system

Abstract

The system according to this embodiment aims to automatically apply the optimal plan and options based on the user's usage. [Solution] The system according to the embodiment comprises a communication acquisition unit, a call acquisition unit, an option acquisition unit, a prediction unit, a proposal unit, and an application unit. The communication acquisition unit acquires the user's communication status. The call acquisition unit acquires the user's call status. The option acquisition unit acquires the user's option usage status. The prediction unit predicts the user's usage pattern based on the information acquired by the communication acquisition unit, the call acquisition unit, and the option acquisition unit. The proposal unit proposes plans and options based on the user's usage pattern based on the usage pattern predicted by the prediction unit. The application unit automatically applies the plans and options proposed by the proposal unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult for a user to select an optimal plan based on their own communication, call, and option usage status.

[0005] The system according to the embodiment aims to automatically apply an optimal plan and options based on the usage status of the user.

Means for Solving the Problems

[0006] The system according to the embodiment comprises a communication acquisition unit, a call acquisition unit, an option acquisition unit, a prediction unit, a proposal unit, and an application unit. The communication acquisition unit acquires the user's communication status. The call acquisition unit acquires the user's call status. The option acquisition unit acquires the user's option usage status. The prediction unit predicts the user's usage pattern based on the information acquired by the communication acquisition unit, the call acquisition unit, and the option acquisition unit. The proposal unit proposes plans and options based on the user's usage pattern, based on the usage pattern predicted by the prediction unit. The application unit automatically applies the plans and options proposed by the proposal unit. [Effects of the Invention]

[0007] The system according to this embodiment can automatically apply the optimal plan and options based on the user's usage. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. 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. Also, the database 24 and the communication I / F 26 are 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).

[0019] The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An AI agent system according to an embodiment of the present invention is a system that automatically applies the optimal plan to a mobile phone user of a telecommunications carrier. This system acquires the user's communication status, call status, and option usage status, predicts the user's usage pattern from past usage status, and proposes the optimal plan and options. This proposal is applied automatically or with the user's approval. In addition, the AI ​​responds to additional requests and questions from the user by automatically responding via chat. For example, it acquires detailed information on the user's communication status, call status, and option usage status. For example, it collects information such as how much data the user is using, how long they are making calls, and which optional services they are using. This allows for an accurate understanding of the user's usage status. Next, it predicts the user's usage pattern from past usage status. The AI ​​analyzes the collected data and predicts how the user will use it in the future. For example, it can predict future usage based on past trends in data usage and call time. This allows for the proposal of the optimal plan to the user. Furthermore, it proposes the optimal plan and options. Based on the predicted usage pattern, the AI ​​proposes the optimal communication plan and options to the user. This proposal is applied automatically or with the user's approval. For example, if a user uses a lot of data, the system will suggest a plan with a larger data allowance, and if the user approves, that plan will be applied. Furthermore, the AI ​​will automatically respond to any additional requests or questions from the user via chat. For instance, if a user asks, "How much data have I used this month?", the AI ​​can automatically provide an answer. This allows users to obtain information quickly. This system automatically applies the optimal plan based on the user's needs and usage, improving user satisfaction. Additionally, because the AI ​​handles everything automatically, it can be operated efficiently without requiring additional personnel. The AI ​​agent system acquires the user's communication status, call status, and option usage, predicts usage patterns, and automatically suggests and applies the optimal plan and options.

[0029] The AI ​​agent system according to this embodiment includes a communication acquisition unit, a call acquisition unit, an option acquisition unit, a prediction unit, a proposal unit, and an application unit. The communication acquisition unit acquires the user's communication status. The communication acquisition unit can collect information such as the user's data communication volume, communication speed, and communication quality. The communication acquisition unit can, for example, monitor the user's data communication volume in real time and evaluate the communication speed and communication quality. The communication acquisition unit can, for example, periodically record the user's communication status and analyze past communication data. The call acquisition unit acquires the user's call status. The call acquisition unit can collect information such as the user's call duration, call frequency, and call quality. The call acquisition unit can, for example, monitor the user's call duration in real time and evaluate the call quality. The call acquisition unit can, for example, periodically record the user's call status and analyze past call data. The option acquisition unit acquires the user's option usage status. The option acquisition unit can, for example, collect information such as the type of options the user is using, their usage frequency, and usage time. The option acquisition unit can, for example, monitor the user's option usage in real time and evaluate usage frequency and duration. The option acquisition unit can, for example, periodically record the user's option usage and analyze past option usage data. The prediction unit predicts the user's usage patterns based on the information acquired by the communication acquisition unit, call acquisition unit, and option acquisition unit. The prediction unit can, for example, predict future usage based on past trends in data communication volume and call duration. The prediction unit can, for example, analyze the user's usage patterns and predict future communication demand. The prediction unit can, for example, use AI to learn the user's usage patterns and improve prediction accuracy. The proposal unit proposes plans and options based on the user's usage patterns predicted by the prediction unit. For example, if the user's data communication volume is high, the proposal unit can propose a plan for users with high data communication volume. For example, if the user's call duration is long, the proposal unit can propose a plan for users with long call durations.The proposal unit can, for example, propose a plan for users who frequently use options if the user frequently uses options. The application unit automatically applies the plan and options proposed by the proposal unit. The application unit can, for example, apply plans and options approved by the user. The application unit can, for example, apply the optimal plan and options after obtaining user approval. The application unit can, for example, use AI to automatically apply the proposed plan and options. As a result, the AI ​​agent system according to the embodiment can acquire the user's communication status, call status, and option usage status, predict usage patterns, propose the optimal plan and options, and apply them automatically.

[0030] The communication acquisition unit acquires the user's communication status. For example, the communication acquisition unit can collect information such as the user's data traffic, communication speed, and communication quality. Specifically, the communication acquisition unit analyzes data packets transmitted from the user's device and monitors data traffic in real time. This allows for an accurate understanding of how much data the user is using. Regarding communication speed, it measures the data transfer speed between the user's device and the network, and regarding communication quality, it evaluates it using indicators such as packet loss and latency. The communication acquisition unit periodically records this information and can analyze past communication data. For example, it can analyze in detail how much data a user is using during a specific time period, how the communication speed fluctuates, and how stable the communication quality is. This allows the communication acquisition unit to comprehensively understand the user's communication status and use this information to improve and optimize the communication environment. Furthermore, the communication acquisition unit can send the collected data to a cloud server and collaborate with other systems and departments. For example, the data collected by the communication acquisition unit can be made accessible to the forecasting unit and the proposal unit, and used to predict user usage patterns and propose optimal plans. This allows the communication acquisition unit to efficiently and effectively acquire the user's communication status, thereby improving the overall system performance.

[0031] The call acquisition unit acquires the user's call status. For example, it can collect information such as the user's call duration, call frequency, and call quality. Specifically, the call acquisition unit analyzes call data transmitted from the user's device and monitors call duration in real time. This allows for an accurate understanding of how long users spend on calls. Regarding call frequency, it records how often users make calls, and for call quality, it evaluates it using indicators such as voice clarity, latency, and echo. The call acquisition unit can periodically record this information and analyze past call data. For example, it can analyze in detail how much a user makes calls during specific time periods and how call quality fluctuates. This allows the call acquisition unit to comprehensively understand the user's call status and use this information to improve and optimize the call environment. Furthermore, the call acquisition unit can send the collected data to a cloud server and integrate with other systems and departments. For example, the data collected by the call acquisition unit can be made accessible to the forecasting and proposal departments, and used to predict user usage patterns and propose optimal plans. This allows the call acquisition unit to efficiently and effectively acquire the user's call status, thereby improving the overall system performance.

[0032] The option acquisition unit acquires information on users' option usage. For example, it can collect information such as the type of option a user is using, the frequency of use, and the duration of use. Specifically, the option acquisition unit analyzes option usage data transmitted from the user's device and monitors usage in real time. This allows for an accurate understanding of which options users are using and to what extent. In addition, it records how often users use each option, and for usage duration, it records the detailed duration of use for each option. The option acquisition unit periodically records this information and can analyze past option usage data. For example, it can analyze in detail which options users are using and to what extent during specific time periods, and how usage frequency and duration fluctuate. This allows the option acquisition unit to comprehensively understand users' option usage and use this information to improve and optimize options. Furthermore, the option acquisition unit can send the collected data to a cloud server and link it with other systems and departments. For example, the data collected by the option acquisition unit can be made accessible to the forecasting unit and the proposal unit, and used to predict user usage patterns and propose optimal plans. This allows the option acquisition unit to efficiently and effectively acquire the user's option usage status, thereby improving the overall system performance.

[0033] The prediction unit predicts user usage patterns based on information acquired by the communication acquisition unit, call acquisition unit, and option acquisition unit. For example, the prediction unit can predict future usage based on past trends in data traffic and call duration. Specifically, the prediction unit uses AI to analyze past data and learn user usage patterns. The AI ​​uses machine learning algorithms to extract features from the user's past usage data and predict future usage patterns. For example, if a user tends to increase their data traffic during certain time periods, the prediction unit can learn this trend and predict future increases in data traffic. Similarly, regarding call duration, it can predict when users tend to make calls based on past call data. Furthermore, regarding option usage, it can predict which options users will use and to what extent based on past usage data. Based on these prediction results, the prediction unit can gain a detailed understanding of user usage patterns and predict future communication demand. This allows the prediction unit to predict user usage patterns with high accuracy and use this information to propose optimal plans and options. In addition, the prediction unit can continuously revise its prediction results based on real-time updated data to respond to the latest situation. This allows the prediction unit to always provide highly accurate predictions based on the latest information, thereby improving the overall system performance.

[0034] The Proposal Department proposes plans and options based on the user's usage patterns, using the usage patterns predicted by the Forecasting Department. For example, if a user uses a lot of data, the Proposal Department can propose a plan for users with high data usage. Specifically, the Proposal Department selects the most suitable plan and options for the user based on the usage pattern predictions provided by the Forecasting Department. For example, if a user uses a lot of data, the Proposal Department can propose a plan for users with high data usage, thereby reducing communication costs. Also, if a user makes long phone calls, the Proposal Department can propose a plan for users with long phone calls, thereby reducing call charges. Furthermore, if a user frequently uses options, the Proposal Department can propose a plan for users who frequently use options, improving the convenience of option usage. The Proposal Department notifies the user of these proposals and sends instructions to the Application Department if the user approves. The Proposal Department can collect user feedback and continuously improve the accuracy and effectiveness of the proposals. For example, based on the user's experience using the proposed plan, the Proposal Department can review the proposal and propose a more appropriate plan. The Proposal Department can also reliably transmit information using multiple communication methods. For example, it can reliably deliver important information by using not only smartphone notifications but also voice calls, SMS, and email. This allows the proposal department to quickly and reliably propose the most suitable plans and options to users, thereby improving user satisfaction.

