system

Abstract

To provide systems.SOLUTION: A system includes the means for: measuring call time of a user in real time; measuring a communication amount of the user in real time; collecting data indicative of call contents and communication contents of the user; analyzing the collected data indicative of the call contents and communication contents, and estimating an emotional state of the user; calculating a price plan on the basis of the measured call time and the communication amount, as well as the estimated emotional state of the user; and notifying the calculated price plan.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Currently, it is difficult for mobile phone users to select the optimal plan based on their call time and data volume. This is because it is difficult for users to accurately grasp their call time and data volume. Furthermore, if users cannot select the optimal plan based on their call time and data volume, user satisfaction may decrease. [Means for solving the problem]

[0005] The present invention provides a system that measures the call time and communication volume of a customer's mobile phone in real time and provides the optimal plan based on the measured call time and communication volume, allowing the customer to select the optimal plan according to their call time and communication volume, thereby improving customer satisfaction. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] As a first embodiment of the present invention, a system for acquiring data through a telecommunications carrier's network can be considered as a means for measuring customer's mobile phone call duration and communication volume in real time. This system acquires data on call duration and communication volume in real time from the telecommunications carrier's network and calculates the optimal plan based on that data.

[0029] "Example 2"

[0030] In Example 2, a system that uses an algorithm to analyze call duration and communication volume patterns can be considered as a means of providing the optimal plan. This system uses a machine learning algorithm to analyze the customer's call and communication patterns based on the acquired call duration and communication volume data, and provides a plan optimized for those patterns.

[0031] "Example 3"

[0032] As a third example, a system that notifies customers of the optimal plan proposal can be considered as a means of providing a service to increase customer satisfaction. This system notifies the customer of the calculated optimal plan and clearly indicates that the customer can save on communication costs by switching to that plan. This can increase customer satisfaction.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: Obtain real-time customer mobile call duration and traffic data from the carrier's network.

[0036] Step 2: Based on the data obtained, calculate the optimal plan based on the customer's call time and data volume.

[0037] Step 3: Offer the calculated optimal plan to the customer.

[0038] "Example 2"

[0039] Step 1: Obtain real-time customer mobile call duration and traffic data from the carrier's network.

[0040] Step 2: Based on the acquired data, machine learning algorithms are used to analyze customer call and communication patterns.

[0041] Step 3: Based on the analysis results, provide the customer with a plan optimized for that pattern. "Example 3"

[0042] Step 1: Obtain real-time customer mobile call duration and traffic data from the carrier's network.

[0043] Step 2: Based on the data obtained, calculate the optimal plan based on the customer's call time and data volume.

[0044] Step 3: Notify the customer of the optimal plan and clearly indicate that they can save on communication costs by switching to that plan.

[0045] Example 1

[0046] Next, a description will be given of Example 1 of Form 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."

[0047] With traditional communication plans, it was difficult to provide optimal plans based on the customer's call time and data volume. In particular, because real-time data acquisition and analysis were not performed, it was not possible to provide plans optimized for the customer's usage patterns. In addition, the provision of services to improve customer satisfaction was insufficient.

[0048] 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.

[0049] In this invention, the server includes means for connecting to a communication network and measuring customer call time in real time, means for connecting to the communication network and measuring customer communication volume in real time, means for storing measured call time and communication volume data in a database, means for performing data calculations based on the stored data, means for calculating an optimal plan based on the results of the data calculations, and means for notifying the customer's terminal of the calculated optimal plan, thereby making it possible to provide an optimal plan in real time based on the customer's usage pattern.

[0050] A "communications network" is an infrastructure for data communication, including the Internet and mobile phone networks.

[0051] "Airtime" refers to the total amount of time a customer spends making or receiving phone calls.

[0052] "Communication volume" refers to the total amount of data used by the customer when conducting data communication.

[0053] "Real-time" means that data is processed immediately at the moment it is generated.

[0054] A "database" refers to a system for efficiently storing, managing, and retrieving data.

[0055] "Data calculation" refers to the process of performing calculations and analysis based on acquired data.

[0056] "Optimal plan" refers to the most suitable telecommunications service plan based on the customer's call time and data volume.

[0057] A "machine learning model" refers to an algorithm or system that learns from data and makes predictions and classifications.

[0058] "Terminal" means a device used by a customer, including a smartphone, tablet, etc.

[0059] "Notification" refers to the act of sending information from a server to a customer's terminal.

[0060] MODE FOR CARRYING OUT THE INVENTION

[0061] This invention is a system that measures the call duration and traffic volume of customers in real time through a communication network and calculates the optimal plan based on that data. A specific embodiment of this system will be described below.

[0062] Hardware and software used

[0063] The server uses the following hardware and software to connect to a communication network, acquire data, store it in a database, and perform data calculations. Specifically, the server uses the following hardware and software:

[0064] Hardware: High-performance servers

[0065] software:

[0066] Database management system (e.g., MySQL (registered trademark), PostgreSQL)

[0067] Programming language (e.g., Python (registered trademark), R)

[0068] Machine learning libraries (e.g., scikit-learn, TENSORFLOW (registered trademark))

[0069] Telecommunications carrier API (e.g., general telecommunications carrier API)

[0070] Data Acquisition and Storage

[0071] The server uses the carrier's API to obtain customer call duration and communication volume data in real time. The obtained data is stored in a database. For example, an INSERT query is executed on a MySQL database to store customer call duration and communication volume data.

[0072] Data calculation and analysis

[0073] The server performs data calculations based on the stored data. Specifically, it uses the Python pandas library to calculate the average call duration and data usage for each customer. It also uses machine learning models to predict the optimal plan for each customer. For example, it uses the scikit-learn library to calculate the optimal plan based on the customer's usage patterns.

[0074] Notification of the best plan

[0075] The server notifies the customer's device of the calculated optimal plan, for example, by sending a push notification using Firebase (registered trademark) Cloud Messaging (FCM) to propose the optimal plan to the customer.

[0076] Specific examples

[0077] User A uses 1,000 minutes of talk time and 5 GB of data communication per month. The server obtains User A's talk time and data volume data in real time through the telecommunications carrier's API. Based on the obtained data, the server calculates the optimal plan for User A. For example, the server proposes to User A a plan that includes 1,000 minutes of talk time and 5 GB of data communication per month.

[0078] Prompt Sentence Examples

[0079] "Please obtain real-time data on user A's call duration and data volume and calculate the optimal plan."

[0080] In this way, the server acquires data through the communication network, stores it in a database, performs data calculations, calculates the optimal plan, and finally notifies the user's terminal of the results.

[0081] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0082] Step 1:

[0083] The server connects to the carrier's API.

[0084] Input: Your carrier's API endpoint URL and authentication information.

[0085] Specific operation: The server sends an HTTP GET request to the carrier's API endpoint to obtain an authentication token. For example, send a request to https: / / api.carrier.com / v1 / auth.

[0086] Output: An authentication token.

[0087] Step 2:

[0088] The server collects customer call duration and traffic data.

[0089] Input: Authentication token and customer identification information.

[0090] Specific operation: The server uses the obtained authentication token to request the customer's call time and traffic data from the carrier's API, for example, by sending a GET request to https: / / api.carrier.com / v1 / user / data.

[0091] Output: Customer call duration and traffic data.

[0092] Step 3:

[0093] The server saves the retrieved data in the database.

[0094] Input: Customer call duration and volume data.

[0095] What happens: The server stores the retrieved data in a MySQL database, for example by executing the following SQL query:

[0096] sql

[0097] INSERT INTO user_data (user_id, call_time, data_usage) VALUES ('userA', 1000, 5);

[0098] Output: Data stored in a database.

[0099] Step 4:

[0100] The server performs data calculations based on the stored data.

[0101] Input: Customer call duration and volume data stored in a database.

[0102] What happens: The server uses the Python pandas library to calculate the average call duration and traffic volume for each customer. For example, it runs the following code:

[0103] python

[0104] import pandas as pd

[0105] data = pd.read_sql('SELECT FROM user_data WHERE user_id="userA"', connection)

[0106] average_call_time = data['call_time'].mean()

[0107] average_data_usage = data['data_usage'].mean()

[0108] Output: Average customer call duration and volume.

[0109] Step 5:

[0110] The server calculates the optimal plan based on the results of the data calculation.

[0111] Input: Average customer call duration and volume.

[0112] What it does: The server uses the scikit-learn library to predict the best plan for the customer using a machine learning model. For example, it runs the following code:

[0113] python

[0114] from sklearn.linear_model import LinearRegression

[0115] model = LinearRegression()

[0116] model.fit(X_train, y_train)

[0117] optimal_plan = model.predict([[average_call_time, average_data_usage]])

[0118] Output: The optimal plan.

[0119] Step 6:

[0120] The server notifies the customer's device of the optimal plan.

[0121] Input: Best plan and customer device information.

[0122] What happens: The server uses Firebase Cloud Messaging (FCM) to send a push notification to recommend the best plan for the customer. For example, it executes the following code:

[0123] python

[0124] import firebase_admin

[0125] from firebase_admin import messaging

[0126] message = messaging.Message(

[0127] notification=messaging.Notification(

[0128] title='Optimal plan proposal',

[0129] body=f'The best plan for you is {optimal_plan}.'

[0130] ),

[0131] token=userA_device_token,

[0132] )

[0133] response = messaging.send(message)

[0134] Output: Push notification sent to customer's device.

[0135] (Application example 1)

[0136] Next, a description will be given of Application Example 1 of Embodiment 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."

[0137] With modern telecommunications services, it is difficult for customers to select the optimal plan based on their call time and data volume. Furthermore, the procedures for changing plans and purchasing additional data are complicated, which is a factor in reducing customer satisfaction. Furthermore, the lack of real-time data collection and analysis makes it difficult to offer the optimal plan to customers. To solve these issues, a system is needed that measures customers' call time and data volume in real time, provides the optimal plan, and allows them to easily change plans and purchase additional data in conjunction with electronic payment services.

[0138] 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.

[0139] In this invention, the server includes means for measuring the call time of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for providing an optimal plan based on the measured call time and communication volume, and means for the means for providing the optimal plan to change plans or purchase additional data in cooperation with an electronic payment service. This allows the customer to be offered an optimal plan in real time based on their call time and communication volume, and to easily change plans or purchase additional data.

[0140] "Customer" means any person or entity that uses the telecommunications services.

[0141] "Mobile" refers to mobile communication devices such as mobile phones and smartphones.

[0142] "Talk Time" refers to the cumulative time during which a Customer makes voice calls using a mobile phone.

[0143] "Data volume" refers to the total amount of data sent and received by a customer using their mobile phone.

[0144] "Real-time" means that data is processed and analyzed immediately at the moment it is generated.

[0145] "Means for measuring" refers to a combination of hardware and software for measuring call duration and traffic.

[0146] The "optimal plan" refers to the communications service plan that offers the best cost performance and convenience based on the customer's call time and data volume.

[0147] "Means of provision" refers to the systems and methods for presenting the optimal plan to customers.

[0148] "Electronic payment services" refers to financial transaction services conducted via the Internet.

[0149] "Plan change" refers to switching from your current communications service plan to another plan.

[0150] "Additional data purchase" refers to purchasing additional data capacity in addition to an existing communication plan.

[0151] "Collaboration" refers to different systems and services working together.

[0152] The following system configuration will be described as an embodiment of the present invention.

[0153] System Configuration

[0154] 1. Hardware Configuration

[0155] Server: A server is used that connects to the carrier's network to obtain customer call time and data volume in real time. This server collects and analyzes data, calculates optimal plans, and connects with electronic payment services.

[0156] Terminal: Refers to a mobile communication terminal such as a mobile phone or smartphone used by a customer. These terminals communicate with the server and send and receive data in real time.

[0157] 2. Software Configuration

[0158] Data acquisition module: This module uses the carrier's API to acquire customer call duration and data volume in real time. It uses the Python requests library to acquire data from the API.

[0159] Data analysis module: This module analyzes customer call duration and data usage patterns based on the acquired data and calculates the optimal plan. Data analysis uses Python's pandas and numpy libraries.

[0160] Plan offering module: This module presents the most suitable plan to the customer. It displays the plan details to the customer through the user interface.

[0161] Electronic payment module: This module uses the API of the electronic payment service to change plans and purchase additional data. It calls the payment API using the Python requests library.

[0162] Processing flow

[0163] 1. Data Acquisition

[0164] The server retrieves customer call duration and traffic data in real time through the carrier's API, which is securely retrieved using the customer's authentication information.

[0165] 2. Data analysis

[0166] The server analyzes the acquired data to understand the customer's call duration and data volume patterns, and then calculates the optimal communication plan for the customer.

[0167] 3. Plan Offering

[0168] The server then notifies the customer of the optimal plan it has calculated, and the customer can check the plan details through a smartphone application.

[0169] 4. Electronic Payments

[0170] When a customer wishes to change their plan or purchase additional data, the server calls the API of the electronic payment service to execute the payment, allowing customers to easily change their plan or purchase additional data.

[0171] Specific examples

[0172] For example, if a customer uses more than 1,000 minutes of calls and 10GB of data per month, the server will suggest the "Premium Plan." This suggestion will be sent to the customer's smartphone, and the customer can check the plan details through the application. Furthermore, if the customer wants to change to the "Premium Plan," the server will execute the plan change through an electronic payment service.

[0173] Prompt Sentence Examples

[0174] "You will develop an application that monitors the user's call time and data usage in real time and proposes the optimal data plan. The application will obtain user data from the carrier's API and calculate the optimal plan. It will also use the API of an electronic payment service to change plans and purchase additional data."

[0175] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0176] Step 1:

[0177] The server obtains customer call duration and traffic data in real time through the carrier's API. The input is customer authentication information, and the output is call duration and traffic data. Specifically, it uses the Python requests library to send requests to the API endpoint and receives data in JSON format.

[0178] Step 2:

[0179] The server analyzes the acquired call duration and communication volume data. The input is the data acquired in step 1, and the output is the customer's call duration and communication volume patterns. Specifically, it processes the data using Python's pandas and numpy libraries to extract customer usage patterns.

[0180] Step 3:

[0181] The server calculates the optimal communication plan based on the analysis results. The input is the usage pattern obtained in step 2, and the output is a proposal for the optimal plan. Specifically, it compares the customer's usage pattern with the pre-set plan conditions and selects the most suitable plan.

[0182] Step 4:

[0183] The server notifies the customer's device of the calculated optimal plan. The input is the optimal plan calculated in step 3, and the output is the plan information displayed on the customer's device. Specifically, push notifications or in-app notifications are used to inform the customer of the plan details.

[0184] Step 5:

[0185] When a user wishes to change their plan or purchase additional data, they send a request from their device to the server. The input is the user's request to change their plan or purchase additional data, and the output is the request data sent to the server. Specifically, the user makes a selection through the application interface, and that information is sent to the server.

[0186] Step 6:

[0187] The server calls the API of the electronic payment service to change the plan or purchase additional data. The input is the request data received in step 5, and the output is confirmation data that the payment has been completed. Specifically, the server uses the Python requests library to send a request to the payment API and receive the payment result.

[0188] Step 7:

[0189] The server notifies the customer's device of the payment completion confirmation data. The input is the payment completion confirmation data obtained in step 6, and the output is a payment completion notification that is displayed on the customer's device. Specifically, the server notifies the customer of the payment completion information using a push notification or in-app notification.

[0190] Example 2

[0191] Next, a description will be given of Example 2 of Form 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."

[0192] With conventional communication plans, it was difficult to provide the optimal plan based on the customer's call time and data volume, making it difficult to find a plan that suited the customer's usage pattern. In addition, the provision of services to improve customer satisfaction was insufficient.

[0193] 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.

[0194] In this invention, the server includes means for measuring the call duration of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for storing the measured call duration and communication volume in a database, means for preprocessing the stored data, means for analyzing call and communication patterns using a machine learning algorithm based on the preprocessed data, and means for providing an optimal plan based on the analysis results, thereby making it possible to provide a communication plan optimized for the customer's usage pattern and improving customer satisfaction.

[0195] "Means for measuring customer mobile phone call duration in real time" refers to a device or software for instantly measuring the duration of calls made by customers on their mobile phones and obtaining that data.

[0196] "Means for measuring customer mobile phone traffic in real time" refers to a device or software that instantly measures the amount of data traffic used by a customer on their mobile phone and obtains that data.

[0197] The "means for storing the measured call duration and communication volume in a database" refers to a device or software for storing the acquired call duration and communication volume data in a database so that it can be used later.

[0198] "Means for preprocessing stored data" refers to devices or software that perform processes such as filling in missing values ​​and removing outliers in order to prepare data stored in a database in a form that is easier to analyze.

[0199] "Means for analyzing call and communication patterns using machine learning algorithms based on preprocessed data" means devices or software that use preprocessed data as input and machine learning algorithms to analyze customers' call and communication usage patterns.

[0200] The "means for providing the optimal plan based on the analysis results" refers to a device or software that proposes the optimal communication plan to a customer based on the analysis results of a machine learning algorithm.

[0201] The present invention is a system that collects data on customer call duration and communication volume, and uses a machine learning algorithm to provide optimal communication plans. Specific embodiments of this system will be described below.

[0202] First, the server collects data by measuring the customer's mobile phone call duration and the customer's mobile phone data usage in real time. These methods are realized using the telecommunications carrier's API. For example, a request is sent to the telecommunications carrier's API endpoint and JSON format data is received as a response.

[0203] The server then stores the collected data in a database, typically a relational database such as MySQL or PostgreSQL. The stored data includes user IDs, call duration, communication volume, and collection date and time.

[0204] The server then preprocesses the stored data. Specifically, it imputes missing values ​​and removes outliers. It uses the Python Pandas library to clean the data. For example, it executes the following code to impute missing values:

[0205] The server then uses machine learning algorithms to analyze users' call and communication patterns based on the preprocessed data. Specifically, it uses a clustering algorithm (e.g., K-means clustering) to classify users into several groups. The clustering is performed using the Scikit-learn library.

[0206] Finally, the server proposes the optimal communication plan for the user based on the analysis results. The proposed plan is notified to the user's device. For example, if the user has a long call duration and a low data volume, an unlimited call plan is proposed.

[0207] As a concrete example, consider the call time and data volume data of User A. User A makes a total of 300 minutes of calls per month and uses 5GB of data. Based on this data, the server analyzes User A's call and communication patterns. As a result of the analysis, it is determined that an unlimited call plan and 5GB data plan is optimal for User A.

[0208] Examples of prompts to be input to a generative AI model include:

[0209] "User A has 300 minutes of talk time and 5GB of data usage per month. Please suggest the best data plan for this user."

[0210] By inputting this prompt into the generative AI model, the AI ​​will suggest the optimal communication plan for User A.

[0211] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0212] Step 1:

[0213] The server collects data by measuring the customer's mobile phone call duration in real time and the customer's mobile phone data traffic in real time. Specifically, it calls the telecommunications carrier's API to obtain data on the user's call duration and data traffic. The input is the response data from the telecommunications carrier's API endpoint, and the output is data on the call duration and data traffic.

[0214] Step 2:

[0215] The server stores the collected data in a database. Specifically, it uses a relational database such as MySQL or PostgreSQL to store the acquired call duration and communication volume data. The input is the call duration and communication volume data acquired in step 1, and the output is the data stored in the database.

[0216] Step 3:

[0217] The server preprocesses the stored data. Specifically, it imputes missing values ​​and removes outliers. It uses the Python Pandas library to clean the data. The input is the raw data stored in the database, and the output is the preprocessed, clean data.

[0218] Step 4:

[0219] The server uses a machine learning algorithm to analyze users' call and communication patterns based on the preprocessed data. Specifically, it uses the Scikit-learn library to perform K-means clustering and classify users into several groups. The input is the preprocessed data, and the output is the clustering results.

[0220] Step 5:

[0221] The server proposes the optimal communication plan to the user based on the analysis results. Specifically, it analyzes the clustering results and determines the optimal plan for each cluster. The proposed plan is notified to the user's device. The input is the clustering results, and the output is the optimal communication plan proposed to the user.

[0222] Step 6:

[0223] The user receives the proposed communication plan from the server and changes the plan as needed. Specifically, the user checks the plan notified on the user's device and changes the plan through the carrier's website or app. The input is the proposed plan from the server, and the output is the new communication plan selected by the user.

[0224] (Application example 2)

[0225] Next, a description will be given of Application Example 2 of Form 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."

[0226] While the conventional system can provide optimal plans based on the customer's call time and data volume, it has the problem of not being able to provide optimal payment plans that take into account the usage patterns of electronic payments. There was also the problem of insufficient service provision to improve customer satisfaction.

[0227] 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.

[0228] In this invention, the server includes means for measuring the call duration of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for providing an optimal plan based on the measured call duration and communication volume, means for analyzing the customer's electronic payment usage patterns, and means for providing an optimal payment plan based on the analysis results. This makes it possible to comprehensively analyze the customer's call and communication patterns and electronic payment usage patterns and provide an optimal plan.

[0229] "Airtime" refers to the total time a customer makes calls using a mobile phone.

[0230] "Communication volume" refers to the total volume of data transmitted by a customer using a mobile phone.

[0231] "Optimal Plan" refers to the service plan that is most economical and convenient for the Customer based on the Customer's call duration and communication volume patterns.

[0232] "Electronic payment" refers to the act of a customer paying for goods or services by electronic means.

[0233] "Usage patterns" refers to the frequency or tendency of a customer to use a particular service or feature.

[0234] "Analytical tools" refers to algorithms or software that are used to identify patterns or trends based on collected data.

[0235] "Means of provision" refers to methods and systems for presenting optimal plans and services to customers based on the analysis results.

[0236] The system for implementing this invention measures the call time and communication volume of a customer's mobile phone in real time, and further analyzes the customer's electronic payment usage patterns to provide the optimal plan. A specific embodiment of this system will be described below.

[0237] System configuration

[0238] The system consists of the following main components:

[0239] 1. Call duration measurement means: Measure the call duration of customers' mobile phones in real time.

[0240] 2. Data traffic measurement method: Measures data traffic on customers' mobile phones in real time.

[0241] 3. Data collection server: collects and stores call duration and traffic data.

[0242] 4. Analysis Server: Based on the collected data, machine learning algorithms are used to analyze customer usage patterns.

[0243] 5. Plan provision server: Based on the analysis results, it provides the optimal plan to the customer.

[0244] 6. Means of analyzing electronic payment usage patterns: Analyze customers' electronic payment usage patterns.

[0245] 7. Payment plan offering method: Based on the analysis results, the optimal payment plan is offered.

[0246] Hardware and software used

[0247] Hardware: Smartphones, servers

[0248] Software: Python, Pandas, Scikit-learn

[0249] Data processing and calculation

[0250] 1. Data collection: Call duration and communication volume data are collected in real time from smartphones and sent to a data collection server.

[0251] 2. Data preprocessing: The collected data is standardized and sent to the analysis server.

[0252] 3. Applying machine learning algorithms: The analytics server uses machine learning algorithms (e.g., KMeans clustering) to analyze customer usage patterns.

[0253] 4. Proposing the optimal plan: Based on the analysis results, the plan providing server proposes the optimal plan to the customer.

[0254] 5. Analysis of electronic payment usage patterns: Analyze the usage patterns of electronic payments and provide optimal payment plans.

[0255] Specific examples

[0256] For example, if User A makes more than 20 payments per month and primarily uses the service in urban areas, the "high-frequency user plan" will be offered to this user. On the other hand, User B makes around 10 payments per month and primarily uses the service in suburban areas. The "medium-frequency user plan" will be offered to this user.

