions and voice tones, and also sends this data to the server.

[1716] The server stores the received data in a database, recording each customer's usage and emotional state in detail. This is done using a database management system (DBMS), such as an open-source database like MySQL or PostgreSQL.

[1717] Data analysis

[1718] The server periodically analyzes the accumulated usage and sentiment data, and uses machine learning algorithms to identify each customer's usage patterns based on past usage data and make future usage predictions. This can be done using machine learning libraries such as TensorFlow and scikit-learn.

[1719] Emotional data is also analyzed by an emotion engine, and analysis is carried out taking into account the user's emotional state. For example, if a user's stress level is high during a particular time period or situation, it is possible to adjust notifications to avoid those times.

[1720] Plan selection

[1721] Based on the analysis results, the server selects the optimal plan for the customer, taking into account usage data and emotional data. Specifically, it selects the optimal plan based on data traffic, call time, and SMS usage, and provides a plan that the user can reasonably accept based on emotional data.

[1722] Plan presentation and notification

[1723] The server then notifies the device of the optimal pricing plan. The notification message includes details of the recommended plan and the reasons for its selection, providing information to the customer in a transparent manner. The timing and method of notifications are also adjusted based on emotional data. For example, notifications can be sent at times when the user is relaxed, increasing the likelihood of approval.

[1724] Change plan

[1725] When the user receives the notification, they can review the proposed plan and choose whether to accept it. If the user accepts the new plan, the information is sent from the device to the server. The server receives the approval information and updates the customer's settings, so the new pricing plan is automatically applied.

[1726] Specific examples

[1727] User D's scenario

[1728] As a specific example, the case of user D will be described.

[1729] 1. Data Collection

[1730] Device: User D's device records 20GB of data traffic, 80 minutes of talk time, and 15 SMS messages this month. The emotion engine analyzes User D's emotional state in real time and records his stress level, relaxation state, etc.

[1731] Server: Collects usage data and emotion data from devices and stores them in a database.

[1732] 2. Data analysis

[1733] Server: Based on usage data from the past three months, the server analyzes that User D's average data usage is 18GB, talk time is 85 minutes, and SMS usage is 12 messages. It also uses a machine learning algorithm to predict future usage. At the same time, it analyzes emotion data and determines that User D's stress level tends to be higher in the morning.

[1734] 3. Plan selection

[1735] Server: Based on the analysis results, it determines that the 25GB data plan + 100 minutes call plan is optimal. Taking into account the emotional data, it sends notifications during the day, avoiding the morning.

[1736] 4. Plan presentation and notification

[1737] Server: Generates a notification message of the optimal plan and sends it to User D's device. The notification contains details of the proposed plan and the reasons for it.

[1738] Terminal: Receives notifications and displays them to the user.

[1739] 5. Change of plan

[1740] User: Check the notification and accept the proposed plan. Select "Change" on the device settings screen.

[1741] Terminal: Sends authorization information to the server.

[1742] Server: Receives the approval information and updates User D's settings. The new pricing plan is applied immediately and the server notifies the user that the plan change was successful.

[1743] Device: Receives notifications and displays them to the user.

[1744] In this way, by taking into account the user's usage and emotional state, we can provide more personalized and optimal pricing plans, improving customer satisfaction and preventing excessive payment of fees.

[1745] Prompt Sentence Examples

[1746] Below are some example prompts to input into the generative AI model to illustrate how this system can be used.

[1747] A user has a mobile plan with a high data usage and relatively long talk time. Analysis by the emotion engine reveals that the user's stress level tends to be higher in the morning. Design a system to recommend the optimal plan for this user and send notifications at appropriate times taking into account the emotion data.

[1748] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1749] Step 1:

[1750] Data collection

[1751] Input: Data from on-device sensors and logs, user facial expressions and vocal tones

[1752] Specific operation: The device periodically records usage data such as data traffic, call time, and SMS usage. The emotion engine analyzes the user's emotional state (e.g., stress level, relaxation level) from their facial expressions and voice.

[1753] Output: Collected usage and sentiment data

[1754] Step 2:

[1755] Data transmission

[1756] Input: Collected usage and sentiment data

[1757] Specific operation: The device periodically sends the collected data to the server. At this time, the data is encrypted and sent securely.

[1758] Output: Usage and emotion data sent to the server

[1759] Step 3:

[1760] Data accumulation

[1761] Input: Usage data and emotion data received by the server

[1762] Specific operation: The server stores the received data in a database, where data is organized for each user and managed in an easily accessible format.