[0035] The application unit automatically applies the plans and options proposed by the proposal unit. For example, the application unit can apply plans and options approved by the user. Specifically, the application unit updates the user's account information and applies the new plan and options based on instructions from the proposal unit. The application unit can use AI to automatically apply proposed plans and options. For example, if a user approves a proposed plan, the application unit automatically updates the user's account information and applies the new plan. Options can also be automatically applied if approved by the user. By performing these processes quickly and accurately, the application unit can improve user convenience. Furthermore, the application unit can monitor the effectiveness of the applied plans and options and make adjustments as needed. For example, if the applied plan does not match the user's usage pattern, the application unit will send instructions to the proposal unit again to propose an optimal plan. The application unit can also collect user feedback and continuously improve the accuracy and effectiveness of the applied content. As a result, the application unit can quickly and reliably apply the optimal plan and options to users, improving user satisfaction.

[0036] The proposal unit may include an approval receiving unit that applies the optimal plan and options after obtaining user approval. The proposal unit may, for example, provide an interface for the user to approve the proposed plan and options. The proposal unit may, for example, provide an interface that allows the user to approve by clicking or tapping. The proposal unit may, for example, accept voice approval from the user using speech recognition technology. This allows the application of the optimal plan and options after obtaining user approval.

[0037] The prediction unit can predict future usage based on past trends in data traffic and call duration. For example, the prediction unit can predict future usage based on data traffic and call duration data from the past month. For example, the prediction unit can predict future usage by analyzing trends in data traffic and call duration over the past year. For example, the prediction unit can use AI to learn past trends in data traffic and call duration and improve prediction accuracy. This allows it to predict future usage based on past trends in data traffic and call duration.

[0038] The proposal department can suggest data plans for users with high data usage if their data usage exceeds a certain level. For example, the proposal department can suggest a data plan for users with monthly data usage of 10GB or more. When suggesting a plan for users with high data usage, the proposal department can make suggestions based on the user's past data usage. The proposal department can also use AI to analyze the user's data usage and suggest the optimal plan. This allows the proposal to suggest a plan suitable for users with high data usage.

[0039] The application unit can apply user-approved plans and options. For example, the application unit can automatically apply user-approved plans and options. For example, the application unit can apply the optimal plans and options after obtaining user approval. For example, the application unit can use AI to apply user-approved plans and options. This allows the application of user-approved plans and options.

[0040] The response unit allows the AI ​​to automatically respond to additional requests and questions from users via chat. For example, the AI ​​can automatically answer questions submitted by users via chat. For example, the AI ​​can automatically respond to additional requests sent by users via chat. The response unit can use AI to quickly respond to user questions and requests. This allows the AI ​​to automatically respond to additional requests and questions from users via chat.

[0041] The communication acquisition unit can analyze the user's past communication history and select the optimal acquisition method. For example, the communication acquisition unit can select the optimal acquisition method based on communication patterns frequently used by the user in the past. For example, the communication acquisition unit can select an acquisition timing to avoid congestion based on the user's past communication history. For example, the communication acquisition unit can analyze the user's past communication history and select the most efficient acquisition method. This allows the communication acquisition unit to analyze the user's past communication history and select the optimal acquisition method. Some or all of the above processing in the communication acquisition unit may be performed using AI, for example, or without AI. For example, the communication acquisition unit can input the user's past communication history data into a generating AI and have the generating AI select the optimal acquisition method.

[0042] The communication acquisition unit can filter the communication status data based on the user's current device usage when acquiring it. For example, the communication acquisition unit refrains from acquiring the communication status data if the user is using the device. For example, the communication acquisition unit can acquire detailed communication status data if the user is not using the device. The communication acquisition unit can filter the acquired communication data based on the user's device usage. This allows the communication data to be filtered based on the user's current device usage. Some or all of the above processing in the communication acquisition unit may be performed using AI, for example, or without AI. For example, the communication acquisition unit can input the user's device usage data into a generating AI and have the generating AI perform the filtering.

[0043] The communication acquisition unit can prioritize the acquisition of highly relevant data based on the user's geographical location information when acquiring communication status. For example, if the user is in a specific region, the communication acquisition unit will prioritize the acquisition of communication data related to that region. For example, if the user is on the move, the communication acquisition unit can acquire highly relevant communication data based on the user's current location. For example, the communication acquisition unit can prioritize the acquisition of optimal communication data based on the user's geographical location information. This allows for the priority acquisition of highly relevant communication data while considering the user's geographical location information. Some or all of the above processing in the communication acquisition unit may be performed using AI, for example, or without AI. For example, the communication acquisition unit can input the user's geographical location information data into a generating AI and have the generating AI execute the acquisition of highly relevant data.

[0044] The communication acquisition unit can analyze the user's social media activity and acquire relevant communication data when acquiring communication status. For example, the communication acquisition unit can acquire relevant communication data based on information shared by the user on social media. For example, the communication acquisition unit can prioritize the acquisition of important communication data from the user's social media activity. For example, the communication acquisition unit can analyze the user's social media activity and acquire optimal communication data. This allows for the analysis of the user's social media activity and the acquisition of relevant communication data. Some or all of the above processing in the communication acquisition unit may be performed using AI, for example, or without AI. For example, the communication acquisition unit can input the user's social media activity data into a generating AI and have the generating AI perform the acquisition of relevant communication data.

[0045] The call acquisition unit can analyze the user's past call history and select the optimal acquisition method. For example, the call acquisition unit can select the optimal acquisition method based on call patterns frequently used by the user in the past. For example, the call acquisition unit can select an acquisition timing to avoid congestion based on the user's past call history. For example, the call acquisition unit can analyze the user's past call history and select the most efficient acquisition method. This allows the system to analyze the user's past call history and select the optimal acquisition method. Some or all of the above processing in the call acquisition unit may be performed using AI, for example, or without AI. For example, the call acquisition unit can input the user's past call history data into a generating AI and have the generating AI select the optimal acquisition method.

[0046] The call acquisition unit can filter call status data based on the user's current call pattern. For example, if the user is on a call, the call acquisition unit refrains from acquiring call status data. For example, if the user is not on a call, the call acquisition unit can acquire detailed call status data. The call acquisition unit can filter the acquired call data based on the user's call pattern. This allows the call data to be filtered based on the user's current call pattern. Some or all of the above processing in the call acquisition unit may be performed using AI, for example, or without AI. For example, the call acquisition unit can input the user's call pattern data into a generating AI and have the generating AI perform the filtering.

[0047] The call acquisition unit can prioritize the acquisition of highly relevant data based on the user's geographical location information when acquiring call status. For example, if the user is in a specific region, the call acquisition unit will prioritize the acquisition of call data related to that region. For example, if the user is on the move, the call acquisition unit can acquire highly relevant call data based on the user's current location. For example, the call acquisition unit can prioritize the acquisition of optimal call data based on the user's geographical location information. This allows for the priority acquisition of highly relevant call data while considering the user's geographical location information. Some or all of the above processing in the call acquisition unit may be performed using AI, for example, or without AI. For example, the call acquisition unit can input the user's geographical location information data into a generating AI and have the generating AI perform the acquisition of highly relevant data.

[0048] The call acquisition unit can analyze the user's social media activity and acquire relevant call data when acquiring call status. For example, the call acquisition unit can acquire relevant call data based on information shared by the user on social media. For example, the call acquisition unit can prioritize the acquisition of important call data from the user's social media activity. For example, the call acquisition unit can analyze the user's social media activity and acquire optimal call data. This allows the user's social media activity to be analyzed and relevant call data to be acquired. Some or all of the above processing in the call acquisition unit may be performed using AI, for example, or without AI. For example, the call acquisition unit can input the user's social media activity data into a generating AI and have the generating AI acquire the relevant call data.

[0049] The option acquisition unit can analyze the user's past option usage history and select the optimal acquisition method. For example, the option acquisition unit can select the optimal acquisition method based on option patterns that the user has frequently used in the past. For example, the option acquisition unit can select an acquisition timing to avoid congestion based on the user's past option usage history. For example, the option acquisition unit can analyze the user's past option usage history and select the most efficient acquisition method. This allows the user to analyze their past option usage history and select the optimal acquisition method. Some or all of the above processing in the option acquisition unit may be performed using AI, for example, or without AI. For example, the option acquisition unit can input the user's past option usage history data into a generating AI and have the generating AI select the optimal acquisition method.

[0050] The option acquisition unit can filter the acquired option usage data based on the user's current option usage pattern. For example, if the user is currently using an option, the option acquisition unit refrains from acquiring the option usage data. For example, if the user is not using an option, the option acquisition unit can acquire detailed option usage data. The option acquisition unit can filter the acquired option data based on the user's option usage pattern. This allows the option data to be filtered based on the user's current option usage pattern. Some or all of the above processing in the option acquisition unit may be performed using AI, for example, or without AI. For example, the option acquisition unit can input the user's option usage pattern data into a generating AI and have the generating AI perform the filtering.

[0051] The option acquisition unit can prioritize the acquisition of highly relevant data based on the user's geographical location information when acquiring option usage status. For example, if the user is in a specific region, the option acquisition unit will prioritize the acquisition of option data related to that region. For example, if the user is on the move, the option acquisition unit can acquire highly relevant option data based on the user's current location. For example, the option acquisition unit can prioritize the acquisition of optimal option data based on the user's geographical location information. This allows for the priority acquisition of highly relevant option data while considering the user's geographical location information. Some or all of the above processing in the option acquisition unit may be performed using AI, for example, or without AI. For example, the option acquisition unit can input the user's geographical location information data into a generating AI and have the generating AI execute the acquisition of highly relevant data.

[0052] The option acquisition unit can analyze the user's social media activity and acquire relevant option data when acquiring option usage status. For example, the option acquisition unit can acquire relevant option data based on information shared by the user on social media. For example, the option acquisition unit can prioritize the acquisition of important option data from the user's social media activity. For example, the option acquisition unit can analyze the user's social media activity and acquire optimal option data. This allows the user's social media activity to be analyzed and relevant option data to be acquired. Some or all of the above processing in the option acquisition unit may be performed using AI, for example, or without AI. For example, the option acquisition unit can input the user's social media activity data into a generating AI and have the generating AI acquire the relevant option data.

[0053] The prediction unit can adjust its prediction algorithm by referring to past usage data during prediction. For example, the prediction unit can select the optimal prediction algorithm based on the user's past data communication volume. For example, the prediction unit can adjust its prediction algorithm based on the user's past call duration. For example, the prediction unit can optimize its prediction algorithm based on the user's past option usage history. This allows the prediction algorithm to be optimized by referring to past usage data. Some or all of the above processing in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can input the user's past usage data into a generating AI and have the generating AI perform the adjustment of the prediction algorithm.