[0257] Prompt Sentence Examples

[0258] I want to develop an application that proposes optimal payment plans based on users' payment history data. Using the following data, please generate Python code that clusters users and proposes the optimal plan for each cluster.

[0259] Data items:

[0260] transaction_amount: Payment amount

[0261] transaction_frequency: Transaction frequency

[0262] location: Location of use

[0263] output:

[0264] suggested_plan: The proposed plan

[0265] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0266] Step 1:

[0267] Data collection

[0268] The device (smartphone) measures the customer's call duration and communication volume data in real time and sends this data to a data collection server. The input is the call duration and communication volume data, and the output is the measurement data sent to the data collection server.

[0269] Step 2:

[0270] Data Preprocessing

[0271] The server standardizes the collected call duration and traffic data. Specifically, it reads the data using the Pandas library and standardizes the data using StandardScaler. The input is the collected raw data, and the output is the standardized data.

[0272] Step 3:

[0273] Applying machine learning algorithms

[0274] The server applies a machine learning algorithm (KMeans clustering) to the standardized data. Specifically, it performs clustering using the Scikit-learn library to analyze customer usage patterns. The input is the standardized data, and the output is the clustering results.

[0275] Step 4:

[0276] Proposing the optimal plan

[0277] The server proposes the optimal plan to the customer based on the clustering results. Specifically, it determines the optimal plan for each cluster and notifies the customer. The input is the clustering results, and the output is the proposed optimal plan.

[0278] Step 5:

[0279] Analysis of electronic payment usage patterns

[0280] The server analyzes the customer's electronic payment usage patterns. Specifically, it collects payment history data and analyzes the usage patterns using machine learning algorithms. The input is the payment history data, and the output is the analysis results of the usage patterns.

[0281] Step 6:

[0282] Offering payment plans

[0283] The server provides optimal payment plans based on the results of analyzing electronic payment usage patterns. Specifically, it determines the optimal payment plan for each usage pattern and notifies the customer. The input is the analysis results of usage patterns, and the output is the proposed optimal payment plan.

[0284] Example 3

[0285] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0286] Traditional communication plans were not optimized for customer usage patterns, resulting in customers often paying unnecessary communication fees. It was also difficult for customers to find the plan that best suited them, leading to low satisfaction. Even when systems existed that suggested optimal plans, the notification methods and plan change procedures were complicated, making it difficult for customers to actually change their plans.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0288] In this invention, the server includes means for measuring the call time of a customer's communication terminal in real time, means for measuring the data usage of the customer's communication terminal in real time, means for calculating an optimal communication plan based on the measured call time and data usage, means for notifying the customer of the calculated optimal communication plan, and means for the customer to change to the notified communication plan. This allows customers to easily find a communication plan that is optimal for their usage pattern, thereby saving on communication costs and improving customer satisfaction.

[0289] "Call time" is the total time during which a customer makes a call using a communication terminal.

[0290] "Data usage" means the total amount of data consumed by a customer when using a communication device to access the Internet or applications.

[0291] A "communication plan" is a pricing structure for communication services provided by a telecommunications carrier, including talk time, data usage, and number of SMS messages sent.

[0292] "Real-time measurement means" refers to technology that instantly measures the call time and data usage of customers' communication devices and records them in a database.

[0293] The "means for calculating the optimal communication plan" refers to algorithms or software that analyzes a customer's call time and data usage patterns and selects the most cost-effective communication plan based on the results.

[0294] "Means of notification" refers to the method used to notify customers of the calculated optimal communication plan, and includes email, SMS, in-app notifications, etc.

[0295] "Plan change method" means the process or interface through which a customer can change to the notified communications plan, including online portals and customer support.

[0296] MODE FOR CARRYING OUT THE INVENTION

[0297] This invention is a system for reducing customer communication costs and improving customer satisfaction. This system measures the call time and data usage of the customer's communication terminal in real time, calculates the optimal communication plan based on that data, and notifies the customer. It also provides a means for the customer to change to the notified communication plan.

[0298] Data collection

[0299] The server measures the call duration and data usage of the customer's communication device in real time. Specifically, it obtains data from the communication carrier's database using an API. The hardware used is a database server (e.g., MySQL, PostgreSQL), and the software used is a data collection script (e.g., Python, Java (registered trademark)).

[0300] Data analysis

[0301] The server analyzes the collected data and identifies customer usage patterns. Specifically, it uses machine learning algorithms to analyze customer communication usage trends. The software used is a machine learning library (e.g., TensorFlow, scikit-learn).

[0302] Calculating the optimal plan

[0303] The server then calculates the optimal communication plan for the customer based on the analysis results. Specifically, it compares existing plan information with the customer's usage patterns to select the most cost-effective plan. The software used is an optimization algorithm (e.g., linear programming).

[0304] notification

[0305] The server notifies the customer of the calculated optimal communication plan. Specifically, it sends the proposal to the customer using methods such as email, SMS, and in-app notifications. The software used is a notification system.

[0306] Change plan

[0307] After receiving the notification, the user can change to the proposed plan. Specifically, the change procedure is carried out through an online portal or customer support. The hardware used is the customer's device (e.g., smartphone, PC), and the software used is the carrier's online portal.

[0308] Specific examples

[0309] As a concrete example, by inputting the following prompt sentence into a generative AI model, it is possible to simulate the behavior of a system that proposes the optimal plan for a customer.

[0310] Example prompt sentence:

[0311] Customer A's communication usage data is as follows:

[0312] Talk time: 300 minutes / month

[0313] Data usage: 5GB / month

[0314] Number of SMS sent: 50 / month

[0315] Based on this data, please propose the best communication plan for Customer A.

[0316] In this way, the customer can save on communication costs and improve satisfaction by switching to the most suitable plan. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0317] Step 1: Data collection

[0318] The server measures the call time and data usage of the customer's communication device in real time. Specifically, it obtains data from the communication carrier's database using an API. As input, it uses customer identification information (e.g., customer ID), and as output, it obtains communication usage data such as call time, data usage, and number of SMS sent. For example, it confirms that customer A's call time is 300 minutes, data usage is 5GB, and the number of SMS sent is 50.

[0319] Step 2: Data analysis

[0320] The server analyzes the collected data and identifies the customer's usage patterns. Specifically, it uses a machine learning algorithm to analyze the customer's communication usage trends. The communication usage data collected in step 1 is used as input, and the customer's usage patterns (e.g., high call time, medium data usage, etc.) are obtained as output. For example, it is identified that Customer A has high call time and medium data usage.

[0321] Step 3: Calculate the optimal plan

[0322] The server calculates the optimal communication plan for the customer based on the analysis results. Specifically, it compares existing plan information with the customer's usage patterns and selects the most cost-effective plan. The usage patterns obtained in step 2 and existing plan information are used as input, and the optimal communication plan is obtained as output. For example, it may determine that an unlimited calling plan is optimal.

[0323] Step 4: Notification

[0324] The server notifies the customer of the calculated optimal communication plan. Specifically, it sends the proposal to the customer using methods such as email, SMS, and in-app notifications. The optimal communication plan obtained in step 3 and the customer's contact information are used as input, and a notification message is sent as output. For example, it notifies Customer A by email that "an unlimited calling plan is the best option."

[0325] Step 5: Change your plan

[0326] After receiving the notification, the user can change to the proposed plan. Specifically, the change procedure is carried out through an online portal or customer support. The notification message and the customer's selection are used as input, and confirmation of the plan change is obtained as output. For example, Customer A uses his smartphone to access the carrier's online portal and change to an unlimited calling plan. After the change procedure is completed, the user confirms that the new plan has been applied.

[0327] (Application example 3)

[0328] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0329] While the conventional system could provide optimal plans based on the customer's call time and data volume, it had the problem of not being able to propose optimal payment plans that took into account the customer's payment history and usage patterns. As a result, customers were unable to enjoy optimal plans not only in terms of saving on communication costs, but also in terms of payment fees and point redemption rates, and improvements in customer satisfaction were limited.

[0330] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0331] In this invention, the server includes means for measuring the customer's mobile phone call time in real time, means for measuring the customer's mobile phone communication volume in real time, means for providing an optimal plan based on the measured call time and communication volume, and means for analyzing the customer's payment history and proposing an optimal payment plan. This enables the customer to enjoy an optimal plan not only in terms of saving on communication costs but also in terms of payment fees, point redemption rates, etc.

[0332] "Means for measuring customer mobile phone call duration in real time" refers to a device or software for measuring and recording in real time the duration of calls made by a customer using a mobile phone.

[0333] "Means for measuring customer mobile phone data traffic in real time" refers to a device or software that measures and records in real time the data traffic when a customer uses a mobile phone for data communication.

[0334] "Means for providing the optimal plan based on the measured call time and communication volume" refers to a device or software that analyzes data on call time and communication volume measured in real time and proposes the most suitable communication plan for the customer.

[0335] "Means for analyzing a customer's payment history and proposing the most suitable payment plan" refers to a device or software that analyzes a customer's past payment history data and proposes the most advantageous payment plan for the customer (e.g., credit card, debit card, electronic money, etc.).

[0336] The system for implementing this invention measures the call time and communication volume of a customer's mobile phone in real time, and further analyzes the customer's payment history to propose the optimal plan. A specific embodiment of this system will be described below.

[0337] System configuration

[0338] The system mainly consists of the following hardware and software:

[0339] Hardware: General purpose PC or server

[0340] Software: Python, pandas, scikit-learn, numpy

[0341] Data collection and processing

[0342] The server collects call duration and traffic data from the customer's mobile phone in real time. This is done using an API that works with the mobile phone's communication module. The collected data is then recorded in real time on the server.

[0343] Next, the server collects the customer's payment history data, which is obtained from the payment methods used by the customer (credit cards, debit cards, electronic money, etc.) using the payment provider's API.

[0344] Analyzing the data

[0345] The server analyzes the collected call duration and traffic data and proposes the best communication plan for the customer, which involves the following steps:

[0346] 1. Data Normalization: To normalize the call duration and traffic data, we use Python's StandardScaler.

[0347] 2. Clustering: Use KMeans clustering to analyze customer usage patterns.

[0348] 3. Plan proposal: Propose the optimal communication plan for each cluster.

[0349] Furthermore, the server analyzes the customer's payment history data and proposes the most suitable payment plan, which includes the following steps:

[0350] 1. Data Normalization: Use Python's StandardScaler to normalize payment history data.

[0351] 2. Clustering: Use KMeans clustering to analyze customer payment patterns.

[0352] 3. Plan proposal: Propose the optimal payment plan for each cluster.

[0353] Proposal Notification

[0354] The server then notifies the customer of the optimal communication and payment plan based on the analysis results. Notification is sent via a smartphone app. The customer can then review the proposed plan through the app and change it if necessary.

[0355] Specific examples

[0356] For example, if a customer uses 1,000 minutes of calls and 10GB of data per month, the server collects this data in real time and proposes the optimal communication plan. At the same time, it analyzes the customer's payment history and proposes the optimal payment plan (for example, a credit card with a high reward point rate).

[0357] Prompt Sentence Examples

[0358] Below are some example prompts to input to a generative AI model:

[0359] Develop an application that analyzes users' payment history data and proposes optimal payment plans. Use features such as the user's payment amount, transaction type, transaction time, and day of the week to perform KMeans clustering and propose the optimal payment plan (credit card, debit card, electronic money, etc.) for each cluster. Use Python and its libraries (pandas, scikit-learn, numpy).

[0360] In this way, customers can not only save on communication costs, but also enjoy the best plan in terms of payment fees and point redemption rates.

[0361] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0362] Step 1:

[0363] The server collects call duration and communication volume data from the customer's mobile phone in real time. Specifically, it uses an API that works with the mobile phone's communication module to obtain information such as the call start time, end time, and data communication volume. The input is real-time data from the mobile phone, and the output is call duration and communication volume data that is stored on the server.

[0364] Step 2:

[0365] The server collects the customer's payment history data. To do this, it uses the payment provider's API to obtain data from the payment methods used by the customer (credit cards, debit cards, electronic money, etc.). The input is the payment history data from the payment provider, and the output is the payment history data stored on the server.

[0366] Step 3:

[0367] The server standardizes the collected call duration and traffic data by using Python's StandardScaler to convert each data point to a mean of 0 and a standard deviation of 1. The input is the raw call duration and traffic data, and the output is the standardized data.

[0368] Step 4:

[0369] The server clusters the normalized call duration and traffic data. Specifically, it uses KMeans clustering to analyze customer usage patterns and classify them into multiple clusters. The input is the normalized data, and the output is the label of the cluster to which each data point belongs.

[0370] Step 5:

[0371] The server proposes the optimal communication plan for each cluster. Specifically, it selects the optimal communication plan (for example, an unlimited calling plan for a cluster with a high call duration) based on the usage pattern of each cluster. The input is the cluster label, and the output is the optimal communication plan proposal.

[0372] Step 6:

[0373] The server standardizes the collected payment history data. Specifically, it uses Python's StandardScaler to convert each data point to a mean of 0 and a standard deviation of 1. The input is the raw payment history data, and the output is the standardized data.

[0374] Step 7:

[0375] The server clusters the standardized payment history data. Specifically, it uses KMeans clustering to analyze customer payment patterns and classify them into multiple clusters. The input is the standardized data, and the output is the label of the cluster to which each data point belongs.

[0376] Step 8:

[0377] The server proposes the optimal payment plan for each cluster. Specifically, it selects the optimal payment plan (e.g., a credit card with a high reward point rate) based on the payment patterns of each cluster. The input is the cluster label, and the output is the optimal payment plan proposal.

[0378] Step 9:

[0379] The server notifies the customer of the optimal communication and payment plan based on the analysis results. Specifically, the notification is sent via a smartphone app. The input is the optimal plan proposal, and the output is a notification to the customer. The customer can check the proposed plan through the app and change the plan if necessary.

[0380] 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.

[0381] "Example 1"

[0382] In one embodiment of the present invention, the emotion engine recognizes emotions from the content of a user's call. Specifically, it analyzes characteristics such as the user's voice tone, volume, and speaking rate, and estimates the user's emotional state from these characteristics. Based on this emotional state, an optimal plan is provided. For example, if a user expresses anger, a special plan such as a discount on call charges can be provided to that user, thereby improving user satisfaction.

[0383] "Example 2"

[0384] In another embodiment of the present invention, the emotion engine recognizes emotions not only from the content of a user's calls but also from the content of their communications. Specifically, the emotion engine analyzes the content of text messages and emails sent by the user and infers the user's emotional state from the content. Based on this emotional state, an optimal plan is provided. For example, if a user expresses joy, a special plan with increased data traffic can be provided to that user, thereby improving user satisfaction.

[0385] "Example 3"

[0386] In yet another embodiment of the present invention, the emotion engine recognizes emotions from the content of a user's calls and communications and provides an optimal plan based on the emotions. Specifically, the emotion engine analyzes the content of text messages and emails sent by the user, as well as the tone, volume, and speaking speed of the user's voice, and estimates the user's emotional state from the content. The optimal plan is provided based on this emotional state. For example, if a user expresses sadness, the emotion engine can improve user satisfaction by providing the user with a special plan, such as a discount on call charges.

[0387] The processing flow of each embodiment will be described below.

[0388] "Example 1"

[0389] Step 1: The user initiates a call.

[0390] Step 2: The emotion engine analyzes the user's voice characteristics such as tone, volume, and speaking rate.

[0391] Step 3: The emotion engine infers the user's emotional state from the analysis results.

[0392] Step 4: Provide an optimal plan based on the estimated emotional state.

[0393] "Example 2"

[0394] Step 1: A user initiates a communication.

[0395] Step 2: The emotion engine analyzes the content of the text message or email sent by the user.

[0396] Step 3: The emotion engine infers the user's emotional state from the analysis results.

[0397] Step 4: Provide an optimal plan based on the estimated emotional state.

[0398] "Example 3"

[0399] Step 1: A user initiates a call or communication.

[0400] Step 2: The emotion engine analyzes the content of the text messages and emails sent by the user, as well as the tone of voice, volume, and speaking rate.

[0401] Step 3: The emotion engine infers the user's emotional state from the analysis results.

[0402] Step 4: Provide an optimal plan based on the estimated emotional state.

[0403] Example 1

[0404] Next, a description will be given of Example 1 of Form 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."

[0405] Conventional communication plan provision systems can provide optimal plans based on the customer's call time and data volume, but they have the problem of not being able to provide plans that take into account the customer's emotional state. This makes it difficult to sufficiently improve customer satisfaction and provide flexible plans that meet customer needs.

[0406] 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.

[0407] In this invention, the server includes means for measuring the call time of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for providing an optimal plan based on the measured call time and communication volume, means for recognizing the emotion of the customer from the content of the call, and means for providing an optimal plan based on the recognized emotion. This makes it possible to provide an optimal plan that takes into account not only the customer's call time and communication volume but also their emotional state, thereby improving customer satisfaction.

[0408] "Means for measuring customer mobile phone call duration in real time" refers to technology that obtains the start and end times of customer calls via a communications network and measures call duration in real time based on that information.

[0409] "Means for measuring customer mobile phone data usage in real time" refers to technology that monitors customer data usage in real time through a communication network and measures data usage based on that information.

[0410] "Means for providing the optimal plan based on measured call time and communication volume" refers to technology that analyzes acquired call time and communication volume data, and calculates and provides the communication plan that is most suitable for the customer's usage pattern.

[0411] The "means for recognizing emotions from the content of a customer's call" is a technology that uses voice recognition technology to analyze the content of a customer's call and estimate the customer's emotional state from characteristics such as tone of voice, volume, and speaking speed.

[0412] "Means for providing optimal plans based on recognized emotions" refers to technology that calculates and provides special communication plans according to the customer's emotional state based on the results of emotion recognition.

[0413] MODE FOR CARRYING OUT THE INVENTION

[0414] This invention is a system that measures the call time and communication volume of a customer's mobile phone in real time and provides the optimal plan based on that data. It also includes a function that recognizes the customer's emotions from the content of the call and provides the optimal plan based on that emotional state.

[0415] The server obtains customer call duration and communication volume data in real time via the communication network. Specifically, it uses the communication carrier's API to collect information such as the start time and end time of the customer's call and the amount of data used during the call. For example, it sends a request to the communication carrier's API endpoint and receives the call data as a response.

[0416] The server then analyzes the data, converting it into a data frame using Python's Pandas library, and calculating the total call duration, average call duration, and total communication volume for each customer, allowing it to identify customer usage patterns.

[0417] The server then uses an emotion engine to recognize emotions from the customer's call. It converts the voice data into text using the Google® Cloud Speech-to-Text API, and inputs the text into an emotion analysis model. The emotion analysis model analyzes the customer's voice characteristics, such as tone, volume, and speaking rate, to estimate their emotional state.

[0418] For example, if a user shows anger during a call, the server can offer the user a special plan with a discount on the call charge, thereby improving user satisfaction.

[0419] Examples of specific prompts include:

[0420] "Design a system that recognizes emotions from the content of a user's calls and offers special plans with discounts on call charges if the user expresses anger. Explain how you would obtain real-time call duration and traffic data from a carrier's network and use voice recognition technology to analyze user emotions."

[0421] Using this prompt, the generative AI model can provide a detailed design and implementation method for the system.

[0422] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0423] Step 1:

[0424] The server obtains customer call duration and communication volume data in real time through the carrier's network. As input, it sends a request to the carrier's API endpoint and receives information such as the call start time, end time, and call data volume as a response. This allows the server to collect customer call duration and communication volume data.

[0425] Step 2:

[0426] The server analyzes the acquired call duration and communication volume data. It uses the data acquired in step 1 as input. It converts it into a data frame using Python's Pandas library and calculates the total call duration, average call duration, total communication volume, etc. for each customer. The output is the usage pattern for each customer. Specific operations include grouping and aggregation of the data frame.

[0427] Step 3:

[0428] The server uses an emotion engine to recognize emotions from the customer's call content. It uses the call's audio data as input. It converts the audio data to text using the Google Cloud Speech-to-Text API and inputs the text into a sentiment analysis model. The output is the customer's emotional state. Specific operations include converting the audio data to text and analyzing sentiment.

[0429] Step 4:

[0430] The server calculates the optimal plan for the customer based on the analysis results and emotion recognition results. As input, it uses the usage pattern obtained in step 2 and the emotional state obtained in step 3. If the customer's call time is long, it proposes an unlimited call plan, and if the customer shows anger, it proposes a special plan with discounted call charges. The optimal plan is obtained as output. As a specific operation, it selects the plan using conditional branching.

[0431] Step 5:

[0432] The server provides the calculated optimal plan to the customer. As input, it uses the optimal plan obtained in step 4. It sends a notification to the customer's device and displays details of the optimal plan. As output, it provides the customer with information about the plan. Specific operations include sending a notification and displaying plan details.

[0433] (Application example 1)

[0434] Next, a description will be given of Application Example 1 of Embodiment 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."

[0435] Conventional communication plan provision systems can provide optimal plans based on the customer's call time and data volume, but they are unable to provide services that take into account the customer's emotional state, limiting the improvement of customer satisfaction. Also, if a customer becomes stressed or angry during a call, they may not be able to respond appropriately, which could result in a security risk. To solve these problems, a system is needed that recognizes the customer's emotional state in real time and provides appropriate services and security alerts based on that.

[0436] 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.

[0437] In this invention, the server includes means for measuring the call time of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for providing an optimal plan based on the measured call time and communication volume, means for recognizing the customer's emotion from the content of the call, and means for issuing a security alert based on the recognized emotion. This makes it possible to provide an optimal plan that takes into account the emotional state of the customer and reduce security risks.

[0438] "Means for measuring customer mobile phone call duration in real time" refers to a device or software for measuring the time a customer is making a call on a mobile phone in real time.

[0439] "Means for measuring customer mobile phone traffic in real time" refers to a device or software for measuring the amount of data traffic used by a customer on a mobile phone in real time.

[0440] "Means for providing the optimal plan based on the measured call time and communication volume" refers to a device or software that calculates and provides the optimal communication plan to a customer based on data on call time and communication volume measured in real time.

[0441] The "means for recognizing emotions from the content of a customer's call" refers to a device or software that analyzes the voice data of a customer during a call and estimates the emotional state of the customer from characteristics such as tone of voice, volume, and speaking speed.

[0442] A "means for issuing a security alert based on a recognized emotion" is a device or software for automatically issuing a security alert when a customer's emotional state meets a specified condition (e.g., anger or stress).

[0443] The following system configuration will be described as an embodiment of the present invention.

[0444] System Configuration

[0445] The system consists of the following main components:

[0446] 1. Call duration measurement module: Measures the call duration of customers' mobile phones in real time.

[0447] 2. Communication volume measurement module: Measures the communication volume of customers' mobile phones in real time.

[0448] 3. Plan offering module: Offers the optimal communication plan to the customer based on the measured call time and communication volume.

[0449] 4. Emotion Recognition Module: Recognizes emotions from the content of customer calls.

[0450] 5. Security Alert Module: Based on the recognized emotions, it issues security alerts as needed.

[0451] Program processing

[0452] The server performs processing by linking each module as follows.

[0453] 1. Call duration measurement module: The server acquires customer call duration data in real time through the carrier's network. This data is used to measure the duration from when the customer starts a call to when it ends.

[0454] 2. Traffic measurement module: The server also collects customer traffic data in real time through the carrier's network. This data is used to measure the amount of data used when the customer uses the Internet.

