system

Abstract

Provide a system. 【Solution means】 Input means for receiving information from customers, Analysis means for analyzing the received information using natural language processing technology, Plan generation means for proposing an optimal product or service plan based on the analyzed information, Means for presenting the proposed plan to the customer's visual display device and obtaining approval, Progress management means for monitoring the progress of the order, detecting problems and providing solutions, Operation means for processing the customer's requests in real time through voice input means and presenting information visually, Feedback collection means for collecting feedback from customers after order completion and using it for service improvement, A system including.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes 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 order reception process of conventional data communication services, it is often performed manually. As a result, there are problems such as complicated procedures and a high risk of human errors. In addition, the response to customer inquiries and requests is often delayed, which often affects customer satisfaction. To solve this problem, a mechanism that automates the entire reception process and quickly and accurately responds to customer needs is required.

Means for Solving the Problems

[0005] This invention proposes a system that can accurately understand customer needs by receiving information from customers through input means and analyzing that information using natural language processing technology. Furthermore, it includes means for generating an optimal data communication service plan based on the analysis results and automating the presentation and approval process. In addition, it minimizes order delays and errors by managing progress, detecting problems, and providing solutions. Moreover, it is possible to collect customer feedback after order completion and obtain insights to improve the quality of service.

[0006] "Input means" refers to a device or system for receiving information from customers.

[0007] "Analysis means" refers to a device or system that analyzes received information using natural language processing technology.

[0008] A "plan generation means" is a device or system for proposing an optimal data communication service plan based on analyzed information.

[0009] "Means of obtaining approval" refers to the apparatus or method for presenting a proposed plan to a customer and obtaining their approval.

[0010] A "progress management tool" is a device or system for monitoring the progress of an order in real time, detecting problems, and providing solutions.

[0011] A "feedback collection method" refers to a device or system used to collect customer opinions and evaluations after an order is completed and to use them for service improvement. [Brief explanation of the drawing]

[0012] [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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0014] First, the language used in the following description will be explained.

[0015] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention provides an AI agent system that automates the acceptance of data communication service orders from customers. Specific embodiments thereof are described below.

[0034] First, when a user initiates a new service order, the terminal's user interface opens, and the customer enters the necessary information. The input device then sends this information to the server as structured data.

[0035] Next, the server uses natural language processing technology to analyze the received data and accurately understand customer requests and needs. This analysis employs machine learning and dictionary-based methods to extract keywords from the input text and grasp customer expectations.

[0036] Based on the analysis results, the server automatically selects the optimal data communication service plan for the customer via a plan generation mechanism. A proposal for the selected plan is generated, and this information is sent to the terminal.

[0037] Customers can view the proposed plan through the interface on their device and either approve it or request a revised proposal. If approved, the server confirms the order and continuously monitors the order's execution status using progress management tools. If any problems arise along the way, the server immediately identifies the problem and notifies the user or relevant technical staff of the solution.

[0038] Finally, once the order is complete, we use feedback collection methods to gather customer opinions and requests. This feedback is used to improve our service and help enhance the quality of future interactions.

[0039] For example, if a user requests a "high-speed internet plan for business," the system will immediately suggest a plan that meets their needs, simplifying the process. This is expected to significantly reduce time and costs compared to traditional manual processes, as well as improve user satisfaction.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user accesses the service order interface, fills in the required information in the form to start a new order, and clicks the submit button.

[0043] Step 2:

[0044] The terminal receives the information entered by the user as digital data and completes the process of sending it to the server as structured data.

[0045] Step 3:

[0046] The server begins processing the data received from the terminal using analysis tools. Specifically, it uses a natural language processing model to extract keywords and phrases from the data and accurately identify customer requests.

[0047] Step 4:

[0048] Based on the analysis results, the server selects the most suitable data communication service plan from among several options and creates a proposed message using a plan generation method.

[0049] Step 5:

[0050] The server sends the generated proposal message to the terminal, preparing it for presentation to the user. The proposal includes plan details, pricing, and terms and conditions.

[0051] Step 6:

[0052] Users view the proposed plan via their device, click the approve button if they are satisfied with the content, and configure their settings on their device if they require a revised proposal.