[0054] The prediction unit can improve the accuracy of its predictions based on the user's current living situation. For example, the prediction unit can improve the accuracy of its predictions by considering the user's current work situation. For example, the prediction unit can improve the accuracy of its predictions by considering the user's current home situation. For example, the prediction unit can improve the accuracy of its predictions by considering the user's current health condition. This allows the prediction accuracy to be improved based on the user's current living situation. Some or all of the above processing in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can input the user's current living situation data into a generating AI and have the generating AI perform the improvement of the prediction accuracy.

[0055] The prediction unit can improve the accuracy of its predictions based on the user's geographical location information. For example, if the user is in a specific region, the prediction unit can improve the accuracy of its predictions based on data related to that region. For example, if the user is on the move, the prediction unit can improve the accuracy of its predictions based on the user's current location. For example, the prediction unit can provide the optimal prediction result based on the user's geographical location information. This allows for improved prediction accuracy by taking the user's geographical location information into consideration. Some or all of the above-described processes in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can input the user's geographical location information data into a generating AI and have the generating AI perform the improvement of prediction accuracy.

[0056] The prediction unit can analyze the user's social media activity during prediction to improve the accuracy of the prediction. For example, the prediction unit can improve the accuracy of the prediction based on information shared by the user on social media. For example, the prediction unit can extract important data from the user's social media activity to improve the accuracy of the prediction. For example, the prediction unit can analyze the user's social media activity and provide the optimal prediction result. This allows for the analysis of the user's social media activity and improvement of the accuracy of the prediction. Some or all of the above-described processes in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can input the user's social media activity data into a generating AI and have the generating AI perform the task of improving the accuracy of the prediction.

[0057] The proposal unit can adjust the level of detail in a proposal based on the importance of the plan. For example, if the plan is important, the proposal unit will provide a proposal with detailed information. For example, if the plan is of low importance, the proposal unit can provide a simplified proposal. The proposal unit can adjust the level of detail in a proposal according to the importance of the plan. This allows the level of detail in a proposal to be adjusted based on the importance of the plan. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input plan importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in the proposal.

[0058] The proposal unit can apply different proposal algorithms depending on the plan category when making a proposal. For example, in the case of a data communication plan, the proposal unit can apply a proposal algorithm based on data usage. For example, in the case of a voice call plan, the proposal unit can apply a proposal algorithm based on call duration. For example, in the case of an optional service, the proposal unit can apply a proposal algorithm based on the usage status of the optional service. This allows different proposal algorithms to be applied depending on the plan category. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input plan category data into a generating AI and have the generating AI execute the application of the proposal algorithm.

[0059] The proposal department can determine the priority of proposals based on the submission timing of the plans. For example, the proposal department will prioritize urgent plans. For example, the proposal department can set a higher priority for plans submitted early. The proposal department can determine the priority based on the submission timing of the proposals. This allows the proposal department to determine the priority of proposals based on the submission timing of the plans. Some or all of the above processes in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input plan submission timing data into a generating AI and have the generating AI perform the determination of proposal priorities.

[0060] The proposal unit can adjust the order of proposals based on the relevance of the plans when making a proposal. For example, the proposal unit may prioritize proposing plans that are highly relevant. For example, the proposal unit may postpone proposing plans that are less relevant. The proposal unit can adjust the order of proposals based on the relevance of the plans. This allows the order of proposals to be adjusted based on the relevance of the plans. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input plan relevance data into a generating AI and have the generating AI perform the adjustment of the order of proposals.

[0061] The application unit can select an application method by referring to the user's past plan change history at the time of application. For example, the application unit can select the optimal application method based on the plan the user has frequently changed in the past. For example, the application unit can select the optimal application timing from the user's past plan change history. For example, the application unit can analyze the user's past plan change history and select the most efficient application method. This allows the application unit to select the optimal application method by referring to the user's past plan change history. Some or all of the above processing in the application unit may be performed using AI, for example, or without using AI. For example, the application unit can input the user's past plan change history data into a generating AI and have the generating AI perform the selection of the application method.

[0062] The application unit can customize the means of applying the plan based on the user's current living situation at the time of application. For example, the application unit can customize the means of applying the plan considering the user's current work situation. For example, the application unit can customize the means of applying the plan considering the user's current home situation. For example, the application unit can customize the means of applying the plan considering the user's current health condition. This allows the means of applying the plan to be customized based on the user's current living situation. Some or all of the above processing in the application unit may be performed using AI, for example, or without using AI. For example, the application unit can input the user's current living situation data into a generating AI and have the generating AI perform the customization of the means of applying the plan.

[0063] The application unit can select a plan application method based on the user's geographical location information at the time of application. For example, if the user is in a specific region, the application unit will prioritize applying a plan related to that region. For example, if the user is on the move, the application unit can apply the optimal plan based on the user's current location. For example, the application unit can select the optimal plan application method based on the user's geographical location information. This allows the application unit to select the optimal plan application method while considering the user's geographical location information. Some or all of the above processing in the application unit may be performed using AI, for example, or without AI. For example, the application unit can input the user's geographical location information data into a generating AI and have the generating AI perform the selection of the plan application method.

[0064] The application unit can analyze the user's social media activity and propose a plan application method during application. For example, the application unit can propose the optimal plan application method based on information shared by the user on social media. For example, the application unit can prioritize the application of important plans based on the user's social media activity. For example, the application unit can analyze the user's social media activity and propose the optimal plan application method. This allows the application unit to analyze the user's social media activity and propose a plan application method. Some or all of the above processing in the application unit may be performed using AI, for example, or without AI. For example, the application unit can input the user's social media activity data into a generating AI and have the generating AI execute the proposal of a plan application method.

[0065] The approval receiving unit can select an approval method by referring to the user's past approval history when an approval is received. For example, the approval receiving unit can select the optimal approval method based on methods the user has frequently approved in the past. For example, the approval receiving unit can select the optimal approval timing from the user's past approval history. For example, the approval receiving unit can analyze the user's past approval history and select the most efficient approval method. This allows the system to select the optimal approval method by referring to the user's past approval history. Some or all of the above processes in the approval receiving unit may be performed using AI, for example, or without AI. For example, the approval receiving unit can input the user's past approval history data into a generating AI and have the generating AI perform the selection of the approval method.

[0066] The approval receiving unit can select an approval method based on the user's geographical location information when an approval is received. For example, if the user is in a specific region, the approval receiving unit will prioritize approvals related to that region. For example, if the user is on the move, the approval receiving unit can accept the most suitable approval based on the user's current location. For example, the approval receiving unit can select the most suitable approval method based on the user's geographical location information. This allows the system to select the most suitable approval method considering the user's geographical location information. Some or all of the above processing in the approval receiving unit may be performed using AI, for example, or without AI. For example, the approval receiving unit can input the user's geographical location information data into a generating AI and have the generating AI perform the selection of the approval method.

[0067] The response unit can select the optimal response method by referring to the user's past question history when responding. For example, the response unit can select the optimal response method based on the content of questions the user has frequently asked in the past. For example, the response unit can select the optimal response timing from the user's past question history. For example, the response unit can analyze the user's past question history and select the most efficient response method. This allows the response unit to select the optimal response method by referring to the user's past question history. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the user's past question history data into a generating AI and have the generating AI perform the selection of a response method.

[0068] The response unit can select a response method based on the user's geographical location information when responding. For example, if the user is in a specific region, the response unit will prioritize responses related to that region. For example, if the user is on the move, the response unit can provide the optimal response based on the user's current location. For example, the response unit can select the optimal response method based on the user's geographical location information. This allows the response unit to select the optimal response method while considering the user's geographical location information. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the user's geographical location information data into a generating AI and have the generating AI perform the selection of the response method.

[0069] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0070] The communication acquisition unit can adjust the acquisition frequency when acquiring the user's communication status, taking into account the battery level of the user's device. For example, if the battery level is low, the frequency of acquiring communication status can be reduced to conserve battery power. Conversely, if the battery level is sufficient, detailed communication status can be acquired frequently to collect more accurate data. Furthermore, if the user's device is charging, the communication acquisition unit can maximize the frequency of acquiring communication status to improve data collection efficiency. This allows for flexible adjustment of the communication status acquisition frequency according to the battery status of the user's device.

[0071] The call acquisition unit can adjust the content acquired when acquiring a user's call status, taking into account the user's relationship with the person they are calling. For example, in the case of calls with family or friends, detailed call content can be acquired and used for analysis. In the case of calls with business partners, emphasis can be placed on acquiring call frequency and duration. Furthermore, if a user frequently calls a particular person, the call acquisition unit can prioritize acquiring call data with that person and use it to predict usage patterns. In this way, the content acquired regarding call status can be adjusted based on the user's relationship with the person they are calling.

[0072] The option acquisition unit can adjust the acquired data based on the user's application usage when acquiring user option usage data. For example, if a user frequently uses a particular application, the unit can prioritize acquiring option data related to that application. Also, if a user installs a new application, the unit can acquire detailed usage data for that application to aid in analysis. Furthermore, if a user uses a particular application for an extended period, the option acquisition unit can focus on acquiring option data related to that application to help predict usage patterns. In this way, the acquired option usage data can be adjusted based on the user's application usage.

[0073] The communication acquisition unit can adjust its acquisition method when acquiring the user's communication status, taking into account the network connection status of the user's device. For example, if the network connection is unstable, the frequency of acquiring communication status can be reduced to maintain data accuracy. Conversely, if the network connection is stable, detailed communication status can be acquired frequently to collect more accurate data. Furthermore, if the user is connected via Wi-Fi, the communication acquisition unit can maximize the frequency of acquiring communication status to improve data collection efficiency. This allows for flexible adjustment of the communication status acquisition method according to the user's network connection status.

[0074] The option acquisition unit can adjust the acquired data based on the user's device usage when acquiring user option usage data. For example, if a user uses their device frequently, the unit can prioritize acquiring option data related to that usage. Conversely, if a user does not use their device for a long period, the unit can acquire detailed option usage data for analysis. Furthermore, if a user uses a specific application for an extended period, the option acquisition unit can focus on acquiring option data related to that application to help predict usage patterns. This allows the acquisition of option usage data to be adjusted based on the user's device usage.

[0075] The following briefly describes the processing flow for example form 1.

[0076] Step 1: The communication acquisition unit acquires the user's communication status. For example, it collects information such as the user's data traffic, communication speed, and communication quality, monitors it in real time, and evaluates the communication speed and quality. It also periodically records the user's communication status and can analyze past communication data. Step 2: The call acquisition unit acquires the user's call status. For example, it collects information such as the user's call duration, call frequency, and call quality, monitors it in real time, and evaluates the call quality. It also periodically records the user's call status and can analyze past call data. Step 3: The option acquisition unit acquires the user's option usage status. For example, it collects information such as the type of option the user is using, the frequency of use, and the duration of use, monitors it in real time, and evaluates the frequency and duration of use. It also periodically records the user's option usage status and can analyze past option usage data. Step 4: The prediction unit predicts user usage patterns based on information acquired by the communication acquisition unit, call acquisition unit, and option acquisition unit. For example, it predicts future usage based on past trends in data traffic and call duration, analyzes user usage patterns, and predicts future communication demand. Furthermore, AI can be used to learn user usage patterns and improve prediction accuracy. Step 5: The proposal unit proposes plans and options based on the user's usage patterns, using the usage patterns predicted by the forecasting unit. For example, if a user uses a lot of data, it proposes a plan for users with high data usage; if a user makes long calls, it proposes a plan for users who make long calls; and if a user frequently uses options, it proposes a plan for users who frequently use options. Step 6: The application unit automatically applies the plans and options proposed by the proposal unit. For example, it applies the plans and options approved by the user, obtains the user's approval, and then applies the optimal plans and options. Furthermore, AI can be used to automatically apply the proposed plans and options.