[0455] 3. Plan provision module: The server calculates the optimal communication plan for the customer based on the acquired call duration and communication volume data. This plan is optimized for the customer's usage pattern and aims to maximize cost performance.

[0456] 4. Emotion Recognition Module: The server analyzes the customer's call content in real time and estimates the customer's emotional state from characteristics such as tone of voice, volume, and speaking speed. This analysis uses an emotion recognition library.

[0457] 5. Security Alert Module: The server automatically issues a security alert when the emotion recognized by the emotion recognition module meets certain conditions (e.g., anger or stress). This alert is sent to emergency contacts via a communication service.

[0458] Specific examples

[0459] For example, if a customer becomes angry during a call, the emotion recognition module will detect that emotion in real time, and the security alert module will automatically send a notification to emergency contacts, including the customer's ID and emotional state, allowing for a prompt response.

[0460] Prompt Sentence Examples

[0461] Here are some examples of prompts to communicate specific requirements to a generative AI model:

[0462] Monitor user calls in real time and analyze their emotional state using an emotion engine. If the user is stressed or angry, trigger a security alert and notify emergency contacts.

[0463] In this way, a system can be realized that can provide optimal plans that take into account the emotional state of the customer and reduce security risks.

[0464] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0465] Step 1:

[0466] The server obtains customer call duration data in real time through the carrier's network.

[0467] Input: The call start and end times obtained from the carrier's API.

[0468] Data processing: Calculate the difference between the call start time and end time to calculate the call duration.

[0469] Output: Real-time call duration data.

[0470] Step 2:

[0471] The server obtains customer traffic data in real time through the carrier's network.

[0472] Input: Data usage obtained from the carrier's API.

[0473] Data processing: The acquired data usage is accumulated and real-time communication volume is calculated.

[0474] Output: Real-time traffic data.

[0475] Step 3:

[0476] The server calculates the optimal communication plan for the customer based on the acquired call time and communication volume data.

[0477] Input: Real-time call duration and traffic data.

[0478] Data calculation: Analyzes call duration and data usage patterns and applies algorithms to select the most suitable plan.

[0479] Output: The best communication plan for the customer.

[0480] Step 4:

[0481] The server analyzes the content of the customer's call in real time and estimates the customer's emotional state from characteristics such as tone of voice, volume, and speaking speed.

[0482] Input: Voice data during a call.

[0483] Data processing: Analyze the audio data and extract features. Estimate the emotional state using an emotion recognition library.

[0484] Output: Customer emotional state data.

[0485] Step 5:

[0486] The server automatically issues a security alert when the emotion recognized by the emotion recognition module meets certain conditions (e.g., anger or stress).

[0487] Input: Customer emotional state data.

[0488] Data calculation: Determine whether the emotional state meets certain conditions.

[0489] Output: Sending a security alert.

[0490] Step 6:

[0491] The server notifies emergency contacts of security alerts.

[0492] Enter: Security Alert.

[0493] Data processing: Converts alert content into a message format and sends notifications using a communication service.

[0494] Output: Notification message to emergency contacts.

[0495] Example 2

[0496] Next, a description will be given of Example 2 of Form 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."

[0497] Conventional communication plan provision systems can provide plans based on the customer's call time and data volume, but do not provide plans that take into account the customer's emotional state. This makes it difficult to maximize customer satisfaction. In addition, because data collection and analysis are not performed in real time, providing the optimal plan can be delayed.

[0498] 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.

[0499] In this invention, the server includes means for measuring customer mobile phone call time in real time, means for measuring customer mobile phone communication volume in real time, means for transmitting the measured call time and communication volume to the server, means for storing data received by the server in a database, means for preprocessing the stored data, means for inputting the preprocessed data into a machine learning algorithm to analyze the customer's call and communication patterns, means for inputting the contents of the customer's text messages and emails into an emotion recognition engine to estimate the customer's emotional state, means for generating an optimal plan based on the analysis results and the emotional state, and means for notifying the customer of the generated plan. This makes it possible to collect and analyze customer behavioral data and emotional data in real time and quickly provide a more personalized, optimal plan.

[0500] "Airtime" refers to the total time a customer makes calls using a mobile phone.

[0501] "Communication volume" refers to the total volume of data transmitted by the customer using their mobile phone.

[0502] "Server" refers to a central processing unit that collects, stores, pre-processes, analyzes, and generates plans from data.

[0503] "Database" refers to a data management system for efficiently storing and retrieving data received by a server.

[0504] "Preprocessing" refers to the preparation of data before data analysis, such as filling in missing values ​​and detecting outliers in collected data.

[0505] A "machine learning algorithm" is a mathematical model that learns patterns from data and makes predictions and classifications.

[0506] An "emotion recognition engine" refers to software that infers a customer's emotional state from the content of text messages and emails.

[0507] "Plan generation" refers to the process of creating the optimal communication plan for a customer based on the analysis results and emotional state.

[0508] "Notification" refers to the means of communication used to inform customers of the created plan.

[0509] This invention is a system that measures customer call time and communication volume in real time and provides optimal communication plans based on this data. It also includes a function to recognize emotions from the content of customers' text messages and emails and optimize plans based on their emotional state.

[0510] Hardware and software used

[0511] Hardware: Servers, devices (smartphones and PCs)

[0512] Software: Machine learning algorithms (e.g., TensorFlow, scikit-learn), emotion recognition engines (e.g., IBM Watson®, Microsoft® Azure® Text Analytics)

[0513] Data collection and transmission

[0514] The device monitors the user's call time and data usage in real time. For example, a smartphone app runs in the background and records call time and data usage.

[0515] The device encrypts the collected data and periodically sends it to the server. For example, it can be set to send all data at once every night.

[0516] Data storage and preprocessing

[0517] The server stores the received data in a database, which uses the user ID as a key to store the data and allows for efficient searches.

[0518] The server preprocesses the stored data, for example, by filling in missing values ​​with the average value and excluding abnormally high traffic volumes as outliers.

[0519] Pattern Analysis and Emotion Recognition

[0520] The server then inputs the preprocessed data into machine learning algorithms, such as K-means clustering, to cluster users' call and communication patterns and identify the best plan for each cluster.

[0521] The server inputs the content of the user's text message or email into an emotion recognition engine, such as IBM Watson, which analyzes the emotion of the text to determine whether the user is expressing emotions such as happiness, sadness, or anger.

[0522] Plan Generation and Notification

[0523] The server generates an optimal plan for the user based on the analysis results and the user's emotional state. For example, a user who has a high call duration and shows a happy emotion may be offered an unlimited call plan and special data bonuses.

[0524] The server notifies the user of the generated plan, for example by sending a push notification via a smartphone application to suggest a new plan to the user.

[0525] Specific examples

[0526] If a user uses 1,000 minutes of talk time and 10 GB of data communication in a month, the device will collect this data and send it to the server.

[0527] The server pre-processes the data and analyzes user patterns using K-means clustering.

[0528] The server recognizes from the text message sent by the user that the user is expressing an emotion of joy.

[0529] The server generates unlimited calling and 20GB data plans with extra data bonuses.

[0530] The server notifies the user of the generated plan and sends a push notification via the smartphone application.

[0531] Prompt Sentence Examples

[0532] "Design a system that will recommend the best plan for a user based on their call duration and data usage. Also, add a feature that recognizes emotions in the content of a user's text messages and emails and offers special plans based on their emotional state."

[0533] In this way, we can utilize user behavioral and emotional data to provide more personalized services.

[0534] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0535] Step 1:

[0536] The device monitors the user's call time and data usage in real time. Specifically, a smartphone app runs in the background and records call time and data usage.

[0537] Input: User's call time and data usage

[0538] Output: Recorded call duration and traffic data

[0539] Step 2:

[0540] The device encrypts the collected data and periodically sends it to the server. For example, it can be set to send all data at once every night.

[0541] Input: Recorded call duration and traffic data

[0542] Output: Encrypted call duration and traffic data

[0543] Step 3:

[0544] The server stores the received data in a database, which uses the user ID as a key to store the data and allows for efficient searches.

[0545] Input: Encrypted call time and traffic data

[0546] Output: Data stored in the database

[0547] Step 4:

[0548] The server preprocesses the stored data, specifically filling in missing values ​​with the average value and excluding abnormally high traffic volumes as outliers.

[0549] Input: Data stored in the database

[0550] Output: Preprocessed data

[0551] Step 5:

[0552] The server then inputs the preprocessed data into machine learning algorithms, such as K-means clustering, to cluster users' call and communication patterns and identify the best plan for each cluster.

[0553] Input: Preprocessed data

[0554] Output: Call and communication patterns of clustered users

[0555] Step 6:

[0556] The server inputs the content of the user's text message or email into an emotion recognition engine, which, for example, analyzes the emotion of the text to determine whether the user is expressing an emotion such as happiness, sadness, or anger.

[0557] Input: The contents of a user's text message or email

[0558] Output: Estimated user emotional state

[0559] Step 7:

[0560] The server generates an optimal plan for the user based on the analysis results and the user's emotional state. For example, a user who has a high call duration and shows a happy emotion may be offered an unlimited call plan and special data bonuses.

[0561] Input: Clustered users' call and communication patterns, estimated users' emotional states

[0562] Output: The optimal plan generated

[0563] Step 8:

[0564] The server notifies the user of the generated plan, for example by sending a push notification via a smartphone application to suggest a new plan to the user.

[0565] Input: Generated optimal plan

[0566] Output: Plan notified to user

[0567] (Application example 2)

[0568] Next, a description will be given of Application Example 2 of Form 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."

[0569] Conventional systems can provide optimal plans based on the customer's call time and data volume, but they cannot provide plans that take into account the customer's emotional state, which means they cannot fully improve customer satisfaction. Furthermore, there is a need to grasp the customer's emotional state in real time and provide flexible plans based on that, but there is also the problem of a lack of technology to achieve this.

[0570] 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.

[0571] In this invention, the server includes means for measuring the call time of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for providing an optimal plan based on the measured call time and communication volume, means for estimating the emotional state of the customer by analyzing the content of the customer's text messages and emails, and means for providing an optimal plan based on the estimated emotional state. This makes it possible to provide an optimal plan that takes into account not only the customer's call time and communication volume but also their emotional state.

[0572] "Customer" means an individual or legal entity using the Service.

[0573] "Mobile" refers to mobile communication devices such as mobile phones and smartphones.

[0574] "Talk time" is the total amount of time a customer makes calls using their mobile phone.

[0575] "Communication volume" refers to the total amount of data communication carried out by a customer using their mobile phone.

[0576] "Real-time" refers to data being processed as it is generated.

[0577] "Means for measuring" refers to a combination of hardware and software for measuring call duration and traffic volume.

[0578] The "optimal plan" is the most suitable service plan offered based on the customer's usage patterns and emotional state.

[0579] The "means of delivery" is a combination of hardware and software for presenting and applying the optimal plan to the customer.

[0580] A "text message" is text information sent and received via SMS or instant messaging apps.

[0581] "Email" is an electronic letter sent and received over the Internet.

[0582] "Analyzing" means processing data and extracting meaning and patterns.

[0583] "Emotional state" refers to the type and intensity of emotion a customer is feeling at a particular point in time.

[0584] To "estimate" means to predict unknown information based on data.

[0585] A system for implementing the present invention includes means for measuring a customer's mobile phone call duration in real time, means for measuring a customer's mobile phone communication volume in real time, means for providing an optimal plan based on the measured call duration and communication volume, means for analyzing the content of a customer's text messages and emails to estimate an emotional state, and means for providing an optimal plan based on the estimated emotional state.

[0586] The server obtains real-time call duration and traffic data from the customer's mobile phone. This is done using APIs and databases that collect data through the mobile carrier's network. For example, call duration is obtained from call logs, and traffic is obtained from data usage logs.

[0587] The server then uses the acquired data to apply machine learning algorithms to analyze customer call duration and traffic patterns, using clustering algorithms (e.g., KMeans) with Python's scikit-learn library, allowing it to offer optimal plans based on customer usage patterns.

[0588] Additionally, the server analyzes the content of customers' text messages and emails to estimate their emotional state using TextBlob, a natural language processing library. It extracts emotions from the content of text messages and emails and provides the optimal plan based on that emotional state.

[0589] For example, if a customer shows emotions of joy, a special cashback plan can be offered, which can improve customer satisfaction.

[0590] As a concrete example, consider a case where user A has recently had a long call time and a large amount of data traffic. Furthermore, if the contents of text messages and emails indicate that user A is expressing joy, user A will be offered a special cashback plan.

[0591] An example of a prompt might be:

[0592] Develop an application that analyzes the user's call time, data usage, text message and email content, and offers optimal electronic payment plans based on the user's emotional state. For example, consider a scenario where a user expresses happiness and is offered a special cashback plan.

[0593] In this way, it becomes possible to provide optimal plans that take into account not only the customer's call time and data volume, but also their emotional state.

[0594] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0595] Step 1:

[0596] The server obtains call duration and communication volume data from the customer's mobile phone in real time. Specifically, it uses APIs through the mobile carrier's network to collect call logs and data usage logs. The input is call duration and communication volume data from the customer's mobile phone, and the output is that this data is stored on the server.

[0597] Step 2:

[0598] The server uses the acquired call duration and communication volume data to apply a machine learning algorithm to analyze customer call duration and communication volume patterns. Specifically, it uses the KMeans clustering algorithm, which uses the Python scikit-learn library. The input is call duration and communication volume data, and the output is the clustering results based on customer usage patterns.

[0599] Step 3:

[0600] The server analyzes the content of the customer's text messages and emails to estimate their emotional state. Specifically, it uses TextBlob, a natural language processing library, to analyze the text data. The input is the content of the text messages and emails, and the output is the estimated emotional state.

[0601] Step 4:

[0602] The server provides the optimal plan based on the estimated emotional state. Specifically, it selects a plan according to the emotional state, such as offering a special cashback plan if the emotional state is joy. The input is the estimated emotional state and the clustering result, and the output is the optimal plan.

[0603] Step 5:

[0604] The server notifies the customer of the optimal plan. Specifically, it sends a push notification or email to the customer's mobile phone. The input is the information about the optimal plan, and the output is a notification to the customer.

[0605] In this way, it becomes possible to provide optimal plans that take into account not only the customer's call time and data volume, but also their emotional state.

[0606] Example 3

[0607] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0608] Conventional systems can provide optimal plans based on the customer's call time and data volume, but do not provide plans that take into account the customer's emotional state. Therefore, in order to further improve customer satisfaction, a system is needed that analyzes the customer's emotional state and provides optimal plans based on that.

[0609] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0610] In this invention, the server includes means for measuring the call time of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for providing an optimal plan based on the measured call time and communication volume, means for collecting the content of the customer's calls and communication, means for analyzing the collected data to estimate the emotional state of the customer, means for calculating an optimal plan based on the estimated emotional state, means for notifying the customer of the calculated optimal plan, and means for confirming whether the customer wishes to change the plan and applying the change. This makes it possible to provide an optimal plan based on the emotional state of the customer, thereby improving customer satisfaction.

[0611] "Means for measuring customer mobile phone call duration in real time" refers to a device or software for measuring the time a customer is making a call on a mobile phone in real time.

[0612] "Means for measuring customer mobile phone traffic in real time" refers to a device or software for measuring the amount of data traffic used by a customer on a mobile phone in real time.

[0613] The "means for providing the optimal plan" refers to a device or software that selects and provides the most suitable communication plan to a customer based on data such as the customer's call time, communication volume, and emotional state.

[0614] "Means for collecting customer calls and communications" refers to devices or software used to collect communications such as calls, text messages, and emails made by customers on their mobile phones.

[0615] The "means for analyzing collected data to estimate the emotional state of a customer" refers to a device or software for analyzing collected call content or communication content to estimate the emotional state of a customer.

[0616] The "means for calculating an optimal plan based on an estimated emotional state" is a device or software for calculating a communication plan that is most suitable for a customer based on the estimated emotional state of the customer.

[0617] The "means for notifying the customer of the calculated optimum plan" is a device or software for notifying the customer of the calculated optimum communication plan.

[0618] "Means for checking whether the customer wishes to change plans and applying the changes" means a device or software that checks whether the customer wishes to change to a proposed communications plan and applies the plan if the customer wishes to change.

[0619] MODE FOR CARRYING OUT THE INVENTION

[0620] This invention provides a system for providing optimal communication plans based on a customer's call duration, communication volume, and emotional state in order to improve customer satisfaction. This system is implemented using the following hardware and software.

[0621] Hardware and software used

[0622] Hardware: High performance servers, voice recognition devices, database servers

[0623] Software: Natural Language Processing (NLP) libraries (e.g., SpaCy, NLTK), speech analysis software, machine learning models (e.g., TensorFlow, PyTorch)

[0624] Program processing

[0625] The server first measures the customer's call duration and communication volume in real time using a voice recognition device and a database server. The server then collects the content of the customer's calls and communications and analyzes this data to estimate the customer's emotional state. It uses natural language processing (NLP) libraries and speech analysis software to analyze the content of text messages and emails, as well as the tone of voice, volume, and speaking rate.

[0626] Based on the analyzed emotional state, the server uses a machine learning model to calculate the optimal communication plan. For example, if a customer sends a text message saying, "I've been having trouble with high call charges lately," the server can recognize the customer's feelings of confusion or sadness and calculate a plan that offers discounts on call charges.

[0627] The server notifies the customer of the calculated optimal plan via SMS, email, in-app notification, etc. The customer receives the notification and confirms whether they want to change to the proposed plan. If they do, the server receives the request, updates the database, and applies the new plan.

[0628] Specific examples

[0629] As a concrete example, consider a case where a user sends a text message saying, "I'm having trouble with high phone charges these days." In this case, the emotion engine recognizes the user's feelings of confusion or sadness, and the server proposes a special plan that offers discounts on phone charges to the user.

[0630] Example prompt sentence:

[0631] Analyze the content of text messages and emails sent by the user, as well as the tone, volume, and speaking speed of the user's voice, and infer the user's emotional state from the content. For example, if a user sends a message saying, "I've been having trouble with high phone charges lately," suggest a plan that offers discounts on phone charges to that user.

[0632] In this way, the server can provide an optimal plan based on the emotional state of the user, thereby improving customer satisfaction. The flow of the specification process in the third embodiment will be described with reference to FIG.

[0633] Step 1:

[0634] User data collection

[0635] The server collects data such as the contents of user calls, text messages, emails, etc. Specifically, using a voice recognition device and a database server, it automatically collects voice data when a user initiates a call, and stores the contents of each text message and email sent in a database.

[0636] Input: User calls, text messages, emails

[0637] Output: Calls, text messages, emails stored in a database

[0638] Step 2:

[0639] Emotion analysis

[0640] The server inputs the collected data into an emotion engine to analyze the user's emotional state. It uses natural language processing (NLP) libraries and speech analysis software. Specifically, it converts the voice data into text and analyzes the emotion of the text using an NLP library. It also uses speech analysis software to analyze the tone, volume, and speaking rate of the voice to estimate the user's overall emotional state.

[0641] Input: Calls, text messages, emails stored in the database

[0642] Output: Estimated emotional state

[0643] Step 3:

[0644] Calculating the optimal plan

[0645] The server calculates the optimal plan for the user based on the results of the emotion analysis. It uses a machine learning model to select a plan that corresponds to the user's emotional state. Specifically, the results of the emotion analysis are input into the machine learning model, and if the emotion of "sadness" is detected, for example, a plan that offers a discount on call charges is calculated.

[0646] Input: Estimated emotional state

[0647] Output: Optimal plan

[0648] Step 4:

[0649] Plan Notification

[0650] The server notifies the user of the optimal plan it has calculated. Notification methods include SMS, email, and in-app notifications. Specifically, it references the user's contact information and sends a message containing details of the optimal plan. For example, it may notify the user by SMS that "A new plan with discounts on calling charges is available."

[0651] Input: Best Plan

[0652] Output: Notification sent to the user

[0653] Step 5:

[0654] Check and apply plan changes

[0655] The user receives the notification and confirms whether they want to change to the proposed plan. If they do, they reply to the server. Specifically, when the user replies "I want to change the plan," the server receives the request, updates the database, and applies the new plan.

[0656] Input: User reply

[0657] Output: Updated database with new plan applied

[0658] (Application example 3)

[0659] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0660] While conventional systems can provide optimal plans based on the customer's call time and data volume, they do not provide plans that take into account the customer's emotional state. Therefore, in order to further improve customer satisfaction, it is necessary to recognize the customer's emotional state and provide the optimal plan accordingly.

[0661] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0662] In this invention, the server includes means for measuring the call time of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for providing an optimal plan based on the measured call time and communication volume, means for recognizing the customer's emotion from the content of the call or communication, and means for providing an optimal plan based on the recognized emotion. This makes it possible to provide an optimal plan that takes into account the emotional state of the customer.

[0663] "Customer" means any person or entity using the Services.

[0664] "Mobile" refers to mobile communication devices such as mobile phones and smartphones.

[0665] "Airtime" refers to the total amount of time a customer makes calls using their mobile phone.

[0666] "Data volume" refers to the total amount of data sent and received by a customer using their mobile phone.

[0667] "Real-time" refers to processing and measurement occurring immediately, without delay.

[0668] The "optimal plan" refers to the most appropriate pricing plan and service content based on the customer's usage and emotional state.

[0669] "Call content" refers to what the customer said during the call.

[0670] "Communication Content" refers to the content of messages and data sent and received by Customer.

[0671] "Means of emotion recognition" refers to technologies and algorithms for inferring a customer's emotional state from the content of their calls or communications.

[0672] "Emotional state" refers to the type and intensity of emotions a customer is experiencing.

[0673] "Server" refers to a computer system that processes and stores data.

[0674] The system for implementing this invention measures the call time and communication volume of a customer's mobile phone in real time, and also has the function of recognizing the customer's emotions from the content of their calls and communications, making it possible to provide the optimal plan based on the customer's emotional state.

[0675] System Configuration

[0676] 1. Hardware Configuration

[0677] Mobile devices: Mobile phones and smartphones used by customers.

[0678] Server: A computer system that processes and stores data.

[0679] Microphone: A device for capturing audio input.

[0680] 2. Software Configuration

[0681] Speech recognition software: Uses speech recognition libraries to convert customer speech into text.

[0682] Sentiment analysis software: Uses the TextBlob library to analyze the sentiment of text.

[0683] Email sending software: Uses smtplib and email.mime.text to send emails with special cashback or discount offers.

[0684] Processing flow

[0685] 1. Acquiring voice input

[0686] The microphone of the mobile device is used to capture the customer's voice.

[0687] Speech recognition software is used to convert the captured speech into text.

[0688] 2. Sentiment analysis

[0689] The converted text is fed into sentiment analysis software to determine the customer's emotional state.

[0690] Emotional states are divided into three categories: positive, neutral, and negative.

[0691] 3. Providing the best plan

[0692] Based on the emotional state, the server chooses the optimal plan.

[0693] For example, offer special cashback or discounts if a customer is in a negative emotional state.

[0694] 4. Notification

[0695] Use email sending software to let your customers know which plan is best for them.

[0696] Specific examples

[0697] If a user says, "I'm stressed because I've had so many payments lately," the system will interpret that statement as negative and send them an email with a special cashback offer.

[0698] Prompt Sentence Examples

[0699] If a user says, "I'm stressed because I've had so many payments lately," create a program that will email them a special cashback offer.

[0700] In this way, it becomes possible to provide an optimal plan that takes into account the emotional state of the customer, thereby improving customer satisfaction.

[0701] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0702] Step 1:

[0703] The user uses the microphone of the mobile terminal to input voice.