[1763] Output: Usage data and emotion data stored in a database

[1764] Step 4:

[1765] Data analysis

[1766] Input: Usage data and emotion data stored in a database

[1767] How it works: The server uses machine learning algorithms to analyze usage data and identify each customer's usage patterns. It also analyzes emotion data to understand patterns of emotional states (e.g., stress levels) during specific times and situations. The libraries used include TensorFlow and scikit-learn.

[1768] Output: Usage and sentiment patterns for each customer

[1769] Step 5:

[1770] Plan selection

[1771] Input: Usage patterns and emotion patterns

[1772] Specific operation: The server selects the optimal pricing plan for each customer based on their usage patterns. It also takes into account their emotional patterns and provides a plan that the user can reasonably accept.

[1773] Output: The optimal pricing plan selected

[1774] Step 6:

[1775] Notification generation

[1776] Input: Selected optimal pricing plan and sentiment patterns

[1777] Specific operation: The server generates a notification message of the optimal plan and sends it to the device at the optimal time based on the emotional pattern. The notification includes details of the recommended plan and the reasons for it.

[1778] Output: Notification message sent to the terminal

[1779] Step 7:

[1780] Notification display

[1781] Input: Notification message sent from the server

[1782] Specific operation: The terminal displays the received notification message to the user.

[1783] Output: Notification message displayed to the user

[1784] Step 8:

[1785] Plan Approval

[1786] Input: User confirmed notification message

[1787] Specific operation: The user checks the notification and selects "Change" on the device settings screen.

[1788] Output: Plan Approval Selection

[1789] Step 9:

[1790] Send approval information

[1791] Input: User selected plan approval information

[1792] Specific operation: The terminal sends the plan approval information to the server. The information is encrypted.

[1793] Output: Plan approval information sent to the server

[1794] Step 10:

[1795] Update settings

[1796] Input: Plan approval information sent to the server

[1797] What happens: The server receives the authorization information and updates the customer's settings to apply the new pricing plan.

[1798] Output: New pricing plan applied

[1799] Step 11:

[1800] Change Notification

[1801] Input: New pricing plan applied

[1802] Specific operation: The server notifies the terminal that the plan change was successful.

[1803] Output: Change notification messages sent to the terminal

[1804] Step 12:

[1805] Change result display

[1806] Input: Change notification message sent from the server

[1807] Specific behavior: The device receives the notification and displays it to the user.

[1808] Output: The change notification message displayed to the user

[1809] (Application example 2)

[1810] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1811] Current electronic payment services have difficulty offering plans and promotions that take into account a customer's usage status and spending patterns. Furthermore, notifications are sent without considering the customer's emotional state, so the information provided is not always timely or effective for the customer. As a result, customer satisfaction declines and it becomes difficult to provide optimal service.

[1812] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1813] In this invention, the server includes means for collecting usage data and emotional data from the terminal, means for storing the collected data, means for analyzing the stored data and selecting an optimal electronic payment plan and promotion for the customer, means for notifying the customer of the selected electronic payment plan and promotion, and means for changing the plan and promotion with the customer's approval, thereby enabling timely and effective service provision that takes into account the customer's spending patterns and emotional state.

[1814] "Terminal" means a device used by a User to input or collect Usage Data and Emotional Data.

[1815] "Usage data" refers to information related to electronic payments, such as a user's spending history and purchase details.

[1816] "Emotional Data" means data collected to describe a user's emotional state, including facial expressions and vocal tones.

[1817] "Storage" is the process of storing collected usage data and emotion data in a database.

[1818] "Analysis" is the process of analyzing accumulated data using machine learning algorithms and other methods to identify users' spending patterns and emotional states.

[1819] An "electronic payment plan" is a plan that includes fee plans and point rewards when a user uses electronic payment.

[1820] "Promotion" refers to an advertising campaign such as cashback or special offers offered to users.

[1821] "Notification" means the act of informing a User of the details of the selected Electronic Payment Plan or Promotion and the reasons for such selection.

[1822] "Acceptance" means the user's acceptance of a proposed plan or promotion.

[1823] "Modification" is the process of updating an electronic payment plan or promotion based on user approval.

[1824] The system that realizes this application example is mainly composed of a terminal, a server, and an emotion recognition engine. A specific implementation method is described below.

[1825] Hardware and Software Configuration

[1826] Hardware and software used:

[1827] 1. Device: This refers to the smartphone held by the user, and is the device that collects usage data and emotional data.

[1828] 2. Emotion recognition engine: For example, using the Microsoft Azure Emotion API to analyze a user's emotions from facial expressions and voice tones collected via a smartphone's camera and microphone.

[1829] 3. Server: Stores usage data and emotion data in a database (e.g., MySQL) and performs data analysis.