[0077] (Example of form 2) An AI agent system according to an embodiment of the present invention is a system that automatically applies the optimal plan to a mobile phone user of a telecommunications carrier. This system acquires the user's communication status, call status, and option usage status, predicts the user's usage pattern from past usage status, and proposes the optimal plan and options. This proposal is applied automatically or with the user's approval. In addition, the AI ​​responds to additional requests and questions from the user by automatically responding via chat. For example, it acquires detailed information on the user's communication status, call status, and option usage status. For example, it collects information such as how much data the user is using, how long they are making calls, and which optional services they are using. This allows for an accurate understanding of the user's usage status. Next, it predicts the user's usage pattern from past usage status. The AI ​​analyzes the collected data and predicts how the user will use it in the future. For example, it can predict future usage based on past trends in data usage and call time. This allows for the proposal of the optimal plan to the user. Furthermore, it proposes the optimal plan and options. Based on the predicted usage pattern, the AI ​​proposes the optimal communication plan and options to the user. This proposal is applied automatically or with the user's approval. For example, if a user uses a lot of data, the system will suggest a plan with a larger data allowance, and if the user approves, that plan will be applied. Furthermore, the AI ​​will automatically respond to any additional requests or questions from the user via chat. For instance, if a user asks, "How much data have I used this month?", the AI ​​can automatically provide an answer. This allows users to obtain information quickly. This system automatically applies the optimal plan based on the user's needs and usage, improving user satisfaction. Additionally, because the AI ​​handles everything automatically, it can be operated efficiently without requiring additional personnel. The AI ​​agent system acquires the user's communication status, call status, and option usage, predicts usage patterns, and automatically suggests and applies the optimal plan and options.

[0078] The AI ​​agent system according to this embodiment includes a communication acquisition unit, a call acquisition unit, an option acquisition unit, a prediction unit, a proposal unit, and an application unit. The communication acquisition unit acquires the user's communication status. The communication acquisition unit can collect information such as the user's data communication volume, communication speed, and communication quality. The communication acquisition unit can, for example, monitor the user's data communication volume in real time and evaluate the communication speed and communication quality. The communication acquisition unit can, for example, periodically record the user's communication status and analyze past communication data. The call acquisition unit acquires the user's call status. The call acquisition unit can collect information such as the user's call duration, call frequency, and call quality. The call acquisition unit can, for example, monitor the user's call duration in real time and evaluate the call quality. The call acquisition unit can, for example, periodically record the user's call status and analyze past call data. The option acquisition unit acquires the user's option usage status. The option acquisition unit can, for example, collect information such as the type of options the user is using, their usage frequency, and usage time. The option acquisition unit can, for example, monitor the user's option usage in real time and evaluate usage frequency and duration. The option acquisition unit can, for example, periodically record the user's option usage and analyze past option usage data. The prediction unit predicts the user's usage patterns based on the information acquired by the communication acquisition unit, call acquisition unit, and option acquisition unit. The prediction unit can, for example, predict future usage based on past trends in data communication volume and call duration. The prediction unit can, for example, analyze the user's usage patterns and predict future communication demand. The prediction unit can, for example, use AI to learn the user's usage patterns and improve prediction accuracy. The proposal unit proposes plans and options based on the user's usage patterns predicted by the prediction unit. For example, if the user's data communication volume is high, the proposal unit can propose a plan for users with high data communication volume. For example, if the user's call duration is long, the proposal unit can propose a plan for users with long call durations.The proposal unit can, for example, propose a plan for users who frequently use options if the user frequently uses options. The application unit automatically applies the plan and options proposed by the proposal unit. The application unit can, for example, apply plans and options approved by the user. The application unit can, for example, apply the optimal plan and options after obtaining user approval. The application unit can, for example, use AI to automatically apply the proposed plan and options. As a result, the AI ​​agent system according to the embodiment can acquire the user's communication status, call status, and option usage status, predict usage patterns, propose the optimal plan and options, and apply them automatically.

[0079] The communication acquisition unit acquires the user's communication status. For example, the communication acquisition unit can collect information such as the user's data traffic, communication speed, and communication quality. Specifically, the communication acquisition unit analyzes data packets transmitted from the user's device and monitors data traffic in real time. This allows for an accurate understanding of how much data the user is using. Regarding communication speed, it measures the data transfer speed between the user's device and the network, and regarding communication quality, it evaluates it using indicators such as packet loss and latency. The communication acquisition unit periodically records this information and can analyze past communication data. For example, it can analyze in detail how much data a user is using during a specific time period, how the communication speed fluctuates, and how stable the communication quality is. This allows the communication acquisition unit to comprehensively understand the user's communication status and use this information to improve and optimize the communication environment. Furthermore, the communication acquisition unit can send the collected data to a cloud server and collaborate with other systems and departments. For example, the data collected by the communication acquisition unit can be made accessible to the forecasting unit and the proposal unit, and used to predict user usage patterns and propose optimal plans. This allows the communication acquisition unit to efficiently and effectively acquire the user's communication status, thereby improving the overall system performance.

[0080] The call acquisition unit acquires the user's call status. For example, it can collect information such as the user's call duration, call frequency, and call quality. Specifically, the call acquisition unit analyzes call data transmitted from the user's device and monitors call duration in real time. This allows for an accurate understanding of how long users spend on calls. Regarding call frequency, it records how often users make calls, and for call quality, it evaluates it using indicators such as voice clarity, latency, and echo. The call acquisition unit can periodically record this information and analyze past call data. For example, it can analyze in detail how much a user makes calls during specific time periods and how call quality fluctuates. This allows the call acquisition unit to comprehensively understand the user's call status and use this information to improve and optimize the call environment. Furthermore, the call acquisition unit can send the collected data to a cloud server and integrate with other systems and departments. For example, the data collected by the call acquisition unit can be made accessible to the forecasting and proposal departments, and used to predict user usage patterns and propose optimal plans. This allows the call acquisition unit to efficiently and effectively acquire the user's call status, thereby improving the overall system performance.

[0081] The option acquisition unit acquires information on users' option usage. For example, it can collect information such as the type of option a user is using, the frequency of use, and the duration of use. Specifically, the option acquisition unit analyzes option usage data transmitted from the user's device and monitors usage in real time. This allows for an accurate understanding of which options users are using and to what extent. In addition, it records how often users use each option, and for usage duration, it records the detailed duration of use for each option. The option acquisition unit periodically records this information and can analyze past option usage data. For example, it can analyze in detail which options users are using and to what extent during specific time periods, and how usage frequency and duration fluctuate. This allows the option acquisition unit to comprehensively understand users' option usage and use this information to improve and optimize options. Furthermore, the option acquisition unit can send the collected data to a cloud server and link it with other systems and departments. For example, the data collected by the option acquisition unit can be made accessible to the forecasting unit and the proposal unit, and used to predict user usage patterns and propose optimal plans. This allows the option acquisition unit to efficiently and effectively acquire the user's option usage status, thereby improving the overall system performance.

[0082] The prediction unit predicts user usage patterns based on information acquired by the communication acquisition unit, call acquisition unit, and option acquisition unit. For example, the prediction unit can predict future usage based on past trends in data traffic and call duration. Specifically, the prediction unit uses AI to analyze past data and learn user usage patterns. The AI ​​uses machine learning algorithms to extract features from the user's past usage data and predict future usage patterns. For example, if a user tends to increase their data traffic during certain time periods, the prediction unit can learn this trend and predict future increases in data traffic. Similarly, regarding call duration, it can predict when users tend to make calls based on past call data. Furthermore, regarding option usage, it can predict which options users will use and to what extent based on past usage data. Based on these prediction results, the prediction unit can gain a detailed understanding of user usage patterns and predict future communication demand. This allows the prediction unit to predict user usage patterns with high accuracy and use this information to propose optimal plans and options. In addition, the prediction unit can continuously revise its prediction results based on real-time updated data to respond to the latest situation. This allows the prediction unit to always provide highly accurate predictions based on the latest information, thereby improving the overall system performance.

[0083] The Proposal Department proposes plans and options based on the user's usage patterns, using the usage patterns predicted by the Forecasting Department. For example, if a user uses a lot of data, the Proposal Department can propose a plan for users with high data usage. Specifically, the Proposal Department selects the most suitable plan and options for the user based on the usage pattern predictions provided by the Forecasting Department. For example, if a user uses a lot of data, the Proposal Department can propose a plan for users with high data usage, thereby reducing communication costs. Also, if a user makes long phone calls, the Proposal Department can propose a plan for users with long phone calls, thereby reducing call charges. Furthermore, if a user frequently uses options, the Proposal Department can propose a plan for users who frequently use options, improving the convenience of option usage. The Proposal Department notifies the user of these proposals and sends instructions to the Application Department if the user approves. The Proposal Department can collect user feedback and continuously improve the accuracy and effectiveness of the proposals. For example, based on the user's experience using the proposed plan, the Proposal Department can review the proposal and propose a more appropriate plan. The Proposal Department can also reliably transmit information using multiple communication methods. For example, it can reliably deliver important information by using not only smartphone notifications but also voice calls, SMS, and email. This allows the proposal department to quickly and reliably propose the most suitable plans and options to users, thereby improving user satisfaction.

[0084] The application unit automatically applies the plans and options proposed by the proposal unit. For example, the application unit can apply plans and options approved by the user. Specifically, the application unit updates the user's account information and applies the new plan and options based on instructions from the proposal unit. The application unit can use AI to automatically apply proposed plans and options. For example, if a user approves a proposed plan, the application unit automatically updates the user's account information and applies the new plan. Options can also be automatically applied if approved by the user. By performing these processes quickly and accurately, the application unit can improve user convenience. Furthermore, the application unit can monitor the effectiveness of the applied plans and options and make adjustments as needed. For example, if the applied plan does not match the user's usage pattern, the application unit will send instructions to the proposal unit again to propose an optimal plan. The application unit can also collect user feedback and continuously improve the accuracy and effectiveness of the applied content. As a result, the application unit can quickly and reliably apply the optimal plan and options to users, improving user satisfaction.