[0704] Input: User's voice

[0705] Output: Audio data

[0706] Specific operation: When a user speaks into a mobile terminal, voice data is acquired by a microphone.

[0707] Step 2:

[0708] The device uses voice recognition software to convert the captured voice data into text.

[0709] Input: Audio data

[0710] Output: Text data

[0711] What it does: Speech recognition software analyzes the audio data and generates corresponding text data.

[0712] Step 3:

[0713] The server feeds the text data into sentiment analysis software to determine the customer's emotional state.

[0714] Input: Text data

[0715] Output: Emotional state (positive, neutral, negative)

[0716] What it does: Sentiment analysis software (e.g., the TextBlob library) analyzes text data and calculates positive, neutral, or negative sentiment.

[0717] Step 4:

[0718] The server selects the optimal plan based on the emotional state.

[0719] Input: Emotional state

[0720] Output: Best deal (e.g. special cashback or discount)

[0721] Specific operation: The server evaluates the emotional state and selects a plan that offers special cashback or discounts if the emotional state is negative.

[0722] Step 5:

[0723] The server uses email sending software to notify the customer of the best plan.

[0724] Input: Optimal plan

[0725] Output: Notification email

[0726] What happens: The email sending software (e.g. smtplib and email.mime.text) generates an email containing the best offer and sends it to the customer's email address.

[0727] In this way, it becomes possible to provide an optimal plan that takes into account the emotional state of the user, thereby improving customer satisfaction.

[0728] 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.

[0729] 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> ) 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.

[0730] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0731] 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.

[0732] [Second embodiment]

[0733] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0734] 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.

[0735] 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).

[0736] 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.

[0737] 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.

[0738] 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).

[0739] 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.

[0740] 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.

[0741] 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.

[0742] 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.

[0743] 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.

[0744] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0745] "Example 1"

[0746] As a first embodiment of the present invention, a system for acquiring data through a telecommunications carrier's network can be considered as a means for measuring customer's mobile phone call duration and communication volume in real time. This system acquires data on call duration and communication volume in real time from the telecommunications carrier's network and calculates the optimal plan based on that data.

[0747] "Example 2"

[0748] In Example 2, a system that uses an algorithm to analyze call duration and communication volume patterns can be considered as a means of providing the optimal plan. This system uses a machine learning algorithm to analyze the customer's call and communication patterns based on the acquired call duration and communication volume data, and provides a plan optimized for those patterns.

[0749] "Example 3"

[0750] As a third example, a system that notifies customers of the optimal plan proposal can be considered as a means of providing a service to increase customer satisfaction. This system notifies the customer of the calculated optimal plan and clearly indicates that the customer can save on communication costs by switching to that plan. This can increase customer satisfaction.

[0751] The processing flow of each embodiment will be described below.

[0752] "Example 1"

[0753] Step 1: Obtain real-time customer mobile call duration and traffic data from the carrier's network.

[0754] Step 2: Based on the data obtained, calculate the optimal plan based on the customer's call time and data volume.

[0755] Step 3: Offer the calculated optimal plan to the customer.

[0756] "Example 2"

[0757] Step 1: Obtain real-time customer mobile call duration and traffic data from the carrier's network.

[0758] Step 2: Based on the acquired data, machine learning algorithms are used to analyze customer call and communication patterns.

[0759] Step 3: Based on the analysis results, provide the customer with a plan optimized for that pattern. "Example 3"

[0760] Step 1: Obtain real-time customer mobile call duration and traffic data from the carrier's network.

[0761] Step 2: Based on the data obtained, calculate the optimal plan based on the customer's call time and data volume.

[0762] Step 3: Notify the customer of the optimal plan and clearly indicate that they can save on communication costs by switching to that plan.

[0763] Example 1

[0764] Next, a description will be given of Example 1 of Form 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."

[0765] With traditional communication plans, it was difficult to provide optimal plans based on the customer's call time and data volume. In particular, because real-time data acquisition and analysis were not performed, it was not possible to provide plans optimized for the customer's usage patterns. In addition, the provision of services to improve customer satisfaction was insufficient.

[0766] 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.

[0767] In this invention, the server includes means for connecting to a communication network and measuring customer call time in real time, means for connecting to the communication network and measuring customer communication volume in real time, means for storing measured call time and communication volume data in a database, means for performing data calculations based on the stored data, means for calculating an optimal plan based on the results of the data calculations, and means for notifying the customer's terminal of the calculated optimal plan, thereby making it possible to provide an optimal plan in real time based on the customer's usage pattern.

[0768] A "communications network" is an infrastructure for data communication, including the Internet and mobile phone networks.

[0769] "Airtime" refers to the total amount of time a customer spends making or receiving phone calls.

[0770] "Communication volume" refers to the total amount of data used by the customer when conducting data communication.

[0771] "Real-time" means that data is processed immediately at the moment it is generated.

[0772] A "database" refers to a system for efficiently storing, managing, and retrieving data.

[0773] "Data calculation" refers to the process of performing calculations and analysis based on acquired data.

[0774] "Optimal plan" refers to the most suitable telecommunications service plan based on the customer's call time and data volume.

[0775] A "machine learning model" refers to an algorithm or system that learns from data and makes predictions and classifications.

[0776] "Terminal" means a device used by a customer, including a smartphone, tablet, etc.

[0777] "Notification" refers to the act of sending information from a server to a customer's terminal.

[0778] MODE FOR CARRYING OUT THE INVENTION

[0779] This invention is a system that measures the call duration and traffic volume of customers in real time through a communication network and calculates the optimal plan based on that data. A specific embodiment of this system will be described below.

[0780] Hardware and software used

[0781] The server uses the following hardware and software to connect to a communication network, acquire data, store it in a database, and perform data calculations. Specifically, the server uses the following hardware and software:

[0782] Hardware: High-performance servers

[0783] software:

[0784] Database management systems (e.g., MySQL, PostgreSQL)

[0785] Programming language (e.g. Python, R)

[0786] Machine learning libraries (e.g., scikit-learn, TensorFlow)

[0787] Telecommunications carrier API (e.g., general telecommunications carrier API)

[0788] Data Acquisition and Storage

[0789] The server uses the carrier's API to obtain customer call duration and communication volume data in real time. The obtained data is stored in a database. For example, an INSERT query is executed on a MySQL database to store customer call duration and communication volume data.

[0790] Data calculation and analysis

[0791] The server performs data calculations based on the stored data. Specifically, it uses the Python pandas library to calculate the average call duration and data usage for each customer. It also uses machine learning models to predict the optimal plan for each customer. For example, it uses the scikit-learn library to calculate the optimal plan based on the customer's usage patterns.

[0792] Notification of the best plan

[0793] The server notifies the customer's device of the calculated optimal plan, for example by sending a push notification using Firebase Cloud Messaging (FCM) to propose the optimal plan to the customer.

[0794] Specific examples

[0795] User A uses 1,000 minutes of talk time and 5 GB of data communication per month. The server obtains User A's talk time and data volume data in real time through the telecommunications carrier's API. Based on the obtained data, the server calculates the optimal plan for User A. For example, the server proposes to User A a plan that includes 1,000 minutes of talk time and 5 GB of data communication per month.

[0796] Prompt Sentence Examples

[0797] "Please obtain real-time data on user A's call duration and data volume and calculate the optimal plan."

[0798] In this way, the server acquires data through the communication network, stores it in a database, performs data calculations, calculates the optimal plan, and finally notifies the user's terminal of the results.

[0799] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0800] Step 1:

[0801] The server connects to the carrier's API.

[0802] Input: Your carrier's API endpoint URL and authentication information.

[0803] Specific operation: The server sends an HTTP GET request to the carrier's API endpoint to obtain an authentication token. For example, send a request to https: / / api.carrier.com / v1 / auth.

[0804] Output: An authentication token.

[0805] Step 2:

[0806] The server collects customer call duration and traffic data.

[0807] Input: Authentication token and customer identification information.

[0808] Specific operation: The server uses the obtained authentication token to request the customer's call time and traffic data from the carrier's API, for example, by sending a GET request to https: / / api.carrier.com / v1 / user / data.

[0809] Output: Customer call duration and traffic data.

[0810] Step 3:

[0811] The server saves the retrieved data in the database.

[0812] Input: Customer call duration and volume data.

[0813] What happens: The server stores the retrieved data in a MySQL database, for example by executing the following SQL query:

[0814] sql

[0815] INSERT INTO user_data (user_id, call_time, data_usage) VALUES ('userA', 1000, 5);

[0816] Output: Data stored in a database.

[0817] Step 4:

[0818] The server performs data calculations based on the stored data.

[0819] Input: Customer call duration and volume data stored in a database.

[0820] What happens: The server uses the Python pandas library to calculate the average call duration and traffic volume for each customer. For example, it runs the following code:

[0821] python

[0822] import pandas as pd

[0823] data = pd.read_sql('SELECT FROM user_data WHERE user_id="userA"', connection)

[0824] average_call_time = data['call_time'].mean()

[0825] average_data_usage = data['data_usage'].mean()

[0826] Output: Average customer call duration and volume.

[0827] Step 5:

[0828] The server calculates the optimal plan based on the results of the data calculation.

[0829] Input: Average customer call duration and volume.

[0830] What it does: The server uses the scikit-learn library to predict the best plan for the customer using a machine learning model. For example, it runs the following code:

[0831] python

[0832] from sklearn.linear_model import LinearRegression

[0833] model = LinearRegression()

[0834] model.fit(X_train, y_train)

[0835] optimal_plan = model.predict([[average_call_time, average_data_usage]])

[0836] Output: The optimal plan.

[0837] Step 6:

[0838] The server notifies the customer's device of the optimal plan.

[0839] Input: Best plan and customer device information.

[0840] What happens: The server uses Firebase Cloud Messaging (FCM) to send a push notification to recommend the best plan for the customer. For example, it executes the following code:

[0841] python

[0842] import firebase_admin

[0843] from firebase_admin import messaging

[0844] message = messaging.Message(

[0845] notification=messaging.Notification(

[0846] title='Optimal plan proposal',

[0847] body=f'The best plan for you is {optimal_plan}.'

[0848] ),

[0849] token=userA_device_token,

[0850] )

[0851] response = messaging.send(message)

[0852] Output: Push notification sent to customer's device.

[0853] (Application example 1)

[0854] Next, a description will be given of Application Example 1 of Form 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."

[0855] With modern telecommunications services, it is difficult for customers to select the optimal plan based on their call time and data volume. Furthermore, the procedures for changing plans and purchasing additional data are complicated, which is a factor in reducing customer satisfaction. Furthermore, the lack of real-time data collection and analysis makes it difficult to offer the optimal plan to customers. To solve these issues, a system is needed that measures customers' call time and data volume in real time, provides the optimal plan, and allows them to easily change plans and purchase additional data in conjunction with electronic payment services.

[0856] 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.

[0857] In this invention, the server includes means for measuring the call time of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for providing an optimal plan based on the measured call time and communication volume, and means for the means for providing the optimal plan to change plans or purchase additional data in cooperation with an electronic payment service. This allows the customer to be offered an optimal plan in real time based on their call time and communication volume, and to easily change plans or purchase additional data.

[0858] "Customer" means any person or entity that uses the telecommunications services.

[0859] "Mobile" refers to mobile communication devices such as mobile phones and smartphones.

[0860] "Talk Time" refers to the cumulative time during which a Customer makes voice calls using a mobile phone.

[0861] "Data volume" refers to the total amount of data sent and received by a customer using their mobile phone.

[0862] "Real-time" means that data is processed and analyzed immediately at the moment it is generated.

[0863] "Means for measuring" refers to a combination of hardware and software for measuring call duration and traffic.

[0864] The "optimal plan" refers to the communications service plan that offers the best cost performance and convenience based on the customer's call time and data volume.

[0865] "Means of provision" refers to the systems and methods for presenting the optimal plan to customers.

[0866] "Electronic payment services" refers to financial transaction services conducted via the Internet.

[0867] "Plan change" refers to switching from your current communications service plan to another plan.

[0868] "Additional data purchase" refers to purchasing additional data capacity in addition to an existing communication plan.

[0869] "Collaboration" refers to different systems and services working together.

[0870] The following system configuration will be described as an embodiment of the present invention.

[0871] System Configuration

[0872] 1. Hardware Configuration

[0873] Server: A server is used that connects to the carrier's network to obtain customer call time and data volume in real time. This server collects and analyzes data, calculates optimal plans, and connects with electronic payment services.

[0874] Terminal: Refers to a mobile communication terminal such as a mobile phone or smartphone used by a customer. These terminals communicate with the server and send and receive data in real time.

[0875] 2. Software Configuration

[0876] Data acquisition module: This module uses the carrier's API to acquire customer call duration and data volume in real time. It uses the Python requests library to acquire data from the API.

[0877] Data analysis module: This module analyzes customer call duration and data usage patterns based on the acquired data and calculates the optimal plan. Data analysis uses Python's pandas and numpy libraries.

[0878] Plan offering module: This module presents the most suitable plan to the customer. It displays the plan details to the customer through the user interface.

[0879] Electronic payment module: This module uses the API of the electronic payment service to change plans and purchase additional data. It calls the payment API using the Python requests library.

[0880] Processing flow

[0881] 1. Data Acquisition

[0882] The server retrieves customer call duration and traffic data in real time through the carrier's API, which is securely retrieved using the customer's authentication information.

[0883] 2. Data analysis

[0884] The server analyzes the acquired data to understand the customer's call duration and data volume patterns, and then calculates the optimal communication plan for the customer.

[0885] 3. Plan Offering

[0886] The server then notifies the customer of the optimal plan it has calculated, and the customer can check the plan details through a smartphone application.

[0887] 4. Electronic Payments

[0888] When a customer wishes to change their plan or purchase additional data, the server calls the API of the electronic payment service to execute the payment, allowing customers to easily change their plan or purchase additional data.

[0889] Specific examples

[0890] For example, if a customer uses more than 1,000 minutes of calls and 10GB of data per month, the server will suggest the "Premium Plan." This suggestion will be sent to the customer's smartphone, and the customer can check the plan details through the application. Furthermore, if the customer wants to change to the "Premium Plan," the server will execute the plan change through an electronic payment service.

[0891] Prompt Sentence Examples

[0892] "You will develop an application that monitors the user's call time and data usage in real time and proposes the optimal data plan. The application will obtain user data from the carrier's API and calculate the optimal plan. It will also use the API of an electronic payment service to change plans and purchase additional data."

[0893] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0894] Step 1:

[0895] The server obtains customer call duration and traffic data in real time through the carrier's API. The input is customer authentication information, and the output is call duration and traffic data. Specifically, it uses the Python requests library to send requests to the API endpoint and receives data in JSON format.

[0896] Step 2:

[0897] The server analyzes the acquired call duration and communication volume data. The input is the data acquired in step 1, and the output is the customer's call duration and communication volume patterns. Specifically, it processes the data using Python's pandas and numpy libraries to extract customer usage patterns.

[0898] Step 3:

[0899] The server calculates the optimal communication plan based on the analysis results. The input is the usage pattern obtained in step 2, and the output is a proposal for the optimal plan. Specifically, it compares the customer's usage pattern with the pre-set plan conditions and selects the most suitable plan.

[0900] Step 4:

[0901] The server notifies the customer's device of the calculated optimal plan. The input is the optimal plan calculated in step 3, and the output is the plan information displayed on the customer's device. Specifically, push notifications or in-app notifications are used to inform the customer of the plan details.

[0902] Step 5:

[0903] When a user wishes to change their plan or purchase additional data, they send a request from their device to the server. The input is the user's request to change their plan or purchase additional data, and the output is the request data sent to the server. Specifically, the user makes a selection through the application interface, and that information is sent to the server.

[0904] Step 6:

[0905] The server calls the API of the electronic payment service to change the plan or purchase additional data. The input is the request data received in step 5, and the output is confirmation data that the payment has been completed. Specifically, the server uses the Python requests library to send a request to the payment API and receive the payment result.

[0906] Step 7:

[0907] The server notifies the customer's device of the payment completion confirmation data. The input is the payment completion confirmation data obtained in step 6, and the output is a payment completion notification that is displayed on the customer's device. Specifically, the server notifies the customer of the payment completion information using a push notification or in-app notification.

[0908] Example 2

[0909] Next, a description will be given of Example 2 of Form 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."

[0910] With conventional communication plans, it was difficult to provide the optimal plan based on the customer's call time and data volume, making it difficult to find a plan that suited the customer's usage pattern. In addition, the provision of services to improve customer satisfaction was insufficient.

[0911] 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.

[0912] In this invention, the server includes means for measuring the call duration of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for storing the measured call duration and communication volume in a database, means for preprocessing the stored data, means for analyzing call and communication patterns using a machine learning algorithm based on the preprocessed data, and means for providing an optimal plan based on the analysis results, thereby making it possible to provide a communication plan optimized for the customer's usage pattern and improving customer satisfaction.

[0913] "Means for measuring customer mobile phone call duration in real time" refers to a device or software for instantly measuring the duration of calls made by customers on their mobile phones and obtaining that data.

[0914] "Means for measuring customer mobile phone traffic in real time" refers to a device or software that instantly measures the amount of data traffic used by a customer on their mobile phone and obtains that data.

[0915] The "means for storing the measured call duration and communication volume in a database" refers to a device or software for storing the acquired call duration and communication volume data in a database so that it can be used later.

[0916] "Means for preprocessing stored data" refers to devices or software that perform processes such as filling in missing values ​​and removing outliers in order to prepare data stored in a database in a form that is easier to analyze.

[0917] "Means for analyzing call and communication patterns using machine learning algorithms based on preprocessed data" means devices or software that use preprocessed data as input and machine learning algorithms to analyze customers' call and communication usage patterns.

[0918] The "means for providing the optimal plan based on the analysis results" refers to a device or software that proposes the optimal communication plan to a customer based on the analysis results of a machine learning algorithm.

[0919] The present invention is a system that collects data on customer call duration and communication volume, and uses a machine learning algorithm to provide optimal communication plans. Specific embodiments of this system will be described below.

[0920] First, the server collects data by measuring the customer's mobile phone call duration and the customer's mobile phone data usage in real time. These methods are realized using the telecommunications carrier's API. For example, a request is sent to the telecommunications carrier's API endpoint and JSON format data is received as a response.

[0921] The server then stores the collected data in a database, typically a relational database such as MySQL or PostgreSQL. The stored data includes user IDs, call duration, communication volume, and collection date and time.

[0922] The server then preprocesses the stored data. Specifically, it imputes missing values ​​and removes outliers. It uses the Python Pandas library to clean the data. For example, it executes the following code to impute missing values:

[0923] The server then uses machine learning algorithms to analyze users' call and communication patterns based on the preprocessed data. Specifically, it uses a clustering algorithm (e.g., K-means clustering) to classify users into several groups. The clustering is performed using the Scikit-learn library.

[0924] Finally, the server proposes the optimal communication plan for the user based on the analysis results. The proposed plan is notified to the user's device. For example, if the user has a long call duration and a low data volume, an unlimited call plan is proposed.

[0925] As a concrete example, consider the call time and data volume data of User A. User A makes a total of 300 minutes of calls per month and uses 5GB of data. Based on this data, the server analyzes User A's call and communication patterns. As a result of the analysis, it is determined that an unlimited call plan and 5GB data plan is optimal for User A.

[0926] Examples of prompts to be input to a generative AI model include:

[0927] "User A has 300 minutes of talk time and 5GB of data usage per month. Please suggest the best data plan for this user."

[0928] By inputting this prompt into the generative AI model, the AI ​​will suggest the optimal communication plan for User A.

[0929] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0930] Step 1:

[0931] The server collects data by measuring the customer's mobile phone call duration in real time and the customer's mobile phone data traffic in real time. Specifically, it calls the telecommunications carrier's API to obtain data on the user's call duration and data traffic. The input is the response data from the telecommunications carrier's API endpoint, and the output is data on the call duration and data traffic.

[0932] Step 2:

[0933] The server stores the collected data in a database. Specifically, it uses a relational database such as MySQL or PostgreSQL to store the acquired call duration and communication volume data. The input is the call duration and communication volume data acquired in step 1, and the output is the data stored in the database.

[0934] Step 3:

[0935] The server preprocesses the stored data. Specifically, it imputes missing values ​​and removes outliers. It uses the Python Pandas library to clean the data. The input is the raw data stored in the database, and the output is the preprocessed, clean data.

[0936] Step 4:

[0937] The server uses a machine learning algorithm to analyze users' call and communication patterns based on the preprocessed data. Specifically, it uses the Scikit-learn library to perform K-means clustering and classify users into several groups. The input is the preprocessed data, and the output is the clustering results.

[0938] Step 5:

[0939] The server proposes the optimal communication plan to the user based on the analysis results. Specifically, it analyzes the clustering results and determines the optimal plan for each cluster. The proposed plan is notified to the user's device. The input is the clustering results, and the output is the optimal communication plan proposed to the user.

[0940] Step 6:

[0941] The user receives the proposed communication plan from the server and changes the plan as needed. Specifically, the user checks the plan notified on the user's device and changes the plan through the carrier's website or app. The input is the proposed plan from the server, and the output is the new communication plan selected by the user.

[0942] (Application example 2)

[0943] Next, a description will be given of Application Example 2 of Form 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."

[0944] While the conventional system can provide optimal plans based on the customer's call time and data volume, it has the problem of not being able to provide optimal payment plans that take into account the usage patterns of electronic payments. There was also the problem of insufficient service provision to improve customer satisfaction.

[0945] 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.

[0946] In this invention, the server includes means for measuring the call duration of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for providing an optimal plan based on the measured call duration and communication volume, means for analyzing the customer's electronic payment usage patterns, and means for providing an optimal payment plan based on the analysis results. This makes it possible to comprehensively analyze the customer's call and communication patterns and electronic payment usage patterns and provide an optimal plan.

[0947] "Airtime" refers to the total time a customer makes calls using a mobile phone.

[0948] "Communication volume" refers to the total volume of data transmitted by a customer using a mobile phone.

[0949] "Optimal Plan" refers to the service plan that is most economical and convenient for the Customer based on the Customer's call duration and communication volume patterns.

[0950] "Electronic payment" refers to the act of a customer paying for goods or services by electronic means.

[0951] "Usage patterns" refers to the frequency or tendency of a customer to use a particular service or feature.

[0952] "Analytical tools" refers to algorithms or software that are used to identify patterns or trends based on collected data.

[0953] "Means of provision" refers to methods and systems for presenting optimal plans and services to customers based on the analysis results.

[0954] The system for implementing this invention measures the call time and communication volume of a customer's mobile phone in real time, and further analyzes the customer's electronic payment usage patterns to provide the optimal plan. A specific embodiment of this system will be described below.

[0955] System configuration

[0956] The system consists of the following main components:

[0957] 1. Call duration measurement means: Measure the call duration of customers' mobile phones in real time.

[0958] 2. Data traffic measurement method: Measures data traffic on customers' mobile phones in real time.

[0959] 3. Data collection server: collects and stores call duration and traffic data.

[0960] 4. Analysis Server: Based on the collected data, machine learning algorithms are used to analyze customer usage patterns.

[0961] 5. Plan provision server: Based on the analysis results, it provides the optimal plan to the customer.

[0962] 6. Means of analyzing electronic payment usage patterns: Analyze customers' electronic payment usage patterns.

[0963] 7. Payment plan offering method: Based on the analysis results, the optimal payment plan is offered.