[1830] 4. Data analysis platform: Responsible for processing and analyzing large-scale data using Apache Spark and other technologies.

[1831] 5. Machine learning algorithms: Using TensorFlow and other technologies, we analyze user usage patterns and sentiment data to select optimal e-payment plans and promotions.

[1832] Program processing

[1833] The system performs data processing and calculation as follows.

[1834] Data collection:

[1835] The device periodically records usage data such as the user's spending history and purchase details and sends it to the server. In addition, an emotion recognition engine analyzes the user's emotional state in real time and sends that data to the server.

[1836] Data accumulation:

[1837] The server stores the usage data and emotion data sent from the device in a database. The data is periodically updated and stored, so that the latest usage status and emotion state are always maintained.

[1838] Data Analysis:

[1839] The server analyzes the accumulated data using machine learning algorithms. It identifies the user's spending patterns from past usage data and predicts future usage. At the same time, it analyzes emotional data to understand the user's stress level and relaxation state.

[1840] Plan Selection and Notification:

[1841] Based on the analysis results, the server selects the most suitable electronic payment plan and promotion for the user, and the selected plan or promotion is notified to the terminal, adjusting the notification timing based on the user's emotional state.

[1842] Plan Change:

[1843] The user can review the notification and accept or reject the proposed plans and promotions. If accepted, the server uses that information to modify the plans and promotions and update the user's settings.

[1844] Specific examples

[1845] For example, if a user recently made a large purchase, the system will detect that spending data and store it in a database. At the same time, an emotion recognition engine will analyze the user's state of relaxation, and notify them of a specific cashback campaign at a time when they are relaxed, which is expected to increase approval rates. Furthermore, the system can predict a user's spending patterns from past data and provide them with the optimal electronic payment plan.

[1846] Prompt Sentence Examples

[1847] "Based on the spending data (50 items) and emotional data (50 items) from the past three months, please generate a code that analyzes the user's spending patterns and emotional state and suggests the optimal payment plan."

[1848] In this way, timely and effective service delivery can be achieved that takes into account the customer's spending patterns and emotional state.

[1849] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1850] Step 1:

[1851] Data collection

[1852] The device collects usage data such as the user's spending history and purchases, and simultaneously collects the user's emotional state by analyzing facial expressions and vocal tone using an emotion recognition engine.

[1853] Input: spending history, purchase details, facial expressions, voice tones

[1854] Data processing: Organize and structure the collected usage data and sentiment data.

[1855] Output: Structured usage and sentiment data

[1856] Step 2:

[1857] Data transmission

[1858] The device transmits the collected usage and emotion data to a server, either periodically or in real time.

[1859] Input: Structured usage data and sentiment data

[1860] Data Calculation: Convert the data into the appropriate format and send it to the server.

[1861] Output: Data sent to the server

[1862] Step 3:

[1863] Data accumulation

[1864] The server stores the usage data and emotion data sent from the terminal in a database.

[1865] Input: Submitted usage data and emotion data

[1866] Data processing: Record and save the received data in a database.

[1867] Output: Data stored in the database

[1868] Step 4:

[1869] Data analysis

[1870] The server analyzes the accumulated usage data and emotional data using machine learning algorithms to identify the user's spending patterns from past usage data and understand the user's emotional state from emotional data.

[1871] Input: Usage data and emotion data stored in a database

[1872] Data Computing: Data Analysis and Pattern Recognition with Machine Learning Models

[1873] Output: Analysis of user spending patterns and emotional state

[1874] Step 5:

[1875] Plan selection

[1876] The server selects the most suitable e-payment plan and promotion for the user based on the analysis results, and adjusts notifications to be sent at the appropriate time, taking into account emotional data.

[1877] Input: Analysis results (spending patterns and emotional state)

[1878] Data calculation: Selecting the best plan and promotion

[1879] Output: Selected electronic payment plans and promotions

[1880] Step 6:

[1881] notification

[1882] The server sends a notification message containing details of the selected electronic payment plan and promotion to the terminal, optimizing the timing of the notification based on the emotion data.

[1883] Input: Selected plan and promotion

[1884] Data calculation: Notification message generation and timing adjustment

[1885] Output: Notification message sent to the terminal

[1886] Step 7:

[1887] Change plan

[1888] The user reviews the notification and can accept or reject the proposed plan or promotion. If accepted, the device sends the information to the server, which then changes the plan or promotion and updates the user's settings.

[1889] Input: User approval / rejection

[1890] Data operation: Plan and promotion update processing

[1891] Output: Updated electronic payment plans and promotions

[1892] In this way, a system is realized that comprehensively analyzes the spending patterns and emotional state of customers and provides timely and effective electronic payment plans and promotions.