[0053] Step 7:

[0054] The terminal sends the user's selection to the server, which then processes the order accordingly. If approved, the order moves to the execution phase.

[0055] Step 8:

[0056] The server uses progress management tools to monitor the progress of orders and updates statuses such as "Currently processing" and "Technical team is working on it" in real time.

[0057] Step 9:

[0058] If a problem occurs in the order process, the server will immediately detect the anomaly and notify the user or technical staff of the steps and recommended actions for resolving the problem.

[0059] Step 10:

[0060] After an order is completed, the server collects user ratings and comments through feedback collection mechanisms and saves this data as material for service improvement.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] Modern communication services require efficient and accurate responses to diverse customer needs. However, traditional manual order processing and plan proposals are time-consuming and may not fully achieve customer satisfaction. Furthermore, there are challenges in managing order progress, responding quickly to problems, and collecting feedback for service improvement.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes an input means for acquiring customer information as structured data, a means for analyzing the received information using natural language processing technology, and a means for generating an optimal data communication service plan based on the analysis results. This enables rapid understanding of customer needs and provision of appropriate plans, continuous order management and problem handling, and collection of feedback for improving service quality.

[0066] "Input method" refers to a method for obtaining necessary information from customers and inputting it into the system in a format that can be processed.

[0067] "Communication means" refers to a means of transmitting data from a terminal to a server, and involves transferring structured data according to a predetermined protocol.

[0068] "Analysis means" refers to the process of analyzing received information using natural language processing technology to extract customer needs.

[0069] The "plan generation method" is a method for generating a data communication service plan that is suitable for the customer's needs based on the analysis results.

[0070] A "proposal presentation method" refers to a means of presenting the generated plan to the customer as a proposal and receiving requests for approval or revisions.

[0071] A "progress management system" is a process for monitoring the progress of an order and taking immediate action if a problem arises.

[0072] A "feedback collection method" is a method of gathering evaluation information from customers after an order is completed and using that information to improve the service.

[0073] A "generative AI model" is an artificial intelligence model that uses machine learning techniques to analyze data and select the optimal service plan.

[0074] A "prompt message" is a sentence used to give instructions or requests to an AI system, and is used when processing data or proposing services.

[0075] The embodiments for carrying out the present invention will be described in detail.

[0076] This AI agent system is designed to efficiently obtain data communication service orders from customers and provide appropriate plans. The system primarily functions through the cooperation of users, terminals, and servers.

[0077] The user initiates an order for a data communication service using a terminal. They input the necessary information into the terminal's user interface and transmit it. The input information is converted into structured data by the terminal and sent to the server.

[0078] The terminal is responsible for packaging user input data into a standard data format such as JSON and sending it to the server using an HTTP POST request. In this process, the terminal maintains the accuracy and integrity of the data.

[0079] The server uses natural language processing techniques to analyze the received data. Specifically, it extracts customer needs from text data using Python's NLTK library and generative AI models. Based on the results, the server generates an appropriate data communication service plan. The generated plan is then constructed as a proposal by a template engine and sent to the terminal.

[0080] Once a plan is presented to the user, they can review the proposed plan on their device and either approve it or request a revised proposal. The server confirms the order based on this response and monitors the order's progress. In case of any problems, the server identifies the issue and notifies the user or relevant technical staff of the necessary information.

[0081] Finally, once the order is completed, the server uses feedback collection tools to gather evaluation information from the customer. This feedback data is analyzed using AI models to help improve future services.

[0082] As a concrete example, consider a case where a user requests a "high-speed internet plan for business." An example of a prompt message for this system would be, "I would like high-speed internet service for business. Please suggest a recommended plan." This allows the system to quickly and accurately suggest a plan that meets the user's needs, thereby improving service efficiency and customer satisfaction.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The user initiates an order for a data communication service and enters the necessary information into the user interface on the terminal. Specifically, the user enters data such as their name, contact information, and desired service into a form. The input in this step is data entered by the user, and the output is structured data on the terminal.

[0086] Step 2:

[0087] The terminal packages the user's input data as structured data and sends it to the server. Specifically, the terminal converts the input data into JSON format and sends it to the server via an HTTP POST request. In this step, the input is the structured data received from the user interface, and the output is the data sent to the server.