[0964] Hardware and software used

[0965] Hardware: Smartphones, servers

[0966] Software: Python, Pandas, Scikit-learn

[0967] Data processing and calculation

[0968] 1. Data collection: Call duration and communication volume data are collected in real time from smartphones and sent to a data collection server.

[0969] 2. Data preprocessing: The collected data is standardized and sent to the analysis server.

[0970] 3. Applying machine learning algorithms: The analytics server uses machine learning algorithms (e.g., KMeans clustering) to analyze customer usage patterns.

[0971] 4. Proposing the optimal plan: Based on the analysis results, the plan providing server proposes the optimal plan to the customer.

[0972] 5. Analysis of electronic payment usage patterns: Analyze the usage patterns of electronic payments and provide optimal payment plans.

[0973] Specific examples

[0974] For example, if User A makes more than 20 payments per month and primarily uses the service in urban areas, the "high-frequency user plan" will be offered to this user. On the other hand, User B makes around 10 payments per month and primarily uses the service in suburban areas. The "medium-frequency user plan" will be offered to this user.

[0975] Prompt Sentence Examples

[0976] I want to develop an application that proposes optimal payment plans based on users' payment history data. Using the following data, please generate Python code that clusters users and proposes the optimal plan for each cluster.

[0977] Data items:

[0978] transaction_amount: Payment amount

[0979] transaction_frequency: Transaction frequency

[0980] location: Location of use

[0981] output:

[0982] suggested_plan: The proposed plan

[0983] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0984] Step 1:

[0985] Data collection

[0986] The device (smartphone) measures the customer's call duration and communication volume data in real time and sends this data to a data collection server. The input is the call duration and communication volume data, and the output is the measurement data sent to the data collection server.

[0987] Step 2:

[0988] Data Preprocessing

[0989] The server standardizes the collected call duration and traffic data. Specifically, it reads the data using the Pandas library and standardizes the data using StandardScaler. The input is the collected raw data, and the output is the standardized data.

[0990] Step 3:

[0991] Applying machine learning algorithms

[0992] The server applies a machine learning algorithm (KMeans clustering) to the standardized data. Specifically, it performs clustering using the Scikit-learn library to analyze customer usage patterns. The input is the standardized data, and the output is the clustering results.

[0993] Step 4:

[0994] Proposing the optimal plan

[0995] The server proposes the optimal plan to the customer based on the clustering results. Specifically, it determines the optimal plan for each cluster and notifies the customer. The input is the clustering results, and the output is the proposed optimal plan.

[0996] Step 5:

[0997] Analysis of electronic payment usage patterns

[0998] The server analyzes the customer's electronic payment usage patterns. Specifically, it collects payment history data and analyzes the usage patterns using machine learning algorithms. The input is the payment history data, and the output is the analysis results of the usage patterns.

[0999] Step 6:

[1000] Offering payment plans

[1001] The server provides optimal payment plans based on the results of analyzing electronic payment usage patterns. Specifically, it determines the optimal payment plan for each usage pattern and notifies the customer. The input is the analysis results of usage patterns, and the output is the proposed optimal payment plan.

[1002] Example 3

[1003] Next, a description will be given of Example 3 of Form Example 3. 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."

[1004] Traditional communication plans were not optimized for customer usage patterns, resulting in customers often paying unnecessary communication fees. It was also difficult for customers to find the plan that best suited them, leading to low satisfaction. Even when systems existed that suggested optimal plans, the notification methods and plan change procedures were complicated, making it difficult for customers to actually change their plans.

[1005] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1006] In this invention, the server includes means for measuring the call time of a customer's communication terminal in real time, means for measuring the data usage of the customer's communication terminal in real time, means for calculating an optimal communication plan based on the measured call time and data usage, means for notifying the customer of the calculated optimal communication plan, and means for the customer to change to the notified communication plan. This allows customers to easily find a communication plan that is optimal for their usage pattern, thereby saving on communication costs and improving customer satisfaction.

[1007] "Call time" is the total time during which a customer makes a call using a communication terminal.

[1008] "Data usage" means the total amount of data consumed by a customer when using a communication device to access the Internet or applications.

[1009] A "communication plan" is a pricing structure for communication services provided by a telecommunications carrier, including talk time, data usage, and number of SMS messages sent.

[1010] "Real-time measurement means" refers to technology that instantly measures the call time and data usage of customers' communication devices and records them in a database.

[1011] The "means for calculating the optimal communication plan" refers to algorithms or software that analyzes a customer's call time and data usage patterns and selects the most cost-effective communication plan based on the results.

[1012] "Means of notification" refers to the method used to notify customers of the calculated optimal communication plan, and includes email, SMS, in-app notifications, etc.

[1013] "Plan change method" means the process or interface through which a customer can change to the notified communications plan, including online portals and customer support.

[1014] MODE FOR CARRYING OUT THE INVENTION

[1015] This invention is a system for reducing customer communication costs and improving customer satisfaction. This system measures the call time and data usage of the customer's communication terminal in real time, calculates the optimal communication plan based on that data, and notifies the customer. It also provides a means for the customer to change to the notified communication plan.

[1016] Data collection

[1017] The server measures the call duration and data usage of the customer's communication device in real time. Specifically, it retrieves data from the carrier's database using an API. The hardware used is a database server (e.g., MySQL, PostgreSQL), and the software used is a data collection script (e.g., Python, Java).

[1018] Data analysis

[1019] The server analyzes the collected data and identifies customer usage patterns. Specifically, it uses machine learning algorithms to analyze customer communication usage trends. The software used is a machine learning library (e.g., TensorFlow, scikit-learn).

[1020] Calculating the optimal plan

[1021] The server then calculates the optimal communication plan for the customer based on the analysis results. Specifically, it compares existing plan information with the customer's usage patterns to select the most cost-effective plan. The software used is an optimization algorithm (e.g., linear programming).

[1022] notification

[1023] The server notifies the customer of the calculated optimal communication plan. Specifically, it sends the proposal to the customer using methods such as email, SMS, and in-app notifications. The software used is a notification system.

[1024] Change plan

[1025] After receiving the notification, the user can change to the proposed plan. Specifically, the change procedure is carried out through an online portal or customer support. The hardware used is the customer's device (e.g., smartphone, PC), and the software used is the carrier's online portal.

[1026] Specific examples

[1027] As a concrete example, by inputting the following prompt sentence into a generative AI model, it is possible to simulate the behavior of a system that proposes the optimal plan for a customer.

[1028] Example prompt sentence:

[1029] Customer A's communication usage data is as follows:

[1030] Talk time: 300 minutes / month

[1031] Data usage: 5GB / month

[1032] Number of SMS sent: 50 / month

[1033] Based on this data, please propose the best communication plan for Customer A.

[1034] In this way, the customer can save on communication costs and improve satisfaction by switching to the most suitable plan. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1035] Step 1: Data collection

[1036] The server measures the call time and data usage of the customer's communication device in real time. Specifically, it obtains data from the communication carrier's database using an API. As input, it uses customer identification information (e.g., customer ID), and as output, it obtains communication usage data such as call time, data usage, and number of SMS sent. For example, it confirms that customer A's call time is 300 minutes, data usage is 5GB, and the number of SMS sent is 50.

[1037] Step 2: Data analysis

[1038] The server analyzes the collected data and identifies the customer's usage patterns. Specifically, it uses a machine learning algorithm to analyze the customer's communication usage trends. The communication usage data collected in step 1 is used as input, and the customer's usage patterns (e.g., high call time, medium data usage, etc.) are obtained as output. For example, it is identified that Customer A has high call time and medium data usage.

[1039] Step 3: Calculate the optimal plan

[1040] The server calculates the optimal communication plan for the customer based on the analysis results. Specifically, it compares existing plan information with the customer's usage patterns and selects the most cost-effective plan. The usage patterns obtained in step 2 and existing plan information are used as input, and the optimal communication plan is obtained as output. For example, it may determine that an unlimited calling plan is optimal.

[1041] Step 4: Notification

[1042] The server notifies the customer of the calculated optimal communication plan. Specifically, it sends the proposal to the customer using methods such as email, SMS, and in-app notifications. The optimal communication plan obtained in step 3 and the customer's contact information are used as input, and a notification message is sent as output. For example, it notifies Customer A by email that "an unlimited calling plan is the best option."

[1043] Step 5: Change your plan

[1044] After receiving the notification, the user can change to the proposed plan. Specifically, the change procedure is carried out through an online portal or customer support. The notification message and the customer's selection are used as input, and confirmation of the plan change is obtained as output. For example, Customer A uses his smartphone to access the carrier's online portal and change to an unlimited calling plan. After the change procedure is completed, the user confirms that the new plan has been applied.

[1045] (Application example 3)

[1046] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1047] While the conventional system could provide optimal plans based on the customer's call time and data volume, it had the problem of not being able to propose optimal payment plans that took into account the customer's payment history and usage patterns. As a result, customers were unable to enjoy optimal plans not only in terms of saving on communication costs, but also in terms of payment fees and point redemption rates, and improvements in customer satisfaction were limited.

[1048] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1049] In this invention, the server includes means for measuring the customer's mobile phone call time in real time, means for measuring the customer's mobile phone communication volume in real time, means for providing an optimal plan based on the measured call time and communication volume, and means for analyzing the customer's payment history and proposing an optimal payment plan. This enables the customer to enjoy an optimal plan not only in terms of saving on communication costs but also in terms of payment fees, point redemption rates, etc.

[1050] "Means for measuring customer mobile phone call duration in real time" refers to a device or software for measuring and recording in real time the duration of calls made by a customer using a mobile phone.

[1051] "Means for measuring customer mobile phone data traffic in real time" refers to a device or software that measures and records in real time the data traffic when a customer uses a mobile phone for data communication.

[1052] "Means for providing the optimal plan based on the measured call time and communication volume" refers to a device or software that analyzes data on call time and communication volume measured in real time and proposes the most suitable communication plan for the customer.

[1053] "Means for analyzing a customer's payment history and proposing the most suitable payment plan" refers to a device or software that analyzes a customer's past payment history data and proposes the most advantageous payment plan for the customer (e.g., credit card, debit card, electronic money, etc.).

[1054] The system for implementing this invention measures the call time and communication volume of a customer's mobile phone in real time, and further analyzes the customer's payment history to propose the optimal plan. A specific embodiment of this system will be described below.

[1055] System configuration

[1056] The system mainly consists of the following hardware and software:

[1057] Hardware: General purpose PC or server

[1058] Software: Python, pandas, scikit-learn, numpy

[1059] Data collection and processing

[1060] The server collects call duration and traffic data from the customer's mobile phone in real time. This is done using an API that works with the mobile phone's communication module. The collected data is then recorded in real time on the server.

[1061] Next, the server collects the customer's payment history data, which is obtained from the payment methods used by the customer (credit cards, debit cards, electronic money, etc.) using the payment provider's API.

[1062] Analyzing the data

[1063] The server analyzes the collected call duration and traffic data and proposes the best communication plan for the customer, which involves the following steps:

[1064] 1. Data Normalization: To normalize the call duration and traffic data, we use Python's StandardScaler.

[1065] 2. Clustering: Use KMeans clustering to analyze customer usage patterns.

[1066] 3. Plan proposal: Propose the optimal communication plan for each cluster.

[1067] Furthermore, the server analyzes the customer's payment history data and proposes the most suitable payment plan, which includes the following steps:

[1068] 1. Data Normalization: Use Python's StandardScaler to normalize payment history data.

[1069] 2. Clustering: Use KMeans clustering to analyze customer payment patterns.

[1070] 3. Plan proposal: Propose the optimal payment plan for each cluster.

[1071] Proposal Notification

[1072] The server then notifies the customer of the optimal communication and payment plan based on the analysis results. Notification is sent via a smartphone app. The customer can then review the proposed plan through the app and change it if necessary.

[1073] Specific examples

[1074] For example, if a customer uses 1,000 minutes of calls and 10GB of data per month, the server collects this data in real time and proposes the optimal communication plan. At the same time, it analyzes the customer's payment history and proposes the optimal payment plan (for example, a credit card with a high reward point rate).

[1075] Prompt Sentence Examples

[1076] Below are some example prompts to input to a generative AI model:

[1077] Develop an application that analyzes users' payment history data and proposes optimal payment plans. Use features such as the user's payment amount, transaction type, transaction time, and day of the week to perform KMeans clustering and propose the optimal payment plan (credit card, debit card, electronic money, etc.) for each cluster. Use Python and its libraries (pandas, scikit-learn, numpy).

[1078] In this way, customers can not only save on communication costs, but also enjoy the best plan in terms of payment fees and point redemption rates.

[1079] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1080] Step 1:

[1081] The server collects call duration and communication volume data from the customer's mobile phone in real time. Specifically, it uses an API that works with the mobile phone's communication module to obtain information such as the call start time, end time, and data communication volume. The input is real-time data from the mobile phone, and the output is call duration and communication volume data that is stored on the server.

[1082] Step 2:

[1083] The server collects the customer's payment history data. To do this, it uses the payment provider's API to obtain data from the payment methods used by the customer (credit cards, debit cards, electronic money, etc.). The input is the payment history data from the payment provider, and the output is the payment history data stored on the server.

[1084] Step 3:

[1085] The server standardizes the collected call duration and traffic data by using Python's StandardScaler to convert each data point to a mean of 0 and a standard deviation of 1. The input is the raw call duration and traffic data, and the output is the standardized data.

[1086] Step 4:

[1087] The server clusters the normalized call duration and traffic data. Specifically, it uses KMeans clustering to analyze customer usage patterns and classify them into multiple clusters. The input is the normalized data, and the output is the label of the cluster to which each data point belongs.

[1088] Step 5:

[1089] The server proposes the optimal communication plan for each cluster. Specifically, it selects the optimal communication plan (for example, an unlimited calling plan for a cluster with a high call duration) based on the usage pattern of each cluster. The input is the cluster label, and the output is the optimal communication plan proposal.

[1090] Step 6:

[1091] The server standardizes the collected payment history data. Specifically, it uses Python's StandardScaler to convert each data point to a mean of 0 and a standard deviation of 1. The input is the raw payment history data, and the output is the standardized data.

[1092] Step 7:

[1093] The server clusters the standardized payment history data. Specifically, it uses KMeans clustering to analyze customer payment patterns and classify them into multiple clusters. The input is the standardized data, and the output is the label of the cluster to which each data point belongs.

[1094] Step 8:

[1095] The server proposes the optimal payment plan for each cluster. Specifically, it selects the optimal payment plan (e.g., a credit card with a high reward point rate) based on the payment patterns of each cluster. The input is the cluster label, and the output is the optimal payment plan proposal.

[1096] Step 9:

[1097] The server notifies the customer of the optimal communication and payment plan based on the analysis results. Specifically, the notification is sent via a smartphone app. The input is the optimal plan proposal, and the output is a notification to the customer. The customer can check the proposed plan through the app and change the plan if necessary.

[1098] 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.

[1099] "Example 1"

[1100] In one embodiment of the present invention, the emotion engine recognizes emotions from the content of a user's call. Specifically, it analyzes characteristics such as the user's voice tone, volume, and speaking rate, and estimates the user's emotional state from these characteristics. Based on this emotional state, an optimal plan is provided. For example, if a user expresses anger, a special plan such as a discount on call charges can be provided to that user, thereby improving user satisfaction.

[1101] "Example 2"

[1102] In another embodiment of the present invention, the emotion engine recognizes emotions not only from the content of a user's calls but also from the content of their communications. Specifically, the emotion engine analyzes the content of text messages and emails sent by the user and infers the user's emotional state from the content. Based on this emotional state, an optimal plan is provided. For example, if a user expresses joy, a special plan with increased data traffic can be provided to that user, thereby improving user satisfaction.

[1103] "Example 3"

[1104] In yet another embodiment of the present invention, the emotion engine recognizes emotions from the content of a user's calls and communications and provides an optimal plan based on the emotions. Specifically, the emotion engine analyzes the content of text messages and emails sent by the user, as well as the tone, volume, and speaking speed of the user's voice, and estimates the user's emotional state from the content. The optimal plan is provided based on this emotional state. For example, if a user expresses sadness, the emotion engine can improve user satisfaction by providing the user with a special plan, such as a discount on call charges.

[1105] The processing flow of each embodiment will be described below.

[1106] "Example 1"

[1107] Step 1: The user initiates a call.

[1108] Step 2: The emotion engine analyzes the user's voice characteristics such as tone, volume, and speaking rate.

[1109] Step 3: The emotion engine infers the user's emotional state from the analysis results.

[1110] Step 4: Provide an optimal plan based on the estimated emotional state.

[1111] "Example 2"

[1112] Step 1: A user initiates a communication.

[1113] Step 2: The emotion engine analyzes the content of the text message or email sent by the user.

[1114] Step 3: The emotion engine infers the user's emotional state from the analysis results.

[1115] Step 4: Provide an optimal plan based on the estimated emotional state.

[1116] "Example 3"

[1117] Step 1: A user initiates a call or communication.

[1118] Step 2: The emotion engine analyzes the content of the text messages and emails sent by the user, as well as the tone of voice, volume, and speaking rate.

[1119] Step 3: The emotion engine infers the user's emotional state from the analysis results.

[1120] Step 4: Provide an optimal plan based on the estimated emotional state.

[1121] Example 1

[1122] Next, a description will be given of Example 1 of Form 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."

[1123] Conventional communication plan provision systems can provide optimal plans based on the customer's call time and data volume, but they have the problem of not being able to provide plans that take into account the customer's emotional state. This makes it difficult to sufficiently improve customer satisfaction and provide flexible plans that meet customer needs.

[1124] 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.

[1125] In this invention, the server includes means for measuring the call time of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for providing an optimal plan based on the measured call time and communication volume, means for recognizing the emotion of the customer from the content of the call, and means for providing an optimal plan based on the recognized emotion. This makes it possible to provide an optimal plan that takes into account not only the customer's call time and communication volume but also their emotional state, thereby improving customer satisfaction.

[1126] "Means for measuring customer mobile phone call duration in real time" refers to technology that obtains the start and end times of customer calls via a communications network and measures call duration in real time based on that information.

[1127] "Means for measuring customer mobile phone data usage in real time" refers to technology that monitors customer data usage in real time through a communication network and measures data usage based on that information.

[1128] "Means for providing the optimal plan based on measured call time and communication volume" refers to technology that analyzes acquired call time and communication volume data, and calculates and provides the communication plan that is most suitable for the customer's usage pattern.

[1129] The "means for recognizing emotions from the content of a customer's call" is a technology that uses voice recognition technology to analyze the content of a customer's call and estimate the customer's emotional state from characteristics such as tone of voice, volume, and speaking speed.

[1130] "Means for providing optimal plans based on recognized emotions" refers to technology that calculates and provides special communication plans according to the customer's emotional state based on the results of emotion recognition.

[1131] MODE FOR CARRYING OUT THE INVENTION

[1132] This invention is a system that measures the call time and communication volume of a customer's mobile phone in real time and provides the optimal plan based on that data. It also includes a function that recognizes the customer's emotions from the content of the call and provides the optimal plan based on that emotional state.

[1133] The server obtains customer call duration and communication volume data in real time via the communication network. Specifically, it uses the communication carrier's API to collect information such as the start time and end time of the customer's call and the amount of data used during the call. For example, it sends a request to the communication carrier's API endpoint and receives the call data as a response.

[1134] The server then analyzes the data, converting it into a data frame using Python's Pandas library, and calculating the total call duration, average call duration, and total communication volume for each customer, allowing it to identify customer usage patterns.

[1135] The server then uses an emotion engine to recognize emotions from the customer's call. It converts the voice data into text using the Google Cloud Speech-to-Text API, and inputs the text into an emotion analysis model. The emotion analysis model analyzes the customer's voice characteristics, such as tone, volume, and speaking rate, to estimate their emotional state.

[1136] For example, if a user shows anger during a call, the server can offer the user a special plan with a discount on the call charge, thereby improving user satisfaction.

[1137] Examples of specific prompts include:

[1138] "Design a system that recognizes emotions from the content of a user's calls and offers special plans with discounts on call charges if the user expresses anger. Explain how you would obtain real-time call duration and traffic data from a carrier's network and use voice recognition technology to analyze user emotions."

[1139] Using this prompt, the generative AI model can provide a detailed design and implementation method for the system.

[1140] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1141] Step 1:

[1142] The server obtains customer call duration and communication volume data in real time through the carrier's network. As input, it sends a request to the carrier's API endpoint and receives information such as the call start time, end time, and call data volume as a response. This allows the server to collect customer call duration and communication volume data.

[1143] Step 2:

[1144] The server analyzes the acquired call duration and communication volume data. It uses the data acquired in step 1 as input. It converts it into a data frame using Python's Pandas library and calculates the total call duration, average call duration, total communication volume, etc. for each customer. The output is the usage pattern for each customer. Specific operations include grouping and aggregation of the data frame.

[1145] Step 3:

[1146] The server uses an emotion engine to recognize emotions from the customer's call content. It uses the call's audio data as input. It converts the audio data to text using the Google Cloud Speech-to-Text API and inputs the text into a sentiment analysis model. The output is the customer's emotional state. Specific operations include converting the audio data to text and analyzing sentiment.

[1147] Step 4:

[1148] The server calculates the optimal plan for the customer based on the analysis results and emotion recognition results. As input, it uses the usage pattern obtained in step 2 and the emotional state obtained in step 3. If the customer's call time is long, it proposes an unlimited call plan, and if the customer shows anger, it proposes a special plan with discounted call charges. The optimal plan is obtained as output. As a specific operation, it selects the plan using conditional branching.

[1149] Step 5:

[1150] The server provides the calculated optimal plan to the customer. As input, it uses the optimal plan obtained in step 4. It sends a notification to the customer's device and displays details of the optimal plan. As output, it provides the customer with information about the plan. Specific operations include sending a notification and displaying plan details.

[1151] (Application example 1)

[1152] Next, a description will be given of Application Example 1 of Form 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."

[1153] Conventional communication plan provision systems can provide optimal plans based on the customer's call time and data volume, but they are unable to provide services that take into account the customer's emotional state, limiting the improvement of customer satisfaction. Also, if a customer becomes stressed or angry during a call, they may not be able to respond appropriately, which could result in a security risk. To solve these problems, a system is needed that recognizes the customer's emotional state in real time and provides appropriate services and security alerts based on that.

[1154] 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.

[1155] In this invention, the server includes means for measuring the call time of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for providing an optimal plan based on the measured call time and communication volume, means for recognizing the customer's emotion from the content of the call, and means for issuing a security alert based on the recognized emotion. This makes it possible to provide an optimal plan that takes into account the emotional state of the customer and reduce security risks.

[1156] "Means for measuring customer mobile phone call duration in real time" refers to a device or software for measuring the time a customer is making a call on a mobile phone in real time.

[1157] "Means for measuring customer mobile phone traffic in real time" refers to a device or software for measuring the amount of data traffic used by a customer on a mobile phone in real time.

[1158] "Means for providing the optimal plan based on the measured call time and communication volume" refers to a device or software that calculates and provides the optimal communication plan to a customer based on data on call time and communication volume measured in real time.

[1159] The "means for recognizing emotions from the content of a customer's call" refers to a device or software that analyzes the voice data of a customer during a call and estimates the emotional state of the customer from characteristics such as tone of voice, volume, and speaking speed.

[1160] A "means for issuing a security alert based on a recognized emotion" is a device or software for automatically issuing a security alert when a customer's emotional state meets a specified condition (e.g., anger or stress).

[1161] The following system configuration will be described as an embodiment of the present invention.