[0085] The proposal unit may include an approval receiving unit that applies the optimal plan and options after obtaining user approval. The proposal unit may, for example, provide an interface for the user to approve the proposed plan and options. The proposal unit may, for example, provide an interface that allows the user to approve by clicking or tapping. The proposal unit may, for example, accept voice approval from the user using speech recognition technology. This allows the application of the optimal plan and options after obtaining user approval.

[0086] The prediction unit can predict future usage based on past trends in data traffic and call duration. For example, the prediction unit can predict future usage based on data traffic and call duration data from the past month. For example, the prediction unit can predict future usage by analyzing trends in data traffic and call duration over the past year. For example, the prediction unit can use AI to learn past trends in data traffic and call duration and improve prediction accuracy. This allows it to predict future usage based on past trends in data traffic and call duration.

[0087] The proposal department can suggest data plans for users with high data usage if their data usage exceeds a certain level. For example, the proposal department can suggest a data plan for users with monthly data usage of 10GB or more. When suggesting a plan for users with high data usage, the proposal department can make suggestions based on the user's past data usage. The proposal department can also use AI to analyze the user's data usage and suggest the optimal plan. This allows the proposal to suggest a plan suitable for users with high data usage.

[0088] The application unit can apply user-approved plans and options. For example, the application unit can automatically apply user-approved plans and options. For example, the application unit can apply the optimal plans and options after obtaining user approval. For example, the application unit can use AI to apply user-approved plans and options. This allows the application of user-approved plans and options.

[0089] The response unit allows the AI ​​to automatically respond to additional requests and questions from users via chat. For example, the AI ​​can automatically answer questions submitted by users via chat. For example, the AI ​​can automatically respond to additional requests sent by users via chat. The response unit can use AI to quickly respond to user questions and requests. This allows the AI ​​to automatically respond to additional requests and questions from users via chat.

[0090] The communication acquisition unit can estimate the user's emotions and adjust the timing of acquiring communication data based on the estimated user emotions. For example, if the user is stressed, the communication acquisition unit can refrain from acquiring communication data and acquire it when the user is relaxed. For example, if the user is relaxed, the communication acquisition unit can acquire detailed communication data and use it for analysis. For example, if the user is in a hurry, the communication acquisition unit can quickly acquire simplified communication data. This allows the timing of acquiring communication data to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the communication acquisition unit may be performed using AI, for example, or without AI. For example, the communication acquisition unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0091] The communication acquisition unit can analyze the user's past communication history and select the optimal acquisition method. For example, the communication acquisition unit can select the optimal acquisition method based on communication patterns frequently used by the user in the past. For example, the communication acquisition unit can select an acquisition timing to avoid congestion based on the user's past communication history. For example, the communication acquisition unit can analyze the user's past communication history and select the most efficient acquisition method. This allows the communication acquisition unit to analyze the user's past communication history and select the optimal acquisition method. Some or all of the above processing in the communication acquisition unit may be performed using AI, for example, or without AI. For example, the communication acquisition unit can input the user's past communication history data into a generating AI and have the generating AI select the optimal acquisition method.

[0092] The communication acquisition unit can filter the communication status data based on the user's current device usage when acquiring it. For example, the communication acquisition unit refrains from acquiring the communication status data if the user is using the device. For example, the communication acquisition unit can acquire detailed communication status data if the user is not using the device. The communication acquisition unit can filter the acquired communication data based on the user's device usage. This allows the communication data to be filtered based on the user's current device usage. Some or all of the above processing in the communication acquisition unit may be performed using AI, for example, or without AI. For example, the communication acquisition unit can input the user's device usage data into a generating AI and have the generating AI perform the filtering.

[0093] The communication acquisition unit can estimate the user's emotions and determine the priority of communication data to acquire based on the estimated user emotions. For example, if the user is stressed, the communication acquisition unit will prioritize acquiring important communication data. For example, if the user is relaxed, the communication acquisition unit can prioritize acquiring detailed communication data. For example, if the user is in a hurry, the communication acquisition unit can prioritize acquiring simplified communication data. This allows the priority of communication data to be determined based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the communication acquisition unit may be performed using AI, for example, or without AI. For example, the communication acquisition unit can input user emotion data into a generative AI and have the generative AI determine the priority of communication data.

[0094] The communication acquisition unit can prioritize the acquisition of highly relevant data based on the user's geographical location information when acquiring communication status. For example, if the user is in a specific region, the communication acquisition unit will prioritize the acquisition of communication data related to that region. For example, if the user is on the move, the communication acquisition unit can acquire highly relevant communication data based on the user's current location. For example, the communication acquisition unit can prioritize the acquisition of optimal communication data based on the user's geographical location information. This allows for the priority acquisition of highly relevant communication data while considering the user's geographical location information. Some or all of the above processing in the communication acquisition unit may be performed using AI, for example, or without AI. For example, the communication acquisition unit can input the user's geographical location information data into a generating AI and have the generating AI execute the acquisition of highly relevant data.

[0095] The communication acquisition unit can analyze the user's social media activity and acquire relevant communication data when acquiring communication status. For example, the communication acquisition unit can acquire relevant communication data based on information shared by the user on social media. For example, the communication acquisition unit can prioritize the acquisition of important communication data from the user's social media activity. For example, the communication acquisition unit can analyze the user's social media activity and acquire optimal communication data. This allows for the analysis of the user's social media activity and the acquisition of relevant communication data. Some or all of the above processing in the communication acquisition unit may be performed using AI, for example, or without AI. For example, the communication acquisition unit can input the user's social media activity data into a generating AI and have the generating AI perform the acquisition of relevant communication data.

[0096] The call acquisition unit can estimate the user's emotions and adjust the timing of acquiring call data based on the estimated emotions. For example, if the user is stressed, the call acquisition unit can refrain from acquiring call data and acquire it when the user is relaxed. For example, if the user is relaxed, the call acquisition unit can acquire detailed call data for analysis. For example, if the user is in a hurry, the call acquisition unit can quickly acquire a simplified call data. This allows the timing of acquiring call data to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the call acquisition unit may be performed using AI or not. For example, the call acquisition unit can input user emotion data into a generative AI and have the generative AI adjust the timing of acquiring call data.

[0097] The call acquisition unit can analyze the user's past call history and select the optimal acquisition method. For example, the call acquisition unit can select the optimal acquisition method based on call patterns frequently used by the user in the past. For example, the call acquisition unit can select an acquisition timing to avoid congestion based on the user's past call history. For example, the call acquisition unit can analyze the user's past call history and select the most efficient acquisition method. This allows the system to analyze the user's past call history and select the optimal acquisition method. Some or all of the above processing in the call acquisition unit may be performed using AI, for example, or without AI. For example, the call acquisition unit can input the user's past call history data into a generating AI and have the generating AI select the optimal acquisition method.

[0098] The call acquisition unit can filter call status data based on the user's current call pattern. For example, if the user is on a call, the call acquisition unit refrains from acquiring call status data. For example, if the user is not on a call, the call acquisition unit can acquire detailed call status data. The call acquisition unit can filter the acquired call data based on the user's call pattern. This allows the call data to be filtered based on the user's current call pattern. Some or all of the above processing in the call acquisition unit may be performed using AI, for example, or without AI. For example, the call acquisition unit can input the user's call pattern data into a generating AI and have the generating AI perform the filtering.

[0099] The call acquisition unit can estimate the user's emotions and determine the priority of call data to acquire based on the estimated user emotions. For example, if the user is stressed, the call acquisition unit can prioritize acquiring important call data. For example, if the user is relaxed, the call acquisition unit can prioritize acquiring detailed call data. For example, if the user is in a hurry, the call acquisition unit can prioritize acquiring simplified call data. This allows the priority of call data to be determined based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the call acquisition unit may be performed using AI or not using AI. For example, the call acquisition unit can input user emotion data into a generative AI and have the generative AI determine the priority of call data.

[0100] The call acquisition unit can prioritize the acquisition of highly relevant data based on the user's geographical location information when acquiring call status. For example, if the user is in a specific region, the call acquisition unit will prioritize the acquisition of call data related to that region. For example, if the user is on the move, the call acquisition unit can acquire highly relevant call data based on the user's current location. For example, the call acquisition unit can prioritize the acquisition of optimal call data based on the user's geographical location information. This allows for the priority acquisition of highly relevant call data while considering the user's geographical location information. Some or all of the above processing in the call acquisition unit may be performed using AI, for example, or without AI. For example, the call acquisition unit can input the user's geographical location information data into a generating AI and have the generating AI perform the acquisition of highly relevant data.

[0101] The call acquisition unit can analyze the user's social media activity and acquire relevant call data when acquiring call status. For example, the call acquisition unit can acquire relevant call data based on information shared by the user on social media. For example, the call acquisition unit can prioritize the acquisition of important call data from the user's social media activity. For example, the call acquisition unit can analyze the user's social media activity and acquire optimal call data. This allows the user's social media activity to be analyzed and relevant call data to be acquired. Some or all of the above processing in the call acquisition unit may be performed using AI, for example, or without AI. For example, the call acquisition unit can input the user's social media activity data into a generating AI and have the generating AI acquire the relevant call data.

[0102] The option acquisition unit can estimate the user's emotions and adjust the timing of acquiring option usage data based on the estimated user emotions. For example, if the user is stressed, the option acquisition unit can refrain from acquiring option usage data and acquire it when the user is relaxed. For example, if the user is relaxed, the option acquisition unit can acquire detailed option usage data and use it for analysis. For example, if the user is in a hurry, the option acquisition unit can quickly acquire simplified option usage data. This allows the timing of acquiring option usage data to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the option acquisition unit may be performed using AI, for example, or without AI. For example, the option acquisition unit can input user emotion data into the generative AI and have the generative AI adjust the timing of acquiring option usage data.

[0103] The option acquisition unit can analyze the user's past option usage history and select the optimal acquisition method. For example, the option acquisition unit can select the optimal acquisition method based on option patterns that the user has frequently used in the past. For example, the option acquisition unit can select an acquisition timing to avoid congestion based on the user's past option usage history. For example, the option acquisition unit can analyze the user's past option usage history and select the most efficient acquisition method. This allows the user to analyze their past option usage history and select the optimal acquisition method. Some or all of the above processing in the option acquisition unit may be performed using AI, for example, or without AI. For example, the option acquisition unit can input the user's past option usage history data into a generating AI and have the generating AI select the optimal acquisition method.

[0104] The option acquisition unit can filter the acquired option usage data based on the user's current option usage pattern. For example, if the user is currently using an option, the option acquisition unit refrains from acquiring the option usage data. For example, if the user is not using an option, the option acquisition unit can acquire detailed option usage data. The option acquisition unit can filter the acquired option data based on the user's option usage pattern. This allows the option data to be filtered based on the user's current option usage pattern. Some or all of the above processing in the option acquisition unit may be performed using AI, for example, or without AI. For example, the option acquisition unit can input the user's option usage pattern data into a generating AI and have the generating AI perform the filtering.