[0088] Step 3:

[0089] The server analyzes the received structured data using natural language processing techniques. Specifically, the server uses generative AI models and natural language tools to analyze text data and extract customer needs and expectations. The input for this step is data sent from the terminal, and the output is the analyzed needs information.

[0090] Step 4:

[0091] The server generates an appropriate data communication service plan based on the analysis results. Specifically, the server utilizes a generation AI model to construct a plan based on customer needs and selects the most suitable option from its internal database. The input for this step is the analyzed needs information, and the output is a proposed plan.

[0092] Step 5:

[0093] The server sends the generated plan proposal to the terminal. Specifically, the server generates the proposal in HTML or PDF format and sends it to the terminal via real-time notification or email. The input for this step is the generated plan proposal, and the output is the proposal delivered to the terminal.

[0094] Step 6:

[0095] The user reviews the proposed plan using their device and requests approval or a revised proposal. Specifically, the user views the proposal on the device's interface and clicks a selection button to determine the next action. The input for this step is the proposal from the server, and the output is the user's request for approval or a revised proposal.

[0096] Step 7:

[0097] The server confirms the order upon user approval and manages its progress. Specifically, the server monitors the order's progress and takes steps to quickly address any problems that arise. The input for this step is the user's actions, and the output is the confirmed order and its monitoring information.

[0098] Step 8:

[0099] The server collects evaluation information from customers using a feedback collection mechanism after the order is completed. Specifically, the server generates a questionnaire and sends it along with the completion notification to request feedback. The input for this step is the completed order information, and the output is customer feedback data.

[0100] (Application Example 1)

[0101] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0102] Modern consumers want to efficiently and quickly select from a wide variety of goods and services, but information overload often makes the selection process time-consuming. Furthermore, while they desire to shop while receiving abundant visual information, traditional methods have presented challenges in quickly suggesting products that meet customer needs.

[0103] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0104] In this invention, the server includes an input means for receiving information from the customer, an operation means for processing customer requests in real time via voice input and presenting information visually, and a means for presenting a proposed plan on the customer's visual display device and obtaining approval. This enables the customer to efficiently select products and obtain information in real time through a visually assisted shopping assistant.

[0105] "Customer information" is a general term for personal data and data related to requests provided by customers.

[0106] "Natural language processing technology" refers to the technology used by computers to understand and process human language, and involves analyzing text data and extracting keywords.

[0107] A "plan generation method" is a function that automatically selects the optimal product or service plan in response to customer requests based on the analyzed information.

[0108] A "visual display device" is a device that displays electronically generated information in the user's field of vision, and includes smart glasses, among other things.

[0109] "Voice input means" refers to a device or function that receives the user's voice as a digital signal and converts it into analyzable text data.

[0110] A "generative AI model" is an artificial intelligence model that uses machine learning to process customer information in real time and select appropriate products and services.

[0111] A "prompt" is a text instruction input into a generative AI model, serving as a guideline for performing specific analysis or generation tasks.

[0112] This invention adopts the following configuration to realize a visually assisted shopping assistant system. A visual display device, such as smart glasses, and a server work together in cooperation.

[0113] The server receives requests from users through voice input. At this stage, the voice data is converted into text data using speech recognition technology such as Google® Speech-to-Text API. This text data is then analyzed using natural language processing techniques such as the Python libraries SpaCy and NLTK. From the analyzed information, keywords and intentions related to the user's request are extracted and processed using machine learning models (using TENSORFLOW® or PyTorch) to select appropriate products and services.

[0114] The visual display device overlays information transmitted from the server onto the user's field of view. This allows the user to check selected product information in real time. Furthermore, to collect user feedback, a generative AI model is used to analyze user evaluations using prompt messages and generate insights.

[0115] For example, if a user gives a voice command such as "I'm looking for lightweight running shoes," the server analyzes the request and displays potential products on the glasses' display. The user can then view detailed information about the selected products and proceed with the purchase.

[0116] An example of a prompt to be input into the generating AI model would be: "Develop an algorithm that uses an AI agent to analyze the user's intent from their voice input and select products that match that intent." This would enable a system that allows users to more smoothly select the products they need and streamline the purchase process.