[1162] System Configuration

[1163] The system consists of the following main components:

[1164] 1. Call duration measurement module: Measures the call duration of customers' mobile phones in real time.

[1165] 2. Communication volume measurement module: Measures the communication volume of customers' mobile phones in real time.

[1166] 3. Plan offering module: Offers the optimal communication plan to the customer based on the measured call time and communication volume.

[1167] 4. Emotion Recognition Module: Recognizes emotions from the content of customer calls.

[1168] 5. Security Alert Module: Based on the recognized emotions, it issues security alerts as needed.

[1169] Program processing

[1170] The server performs processing by linking each module as follows.

[1171] 1. Call duration measurement module: The server acquires customer call duration data in real time through the carrier's network. This data is used to measure the duration from when the customer starts a call to when it ends.

[1172] 2. Traffic measurement module: The server also collects customer traffic data in real time through the carrier's network. This data is used to measure the amount of data used when the customer uses the Internet.

[1173] 3. Plan provision module: The server calculates the optimal communication plan for the customer based on the acquired call duration and communication volume data. This plan is optimized for the customer's usage pattern and aims to maximize cost performance.

[1174] 4. Emotion Recognition Module: The server analyzes the customer's call content in real time and estimates the customer's emotional state from characteristics such as tone of voice, volume, and speaking speed. This analysis uses an emotion recognition library.

[1175] 5. Security Alert Module: The server automatically issues a security alert when the emotion recognized by the emotion recognition module meets certain conditions (e.g., anger or stress). This alert is sent to emergency contacts via a communication service.

[1176] Specific examples

[1177] For example, if a customer becomes angry during a call, the emotion recognition module will detect that emotion in real time, and the security alert module will automatically send a notification to emergency contacts, including the customer's ID and emotional state, allowing for a prompt response.

[1178] Prompt Sentence Examples

[1179] Here are some examples of prompts to communicate specific requirements to a generative AI model:

[1180] Monitor user calls in real time and analyze their emotional state using an emotion engine. If the user is stressed or angry, trigger a security alert and notify emergency contacts.

[1181] In this way, a system can be realized that can provide optimal plans that take into account the emotional state of the customer and reduce security risks.

[1182] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1183] Step 1:

[1184] The server obtains customer call duration data in real time through the carrier's network.

[1185] Input: The call start and end times obtained from the carrier's API.

[1186] Data processing: Calculate the difference between the call start time and end time to calculate the call duration.

[1187] Output: Real-time call duration data.

[1188] Step 2:

[1189] The server obtains customer traffic data in real time through the carrier's network.

[1190] Input: Data usage obtained from the carrier's API.

[1191] Data processing: The acquired data usage is accumulated and real-time communication volume is calculated.

[1192] Output: Real-time traffic data.

[1193] Step 3:

[1194] The server calculates the optimal communication plan for the customer based on the acquired call time and communication volume data.

[1195] Input: Real-time call duration and traffic data.

[1196] Data calculation: Analyzes call duration and data usage patterns and applies algorithms to select the most suitable plan.

[1197] Output: The best communication plan for the customer.

[1198] Step 4:

[1199] The server analyzes the content of the customer's call in real time and estimates the customer's emotional state from characteristics such as tone of voice, volume, and speaking speed.

[1200] Input: Voice data during a call.

[1201] Data processing: Analyze the audio data and extract features. Estimate the emotional state using an emotion recognition library.

[1202] Output: Customer emotional state data.

[1203] Step 5:

[1204] The server automatically issues a security alert when the emotion recognized by the emotion recognition module meets certain conditions (e.g., anger or stress).

[1205] Input: Customer emotional state data.

[1206] Data calculation: Determine whether the emotional state meets certain conditions.

[1207] Output: Sending a security alert.

[1208] Step 6:

[1209] The server notifies emergency contacts of security alerts.

[1210] Enter: Security Alert.

[1211] Data processing: Converts alert content into a message format and sends notifications using a communication service.

[1212] Output: Notification message to emergency contacts.

[1213] Example 2

[1214] Next, a description will be given of Example 2 of Form 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."

[1215] Conventional communication plan provision systems can provide plans based on the customer's call time and data volume, but do not provide plans that take into account the customer's emotional state. This makes it difficult to maximize customer satisfaction. In addition, because data collection and analysis are not performed in real time, providing the optimal plan can be delayed.

[1216] 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.

[1217] In this invention, the server includes means for measuring customer mobile phone call time in real time, means for measuring customer mobile phone communication volume in real time, means for transmitting the measured call time and communication volume to the server, means for storing data received by the server in a database, means for preprocessing the stored data, means for inputting the preprocessed data into a machine learning algorithm to analyze the customer's call and communication patterns, means for inputting the contents of the customer's text messages and emails into an emotion recognition engine to estimate the customer's emotional state, means for generating an optimal plan based on the analysis results and the emotional state, and means for notifying the customer of the generated plan. This makes it possible to collect and analyze customer behavioral data and emotional data in real time and quickly provide a more personalized, optimal plan.

[1218] "Airtime" refers to the total time a customer makes calls using a mobile phone.

[1219] "Communication volume" refers to the total volume of data transmitted by the customer using their mobile phone.

[1220] "Server" refers to a central processing unit that collects, stores, pre-processes, analyzes, and generates plans from data.

[1221] "Database" refers to a data management system for efficiently storing and retrieving data received by a server.

[1222] "Preprocessing" refers to the preparation of data before data analysis, such as filling in missing values ​​and detecting outliers in collected data.

[1223] A "machine learning algorithm" is a mathematical model that learns patterns from data and makes predictions and classifications.

[1224] An "emotion recognition engine" refers to software that infers a customer's emotional state from the content of text messages and emails.

[1225] "Plan generation" refers to the process of creating the optimal communication plan for a customer based on the analysis results and emotional state.

[1226] "Notification" refers to the means of communication used to inform customers of the created plan.

[1227] This invention is a system that measures customer call time and communication volume in real time and provides optimal communication plans based on this data. It also includes a function to recognize emotions from the content of customers' text messages and emails and optimize plans based on their emotional state.

[1228] Hardware and software used

[1229] Hardware: Servers, devices (smartphones and PCs)

[1230] Software: Machine learning algorithms (e.g., TensorFlow, scikit-learn), emotion recognition engines (e.g., IBM Watson, Microsoft Azure Text Analytics)

[1231] Data collection and transmission

[1232] The device monitors the user's call time and data usage in real time. For example, a smartphone app runs in the background and records call time and data usage.

[1233] The device encrypts the collected data and periodically sends it to the server. For example, it can be set to send all data at once every night.

[1234] Data storage and preprocessing

[1235] The server stores the received data in a database, which uses the user ID as a key to store the data and allows for efficient searches.

[1236] The server preprocesses the stored data, for example, by filling in missing values ​​with the average value and excluding abnormally high traffic volumes as outliers.

[1237] Pattern Analysis and Emotion Recognition

[1238] The server then inputs the preprocessed data into machine learning algorithms, such as K-means clustering, to cluster users' call and communication patterns and identify the best plan for each cluster.

[1239] The server inputs the content of the user's text message or email into an emotion recognition engine, such as IBM Watson, which analyzes the emotion of the text to determine whether the user is expressing emotions such as happiness, sadness, or anger.

[1240] Plan Generation and Notification

[1241] The server generates an optimal plan for the user based on the analysis results and the user's emotional state. For example, a user who has a high call duration and shows a happy emotion may be offered an unlimited call plan and special data bonuses.

[1242] The server notifies the user of the generated plan, for example by sending a push notification via a smartphone application to suggest a new plan to the user.

[1243] Specific examples

[1244] If a user uses 1,000 minutes of talk time and 10 GB of data communication in a month, the device will collect this data and send it to the server.

[1245] The server pre-processes the data and analyzes user patterns using K-means clustering.

[1246] The server recognizes from the text message sent by the user that the user is expressing an emotion of joy.

[1247] The server generates unlimited calling and 20GB data plans with extra data bonuses.

[1248] The server notifies the user of the generated plan and sends a push notification via the smartphone application.

[1249] Prompt Sentence Examples

[1250] "Design a system that will recommend the best plan for a user based on their call duration and data usage. Also, add a feature that recognizes emotions in the content of a user's text messages and emails and offers special plans based on their emotional state."

[1251] In this way, we can utilize user behavioral and emotional data to provide more personalized services.

[1252] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1253] Step 1:

[1254] The device monitors the user's call time and data usage in real time. Specifically, a smartphone app runs in the background and records call time and data usage.

[1255] Input: User's call time and data usage

[1256] Output: Recorded call duration and traffic data

[1257] Step 2:

[1258] The device encrypts the collected data and periodically sends it to the server. For example, it can be set to send all data at once every night.

[1259] Input: Recorded call duration and traffic data

[1260] Output: Encrypted call duration and traffic data

[1261] Step 3:

[1262] The server stores the received data in a database, which uses the user ID as a key to store the data and allows for efficient searches.

[1263] Input: Encrypted call time and traffic data

[1264] Output: Data stored in the database

[1265] Step 4:

[1266] The server preprocesses the stored data, specifically filling in missing values ​​with the average value and excluding abnormally high traffic volumes as outliers.

[1267] Input: Data stored in the database

[1268] Output: Preprocessed data

[1269] Step 5:

[1270] The server then inputs the preprocessed data into machine learning algorithms, such as K-means clustering, to cluster users' call and communication patterns and identify the best plan for each cluster.

[1271] Input: Preprocessed data

[1272] Output: Call and communication patterns of clustered users

[1273] Step 6:

[1274] The server inputs the content of the user's text message or email into an emotion recognition engine, which, for example, analyzes the emotion of the text to determine whether the user is expressing an emotion such as happiness, sadness, or anger.

[1275] Input: The contents of a user's text message or email

[1276] Output: Estimated user emotional state

[1277] Step 7:

[1278] The server generates an optimal plan for the user based on the analysis results and the user's emotional state. For example, a user who has a high call duration and shows a happy emotion may be offered an unlimited call plan and special data bonuses.

[1279] Input: Clustered users' call and communication patterns, estimated users' emotional states

[1280] Output: The optimal plan generated

[1281] Step 8:

[1282] The server notifies the user of the generated plan, for example by sending a push notification via a smartphone application to suggest a new plan to the user.

[1283] Input: Generated optimal plan

[1284] Output: Plan notified to user

[1285] (Application example 2)

[1286] Next, a description will be given of Application Example 2 of Form 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."

[1287] Conventional systems can provide optimal plans based on the customer's call time and data volume, but they cannot provide plans that take into account the customer's emotional state, which means they cannot fully improve customer satisfaction. Furthermore, there is a need to grasp the customer's emotional state in real time and provide flexible plans based on that, but there is also the problem of a lack of technology to achieve this.

[1288] 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.

[1289] In this invention, the server includes means for measuring the call time of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for providing an optimal plan based on the measured call time and communication volume, means for estimating the emotional state of the customer by analyzing the content of the customer's text messages and emails, and means for providing an optimal plan based on the estimated emotional state. This makes it possible to provide an optimal plan that takes into account not only the customer's call time and communication volume but also their emotional state.

[1290] "Customer" means an individual or legal entity using the Service.

[1291] "Mobile" refers to mobile communication devices such as mobile phones and smartphones.

[1292] "Talk time" is the total amount of time a customer makes calls using their mobile phone.

[1293] "Communication volume" refers to the total amount of data communication carried out by a customer using their mobile phone.

[1294] "Real-time" refers to data being processed as it is generated.

[1295] "Means for measuring" refers to a combination of hardware and software for measuring call duration and traffic volume.

[1296] The "optimal plan" is the most suitable service plan offered based on the customer's usage patterns and emotional state.

[1297] The "means of delivery" is a combination of hardware and software for presenting and applying the optimal plan to the customer.

[1298] A "text message" is text information sent and received via SMS or instant messaging apps.

[1299] "Email" is an electronic letter sent and received over the Internet.

[1300] "Analyzing" means processing data and extracting meaning and patterns.

[1301] "Emotional state" refers to the type and intensity of emotion a customer is feeling at a particular point in time.

[1302] To "estimate" means to predict unknown information based on data.

[1303] A system for implementing the present invention includes means for measuring a customer's mobile phone call duration in real time, means for measuring a customer's mobile phone communication volume in real time, means for providing an optimal plan based on the measured call duration and communication volume, means for analyzing the content of a customer's text messages and emails to estimate an emotional state, and means for providing an optimal plan based on the estimated emotional state.

[1304] The server obtains real-time call duration and traffic data from the customer's mobile phone. This is done using APIs and databases that collect data through the mobile carrier's network. For example, call duration is obtained from call logs, and traffic is obtained from data usage logs.

[1305] The server then uses the acquired data to apply machine learning algorithms to analyze customer call duration and traffic patterns, using clustering algorithms (e.g., KMeans) with Python's scikit-learn library, allowing it to offer optimal plans based on customer usage patterns.

[1306] Additionally, the server analyzes the content of customers' text messages and emails to estimate their emotional state using TextBlob, a natural language processing library. It extracts emotions from the content of text messages and emails and provides the optimal plan based on that emotional state.

[1307] For example, if a customer shows emotions of joy, a special cashback plan can be offered, which can improve customer satisfaction.

[1308] As a concrete example, consider a case where user A has recently had a long call time and a large amount of data traffic. Furthermore, if the contents of text messages and emails indicate that user A is expressing joy, user A will be offered a special cashback plan.

[1309] An example of a prompt might be:

[1310] Develop an application that analyzes the user's call time, data usage, text message and email content, and offers optimal electronic payment plans based on the user's emotional state. For example, consider a scenario where a user expresses happiness and is offered a special cashback plan.

[1311] In this way, it becomes possible to provide optimal plans that take into account not only the customer's call time and data volume, but also their emotional state.

[1312] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1313] Step 1:

[1314] The server obtains call duration and communication volume data from the customer's mobile phone in real time. Specifically, it uses APIs through the mobile carrier's network to collect call logs and data usage logs. The input is call duration and communication volume data from the customer's mobile phone, and the output is that this data is stored on the server.

[1315] Step 2:

[1316] The server uses the acquired call duration and communication volume data to apply a machine learning algorithm to analyze customer call duration and communication volume patterns. Specifically, it uses the KMeans clustering algorithm, which uses the Python scikit-learn library. The input is call duration and communication volume data, and the output is the clustering results based on customer usage patterns.

[1317] Step 3:

[1318] The server analyzes the content of the customer's text messages and emails to estimate their emotional state. Specifically, it uses TextBlob, a natural language processing library, to analyze the text data. The input is the content of the text messages and emails, and the output is the estimated emotional state.

[1319] Step 4:

[1320] The server provides the optimal plan based on the estimated emotional state. Specifically, it selects a plan according to the emotional state, such as offering a special cashback plan if the emotional state is joy. The input is the estimated emotional state and the clustering result, and the output is the optimal plan.

[1321] Step 5:

[1322] The server notifies the customer of the optimal plan. Specifically, it sends a push notification or email to the customer's mobile phone. The input is the information about the optimal plan, and the output is a notification to the customer.

[1323] In this way, it becomes possible to provide optimal plans that take into account not only the customer's call time and data volume, but also their emotional state.

[1324] Example 3

[1325] Next, a description will be given of Example 3 of Form Example 3. 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."

[1326] Conventional systems can provide optimal plans based on the customer's call time and data volume, but do not provide plans that take into account the customer's emotional state. Therefore, in order to further improve customer satisfaction, a system is needed that analyzes the customer's emotional state and provides optimal plans based on that.

[1327] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1328] In this invention, the server includes means for measuring the call time of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for providing an optimal plan based on the measured call time and communication volume, means for collecting the content of the customer's calls and communication, means for analyzing the collected data to estimate the emotional state of the customer, means for calculating an optimal plan based on the estimated emotional state, means for notifying the customer of the calculated optimal plan, and means for confirming whether the customer wishes to change the plan and applying the change. This makes it possible to provide an optimal plan based on the emotional state of the customer, thereby improving customer satisfaction.

[1329] "Means for measuring customer mobile phone call duration in real time" refers to a device or software for measuring the time a customer is making a call on a mobile phone in real time.

[1330] "Means for measuring customer mobile phone traffic in real time" refers to a device or software for measuring the amount of data traffic used by a customer on a mobile phone in real time.

[1331] The "means for providing the optimal plan" refers to a device or software that selects and provides the most suitable communication plan to a customer based on data such as the customer's call time, communication volume, and emotional state.

[1332] "Means for collecting customer calls and communications" refers to devices or software used to collect communications such as calls, text messages, and emails made by customers on their mobile phones.

[1333] The "means for analyzing collected data to estimate the emotional state of a customer" refers to a device or software for analyzing collected call content or communication content to estimate the emotional state of a customer.

[1334] The "means for calculating an optimal plan based on an estimated emotional state" is a device or software for calculating a communication plan that is most suitable for a customer based on the estimated emotional state of the customer.

[1335] The "means for notifying the customer of the calculated optimum plan" is a device or software for notifying the customer of the calculated optimum communication plan.

[1336] "Means for checking whether the customer wishes to change plans and applying the changes" means a device or software that checks whether the customer wishes to change to a proposed communications plan and applies the plan if the customer wishes to change.

[1337] MODE FOR CARRYING OUT THE INVENTION

[1338] This invention provides a system for providing optimal communication plans based on a customer's call duration, communication volume, and emotional state in order to improve customer satisfaction. This system is implemented using the following hardware and software.

[1339] Hardware and software used

[1340] Hardware: High performance servers, voice recognition devices, database servers

[1341] Software: Natural Language Processing (NLP) libraries (e.g., SpaCy, NLTK), speech analysis software, machine learning models (e.g., TensorFlow, PyTorch)

[1342] Program processing

[1343] The server first measures the customer's call duration and communication volume in real time using a voice recognition device and a database server. The server then collects the content of the customer's calls and communications and analyzes this data to estimate the customer's emotional state. It uses natural language processing (NLP) libraries and speech analysis software to analyze the content of text messages and emails, as well as the tone of voice, volume, and speaking rate.

[1344] Based on the analyzed emotional state, the server uses a machine learning model to calculate the optimal communication plan. For example, if a customer sends a text message saying, "I've been having trouble with high call charges lately," the server can recognize the customer's feelings of confusion or sadness and calculate a plan that offers discounts on call charges.

[1345] The server notifies the customer of the calculated optimal plan via SMS, email, in-app notification, etc. The customer receives the notification and confirms whether they want to change to the proposed plan. If they do, the server receives the request, updates the database, and applies the new plan.

[1346] Specific examples

[1347] As a concrete example, consider a case where a user sends a text message saying, "I'm having trouble with high phone charges these days." In this case, the emotion engine recognizes the user's feelings of confusion or sadness, and the server proposes a special plan that offers discounts on phone charges to the user.

[1348] Example prompt sentence:

[1349] Analyze the content of text messages and emails sent by the user, as well as the tone, volume, and speaking speed of the user's voice, and infer the user's emotional state from the content. For example, if a user sends a message saying, "I've been having trouble with high phone charges lately," suggest a plan that offers discounts on phone charges to that user.

[1350] In this way, the server can provide an optimal plan based on the emotional state of the user, thereby improving customer satisfaction. The flow of the specification process in the third embodiment will be described with reference to FIG.

[1351] Step 1:

[1352] User data collection

[1353] The server collects data such as the contents of user calls, text messages, emails, etc. Specifically, using a voice recognition device and a database server, it automatically collects voice data when a user initiates a call, and stores the contents of each text message and email sent in a database.

[1354] Input: User calls, text messages, emails

[1355] Output: Calls, text messages, emails stored in a database

[1356] Step 2:

[1357] Emotion analysis

[1358] The server inputs the collected data into an emotion engine to analyze the user's emotional state. It uses natural language processing (NLP) libraries and speech analysis software. Specifically, it converts the voice data into text and analyzes the emotion of the text using an NLP library. It also uses speech analysis software to analyze the tone, volume, and speaking rate of the voice to estimate the user's overall emotional state.

[1359] Input: Calls, text messages, emails stored in the database

[1360] Output: Estimated emotional state

[1361] Step 3:

[1362] Calculating the optimal plan

[1363] The server calculates the optimal plan for the user based on the results of the emotion analysis. It uses a machine learning model to select a plan that corresponds to the user's emotional state. Specifically, the results of the emotion analysis are input into the machine learning model, and if the emotion of "sadness" is detected, for example, a plan that offers a discount on call charges is calculated.

[1364] Input: Estimated emotional state

[1365] Output: Optimal plan

[1366] Step 4:

[1367] Plan Notification

[1368] The server notifies the user of the optimal plan it has calculated. Notification methods include SMS, email, and in-app notifications. Specifically, it references the user's contact information and sends a message containing details of the optimal plan. For example, it may notify the user by SMS that "A new plan with discounts on calling charges is available."

[1369] Input: Best Plan

[1370] Output: Notification sent to the user

[1371] Step 5:

[1372] Check and apply plan changes

[1373] The user receives the notification and confirms whether they want to change to the proposed plan. If they do, they reply to the server. Specifically, when the user replies "I want to change the plan," the server receives the request, updates the database, and applies the new plan.

[1374] Input: User reply

[1375] Output: Updated database with new plan applied

[1376] (Application example 3)

[1377] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1378] While conventional systems can provide optimal plans based on the customer's call time and data volume, they do not provide plans that take into account the customer's emotional state. Therefore, in order to further improve customer satisfaction, it is necessary to recognize the customer's emotional state and provide the optimal plan accordingly.

[1379] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1380] In this invention, the server includes means for measuring the call time of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for providing an optimal plan based on the measured call time and communication volume, means for recognizing the customer's emotion from the content of the call or communication, and means for providing an optimal plan based on the recognized emotion. This makes it possible to provide an optimal plan that takes into account the emotional state of the customer.

[1381] "Customer" means any person or entity using the Services.

[1382] "Mobile" refers to mobile communication devices such as mobile phones and smartphones.

[1383] "Airtime" refers to the total amount of time a customer makes calls using their mobile phone.

[1384] "Data volume" refers to the total amount of data sent and received by a customer using their mobile phone.

[1385] "Real-time" refers to processing and measurement occurring immediately, without delay.

[1386] The "optimal plan" refers to the most appropriate pricing plan and service content based on the customer's usage and emotional state.

[1387] "Call content" refers to what the customer said during the call.

[1388] "Communication Content" refers to the content of messages and data sent and received by Customer.

[1389] "Means of emotion recognition" refers to technologies and algorithms for inferring a customer's emotional state from the content of their calls or communications.

[1390] "Emotional state" refers to the type and intensity of emotions a customer is experiencing.

[1391] "Server" refers to a computer system that processes and stores data.

[1392] The system for implementing this invention measures the call time and communication volume of a customer's mobile phone in real time, and also has the function of recognizing the customer's emotions from the content of their calls and communications, making it possible to provide the optimal plan based on the customer's emotional state.

[1393] System Configuration

[1394] 1. Hardware Configuration

[1395] Mobile devices: Mobile phones and smartphones used by customers.

[1396] Server: A computer system that processes and stores data.

[1397] Microphone: A device for capturing audio input.

[1398] 2. Software Configuration

[1399] Speech recognition software: Uses speech recognition libraries to convert customer speech into text.

[1400] Sentiment analysis software: Uses the TextBlob library to analyze the sentiment of text.

[1401] Email sending software: Uses smtplib and email.mime.text to send emails with special cashback or discount offers.

[1402] Processing flow

[1403] 1. Acquiring voice input

[1404] The microphone of the mobile device is used to capture the customer's voice.

[1405] Speech recognition software is used to convert the captured speech into text.