[0105] The option retrieval unit can estimate the user's emotions and determine the priority of option data to retrieve based on the estimated user emotions. For example, if the user is stressed, the option retrieval unit will prioritize retrieving important option data. For example, if the user is relaxed, the option retrieval unit can prioritize retrieving detailed option data. For example, if the user is in a hurry, the option retrieval unit can prioritize retrieving simplified option data. This allows the priority of option data to be determined based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the option retrieval unit may be performed using AI, for example, or not using AI. For example, the option retrieval unit can input user emotion data into a generative AI and have the generative AI determine the priority of option data.

[0106] The option acquisition unit can prioritize the acquisition of highly relevant data based on the user's geographical location information when acquiring option usage status. For example, if the user is in a specific region, the option acquisition unit will prioritize the acquisition of option data related to that region. For example, if the user is on the move, the option acquisition unit can acquire highly relevant option data based on the user's current location. For example, the option acquisition unit can prioritize the acquisition of optimal option data based on the user's geographical location information. This allows for the priority acquisition of highly relevant option data while considering the user's geographical location information. Some or all of the above processing in the option acquisition unit may be performed using AI, for example, or without AI. For example, the option acquisition unit can input the user's geographical location information data into a generating AI and have the generating AI execute the acquisition of highly relevant data.

[0107] The option acquisition unit can analyze the user's social media activity and acquire relevant option data when acquiring option usage status. For example, the option acquisition unit can acquire relevant option data based on information shared by the user on social media. For example, the option acquisition unit can prioritize the acquisition of important option data from the user's social media activity. For example, the option acquisition unit can analyze the user's social media activity and acquire optimal option data. This allows the user's social media activity to be analyzed and relevant option data to be acquired. Some or all of the above processing in the option acquisition unit may be performed using AI, for example, or without AI. For example, the option acquisition unit can input the user's social media activity data into a generating AI and have the generating AI acquire the relevant option data.

[0108] The prediction unit can estimate the user's emotions and adjust the usage pattern prediction method based on the estimated user emotions. For example, if the user is stressed, the prediction unit can use a simple prediction method and refrain from detailed analysis. For example, if the user is relaxed, the prediction unit can use a detailed prediction method to improve accuracy. For example, if the user is in a hurry, the prediction unit can use a rapid prediction method and provide a simplified result. This allows the usage pattern prediction method to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the prediction unit may be performed using AI or not using AI. For example, the prediction unit can input user emotion data into the generative AI and have the generative AI adjust the usage pattern prediction method.

[0109] The prediction unit can adjust its prediction algorithm by referring to past usage data during prediction. For example, the prediction unit can select the optimal prediction algorithm based on the user's past data communication volume. For example, the prediction unit can adjust its prediction algorithm based on the user's past call duration. For example, the prediction unit can optimize its prediction algorithm based on the user's past option usage history. This allows the prediction algorithm to be optimized by referring to past usage data. Some or all of the above processing in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can input the user's past usage data into a generating AI and have the generating AI perform the adjustment of the prediction algorithm.

[0110] The prediction unit can improve the accuracy of its predictions based on the user's current living situation. For example, the prediction unit can improve the accuracy of its predictions by considering the user's current work situation. For example, the prediction unit can improve the accuracy of its predictions by considering the user's current home situation. For example, the prediction unit can improve the accuracy of its predictions by considering the user's current health condition. This allows the prediction accuracy to be improved based on the user's current living situation. Some or all of the above processing in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can input the user's current living situation data into a generating AI and have the generating AI perform the improvement of the prediction accuracy.

[0111] The prediction unit can estimate the user's emotions and adjust the display method of the prediction results based on the estimated user emotions. For example, if the user is nervous, the prediction unit can provide a simple and highly visible display method. For example, if the user is relaxed, the prediction unit can provide a display method that includes detailed information. For example, if the user is in a hurry, the prediction unit can provide a display method that gets straight to the point. This allows the display method of the prediction results to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the prediction unit may be performed using AI, for example, or not using AI. For example, the prediction unit can input user emotion data into the generative AI and have the generative AI adjust the display method of the prediction results.

[0112] The prediction unit can improve the accuracy of its predictions based on the user's geographical location information. For example, if the user is in a specific region, the prediction unit can improve the accuracy of its predictions based on data related to that region. For example, if the user is on the move, the prediction unit can improve the accuracy of its predictions based on the user's current location. For example, the prediction unit can provide the optimal prediction result based on the user's geographical location information. This allows for improved prediction accuracy by taking the user's geographical location information into consideration. Some or all of the above-described processes in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can input the user's geographical location information data into a generating AI and have the generating AI perform the improvement of prediction accuracy.

[0113] The prediction unit can analyze the user's social media activity during prediction to improve the accuracy of the prediction. For example, the prediction unit can improve the accuracy of the prediction based on information shared by the user on social media. For example, the prediction unit can extract important data from the user's social media activity to improve the accuracy of the prediction. For example, the prediction unit can analyze the user's social media activity and provide the optimal prediction result. This allows for the analysis of the user's social media activity and improvement of the accuracy of the prediction. Some or all of the above-described processes in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can input the user's social media activity data into a generating AI and have the generating AI perform the task of improving the accuracy of the prediction.

[0114] The suggestion unit can estimate the user's emotions and adjust the way it presents its suggestions based on those emotions. For example, if the user is stressed, the suggestion unit can provide simple and easy-to-understand suggestions. If the user is relaxed, the suggestion unit can provide suggestions that include detailed information. If the user is in a hurry, the suggestion unit can provide quick and concise suggestions. This allows the suggestion unit to adjust the way it presents its suggestions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI adjust the way it presents its suggestions.

[0115] The proposal unit can adjust the level of detail in a proposal based on the importance of the plan. For example, if the plan is important, the proposal unit will provide a proposal with detailed information. For example, if the plan is of low importance, the proposal unit can provide a simplified proposal. The proposal unit can adjust the level of detail in a proposal according to the importance of the plan. This allows the level of detail in a proposal to be adjusted based on the importance of the plan. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input plan importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in the proposal.

[0116] The proposal unit can apply different proposal algorithms depending on the plan category when making a proposal. For example, in the case of a data communication plan, the proposal unit can apply a proposal algorithm based on data usage. For example, in the case of a voice call plan, the proposal unit can apply a proposal algorithm based on call duration. For example, in the case of an optional service, the proposal unit can apply a proposal algorithm based on the usage status of the optional service. This allows different proposal algorithms to be applied depending on the plan category. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input plan category data into a generating AI and have the generating AI execute the application of the proposal algorithm.

[0117] The suggestion unit can estimate the user's emotions and adjust the length of the suggestion based on the estimated emotions. For example, if the user is stressed, the suggestion unit can make a short, to-the-point suggestion. If the user is relaxed, the suggestion unit can make a longer suggestion with detailed explanations. If the user is in a hurry, the suggestion unit can make a quick and concise suggestion. This allows the length of the suggestion to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI adjust the length of the suggestion.

[0118] The proposal department can determine the priority of proposals based on the submission timing of the plans. For example, the proposal department will prioritize urgent plans. For example, the proposal department can set a higher priority for plans submitted early. The proposal department can determine the priority based on the submission timing of the proposals. This allows the proposal department to determine the priority of proposals based on the submission timing of the plans. Some or all of the above processes in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input plan submission timing data into a generating AI and have the generating AI perform the determination of proposal priorities.

[0119] The proposal unit can adjust the order of proposals based on the relevance of the plans when making a proposal. For example, the proposal unit may prioritize proposing plans that are highly relevant. For example, the proposal unit may postpone proposing plans that are less relevant. The proposal unit can adjust the order of proposals based on the relevance of the plans. This allows the order of proposals to be adjusted based on the relevance of the plans. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input plan relevance data into a generating AI and have the generating AI perform the adjustment of the order of proposals.

[0120] The application unit can estimate the user's emotions and adjust the timing of plan application based on the estimated user emotions. For example, if the user is stressed, the application unit may refrain from applying the plan and apply it when the user is relaxed. For example, if the user is relaxed, the application unit may apply a detailed plan. For example, if the user is in a hurry, the application unit may apply the plan quickly. This allows the timing of plan application to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the application unit may be performed using AI, for example, or without AI. For example, the application unit can input user emotion data into the generative AI and have the generative AI adjust the timing of plan application.

[0121] The application unit can select an application method by referring to the user's past plan change history at the time of application. For example, the application unit can select the optimal application method based on the plan the user has frequently changed in the past. For example, the application unit can select the optimal application timing from the user's past plan change history. For example, the application unit can analyze the user's past plan change history and select the most efficient application method. This allows the application unit to select the optimal application method by referring to the user's past plan change history. Some or all of the above processing in the application unit may be performed using AI, for example, or without using AI. For example, the application unit can input the user's past plan change history data into a generating AI and have the generating AI perform the selection of the application method.

[0122] The application unit can customize the means of applying the plan based on the user's current living situation at the time of application. For example, the application unit can customize the means of applying the plan considering the user's current work situation. For example, the application unit can customize the means of applying the plan considering the user's current home situation. For example, the application unit can customize the means of applying the plan considering the user's current health condition. This allows the means of applying the plan to be customized based on the user's current living situation. Some or all of the above processing in the application unit may be performed using AI, for example, or without using AI. For example, the application unit can input the user's current living situation data into a generating AI and have the generating AI perform the customization of the means of applying the plan.

[0123] The application unit can estimate the user's emotions and determine the priority of plan application based on the estimated user emotions. For example, if the user is stressed, the application unit may prioritize applying important plans. For example, if the user is relaxed, the application unit may prioritize applying detailed plans. For example, if the user is in a hurry, the application unit may prioritize applying simplified plans. This allows the application unit to determine the priority of plan application based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the application unit may be performed using AI or not using AI. For example, the application unit can input user emotion data into a generative AI and have the generative AI determine the priority of plan application.

[0124] The application unit can select a plan application method based on the user's geographical location information at the time of application. For example, if the user is in a specific region, the application unit will prioritize applying a plan related to that region. For example, if the user is on the move, the application unit can apply the optimal plan based on the user's current location. For example, the application unit can select the optimal plan application method based on the user's geographical location information. This allows the application unit to select the optimal plan application method while considering the user's geographical location information. Some or all of the above processing in the application unit may be performed using AI, for example, or without AI. For example, the application unit can input the user's geographical location information data into a generating AI and have the generating AI perform the selection of the plan application method.

[0125] The application unit can analyze the user's social media activity and propose a plan application method during application. For example, the application unit can propose the optimal plan application method based on information shared by the user on social media. For example, the application unit can prioritize the application of important plans based on the user's social media activity. For example, the application unit can analyze the user's social media activity and propose the optimal plan application method. This allows the application unit to analyze the user's social media activity and propose a plan application method. Some or all of the above processing in the application unit may be performed using AI, for example, or without AI. For example, the application unit can input the user's social media activity data into a generating AI and have the generating AI execute the proposal of a plan application method.