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The user speaks their request through the voice input feature of their smart glasses. The voice data is input and converted into text data by the Google Speech-to-Text API. This input text data is used for natural language processing in the next step.

[0120] Step 2:

[0121] The server receives text data and performs natural language processing using Python libraries such as SpaCy and NLTK. The analysis extracts keywords and user intent from the text data, and these analysis results are output in the next step as information that forms the basis for product selection.

[0122] Step 3:

[0123] Based on the analysis results, the server searches the product database using a machine learning model based on TensorFlow or PyTorch to select products that match the user's needs. The product information selected by this generative AI model is output within the system and used for visual presentation in the next step.

[0124] Step 4:

[0125] The device (smart glasses) receives the selected product information and displays it as an overlay on the user's screen. Specifically, it displays detailed information such as the product name, price, and image within the user's field of view. This allows the user to easily and visually confirm the product.

[0126] Step 5:

[0127] Users select products of interest based on the visually displayed information and proceed to view further details or complete the purchase process. This input is sent to the server as feedback and used to improve subsequent services.

[0128] Step 6:

[0129] The server analyzes the collected feedback based on a generating AI model and uses prompt messages to generate insights from the feedback. Through this process, the system continuously learns, understands user preferences and behavioral patterns, and improves the service.

[0130] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0131] This invention relates to an AI agent system that automates the order acceptance process for customer data communication services by combining it with an emotion engine. In addition to basic functions such as receiving, analyzing, suggesting, and managing customer information, this system can recognize user emotions using the emotion engine and improve the service experience.

[0132] When a user initiates a service order, data such as the text entered and the tone of voice are sent to the server via the terminal, along with the necessary information. The server analyzes this data through natural language processing and simultaneously detects the user's emotional state using an emotion engine. For example, it can accurately recognize emotions such as positive, negative, or neutral from the tone of the text and the choice of words.

[0133] Based on the customer's emotional state, the server utilizes a plan generation mechanism to propose the most suitable data communication plan, and in some cases, offers customized suggestions tailored to the customer's mood. This allows customers to easily select a service that is more appropriate to their emotional state.

[0134] Furthermore, as the user accepts the proposal and the order progresses, progress management tools constantly monitor the process, and the emotion engine tracks emotional fluctuations in real time. For example, if a customer becomes stressed along the way, the server can immediately respond and provide support or make alternative suggestions.

[0135] Furthermore, after an order is completed, feedback is collected from the user through feedback collection methods. This feedback includes the results of the emotion engine analysis and plays a role in providing valuable insights for service improvement.

[0136] For example, if a user is dissatisfied with their internet speed, the server can analyze their feelings using an emotion engine and immediately provide additional information about high-speed plans or discount offers, thereby improving the user experience and increasing customer satisfaction. Implementing such a system allows for more personalized and rapid responses compared to traditional methods.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The user accesses a form on their device, enters information about their desired data communication service, and sends it as a text or voice message.

[0140] Step 2:

[0141] The terminal receives user input information as digital data, converts it into a format that can be processed by the emotion engine and analysis tools, and then sends it to the server.

[0142] Step 3:

[0143] The server first passes the received data to the emotion engine, which analyzes the user's emotional state from their input. During this process, it analyzes the emotional nuances of the text and the tone of voice to identify emotions such as "positive" or "negative."

[0144] Step 4:

[0145] In parallel, the server uses natural language processing technology to analyze user information and extract specific requests and requirements. For example, it identifies keywords such as "high-speed internet is needed."

[0146] Step 5:

[0147] The server integrates the results of sentiment analysis and natural language processing, and uses a plan generation mechanism to automatically generate the optimal data communication plan that matches the user's emotional state, and sends it to the terminal.

[0148] Step 6:

[0149] The terminal displays plan proposals from the server to the user, allowing the user to view them. The user can review the proposal and either approve it or request a revised proposal.

[0150] Step 7:

[0151] If approval is obtained, the server confirms the order and monitors its progress using progress management tools. If the emotion engine detects user stress or dissatisfaction along the way, it quickly considers countermeasures and provides suggested changes and support.