[1893] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1894] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1895] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1896] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1897] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1898] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1899] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1900] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1901] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1902] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1903] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1904] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1905] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1906] 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.

[1907] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1908] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1909] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1910] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1911] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1912] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1913] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1914] The following is further disclosed regarding the above embodiment.

[1915] (Claim 1)

[1916] means for collecting usage data from the device;

[1917] means for storing collected usage data;

[1918] A means of analyzing accumulated usage data and selecting the optimal service plan for each customer;

[1919] a means for notifying the customer of the selected service plan;

[1920] a means to change the service plan with customer approval;

[1921] A system including:

[1922] (Claim 2)

[1923] 10. The system of claim 1, further comprising means for performing analysis using machine learning algorithms based on historical usage data to identify customer usage patterns.

[1924] (Claim 3)

[1925] 10. The system of claim 1, further comprising means for notifying the customer of details of the selected service plan and the reasons for the selection.

[1926] "Example 1"

[1927] (Claim 1)

[1928] means for collecting usage data from the device;

[1929] means for storing collected usage data;

[1930] A means of analyzing accumulated usage data using machine learning algorithms to select the optimal service plan for each customer;

[1931] a means for sending a notice to the Customer containing details of the selected Service Plan and the reasons for the selection;

[1932] a means for automatically changing service plans with customer approval;

[1933] A system including:

[1934] (Claim 2)

[1935] 10. The system of claim 1, further comprising means for performing analysis using machine learning algorithms based on historical usage data to identify customer usage patterns.

[1936] (Claim 3)

[1937] 10. The system of claim 1, further comprising means for notifying the customer of details of the selected service plan and the reasons for the selection.

[1938] "Application Example 1"

[1939] (Claim 1)

[1940] means for collecting usage data from the device;

[1941] means for storing collected usage data;

[1942] A means of analyzing accumulated usage data and selecting the optimal service plan for each customer;

[1943] a means for notifying the customer of the selected service plan;

[1944] a means to change the service plan with customer approval;

[1945] a means for identifying usage data of electronic payment services and using machine learning algorithms to predict optimal pricing plans based on the usage data;

[1946] a means for notifying a user terminal of the selected rate plan and obtaining approval;

[1947] A system including:

[1948] (Claim 2)

[1949] 10. The system of claim 1, further comprising means for performing analysis using machine learning algorithms based on historical usage data to identify customer usage patterns.

[1950] (Claim 3)

[1951] 10. The system of claim 1, further comprising means for notifying the customer of details of the selected service plan and the reasons for the selection.

[1952] "Example 2: Combining Emotion Engines"

[1953] (Claim 1)

[1954] means for collecting usage data and emotion data from the device;

[1955] means for storing the collected usage data and sentiment data;

[1956] A means for analyzing accumulated usage data and sentiment data to select the optimal service plan for the customer;

[1957] a means for notifying the customer of the selected service plan;

[1958] A means to adjust the timing and method of notifications based on the customer's emotional state;

[1959] a means to change the service plan with customer approval;

[1960] A system including:

[1961] (Claim 2)

[1962] 10. The system of claim 1, further comprising means for performing analysis using machine learning algorithms based on historical usage data to identify customer usage patterns.

[1963] (Claim 3)

[1964] 10. The system of claim 1, further comprising means for notifying the customer of details of the selected service plan and the reasons for the selection.

[1965] "Application example 2 when combining emotion engines"

[1966] (Claim 1)

[1967] means for collecting usage data and emotion data from the device;

[1968] a means for storing the collected data;

[1969] A means for analyzing the accumulated data and selecting the most suitable electronic payment plans and promotions for customers;

[1970] A means of informing customers of selected electronic payment plans and promotions;

[1971] A means to change plans and promotions with customer approval;

[1972] A system including:

[1973] (Claim 2)

[1974] 10. The system of claim 1, further comprising means for performing analysis using machine learning algorithms based on historical usage data and sentiment data to identify customer spending patterns and sentiment states.

[1975] (Claim 3)

[1976] 10. The system of claim 1, further comprising means for notifying the customer of details of the selected electronic payment plan and promotion and the reasons for the selection. [Explanation of symbols]

[1977] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for collecting usage data from the device; means for storing collected usage data; A means of analyzing accumulated usage data and selecting the optimal service plan for each customer; a means for notifying the customer of the selected service plan; a means to change the service plan with customer approval; A system including:

2. 10. The system of claim 1, further comprising means for performing analysis using machine learning algorithms based on historical usage data to identify customer usage patterns.

3. 10. The system of claim 1, further comprising means for informing the customer of the details of the service plan selected and the reasons for the selection.

Images