[1406] 2. Sentiment analysis

[1407] The converted text is fed into sentiment analysis software to determine the customer's emotional state.

[1408] Emotional states are divided into three categories: positive, neutral, and negative.

[1409] 3. Providing the best plan

[1410] Based on the emotional state, the server chooses the optimal plan.

[1411] For example, offer special cashback or discounts if a customer is in a negative emotional state.

[1412] 4. Notification

[1413] Use email sending software to let your customers know which plan is best for them.

[1414] Specific examples

[1415] If a user says, "I'm stressed because I've had so many payments lately," the system will interpret that statement as negative and send them an email with a special cashback offer.

[1416] Prompt Sentence Examples

[1417] If a user says, "I'm stressed because I've had so many payments lately," create a program that will email them a special cashback offer.

[1418] In this way, it becomes possible to provide an optimal plan that takes into account the emotional state of the customer, thereby improving customer satisfaction.

[1419] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1420] Step 1:

[1421] The user uses the microphone of the mobile terminal to input voice.

[1422] Input: User's voice

[1423] Output: Audio data

[1424] Specific operation: When a user speaks into a mobile terminal, voice data is acquired by a microphone.

[1425] Step 2:

[1426] The device uses voice recognition software to convert the captured voice data into text.

[1427] Input: Audio data

[1428] Output: Text data

[1429] What it does: Speech recognition software analyzes the audio data and generates corresponding text data.

[1430] Step 3:

[1431] The server feeds the text data into sentiment analysis software to determine the customer's emotional state.

[1432] Input: Text data

[1433] Output: Emotional state (positive, neutral, negative)

[1434] What it does: Sentiment analysis software (e.g., the TextBlob library) analyzes text data and calculates positive, neutral, or negative sentiment.

[1435] Step 4:

[1436] The server selects the optimal plan based on the emotional state.

[1437] Input: Emotional state

[1438] Output: Best deal (e.g. special cashback or discount)

[1439] Specific operation: The server evaluates the emotional state and selects a plan that offers special cashback or discounts if the emotional state is negative.

[1440] Step 5:

[1441] The server uses email sending software to notify the customer of the best plan.

[1442] Input: Optimal plan

[1443] Output: Notification email

[1444] What happens: The email sending software (e.g. smtplib and email.mime.text) generates an email containing the best offer and sends it to the customer's email address.

[1445] In this way, it becomes possible to provide an optimal plan that takes into account the emotional state of the user, thereby improving customer satisfaction.

[1446] 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.

[1447] 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> ) 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.

[1448] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1449] 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.

[1450] [Third embodiment]

[1451] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1452] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1453] 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).

[1454] 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.

[1455] 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.

[1456] 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).

[1457] 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.

[1458] 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.

[1459] 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.

[1460] 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.

[1461] 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.

[1462] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1463] "Example 1"

[1464] As a first embodiment of the present invention, a system for acquiring data through a telecommunications carrier's network can be considered as a means for measuring customer's mobile phone call duration and communication volume in real time. This system acquires data on call duration and communication volume in real time from the telecommunications carrier's network and calculates the optimal plan based on that data.

[1465] "Example 2"

[1466] In Example 2, a system that uses an algorithm to analyze call duration and communication volume patterns can be considered as a means of providing the optimal plan. This system uses a machine learning algorithm to analyze the customer's call and communication patterns based on the acquired call duration and communication volume data, and provides a plan optimized for those patterns.

[1467] "Example 3"

[1468] As a third example, a system that notifies customers of the optimal plan proposal can be considered as a means of providing a service to increase customer satisfaction. This system notifies the customer of the calculated optimal plan and clearly indicates that the customer can save on communication costs by switching to that plan. This can increase customer satisfaction.

[1469] The processing flow of each embodiment will be described below.

[1470] "Example 1"

[1471] Step 1: Obtain real-time customer mobile call duration and traffic data from the carrier's network.

[1472] Step 2: Based on the data obtained, calculate the optimal plan based on the customer's call time and data volume.

[1473] Step 3: Offer the calculated optimal plan to the customer.

[1474] "Example 2"

[1475] Step 1: Obtain real-time customer mobile call duration and traffic data from the carrier's network.

[1476] Step 2: Based on the acquired data, machine learning algorithms are used to analyze customer call and communication patterns.

[1477] Step 3: Based on the analysis results, provide the customer with a plan optimized for that pattern. "Example 3"

[1478] Step 1: Obtain real-time customer mobile call duration and traffic data from the carrier's network.

[1479] Step 2: Based on the data obtained, calculate the optimal plan based on the customer's call time and data volume.

[1480] Step 3: Notify the customer of the optimal plan and clearly indicate that they can save on communication costs by switching to that plan.

[1481] Example 1

[1482] Next, a description will be given of Example 1 of Form 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."

[1483] With traditional communication plans, it was difficult to provide optimal plans based on the customer's call time and data volume. In particular, because real-time data acquisition and analysis were not performed, it was not possible to provide plans optimized for the customer's usage patterns. In addition, the provision of services to improve customer satisfaction was insufficient.

[1484] 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.

[1485] In this invention, the server includes means for connecting to a communication network and measuring customer call time in real time, means for connecting to the communication network and measuring customer communication volume in real time, means for storing measured call time and communication volume data in a database, means for performing data calculations based on the stored data, means for calculating an optimal plan based on the results of the data calculations, and means for notifying the customer's terminal of the calculated optimal plan, thereby making it possible to provide an optimal plan in real time based on the customer's usage pattern.

[1486] A "communications network" is an infrastructure for data communication, including the Internet and mobile phone networks.

[1487] "Airtime" refers to the total amount of time a customer spends making or receiving phone calls.

[1488] "Communication volume" refers to the total amount of data used by the customer when conducting data communication.

[1489] "Real-time" means that data is processed immediately at the moment it is generated.

[1490] A "database" refers to a system for efficiently storing, managing, and retrieving data.

[1491] "Data calculation" refers to the process of performing calculations and analysis based on acquired data.

[1492] "Optimal plan" refers to the most suitable telecommunications service plan based on the customer's call time and data volume.

[1493] A "machine learning model" refers to an algorithm or system that learns from data and makes predictions and classifications.

[1494] "Terminal" means a device used by a customer, including a smartphone, tablet, etc.

[1495] "Notification" refers to the act of sending information from a server to a customer's terminal.

[1496] MODE FOR CARRYING OUT THE INVENTION

[1497] This invention is a system that measures the call duration and traffic volume of customers in real time through a communication network and calculates the optimal plan based on that data. A specific embodiment of this system will be described below.

[1498] Hardware and software used

[1499] The server uses the following hardware and software to connect to a communication network, acquire data, store it in a database, and perform data calculations. Specifically, the server uses the following hardware and software:

[1500] Hardware: High-performance servers

[1501] software:

[1502] Database management systems (e.g., MySQL, PostgreSQL)

[1503] Programming language (e.g. Python, R)

[1504] Machine learning libraries (e.g., scikit-learn, TensorFlow)

[1505] Telecommunications carrier API (e.g., general telecommunications carrier API)

[1506] Data Acquisition and Storage

[1507] The server uses the carrier's API to obtain customer call duration and communication volume data in real time. The obtained data is stored in a database. For example, an INSERT query is executed on a MySQL database to store customer call duration and communication volume data.

[1508] Data calculation and analysis

[1509] The server performs data calculations based on the stored data. Specifically, it uses the Python pandas library to calculate the average call duration and data usage for each customer. It also uses machine learning models to predict the optimal plan for each customer. For example, it uses the scikit-learn library to calculate the optimal plan based on the customer's usage patterns.

[1510] Notification of the best plan

[1511] The server notifies the customer's device of the calculated optimal plan, for example by sending a push notification using Firebase Cloud Messaging (FCM) to propose the optimal plan to the customer.

[1512] Specific examples

[1513] User A uses 1,000 minutes of talk time and 5 GB of data communication per month. The server obtains User A's talk time and data volume data in real time through the telecommunications carrier's API. Based on the obtained data, the server calculates the optimal plan for User A. For example, the server proposes to User A a plan that includes 1,000 minutes of talk time and 5 GB of data communication per month.

[1514] Prompt Sentence Examples

[1515] "Please obtain real-time data on user A's call duration and data volume and calculate the optimal plan."

[1516] In this way, the server acquires data through the communication network, stores it in a database, performs data calculations, calculates the optimal plan, and finally notifies the user's terminal of the results.

[1517] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1518] Step 1:

[1519] The server connects to the carrier's API.

[1520] Input: Your carrier's API endpoint URL and authentication information.

[1521] Specific operation: The server sends an HTTP GET request to the carrier's API endpoint to obtain an authentication token. For example, send a request to https: / / api.carrier.com / v1 / auth.

[1522] Output: An authentication token.

[1523] Step 2:

[1524] The server collects customer call duration and traffic data.

[1525] Input: Authentication token and customer identification information.

[1526] Specific operation: The server uses the obtained authentication token to request the customer's call time and traffic data from the carrier's API, for example, by sending a GET request to https: / / api.carrier.com / v1 / user / data.

[1527] Output: Customer call duration and traffic data.

[1528] Step 3:

[1529] The server saves the retrieved data in the database.

[1530] Input: Customer call duration and volume data.

[1531] What happens: The server stores the retrieved data in a MySQL database, for example by executing the following SQL query:

[1532] sql

[1533] INSERT INTO user_data (user_id, call_time, data_usage) VALUES ('userA', 1000, 5);

[1534] Output: Data stored in a database.

[1535] Step 4:

[1536] The server performs data calculations based on the stored data.

[1537] Input: Customer call duration and volume data stored in a database.

[1538] What happens: The server uses the Python pandas library to calculate the average call duration and traffic volume for each customer. For example, it runs the following code:

[1539] python

[1540] import pandas as pd

[1541] data = pd.read_sql('SELECT FROM user_data WHERE user_id="userA"', connection)

[1542] average_call_time = data['call_time'].mean()

[1543] average_data_usage = data['data_usage'].mean()

[1544] Output: Average customer call duration and volume.

[1545] Step 5:

[1546] The server calculates the optimal plan based on the results of the data calculation.

[1547] Input: Average customer call duration and volume.

[1548] What it does: The server uses the scikit-learn library to predict the best plan for the customer using a machine learning model. For example, it runs the following code:

[1549] python

[1550] from sklearn.linear_model import LinearRegression

[1551] model = LinearRegression()

[1552] model.fit(X_train, y_train)

[1553] optimal_plan = model.predict([[average_call_time, average_data_usage]])

[1554] Output: The optimal plan.

[1555] Step 6:

[1556] The server notifies the customer's device of the optimal plan.

[1557] Input: Best plan and customer device information.

[1558] What happens: The server uses Firebase Cloud Messaging (FCM) to send a push notification to recommend the best plan for the customer. For example, it executes the following code:

[1559] python

[1560] import firebase_admin

[1561] from firebase_admin import messaging

[1562] message = messaging.Message(

[1563] notification=messaging.Notification(

[1564] title='Optimal plan proposal',

[1565] body=f'The best plan for you is {optimal_plan}.'

[1566] ),

[1567] token=userA_device_token,

[1568] )

[1569] response = messaging.send(message)

[1570] Output: Push notification sent to customer's device.

[1571] (Application example 1)

[1572] Next, a description will be given of Application Example 1 of Form 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."

[1573] With modern telecommunications services, it is difficult for customers to select the optimal plan based on their call time and data volume. Furthermore, the procedures for changing plans and purchasing additional data are complicated, which is a factor in reducing customer satisfaction. Furthermore, the lack of real-time data collection and analysis makes it difficult to offer the optimal plan to customers. To solve these issues, a system is needed that measures customers' call time and data volume in real time, provides the optimal plan, and allows them to easily change plans and purchase additional data in conjunction with electronic payment services.

[1574] 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.

[1575] In this invention, the server includes means for measuring the call time of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for providing an optimal plan based on the measured call time and communication volume, and means for the means for providing the optimal plan to change plans or purchase additional data in cooperation with an electronic payment service. This allows the customer to be offered an optimal plan in real time based on their call time and communication volume, and to easily change plans or purchase additional data.

[1576] "Customer" means any person or entity that uses the telecommunications services.

[1577] "Mobile" refers to mobile communication devices such as mobile phones and smartphones.

[1578] "Talk Time" refers to the cumulative time during which a Customer makes voice calls using a mobile phone.

[1579] "Data volume" refers to the total amount of data sent and received by a customer using their mobile phone.

[1580] "Real-time" means that data is processed and analyzed immediately at the moment it is generated.

[1581] "Means for measuring" refers to a combination of hardware and software for measuring call duration and traffic.

[1582] The "optimal plan" refers to the communications service plan that offers the best cost performance and convenience based on the customer's call time and data volume.

[1583] "Means of provision" refers to the systems and methods for presenting the optimal plan to customers.

[1584] "Electronic payment services" refers to financial transaction services conducted via the Internet.

[1585] "Plan change" refers to switching from your current communications service plan to another plan.

[1586] "Additional data purchase" refers to purchasing additional data capacity in addition to an existing communication plan.

[1587] "Collaboration" refers to different systems and services working together.

[1588] The following system configuration will be described as an embodiment of the present invention.

[1589] System Configuration

[1590] 1. Hardware Configuration

[1591] Server: A server is used that connects to the carrier's network to obtain customer call time and data volume in real time. This server collects and analyzes data, calculates optimal plans, and connects with electronic payment services.

[1592] Terminal: Refers to a mobile communication terminal such as a mobile phone or smartphone used by a customer. These terminals communicate with the server and send and receive data in real time.

[1593] 2. Software Configuration

[1594] Data acquisition module: This module uses the carrier's API to acquire customer call duration and data volume in real time. It uses the Python requests library to acquire data from the API.

[1595] Data analysis module: This module analyzes customer call duration and data usage patterns based on the acquired data and calculates the optimal plan. Data analysis uses Python's pandas and numpy libraries.

[1596] Plan offering module: This module presents the most suitable plan to the customer. It displays the plan details to the customer through the user interface.

[1597] Electronic payment module: This module uses the API of the electronic payment service to change plans and purchase additional data. It calls the payment API using the Python requests library.

[1598] Processing flow

[1599] 1. Data Acquisition

[1600] The server retrieves customer call duration and traffic data in real time through the carrier's API, which is securely retrieved using the customer's authentication information.

[1601] 2. Data analysis

[1602] The server analyzes the acquired data to understand the customer's call duration and data volume patterns, and then calculates the optimal communication plan for the customer.

[1603] 3. Plan Offering

[1604] The server then notifies the customer of the optimal plan it has calculated, and the customer can check the plan details through a smartphone application.

[1605] 4. Electronic Payments

[1606] When a customer wishes to change their plan or purchase additional data, the server calls the API of the electronic payment service to execute the payment, allowing customers to easily change their plan or purchase additional data.

[1607] Specific examples

[1608] For example, if a customer uses more than 1,000 minutes of calls and 10GB of data per month, the server will suggest the "Premium Plan." This suggestion will be sent to the customer's smartphone, and the customer can check the plan details through the application. Furthermore, if the customer wants to change to the "Premium Plan," the server will execute the plan change through an electronic payment service.

[1609] Prompt Sentence Examples

[1610] "You will develop an application that monitors the user's call time and data usage in real time and proposes the optimal data plan. The application will obtain user data from the carrier's API and calculate the optimal plan. It will also use the API of an electronic payment service to change plans and purchase additional data."

[1611] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1612] Step 1:

[1613] The server obtains customer call duration and traffic data in real time through the carrier's API. The input is customer authentication information, and the output is call duration and traffic data. Specifically, it uses the Python requests library to send requests to the API endpoint and receives data in JSON format.

[1614] Step 2:

[1615] The server analyzes the acquired call duration and communication volume data. The input is the data acquired in step 1, and the output is the customer's call duration and communication volume patterns. Specifically, it processes the data using Python's pandas and numpy libraries to extract customer usage patterns.

[1616] Step 3:

[1617] The server calculates the optimal communication plan based on the analysis results. The input is the usage pattern obtained in step 2, and the output is a proposal for the optimal plan. Specifically, it compares the customer's usage pattern with the pre-set plan conditions and selects the most suitable plan.

[1618] Step 4:

[1619] The server notifies the customer's device of the calculated optimal plan. The input is the optimal plan calculated in step 3, and the output is the plan information displayed on the customer's device. Specifically, push notifications or in-app notifications are used to inform the customer of the plan details.

[1620] Step 5:

[1621] When a user wishes to change their plan or purchase additional data, they send a request from their device to the server. The input is the user's request to change their plan or purchase additional data, and the output is the request data sent to the server. Specifically, the user makes a selection through the application interface, and that information is sent to the server.

[1622] Step 6:

[1623] The server calls the API of the electronic payment service to change the plan or purchase additional data. The input is the request data received in step 5, and the output is confirmation data that the payment has been completed. Specifically, the server uses the Python requests library to send a request to the payment API and receive the payment result.

[1624] Step 7:

[1625] The server notifies the customer's device of the payment completion confirmation data. The input is the payment completion confirmation data obtained in step 6, and the output is a payment completion notification that is displayed on the customer's device. Specifically, the server notifies the customer of the payment completion information using a push notification or in-app notification.

[1626] Example 2

[1627] Next, a description will be given of Example 2 of Form 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."

[1628] With conventional communication plans, it was difficult to provide the optimal plan based on the customer's call time and data volume, making it difficult to find a plan that suited the customer's usage pattern. In addition, the provision of services to improve customer satisfaction was insufficient.

[1629] 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.

[1630] In this invention, the server includes means for measuring the call duration of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for storing the measured call duration and communication volume in a database, means for preprocessing the stored data, means for analyzing call and communication patterns using a machine learning algorithm based on the preprocessed data, and means for providing an optimal plan based on the analysis results, thereby making it possible to provide a communication plan optimized for the customer's usage pattern and improving customer satisfaction.

[1631] "Means for measuring customer mobile phone call duration in real time" refers to a device or software for instantly measuring the duration of calls made by customers on their mobile phones and obtaining that data.

[1632] "Means for measuring customer mobile phone traffic in real time" refers to a device or software that instantly measures the amount of data traffic used by a customer on their mobile phone and obtains that data.

[1633] The "means for storing the measured call duration and communication volume in a database" refers to a device or software for storing the acquired call duration and communication volume data in a database so that it can be used later.

[1634] "Means for preprocessing stored data" refers to devices or software that perform processes such as filling in missing values ​​and removing outliers in order to prepare data stored in a database in a form that is easier to analyze.

[1635] "Means for analyzing call and communication patterns using machine learning algorithms based on preprocessed data" means devices or software that use preprocessed data as input and machine learning algorithms to analyze customers' call and communication usage patterns.

[1636] The "means for providing the optimal plan based on the analysis results" refers to a device or software that proposes the optimal communication plan to a customer based on the analysis results of a machine learning algorithm.

[1637] The present invention is a system that collects data on customer call duration and communication volume, and uses a machine learning algorithm to provide optimal communication plans. Specific embodiments of this system will be described below.

[1638] First, the server collects data by measuring the customer's mobile phone call duration and the customer's mobile phone data usage in real time. These methods are realized using the telecommunications carrier's API. For example, a request is sent to the telecommunications carrier's API endpoint and JSON format data is received as a response.

[1639] The server then stores the collected data in a database, typically a relational database such as MySQL or PostgreSQL. The stored data includes user IDs, call duration, communication volume, and collection date and time.

[1640] The server then preprocesses the stored data. Specifically, it imputes missing values ​​and removes outliers. It uses the Python Pandas library to clean the data. For example, it executes the following code to impute missing values:

[1641] The server then uses machine learning algorithms to analyze users' call and communication patterns based on the preprocessed data. Specifically, it uses a clustering algorithm (e.g., K-means clustering) to classify users into several groups. The clustering is performed using the Scikit-learn library.

[1642] Finally, the server proposes the optimal communication plan for the user based on the analysis results. The proposed plan is notified to the user's device. For example, if the user has a long call duration and a low data volume, an unlimited call plan is proposed.

[1643] As a concrete example, consider the call time and data volume data of User A. User A makes a total of 300 minutes of calls per month and uses 5GB of data. Based on this data, the server analyzes User A's call and communication patterns. As a result of the analysis, it is determined that an unlimited call plan and 5GB data plan is optimal for User A.

[1644] Examples of prompts to be input to a generative AI model include:

[1645] "User A has 300 minutes of talk time and 5GB of data usage per month. Please suggest the best data plan for this user."

[1646] By inputting this prompt into the generative AI model, the AI ​​will suggest the optimal communication plan for User A.

[1647] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1648] Step 1:

[1649] The server collects data by measuring the customer's mobile phone call duration in real time and the customer's mobile phone data traffic in real time. Specifically, it calls the telecommunications carrier's API to obtain data on the user's call duration and data traffic. The input is the response data from the telecommunications carrier's API endpoint, and the output is data on the call duration and data traffic.

[1650] Step 2:

[1651] The server stores the collected data in a database. Specifically, it uses a relational database such as MySQL or PostgreSQL to store the acquired call duration and communication volume data. The input is the call duration and communication volume data acquired in step 1, and the output is the data stored in the database.

[1652] Step 3:

[1653] The server preprocesses the stored data. Specifically, it imputes missing values ​​and removes outliers. It uses the Python Pandas library to clean the data. The input is the raw data stored in the database, and the output is the preprocessed, clean data.

[1654] Step 4:

[1655] The server uses a machine learning algorithm to analyze users' call and communication patterns based on the preprocessed data. Specifically, it uses the Scikit-learn library to perform K-means clustering and classify users into several groups. The input is the preprocessed data, and the output is the clustering results.

[1656] Step 5:

[1657] The server proposes the optimal communication plan to the user based on the analysis results. Specifically, it analyzes the clustering results and determines the optimal plan for each cluster. The proposed plan is notified to the user's device. The input is the clustering results, and the output is the optimal communication plan proposed to the user.

[1658] Step 6:

[1659] The user receives the proposed communication plan from the server and changes the plan as needed. Specifically, the user checks the plan notified on the user's device and changes the plan through the carrier's website or app. The input is the proposed plan from the server, and the output is the new communication plan selected by the user.

[1660] (Application example 2)

[1661] Next, a description will be given of Application Example 2 of Form 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."

[1662] While the conventional system can provide optimal plans based on the customer's call time and data volume, it has the problem of not being able to provide optimal payment plans that take into account the usage patterns of electronic payments. There was also the problem of insufficient service provision to improve customer satisfaction.

[1663] 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.

[1664] In this invention, the server includes means for measuring the call duration of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for providing an optimal plan based on the measured call duration and communication volume, means for analyzing the customer's electronic payment usage patterns, and means for providing an optimal payment plan based on the analysis results. This makes it possible to comprehensively analyze the customer's call and communication patterns and electronic payment usage patterns and provide an optimal plan.

[1665] "Airtime" refers to the total time a customer makes calls using a mobile phone.

[1666] "Communication volume" refers to the total volume of data transmitted by a customer using a mobile phone.

[1667] "Optimal Plan" refers to the service plan that is most economical and convenient for the Customer based on the Customer's call duration and communication volume patterns.

[1668] "Electronic payment" refers to the act of a customer paying for goods or services by electronic means.

[1669] "Usage patterns" refers to the frequency or tendency of a customer to use a particular service or feature.

[1670] "Analytical tools" refers to algorithms or software that are used to identify patterns or trends based on collected data.

[1671] "Means of provision" refers to methods and systems for presenting optimal plans and services to customers based on the analysis results.