[0152] Step 8:

[0153] After all orders are completed, the server uses various feedback collection methods to obtain feedback from the user. During this process, changes in the user's emotional state are also recorded and used to improve the service and refine future suggestions.

[0154] (Example 2)

[0155] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0156] In data communication services, there is a problem in that customers have difficulty quickly and accurately selecting the optimal plan that suits their emotions and needs. Furthermore, the inability to track and appropriately respond to changes in customer emotions during service use has prevented improvements in the quality of the service experience. In addition, there has been a lack of systematic methods for utilizing feedback after order completion to improve the service.

[0157] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0158] In this invention, the server includes an information analysis device, a plan generation device, and an emotion detection device. This enables automatic proposal of data communication plans that take customer emotions into consideration, and real-time responses to changes in emotions. Furthermore, a feedback collection device allows for systematic analysis of customer opinions, enabling continuous improvement of the service.

[0159] An "information input device" is a device used to collect necessary information from customers and transmit it to the system.

[0160] An "information analysis device" is a device that analyzes received customer information using natural language processing technology.

[0161] A "plan generation device" is a device that generates the optimal data communication plan for a customer based on analyzed information.

[0162] A "presentation device" is a device used to present the generated plan to the customer and obtain their approval.

[0163] A "progress management device" is a device used to monitor the progress of an order, detect problems, and provide solutions.

[0164] A "feedback collection device" is a device used to collect feedback from customers after an order is completed and to use that feedback to improve services.

[0165] An "emotion detection device" is a device that uses emotion analysis technology to detect a customer's emotional state and reflect that in service proposals.

[0166] An "emotion tracking device" is a device that tracks customer emotional fluctuations in real time and provides support as needed.

[0167] This system consists of multiple devices designed to improve the user experience in data communication services. The server plays a central role in processing information transmitted from the terminal. The user first inputs the necessary information through the terminal. This information input device collects information in the form of text input or voice commands and sends it to the server.

[0168] The server processes the received information using an information analysis device and utilizes natural language processing technology to deepen its understanding of user requests. This process employs machine learning models, specifically using the Google Cloud Natural Language API. Based on the analyzed data, a plan generation device automatically creates the optimal data communication plan.

[0169] Furthermore, the server analyzes the user's emotional state through an emotion detection device. This emotion analysis uses techniques including contextual understanding and tone analysis to track the user's emotions in real time. Tools such as Microsoft® Azure® Text Analytics are used for this task. This enables personalized plan suggestions based on emotions, improving user satisfaction.

[0170] The progress management system monitors the order's progress in real time, and the emotion tracking system automatically adjusts support when it detects changes in emotion. This allows, for example, the server to immediately suggest countermeasures if a user experiences stress during the process.

[0171] After an order is completed, user feedback is collected by a feedback collection device and used, along with sentiment analysis results, to improve future services. The insights gained from this feedback enable continuous improvement of service quality.

[0172] For example, if a user expresses dissatisfaction when selecting a communication plan, the server prompts the generated AI model with the message, "Please provide a method for suggesting an appropriate communication plan based on the information entered by the new user," thereby providing the user with a better suggestion. In this way, optimized customer service tailored to the environment becomes possible.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] The user uses a terminal to input the necessary information into the information input device. This information includes text data and voice data. Through the user interface, the user can input, for example, their name, contact information, and desired services. The entered information is sent from the terminal to the server.

[0176] Step 2:

[0177] The server receives information transmitted from the terminal and initiates natural language processing using an information analysis device. The input data is text-based, and the server performs keyword extraction and semantic analysis on this data. Machine learning techniques are used to effectively interpret customer needs and requests from the input information.

[0178] Step 3:

[0179] Based on the analysis results, the server designs the optimal data communication plan using a plan generation device. It receives output from the information analysis device and customizes the plan by taking into account past data and market information. For example, the initial proposed plan is the one best suited to the customer's usage history and requests.

[0180] Step 4:

[0181] The server utilizes an emotion detection device to analyze the user's emotions from the wording and context in the input data. In this process, an emotion analysis model is used to accurately determine positive, negative, or neutral emotional states. An emotional evaluation is generated as output, which is then used to create the plan for the next step.