[0126] The approval reception unit can estimate the user's emotions and adjust the timing of approval reception based on the estimated emotions. For example, if the user is stressed, the approval reception unit will refrain from accepting approval and accept it when the user is relaxed. For example, if the user is relaxed, the approval reception unit can perform detailed approval reception. For example, if the user is in a hurry, the approval reception unit can perform rapid approval reception. This allows the timing of approval reception to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the approval reception unit may be performed using AI, for example, or without AI. For example, the approval reception unit can input user emotion data into the generative AI and have the generative AI adjust the timing of approval reception.

[0127] The approval receiving unit can select an approval method by referring to the user's past approval history when an approval is received. For example, the approval receiving unit can select the optimal approval method based on methods the user has frequently approved in the past. For example, the approval receiving unit can select the optimal approval timing from the user's past approval history. For example, the approval receiving unit can analyze the user's past approval history and select the most efficient approval method. This allows the system to select the optimal approval method by referring to the user's past approval history. Some or all of the above processes in the approval receiving unit may be performed using AI, for example, or without AI. For example, the approval receiving unit can input the user's past approval history data into a generating AI and have the generating AI perform the selection of the approval method.

[0128] The approval receiving unit can estimate the user's emotions and determine the priority of approval requests based on the estimated emotions. For example, if the user is stressed, the approval receiving unit may prioritize important approvals. For example, if the user is relaxed, the approval receiving unit may prioritize detailed approvals. For example, if the user is in a hurry, the approval receiving unit may prioritize simplified approvals. This allows the priority of approval requests to be determined based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the approval receiving unit may be performed using AI or not using AI. For example, the approval receiving unit can input user emotion data into a generative AI and have the generative AI determine the priority of approval requests.

[0129] The approval receiving unit can select an approval method based on the user's geographical location information when an approval is received. For example, if the user is in a specific region, the approval receiving unit will prioritize approvals related to that region. For example, if the user is on the move, the approval receiving unit can accept the most suitable approval based on the user's current location. For example, the approval receiving unit can select the most suitable approval method based on the user's geographical location information. This allows the system to select the most suitable approval method considering the user's geographical location information. Some or all of the above processing in the approval receiving unit may be performed using AI, for example, or without AI. For example, the approval receiving unit can input the user's geographical location information data into a generating AI and have the generating AI perform the selection of the approval method.

[0130] The response unit can estimate the user's emotions and adjust the way it expresses its response based on the estimated emotions. For example, if the user is stressed, the response unit can provide a simple and easy-to-understand response. For example, if the user is relaxed, the response unit can provide a response that includes detailed information. For example, if the user is in a hurry, the response unit can provide a quick and concise response. This allows the response unit to adjust the way it expresses its response based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the response unit may be performed using AI, or not using AI. For example, the response unit can input user emotion data into a generative AI and have the generative AI adjust the way it expresses its response.

[0131] The response unit can select the optimal response method by referring to the user's past question history when responding. For example, the response unit can select the optimal response method based on the content of questions the user has frequently asked in the past. For example, the response unit can select the optimal response timing from the user's past question history. For example, the response unit can analyze the user's past question history and select the most efficient response method. This allows the response unit to select the optimal response method by referring to the user's past question history. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the user's past question history data into a generating AI and have the generating AI perform the selection of a response method.

[0132] The response unit can estimate the user's emotions and determine the priority of responses based on the estimated emotions. For example, if the user is stressed, the response unit will prioritize important responses. For example, if the user is relaxed, the response unit will prioritize detailed responses. For example, if the user is in a hurry, the response unit will prioritize simplified responses. This allows the response unit to determine the priority of responses based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response unit may be performed using AI or not using AI. For example, the response unit can input user emotion data into a generative AI and have the generative AI determine the priority of responses.

[0133] The response unit can select a response method based on the user's geographical location information when responding. For example, if the user is in a specific region, the response unit will prioritize responses related to that region. For example, if the user is on the move, the response unit can provide the optimal response based on the user's current location. For example, the response unit can select the optimal response method based on the user's geographical location information. This allows the response unit to select the optimal response method while considering the user's geographical location information. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the user's geographical location information data into a generating AI and have the generating AI perform the selection of the response method.

[0134] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0135] The communication acquisition unit can adjust the acquisition frequency when acquiring the user's communication status, taking into account the battery level of the user's device. For example, if the battery level is low, the frequency of acquiring communication status can be reduced to conserve battery power. Conversely, if the battery level is sufficient, detailed communication status can be acquired frequently to collect more accurate data. Furthermore, if the user's device is charging, the communication acquisition unit can maximize the frequency of acquiring communication status to improve data collection efficiency. This allows for flexible adjustment of the communication status acquisition frequency according to the battery status of the user's device.

[0136] The call acquisition unit can adjust the content acquired when acquiring a user's call status, taking into account the user's relationship with the person they are calling. For example, in the case of calls with family or friends, detailed call content can be acquired and used for analysis. In the case of calls with business partners, emphasis can be placed on acquiring call frequency and duration. Furthermore, if a user frequently calls a particular person, the call acquisition unit can prioritize acquiring call data with that person and use it to predict usage patterns. In this way, the content acquired regarding call status can be adjusted based on the user's relationship with the person they are calling.

[0137] The option acquisition unit can adjust the acquired data based on the user's application usage when acquiring user option usage data. For example, if a user frequently uses a particular application, the unit can prioritize acquiring option data related to that application. Also, if a user installs a new application, the unit can acquire detailed usage data for that application to aid in analysis. Furthermore, if a user uses a particular application for an extended period, the option acquisition unit can focus on acquiring option data related to that application to help predict usage patterns. In this way, the acquired option usage data can be adjusted based on the user's application usage.

[0138] The suggestion function can estimate the user's emotions and adjust the timing of suggestions based on those emotions. For example, if the user is stressed, it can refrain from making suggestions and make them at a more relaxed time. If the user is relaxed, it can provide more detailed suggestions to deepen their understanding. Furthermore, if the user is in a hurry, it can provide concise and quick suggestions to reduce their burden. In this way, the timing of suggestions can be adjusted based on the user's emotions.

[0139] The application unit can estimate the user's emotions and adjust the method of applying the plan based on those emotions. For example, if the user is stressed, the plan can be applied in a simple and easy-to-understand way. If the user is relaxed, the plan can be applied with detailed explanations to deepen the user's understanding. Furthermore, if the user is in a hurry, the plan can be applied quickly and concisely to reduce the user's burden. In this way, the method of applying the plan can be adjusted based on the user's emotions.

[0140] The communication acquisition unit can adjust its acquisition method when acquiring the user's communication status, taking into account the network connection status of the user's device. For example, if the network connection is unstable, the frequency of acquiring communication status can be reduced to maintain data accuracy. Conversely, if the network connection is stable, detailed communication status can be acquired frequently to collect more accurate data. Furthermore, if the user is connected via Wi-Fi, the communication acquisition unit can maximize the frequency of acquiring communication status to improve data collection efficiency. This allows for flexible adjustment of the communication status acquisition method according to the user's network connection status.

[0141] The call acquisition unit can perform sentiment analysis of the user's call content and adjust the acquired data accordingly. For example, if a user shows positive emotions during a call, detailed call content can be acquired and used for analysis. Conversely, if a user shows negative emotions, the unit can prioritize the acquisition of call frequency and duration. Furthermore, if a user frequently calls a particular person, the call acquisition unit can prioritize acquiring call data with that person to help predict usage patterns. This allows the acquisition of call status data to be adjusted based on sentiment analysis of the user's call content.

[0142] The option acquisition unit can adjust the acquired data based on the user's device usage when acquiring user option usage data. For example, if a user uses their device frequently, the unit can prioritize acquiring option data related to that usage. Conversely, if a user does not use their device for a long period, the unit can acquire detailed option usage data for analysis. Furthermore, if a user uses a specific application for an extended period, the option acquisition unit can focus on acquiring option data related to that application to help predict usage patterns. This allows the acquisition of option usage data to be adjusted based on the user's device usage.

[0143] The suggestion function can estimate the user's emotions and adjust the content of the suggestions based on those emotions. For example, if the user is stressed, it can provide simple and easy-to-understand suggestions. If the user is relaxed, it can provide suggestions with more detailed information to deepen the user's understanding. Furthermore, if the user is in a hurry, it can provide quick and concise suggestions to reduce the user's burden. In this way, the content of suggestions can be adjusted based on the user's emotions.

[0144] The application unit can estimate the user's emotions and adjust the priority of plan application based on those emotions. For example, if the user is stressed, important plans can be applied preferentially. If the user is relaxed, detailed plans can be applied preferentially to deepen the user's understanding. Furthermore, if the user is in a hurry, simplified plans can be applied preferentially to reduce the user's burden. In this way, the priority of plan application can be adjusted based on the user's emotions.

[0145] The following briefly describes the processing flow for example form 2.

[0146] Step 1: The communication acquisition unit acquires the user's communication status. For example, it collects information such as the user's data traffic, communication speed, and communication quality, monitors it in real time, and evaluates the communication speed and quality. It also periodically records the user's communication status and can analyze past communication data. Step 2: The call acquisition unit acquires the user's call status. For example, it collects information such as the user's call duration, call frequency, and call quality, monitors it in real time, and evaluates the call quality. It also periodically records the user's call status and can analyze past call data. Step 3: The option acquisition unit acquires the user's option usage status. For example, it collects information such as the type of option the user is using, the frequency of use, and the duration of use, monitors it in real time, and evaluates the frequency and duration of use. It also periodically records the user's option usage status and can analyze past option usage data. Step 4: The prediction unit predicts user usage patterns based on information acquired by the communication acquisition unit, call acquisition unit, and option acquisition unit. For example, it predicts future usage based on past trends in data traffic and call duration, analyzes user usage patterns, and predicts future communication demand. Furthermore, AI can be used to learn user usage patterns and improve prediction accuracy. Step 5: The proposal unit proposes plans and options based on the user's usage patterns, using the usage patterns predicted by the forecasting unit. For example, if a user uses a lot of data, it proposes a plan for users with high data usage; if a user makes long calls, it proposes a plan for users who make long calls; and if a user frequently uses options, it proposes a plan for users who frequently use options. Step 6: The application unit automatically applies the plans and options proposed by the proposal unit. For example, it applies the plans and options approved by the user, obtains the user's approval, and then applies the optimal plans and options. Furthermore, AI can be used to automatically apply the proposed plans and options.