[1672] The system for implementing this invention measures the call time and communication volume of a customer's mobile phone in real time, and further analyzes the customer's electronic payment usage patterns to provide the optimal plan. A specific embodiment of this system will be described below.

[1673] System configuration

[1674] The system consists of the following main components:

[1675] 1. Call duration measurement means: Measure the call duration of customers' mobile phones in real time.

[1676] 2. Data traffic measurement method: Measures data traffic on customers' mobile phones in real time.

[1677] 3. Data collection server: collects and stores call duration and traffic data.

[1678] 4. Analysis Server: Based on the collected data, machine learning algorithms are used to analyze customer usage patterns.

[1679] 5. Plan provision server: Based on the analysis results, it provides the optimal plan to the customer.

[1680] 6. Means of analyzing electronic payment usage patterns: Analyze customers' electronic payment usage patterns.

[1681] 7. Payment plan offering method: Based on the analysis results, the optimal payment plan is offered.

[1682] Hardware and software used

[1683] Hardware: Smartphones, servers

[1684] Software: Python, Pandas, Scikit-learn

[1685] Data processing and calculation

[1686] 1. Data collection: Call duration and communication volume data are collected in real time from smartphones and sent to a data collection server.

[1687] 2. Data preprocessing: The collected data is standardized and sent to the analysis server.

[1688] 3. Applying machine learning algorithms: The analytics server uses machine learning algorithms (e.g., KMeans clustering) to analyze customer usage patterns.

[1689] 4. Proposing the optimal plan: Based on the analysis results, the plan providing server proposes the optimal plan to the customer.

[1690] 5. Analysis of electronic payment usage patterns: Analyze the usage patterns of electronic payments and provide optimal payment plans.

[1691] Specific examples

[1692] For example, if User A makes more than 20 payments per month and primarily uses the service in urban areas, the "high-frequency user plan" will be offered to this user. On the other hand, User B makes around 10 payments per month and primarily uses the service in suburban areas. The "medium-frequency user plan" will be offered to this user.

[1693] Prompt Sentence Examples

[1694] I want to develop an application that proposes optimal payment plans based on users' payment history data. Using the following data, please generate Python code that clusters users and proposes the optimal plan for each cluster.

[1695] Data items:

[1696] transaction_amount: Payment amount

[1697] transaction_frequency: Transaction frequency

[1698] location: Location of use

[1699] output:

[1700] suggested_plan: The proposed plan

[1701] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1702] Step 1:

[1703] Data collection

[1704] The device (smartphone) measures the customer's call duration and communication volume data in real time and sends this data to a data collection server. The input is the call duration and communication volume data, and the output is the measurement data sent to the data collection server.

[1705] Step 2:

[1706] Data Preprocessing

[1707] The server standardizes the collected call duration and traffic data. Specifically, it reads the data using the Pandas library and standardizes the data using StandardScaler. The input is the collected raw data, and the output is the standardized data.

[1708] Step 3:

[1709] Applying machine learning algorithms

[1710] The server applies a machine learning algorithm (KMeans clustering) to the standardized data. Specifically, it performs clustering using the Scikit-learn library to analyze customer usage patterns. The input is the standardized data, and the output is the clustering results.

[1711] Step 4:

[1712] Proposing the optimal plan

[1713] The server proposes the optimal plan to the customer based on the clustering results. Specifically, it determines the optimal plan for each cluster and notifies the customer. The input is the clustering results, and the output is the proposed optimal plan.

[1714] Step 5:

[1715] Analysis of electronic payment usage patterns

[1716] The server analyzes the customer's electronic payment usage patterns. Specifically, it collects payment history data and analyzes the usage patterns using machine learning algorithms. The input is the payment history data, and the output is the analysis results of the usage patterns.

[1717] Step 6:

[1718] Offering payment plans

[1719] The server provides optimal payment plans based on the results of analyzing electronic payment usage patterns. Specifically, it determines the optimal payment plan for each usage pattern and notifies the customer. The input is the analysis results of usage patterns, and the output is the proposed optimal payment plan.

[1720] Example 3

[1721] Next, a third embodiment of the third embodiment will be described. 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."

[1722] Traditional communication plans were not optimized for customer usage patterns, resulting in customers often paying unnecessary communication fees. It was also difficult for customers to find the plan that best suited them, leading to low satisfaction. Even when systems existed that suggested optimal plans, the notification methods and plan change procedures were complicated, making it difficult for customers to actually change their plans.

[1723] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1724] In this invention, the server includes means for measuring the call time of a customer's communication terminal in real time, means for measuring the data usage of the customer's communication terminal in real time, means for calculating an optimal communication plan based on the measured call time and data usage, means for notifying the customer of the calculated optimal communication plan, and means for the customer to change to the notified communication plan. This allows customers to easily find a communication plan that is optimal for their usage pattern, thereby saving on communication costs and improving customer satisfaction.

[1725] "Call time" is the total time during which a customer makes a call using a communication terminal.

[1726] "Data usage" means the total amount of data consumed by a customer when using a communication device to access the Internet or applications.

[1727] A "communication plan" is a pricing structure for communication services provided by a telecommunications carrier, including talk time, data usage, and number of SMS messages sent.

[1728] "Real-time measurement means" refers to technology that instantly measures the call time and data usage of customers' communication devices and records them in a database.

[1729] The "means for calculating the optimal communication plan" refers to algorithms or software that analyzes a customer's call time and data usage patterns and selects the most cost-effective communication plan based on the results.

[1730] "Means of notification" refers to the method used to notify customers of the calculated optimal communication plan, and includes email, SMS, in-app notifications, etc.

[1731] "Plan change method" means the process or interface through which a customer can change to the notified communications plan, including online portals and customer support.

[1732] MODE FOR CARRYING OUT THE INVENTION

[1733] This invention is a system for reducing customer communication costs and improving customer satisfaction. This system measures the call time and data usage of the customer's communication terminal in real time, calculates the optimal communication plan based on that data, and notifies the customer. It also provides a means for the customer to change to the notified communication plan.

[1734] Data collection

[1735] The server measures the call duration and data usage of the customer's communication device in real time. Specifically, it retrieves data from the carrier's database using an API. The hardware used is a database server (e.g., MySQL, PostgreSQL), and the software used is a data collection script (e.g., Python, Java).

[1736] Data analysis

[1737] The server analyzes the collected data and identifies customer usage patterns. Specifically, it uses machine learning algorithms to analyze customer communication usage trends. The software used is a machine learning library (e.g., TensorFlow, scikit-learn).

[1738] Calculating the optimal plan

[1739] The server then calculates the optimal communication plan for the customer based on the analysis results. Specifically, it compares existing plan information with the customer's usage patterns to select the most cost-effective plan. The software used is an optimization algorithm (e.g., linear programming).

[1740] notification

[1741] The server notifies the customer of the calculated optimal communication plan. Specifically, it sends the proposal to the customer using methods such as email, SMS, and in-app notifications. The software used is a notification system.

[1742] Change plan

[1743] After receiving the notification, the user can change to the proposed plan. Specifically, the change procedure is carried out through an online portal or customer support. The hardware used is the customer's device (e.g., smartphone, PC), and the software used is the carrier's online portal.

[1744] Specific examples

[1745] As a concrete example, by inputting the following prompt sentence into a generative AI model, it is possible to simulate the behavior of a system that proposes the optimal plan for a customer.

[1746] Example prompt sentence:

[1747] Customer A's communication usage data is as follows:

[1748] Talk time: 300 minutes / month

[1749] Data usage: 5GB / month

[1750] Number of SMS sent: 50 / month

[1751] Based on this data, please propose the best communication plan for Customer A.

[1752] In this way, the customer can save on communication costs and improve satisfaction by switching to the most suitable plan. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1753] Step 1: Data collection

[1754] The server measures the call time and data usage of the customer's communication device in real time. Specifically, it obtains data from the communication carrier's database using an API. As input, it uses customer identification information (e.g., customer ID), and as output, it obtains communication usage data such as call time, data usage, and number of SMS sent. For example, it confirms that customer A's call time is 300 minutes, data usage is 5GB, and the number of SMS sent is 50.

[1755] Step 2: Data analysis

[1756] The server analyzes the collected data and identifies the customer's usage patterns. Specifically, it uses a machine learning algorithm to analyze the customer's communication usage trends. The communication usage data collected in step 1 is used as input, and the customer's usage patterns (e.g., high call time, medium data usage, etc.) are obtained as output. For example, it is identified that Customer A has high call time and medium data usage.

[1757] Step 3: Calculate the optimal plan

[1758] The server calculates the optimal communication plan for the customer based on the analysis results. Specifically, it compares existing plan information with the customer's usage patterns and selects the most cost-effective plan. The usage patterns obtained in step 2 and existing plan information are used as input, and the optimal communication plan is obtained as output. For example, it may determine that an unlimited calling plan is optimal.

[1759] Step 4: Notification

[1760] The server notifies the customer of the calculated optimal communication plan. Specifically, it sends the proposal to the customer using methods such as email, SMS, and in-app notifications. The optimal communication plan obtained in step 3 and the customer's contact information are used as input, and a notification message is sent as output. For example, it notifies Customer A by email that "an unlimited calling plan is the best option."

[1761] Step 5: Change your plan

[1762] After receiving the notification, the user can change to the proposed plan. Specifically, the change procedure is carried out through an online portal or customer support. The notification message and the customer's selection are used as input, and confirmation of the plan change is obtained as output. For example, Customer A uses his smartphone to access the carrier's online portal and change to an unlimited calling plan. After the change procedure is completed, the user confirms that the new plan has been applied.

[1763] (Application example 3)

[1764] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1765] While the conventional system could provide optimal plans based on the customer's call time and data volume, it had the problem of not being able to propose optimal payment plans that took into account the customer's payment history and usage patterns. As a result, customers were unable to enjoy optimal plans not only in terms of saving on communication costs, but also in terms of payment fees and point redemption rates, and improvements in customer satisfaction were limited.

[1766] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1767] In this invention, the server includes means for measuring the customer's mobile phone call time in real time, means for measuring the customer's mobile phone communication volume in real time, means for providing an optimal plan based on the measured call time and communication volume, and means for analyzing the customer's payment history and proposing an optimal payment plan. This enables the customer to enjoy an optimal plan not only in terms of saving on communication costs but also in terms of payment fees, point redemption rates, etc.

[1768] "Means for measuring customer mobile phone call duration in real time" refers to a device or software for measuring and recording in real time the duration of calls made by a customer using a mobile phone.

[1769] "Means for measuring customer mobile phone data traffic in real time" refers to a device or software that measures and records in real time the data traffic when a customer uses a mobile phone for data communication.

[1770] "Means for providing the optimal plan based on the measured call time and communication volume" refers to a device or software that analyzes data on call time and communication volume measured in real time and proposes the most suitable communication plan for the customer.

[1771] "Means for analyzing a customer's payment history and proposing the most suitable payment plan" refers to a device or software that analyzes a customer's past payment history data and proposes the most advantageous payment plan for the customer (e.g., credit card, debit card, electronic money, etc.).

[1772] The system for implementing this invention measures the call time and communication volume of a customer's mobile phone in real time, and further analyzes the customer's payment history to propose the optimal plan. A specific embodiment of this system will be described below.

[1773] System configuration

[1774] The system mainly consists of the following hardware and software:

[1775] Hardware: General purpose PC or server

[1776] Software: Python, pandas, scikit-learn, numpy

[1777] Data collection and processing

[1778] The server collects call duration and traffic data from the customer's mobile phone in real time. This is done using an API that works with the mobile phone's communication module. The collected data is then recorded in real time on the server.

[1779] Next, the server collects the customer's payment history data, which is obtained from the payment methods used by the customer (credit cards, debit cards, electronic money, etc.) using the payment provider's API.

[1780] Analyzing the data

[1781] The server analyzes the collected call duration and traffic data and proposes the best communication plan for the customer, which involves the following steps:

[1782] 1. Data Normalization: To normalize the call duration and traffic data, we use Python's StandardScaler.

[1783] 2. Clustering: Use KMeans clustering to analyze customer usage patterns.

[1784] 3. Plan proposal: Propose the optimal communication plan for each cluster.

[1785] Furthermore, the server analyzes the customer's payment history data and proposes the most suitable payment plan, which includes the following steps:

[1786] 1. Data Normalization: Use Python's StandardScaler to normalize payment history data.

[1787] 2. Clustering: Use KMeans clustering to analyze customer payment patterns.

[1788] 3. Plan proposal: Propose the optimal payment plan for each cluster.

[1789] Proposal Notification

[1790] The server then notifies the customer of the optimal communication and payment plan based on the analysis results. Notification is sent via a smartphone app. The customer can then review the proposed plan through the app and change it if necessary.

[1791] Specific examples

[1792] For example, if a customer uses 1,000 minutes of calls and 10GB of data per month, the server collects this data in real time and proposes the optimal communication plan. At the same time, it analyzes the customer's payment history and proposes the optimal payment plan (for example, a credit card with a high reward point rate).

[1793] Prompt Sentence Examples

[1794] Below are some example prompts to input to a generative AI model:

[1795] Develop an application that analyzes users' payment history data and proposes optimal payment plans. Use features such as the user's payment amount, transaction type, transaction time, and day of the week to perform KMeans clustering and propose the optimal payment plan (credit card, debit card, electronic money, etc.) for each cluster. Use Python and its libraries (pandas, scikit-learn, numpy).

[1796] In this way, customers can not only save on communication costs, but also enjoy the best plan in terms of payment fees and point redemption rates.

[1797] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1798] Step 1:

[1799] The server collects call duration and communication volume data from the customer's mobile phone in real time. Specifically, it uses an API that works with the mobile phone's communication module to obtain information such as the call start time, end time, and data communication volume. The input is real-time data from the mobile phone, and the output is call duration and communication volume data that is stored on the server.

[1800] Step 2:

[1801] The server collects the customer's payment history data. To do this, it uses the payment provider's API to obtain data from the payment methods used by the customer (credit cards, debit cards, electronic money, etc.). The input is the payment history data from the payment provider, and the output is the payment history data stored on the server.

[1802] Step 3:

[1803] The server standardizes the collected call duration and traffic data by using Python's StandardScaler to convert each data point to a mean of 0 and a standard deviation of 1. The input is the raw call duration and traffic data, and the output is the standardized data.

[1804] Step 4:

[1805] The server clusters the normalized call duration and traffic data. Specifically, it uses KMeans clustering to analyze customer usage patterns and classify them into multiple clusters. The input is the normalized data, and the output is the label of the cluster to which each data point belongs.

[1806] Step 5:

[1807] The server proposes the optimal communication plan for each cluster. Specifically, it selects the optimal communication plan (for example, an unlimited calling plan for a cluster with a high call duration) based on the usage pattern of each cluster. The input is the cluster label, and the output is the optimal communication plan proposal.

[1808] Step 6:

[1809] The server standardizes the collected payment history data. Specifically, it uses Python's StandardScaler to convert each data point to a mean of 0 and a standard deviation of 1. The input is the raw payment history data, and the output is the standardized data.

[1810] Step 7:

[1811] The server clusters the standardized payment history data. Specifically, it uses KMeans clustering to analyze customer payment patterns and classify them into multiple clusters. The input is the standardized data, and the output is the label of the cluster to which each data point belongs.

[1812] Step 8:

[1813] The server proposes the optimal payment plan for each cluster. Specifically, it selects the optimal payment plan (e.g., a credit card with a high reward point rate) based on the payment patterns of each cluster. The input is the cluster label, and the output is the optimal payment plan proposal.

[1814] Step 9:

[1815] The server notifies the customer of the optimal communication and payment plan based on the analysis results. Specifically, the notification is sent via a smartphone app. The input is the optimal plan proposal, and the output is a notification to the customer. The customer can check the proposed plan through the app and change the plan if necessary.

[1816] 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.

[1817] "Example 1"

[1818] In one embodiment of the present invention, the emotion engine recognizes emotions from the content of a user's call. Specifically, it analyzes characteristics such as the user's voice tone, volume, and speaking rate, and estimates the user's emotional state from these characteristics. Based on this emotional state, an optimal plan is provided. For example, if a user expresses anger, a special plan such as a discount on call charges can be provided to that user, thereby improving user satisfaction.

[1819] "Example 2"

[1820] In another embodiment of the present invention, the emotion engine recognizes emotions not only from the content of a user's calls but also from the content of their communications. Specifically, the emotion engine analyzes the content of text messages and emails sent by the user and infers the user's emotional state from the content. Based on this emotional state, an optimal plan is provided. For example, if a user expresses joy, a special plan with increased data traffic can be provided to that user, thereby improving user satisfaction.

[1821] "Example 3"

[1822] In yet another embodiment of the present invention, the emotion engine recognizes emotions from the content of a user's calls and communications and provides an optimal plan based on the emotions. Specifically, the emotion engine analyzes the content of text messages and emails sent by the user, as well as the tone, volume, and speaking speed of the user's voice, and estimates the user's emotional state from the content. The optimal plan is provided based on this emotional state. For example, if a user expresses sadness, the emotion engine can improve user satisfaction by providing the user with a special plan, such as a discount on call charges.

[1823] The processing flow of each embodiment will be described below.

[1824] "Example 1"

[1825] Step 1: The user initiates a call.

[1826] Step 2: The emotion engine analyzes the user's voice characteristics such as tone, volume, and speaking rate.

[1827] Step 3: The emotion engine infers the user's emotional state from the analysis results.

[1828] Step 4: Provide an optimal plan based on the estimated emotional state.

[1829] "Example 2"

[1830] Step 1: A user initiates a communication.

[1831] Step 2: The emotion engine analyzes the content of the text message or email sent by the user.

[1832] Step 3: The emotion engine infers the user's emotional state from the analysis results.

[1833] Step 4: Provide an optimal plan based on the estimated emotional state.

[1834] "Example 3"

[1835] Step 1: A user initiates a call or communication.

[1836] Step 2: The emotion engine analyzes the content of the text messages and emails sent by the user, as well as the tone of voice, volume, and speaking rate.

[1837] Step 3: The emotion engine infers the user's emotional state from the analysis results.

[1838] Step 4: Provide an optimal plan based on the estimated emotional state.

[1839] Example 1

[1840] Next, a description will be given of Example 1 of Form 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."

[1841] Conventional communication plan provision systems can provide optimal plans based on the customer's call time and data volume, but they have the problem of not being able to provide plans that take into account the customer's emotional state. This makes it difficult to sufficiently improve customer satisfaction and provide flexible plans that meet customer needs.

[1842] 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.

[1843] In this invention, the server includes means for measuring the call time of a customer's mobile phone in real time, means for measuring the communication volume of the customer's mobile phone in real time, means for providing an optimal plan based on the measured call time and communication volume, means for recognizing the emotion of the customer from the content of the call, and means for providing an optimal plan based on the recognized emotion. This makes it possible to provide an optimal plan that takes into account not only the customer's call time and communication volume but also their emotional state, thereby improving customer satisfaction.

[1844] "Means for measuring customer mobile phone call duration in real time" refers to technology that obtains the start and end times of customer calls via a communications network and measures call duration in real time based on that information.

[1845] "Means for measuring customer mobile phone data usage in real time" refers to technology that monitors customer data usage in real time through a communication network and measures data usage based on that information.

[1846] "Means for providing the optimal plan based on measured call time and communication volume" refers to technology that analyzes acquired call time and communication volume data, and calculates and provides the communication plan that is most suitable for the customer's usage pattern.

[1847] The "means for recognizing emotions from the content of a customer's call" is a technology that uses voice recognition technology to analyze the content of a customer's call and estimate the customer's emotional state from characteristics such as tone of voice, volume, and speaking speed.

[1848] "Means for providing optimal plans based on recognized emotions" refers to technology that calculates and provides special communication plans according to the customer's emotional state based on the results of emotion recognition.

[1849] MODE FOR CARRYING OUT THE INVENTION

[1850] This invention is a system that measures the call time and communication volume of a customer's mobile phone in real time and provides the optimal plan based on that data. It also includes a function that recognizes the customer's emotions from the content of the call and provides the optimal plan based on that emotional state.

[1851] The server obtains customer call duration and communication volume data in real time via the communication network. Specifically, it uses the communication carrier's API to collect information such as the start time and end time of the customer's call and the amount of data used during the call. For example, it sends a request to the communication carrier's API endpoint and receives the call data as a response.

[1852] The server then analyzes the data, converting it into a data frame using Python's Pandas library, and calculating the total call duration, average call duration, and total communication volume for each customer, allowing it to identify customer usage patterns.

[1853] The server then uses an emotion engine to recognize emotions from the customer's call. It converts the voice data into text using the Google Cloud Speech-to-Text API, and inputs the text into an emotion analysis model. The emotion analysis model analyzes the customer's voice characteristics, such as tone, volume, and speaking rate, to estimate their emotional state.

[1854] For example, if a user shows anger during a call, the server can offer the user a special plan with a discount on the call charge, thereby improving user satisfaction.

[1855] Examples of specific prompts include:

[1856] "Design a system that recognizes emotions from the content of a user's calls and offers special plans with discounts on call charges if the user expresses anger. Explain how you would obtain real-time call duration and traffic data from a carrier's network and use voice recognition technology to analyze user emotions."

[1857] Using this prompt, the generative AI model can provide a detailed design and implementation method for the system.

[1858] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1859] Step 1:

[1860] The server obtains customer call duration and communication volume data in real time through the carrier's network. As input, it sends a request to the carrier's API endpoint and receives information such as the call start time, end time, and call data volume as a response. This allows the server to collect customer call duration and communication volume data.

[1861] Step 2:

[1862] The server analyzes the acquired call duration and communication volume data. It uses the data acquired in step 1 as input. It converts it into a data frame using Python's Pandas library and calculates the total call duration, average call duration, total communication volume, etc. for each customer. The output is the usage pattern for each customer. Specific operations include grouping and aggregation of the data frame.

[1863] Step 3:

[1864] The server uses an emotion engine to recognize emotions from the customer's call content. It uses the call's audio data as input. It converts the audio data to text using the Google Cloud Speech-to-Text API and inputs the text into a sentiment analysis model. The output is the customer's emotional state. Specific operations include converting the audio data to text and analyzing sentiment.

[1865] Step 4:

[1866] The server calculates the optimal plan for the customer based on the analysis results and emotion recognition results. As input, it uses the usage pattern obtained in step 2 and the emotional state obtained in step 3. If the customer's call time is long, it proposes an unlimited call plan, and if the customer shows anger, it proposes a special plan with discounted call charges. The optimal plan is obtained as output. As a specific operation, it selects the plan using conditional branching.

[1867] Step 5:

[1868] The server provides the calculated optimal plan to the customer. As input, it uses the optimal plan obtained in step 4. It sends a notification to the customer's device and displays details of the optimal plan. As output, it provides the customer with information about the plan. Specific operations include sending a notification and displaying plan details.

[1869] (Application example 1)

[1870] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data p...

Claims

[Claim 1] means for measuring user call duration in real time; means for measuring the traffic volume of the user in real time; means for collecting data indicative of the contents of calls and communications of said users; means for performing pre-processing of the measured call duration and communication volume data to complement missing values ​​and exclude outliers; means for inputting the pre-processed data into a machine learning algorithm to cluster the call duration and communication volume patterns of the user; means for analyzing the collected data indicating the call content and the communication content to estimate the emotional state of the user; a means for generating a prompt sentence according to the clustered patterns and the estimated emotional state of the user, and inputting the prompt sentence into a generation AI model to select a pricing plan; a means for notifying the selected rate plan; A system including:

Images