[0182] Step 5:

[0183] The server uses a plan generator to fine-tune the plan based on the user's emotional data. It provides personalized suggestions while taking emotional states into consideration. For example, if negative emotions are detected, the server will offer the customer a plan with more flexible terms or discounts.

[0184] Step 6:

[0185] The server continuously monitors the progress of orders through a progress management device. During this time, an emotion tracking device tracks customer emotional changes in real time and deploys prompt support as needed. If an emotional change is detected, an alert is immediately sent to support staff, and appropriate assistance is provided to the customer.

[0186] Step 7:

[0187] Once a user completes an order, the server collects feedback using a feedback collection device. The collected opinions and evaluation data are evaluated along with sentiment analysis to derive insights for service improvement. The opinions obtained from the feedback analysis will be used for future service development and improvement measures.

[0188] (Application Example 2)

[0189] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0190] In today's e-commerce industry, it is considered difficult to provide personalized experiences based on individual customer emotions and needs when customers make online purchases. This can lead to increased customer dissatisfaction and abandonment of the purchase process, potentially resulting in decreased customer loyalty. This invention aims to improve the user experience by analyzing customer emotions in real time and making optimal product and service recommendations based on that analysis.

[0191] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0192] In this invention, the server includes an information input means, an information analysis means, a plan generation means, a presentation means, a progress management means, an opinion collection means, and an emotion recognition and suggestion means. This enables the analysis of the customer's emotional state and the suggestion of corresponding product information and discount information in real time, thereby improving customer satisfaction and optimizing the purchase process.

[0193] An "information input means" is a component that receives data provided by a customer and performs the initial process necessary for further analysis or processing within the system.

[0194] "Information analysis means" refers to a device or program that uses natural language processing technology to interpret received customer data and analyze its contents.

[0195] A "plan generation means" is a component for automatically creating the most appropriate information and communication plan based on the analyzed information.

[0196] A "presentation method" refers to a configuration that has the function of displaying the generated information and communication plan to the customer in an easy-to-understand manner and encouraging approval or selection.

[0197] A "progress management system" is a mechanism that monitors the progress of an order, detects problems as needed, and implements a process to provide solutions.

[0198] "Methods for gathering feedback" refer to components used to obtain feedback from customers after an order is completed and to gain insights for service improvement based on that feedback.

[0199] "Emotion recognition suggestion means" refers to a device or function that detects a customer's emotions in real time and dynamically suggests product information and discount information based on those emotions.

[0200] This system has a configuration that transfers data obtained from customers through an information input means to a server, which then supports subsequent processing. The server has powerful information analysis capabilities and analyzes the received data using natural language processing technology. Specifically, it receives voice data and text data and uses a pre-trained machine learning model to determine the customer's emotions. The analysis results are then used by a plan generation means to create an optimal information and communication plan that matches the customer's emotions and needs.

[0201] In this system, emotion recognition and suggestion mechanisms play a crucial role. Using these mechanisms, the server monitors customer emotions in real time and, based on those emotions, presents personalized product and discount information to each individual customer. This allows users to have a more personalized and enriching experience, much like window shopping.

[0202] For example, if voice and text analysis reveals that a user is interested in a product but dissatisfied with its price, the system recognizes this sentiment and suggests relevant discount information or alternative products. Furthermore, if a customer encounters a problem during the purchase process, a progress management system detects this and immediately provides a solution.

[0203] An example of a prompt using a generative AI model is as follows: In response to customer feedback that "this smartphone is a little expensive," consider an approach that offers alternatives or discounts.

[0204] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0205] Step 1:

[0206] The terminal receives voice and text data from the user. This input data includes the user's wishes and opinions. The terminal converts this data into a digital format and sends it to the server.

[0207] Step 2:

[0208] The server analyzes the received audio and text data using information analysis tools. This analysis process applies natural language processing techniques to extract specific keywords and emotional nuances from the data. The analysis results include information about the user's emotions and desires.

[0209] Step 3:

[0210] The server uses a plan generation means to create an optimal information and communication plan based on the analysis results. In this step, emotion recognition suggestion means are utilized, and the generating AI model personalizes the suggested content. The generated plan includes suggestions that reflect the user's emotional state and preferences.