[0147] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0148] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0149] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0150] Each of the multiple elements described above, including the communication acquisition unit, call acquisition unit, option acquisition unit, prediction unit, proposal unit, and application unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the communication acquisition unit is implemented by the control unit 46A of the smart device 14 and monitors the user's data communication volume and communication speed in real time. The call acquisition unit is implemented by the control unit 46A of the smart device 14 and evaluates the user's call duration and call quality. The option acquisition unit is implemented by the control unit 46A of the smart device 14 and monitors the user's option usage. The prediction unit is implemented by the specific processing unit 290 of the data processing device 12 and predicts usage patterns based on past trends in data communication volume and call duration. The proposal unit is implemented by the specific processing unit 290 of the data processing device 12 and proposes an optimal plan based on the predicted usage pattern. The application unit is implemented by the specific processing unit 290 of the data processing device 12 and automatically applies the proposed plan. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0151] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0152] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0153] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0154] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0155] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0156] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0157] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0158] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0159] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0160] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0161] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0162] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0163] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0164] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0165] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0166] Each of the multiple elements described above, including the communication acquisition unit, call acquisition unit, option acquisition unit, prediction unit, proposal unit, and application unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the communication acquisition unit is implemented by the control unit 46A of the smart glasses 214 and monitors the user's data communication volume and communication speed in real time. The call acquisition unit is implemented by the control unit 46A of the smart glasses 214 and evaluates the user's call duration and call quality. The option acquisition unit is implemented by the control unit 46A of the smart glasses 214 and monitors the user's option usage. The prediction unit is implemented by the specific processing unit 290 of the data processing unit 12 and predicts usage patterns based on past trends in data communication volume and call duration. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes an optimal plan based on the predicted usage pattern. The application unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically applies the proposed plan. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0167] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0168] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0169] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0170] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0171] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0172] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0173] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0174] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0175] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0176] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0177] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0178] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0179] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0180] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0181] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0182] Each of the multiple elements described above, including the communication acquisition unit, call acquisition unit, option acquisition unit, prediction unit, proposal unit, and application unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the communication acquisition unit is implemented by the control unit 46A of the headset terminal 314 and monitors the user's data communication volume and communication speed in real time. The call acquisition unit is implemented by the control unit 46A of the headset terminal 314 and evaluates the user's call duration and call quality. The option acquisition unit is implemented by the control unit 46A of the headset terminal 314 and monitors the user's option usage. The prediction unit is implemented by the specific processing unit 290 of the data processing unit 12 and predicts usage patterns based on past trends in data communication volume and call duration. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes an optimal plan based on the predicted usage pattern. The application unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically applies the proposed plan. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0183] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0184] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0185] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0186] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0187] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0188] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0189] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0190] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0191] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0192] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0193] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0194] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0195] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0196] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0197] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0198] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0199] Each of the multiple elements described above, including the communication acquisition unit, call acquisition unit, option acquisition unit, prediction unit, proposal unit, and application unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the communication acquisition unit is implemented by the control unit 46A of the robot 414 and monitors the user's data communication volume and communication speed in real time. The call acquisition unit is implemented by the control unit 46A of the robot 414 and evaluates the user's call duration and call quality. The option acquisition unit is implemented by the control unit 46A of the robot 414 and monitors the user's option usage. The prediction unit is implemented by the specific processing unit 290 of the data processing unit 12 and predicts usage patterns based on past trends in data communication volume and call duration. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes an optimal plan based on the predicted usage pattern. The application unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically applies the proposed plan. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0200] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0201] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0202] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0203] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0204] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0205] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0206] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0207] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0208] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0209] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0210] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0211] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0212] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0213] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0214] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0215] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0216] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0217] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0218] (Note 1) A communication acquisition unit that acquires the user's communication status, A call acquisition unit that acquires the user's call status, An option acquisition unit that acquires the user's option usage status, A prediction unit predicts the user's usage pattern based on the information acquired by the communication acquisition unit, the call acquisition unit, and the option acquisition unit. Based on the usage patterns predicted by the prediction unit, a proposal unit proposes plans and options based on the user's usage patterns. The system includes an application unit that automatically applies the plan and options proposed by the proposal unit. A system characterized by the following features. (Note 2) The aforementioned proposal section is, It includes an approval reception unit that applies the optimal plan and options after obtaining user approval. The system described in Appendix 1, characterized by the features described herein. (Note 3) The prediction unit, Based on past trends in data usage and call duration, we predict future usage. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned proposal section is, If a user's data usage exceeds a certain level, we will suggest a data plan designed for users with high data usage. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned application unit is Apply the plan and options approved by the user. The system described in Appendix 1, characterized by the features described herein. (Note 6) In response to additional requests and questions from users, It features an AI-powered automated response system that provides chat-based answers. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned communication acquisition unit, The system estimates the user's emotions and adjusts the timing of acquiring communication status based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned communication acquisition unit, Analyze the user's past communication history and select the method for obtaining it. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned communication acquisition unit, When acquiring communication status, filtering is performed based on the user's current device usage. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned communication acquisition unit, It estimates the user's emotions and determines the priority of communication data to acquire based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned communication acquisition unit, When acquiring communication status, the system prioritizes acquiring data that is highly relevant based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned communication acquisition unit, When acquiring communication status, the system analyzes the user's social media activity and retrieves relevant communication data. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned call acquisition unit, The system estimates the user's emotions and adjusts the timing of acquiring call status based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned call acquisition unit, Analyze the user's past call history and select the method for obtaining it. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned call acquisition unit, When retrieving call status, filtering is performed based on the user's current call pattern. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned call acquisition unit, It estimates the user's emotions and determines the priority of call data to acquire based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned call acquisition unit, When acquiring call status, the system prioritizes acquiring data that is highly relevant based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned call acquisition unit, When acquiring call status, the system analyzes the user's social media activity and retrieves relevant call data. The system described in Appendix 1, characterized by the features described herein. (Note 19) The option acquisition unit, The system estimates the user's emotions and adjusts the timing of acquiring option usage data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The option acquisition unit, Analyze the user's past option usage history and select a method for obtaining it. The system described in Appendix 1, characterized by the features described herein. (Note 21) The option acquisition unit, When retrieving option usage data, filtering is performed based on the user's current option usage pattern. The system described in Appendix 1, characterized by the features described herein. (Note 22) The option acquisition unit, It estimates the user's emotions and determines the priority of optional data to retrieve based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The option acquisition unit, When acquiring option usage data, the system prioritizes acquiring data that is highly relevant based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The option acquisition unit, When obtaining option usage data, the system analyzes the user's social media activity and retrieves relevant option data. The system described in Appendix 1, characterized by the features described herein. (Note 25) The prediction unit, We estimate user emotions and adjust the method of predicting usage patterns based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The prediction unit, When making predictions, the prediction algorithm is adjusted by referring to past usage data. The system described in Appendix 1, characterized by the features described herein. (Note 27) The prediction unit, During prediction, the accuracy of the prediction is improved based on the user's current living situation. The system described in Appendix 1, characterized by the features described herein. (Note 28) The prediction unit, It estimates the user's emotions and adjusts how the prediction results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The prediction unit, During prediction, the accuracy of the prediction is improved based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The prediction unit, During prediction, we analyze users' social media activity to improve prediction accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned proposal section is, It estimates the user's emotions and adjusts the way suggestions are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned proposal section is, When making a proposal, adjust the level of detail in the proposal based on the importance of the plan. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned proposal section is, When submitting a proposal, different proposal algorithms are applied depending on the plan category. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned proposal section is, It estimates the user's emotions and adjusts the length of the suggestion based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned proposal section is, When submitting proposals, we will prioritize them based on when the plans were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned proposal section is, When making proposals, adjust the order of proposals based on the relevance of the plan. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned application unit is It estimates the user's emotions and adjusts the timing of plan application based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned application unit is When applying the changes, the application method is selected by referring to the user's past plan change history. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned application unit is When applying the plan, the method of application is customized based on the user's current living situation. The system according to appended claim 1, characterized in that... (Appended claim 40) The application unit... estimates the user's emotion and determines the priority order of plan application based on the estimated user emotion The system according to appended claim 1, characterized in that... (Appended claim 41) The application unit... selects a plan application method based on the user's geographical location information at the time of application The system according to appended claim 1, characterized in that... (Appended claim 42) The application unit... analyzes the user's social media activities at the time of application and proposes means for plan application The system according to appended claim 1, characterized in that... (Appended claim 43) The approval reception unit... estimates the user's emotion and adjusts the timing of approval reception based on the estimated user emotion The system according to appended claim 2, characterized in that... (Appended claim 44) The approval reception unit... selects a reception method by referring to the user's past approval history at the time of approval reception The system according to appended claim 2, characterized in that... (Appended claim 45) The approval reception unit... estimates the user's emotion and determines the priority order of approval reception based on the estimated user emotion The system according to appended claim 2, characterized in that... (Appended claim 46) The approval reception unit... selects a reception method based on the user's geographical location information at the time of approval reception The system according to appended claim 2, characterized in that... (Appended claim 47) The response unit... estimates the user's emotion and adjusts the expression method of the response based on the estimated user emotion The system according to appended note 6, characterized in that... (Appended note 48) The response unit At the time of response, selects an optimal response method by referring to the user's past question history The system according to appended note 6, characterized in that... (Appended note 49) The response unit Estimates the user's emotion and determines the priority of responses based on the estimated user emotion The system according to appended note 6, characterized in that... (Appended note 50) The response unit At the time of response, selects a response method based on the user's geographical location information The system according to appended note 6, characterized in that...

Explanation of reference signs

[0219] 10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset-type terminal 414 Robot

Claims

1. A communication acquisition unit that acquires the user's communication status, A call acquisition unit that acquires the user's call status, An option acquisition unit that acquires the user's option usage status, A prediction unit predicts the user's usage pattern based on the information acquired by the communication acquisition unit, the call acquisition unit, and the option acquisition unit. Based on the usage patterns predicted by the prediction unit, a proposal unit proposes plans and options based on the user's usage patterns. The system includes an application unit that automatically applies the plan and options proposed by the proposal unit. A system characterized by the following features.

2. The aforementioned proposal section is, It includes an approval reception unit that applies the optimal plan and options after obtaining user approval. The system according to feature 1.

3. The prediction unit, Based on past trends in data usage and call duration, we predict future usage. The system according to feature 1.

4. The aforementioned proposal section is, If a user's data usage exceeds a certain level, we will suggest a data plan designed for users with high data usage. The system according to feature 1.

5. The aforementioned application unit is Apply the plan and options approved by the user. The system according to feature 1.

6. In response to additional requests and questions from users, It features an AI-powered response unit that automatically responds via chat. The system according to feature 1.

7. The aforementioned communication acquisition unit, The system estimates the user's emotions and adjusts the timing of acquiring communication status based on the estimated emotions. The system according to feature 1.

8. The aforementioned communication acquisition unit, Analyze the user's past communication history and select the method for obtaining it. The system according to feature 1.

9. The aforementioned communication acquisition unit, When acquiring communication status, filtering is performed based on the user's current device usage. The system according to feature 1.

10. The aforementioned communication acquisition unit, It estimates the user's emotions and determines the priority of communication data to acquire based on the estimated user emotions. The system according to feature 1.

Images