[0211] Step 4:

[0212] The server sends the information and communication plan created by the plan generation means back to the terminal via the presentation means. The terminal presents this information to the user, allows them to review the proposal, and requests approval. Based on the user's response, final adjustments to the plan may be made.

[0213] Step 5:

[0214] After the user approves the information and communication plan, the server continues to monitor the order status using progress management tools. If necessary, it detects problems, primarily using generative AI models, and dynamically provides solutions.

[0215] Step 6:

[0216] Once the process is complete, the server collects feedback from users through feedback collection mechanisms. This feedback is analyzed by the server and used to gain insights for service improvement. The generated insights are then used in the next optimization process.

[0217] 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.

[0218] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0219] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0220] [Second Embodiment]

[0221] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0222] 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.

[0223] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0224] 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.

[0225] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0226] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0227] 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.

[0228] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0229] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0230] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0231] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0232] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0233] This invention provides an AI agent system that automates the acceptance of data communication service orders from customers. Specific embodiments thereof are described below.

[0234] First, when a user initiates a new service order, the terminal's user interface opens, and the customer enters the necessary information. The input device then sends this information to the server as structured data.

[0235] Next, the server uses natural language processing technology to analyze the received data and accurately understand customer requests and needs. This analysis employs machine learning and dictionary-based methods to extract keywords from the input text and grasp customer expectations.

[0236] Based on the analysis results, the server automatically selects the optimal data communication service plan for the customer via a plan generation mechanism. A proposal for the selected plan is generated, and this information is sent to the terminal.

[0237] Customers can view the proposed plan through the interface on their device and either approve it or request a revised proposal. If approved, the server confirms the order and continuously monitors the order's execution status using progress management tools. If any problems arise along the way, the server immediately identifies the problem and notifies the user or relevant technical staff of the solution.

[0238] Finally, once the order is complete, we use feedback collection methods to gather customer opinions and requests. This feedback is used to improve our service and help enhance the quality of future interactions.

[0239] For example, if a user requests a "high-speed internet plan for business," the system will immediately suggest a plan that meets their needs, simplifying the process. This is expected to significantly reduce time and costs compared to traditional manual processes, as well as improve user satisfaction.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] The user accesses the service order interface, fills in the required information in the form to start a new order, and clicks the submit button.

[0243] Step 2:

[0244] The terminal receives the information entered by the user as digital data and completes the process of sending it to the server as structured data.

[0245] Step 3:

[0246] The server begins processing the data received from the terminal using analysis tools. Specifically, it uses a natural language processing model to extract keywords and phrases from the data and accurately identify customer requests.

[0247] Step 4:

[0248] Based on the analysis results, the server selects the most suitable data communication service plan from among several options and creates a proposed message using a plan generation method.

[0249] Step 5:

[0250] The server sends the generated proposal message to the terminal, preparing it for presentation to the user. The proposal includes plan details, pricing, and terms and conditions.

[0251] Step 6:

[0252] Users view the proposed plan via their device, click the approve button if they are satisfied with the content, and configure their settings on their device if they require a revised proposal.

[0253] Step 7:

[0254] The terminal sends the user's selection to the server, which then processes the order accordingly. If approved, the order moves to the execution phase.

[0255] Step 8:

[0256] The server uses progress management tools to monitor the progress of orders and updates statuses such as "Currently processing" and "Technical team is working on it" in real time.

[0257] Step 9:

[0258] If a problem occurs in the order process, the server will immediately detect the anomaly and notify the user or technical staff of the steps and recommended actions for resolving the problem.

[0259] Step 10:

[0260] After an order is completed, the server collects user ratings and comments through feedback collection mechanisms and saves this data as material for service improvement.

[0261] (Example 1)

[0262] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0263] Modern communication services require efficient and accurate responses to diverse customer needs. However, traditional manual order processing and plan proposals are time-consuming and may not fully achieve customer satisfaction. Furthermore, there are challenges in managing order progress, responding quickly to problems, and collecting feedback for service improvement.

[0264] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0265] In this invention, the server includes an input means for acquiring customer information as structured data, a means for analyzing the received information using natural language processing technology, and a means for generating an optimal data communication service plan based on the analysis results. This enables rapid understanding of customer needs and provision of appropriate plans, continuous order management and problem handling, and collection of feedback for improving service quality.

[0266] "Input method" refers to a method for obtaining necessary information from customers and inputting it into the system in a format that can be processed.

[0267] "Communication means" refers to a means of transmitting data from a terminal to a server, and involves transferring structured data according to a predetermined protocol.

[0268] "Analysis means" refers to the process of analyzing received information using natural language processing technology to extract customer needs.

[0269] The "plan generation method" is a method for generating a data communication service plan that is suitable for the customer's needs based on the analysis results.

[0270] A "proposal presentation method" refers to a means of presenting the generated plan to the customer as a proposal and receiving requests for approval or revisions.

[0271] A "progress management system" is a process for monitoring the progress of an order and taking immediate action if a problem arises.

[0272] A "feedback collection method" is a method of gathering evaluation information from customers after an order is completed and using that information to improve the service.

[0273] A "generative AI model" is an artificial intelligence model that uses machine learning techniques to analyze data and select the optimal service plan.

[0274] A "prompt message" is a sentence used to give instructions or requests to an AI system, and is used when processing data or proposing services.

[0275] The embodiments for carrying out the present invention will be described in detail.

[0276] This AI agent system is designed to efficiently obtain data communication service orders from customers and provide appropriate plans. The system primarily functions through the cooperation of users, terminals, and servers.

[0277] The user initiates an order for a data communication service using a terminal. They input the necessary information into the terminal's user interface and transmit it. The input information is converted into structured data by the terminal and sent to the server.

[0278] The terminal is responsible for packaging user input data into a standard data format such as JSON and sending it to the server using an HTTP POST request. In this process, the terminal maintains the accuracy and integrity of the data.

[0279] The server uses natural language processing techniques to analyze the received data. Specifically, it extracts customer needs from text data using Python's NLTK library and generative AI models. Based on the results, the server generates an appropriate data communication service plan. The generated plan is then constructed as a proposal by a template engine and sent to the terminal.

[0280] Once a plan is presented to the user, they can review the proposed plan on their device and either approve it or request a revised proposal. The server confirms the order based on this response and monitors the order's progress. In case of any problems, the server identifies the issue and notifies the user or relevant technical staff of the necessary information.

[0281] Finally, when the order is completed, the server uses feedback collection means to collect evaluation information from customers. The feedback data is analyzed using an AI model and used to improve future services.

[0282] As a specific example, consider the case where a user requests a "high-speed business Internet plan". Examples of prompt sentences for this system include "I hope to have a high-speed Internet service for business. Please propose a recommended plan." By doing so, it is possible to quickly and accurately propose a plan that meets the user's needs, and to improve service efficiency and customer satisfaction.

[0283] The flow of the specific process in Example 1 will be described using FIG. 11.

[0284] Step 1:

[0285] The user starts an order for a data communication service and enters the necessary information into the user interface on the terminal. As a specific operation, the user enters data such as their name, contact information, and desired service content into a form. The input for this step is the data entered by the user, and the output is the structured data on the terminal.

[0286] Step 2:

[0287] The terminal packages the user's input data as structured data and sends it to the server. Specifically, the terminal converts the input data into JSON format and sends it to the server using an HTTP POST request. The input for this step is the structured data received from the user interface, and the output is the data sent to the server.

[0288] Step 3:

[0289] The server analyzes the received structured data using natural language processing techniques. Specifically, the server uses generative AI models and natural language tools to analyze text data and extract customer needs and expectations. The input for this step is data sent from the terminal, and the output is the analyzed needs information.

[0290] Step 4:

[0291] The server generates an appropriate data communication service plan based on the analysis results. Specifically, the server utilizes a generation AI model to construct a plan based on customer needs and selects the most suitable option from its internal database. The input for this step is the analyzed needs information, and the output is a proposed plan.

[0292] Step 5:

[0293] The server sends the generated plan proposal to the terminal. Specifically, the server generates the proposal in HTML or PDF format and sends it to the terminal via real-time notification or email. The input for this step is the generated plan proposal, and the output is the proposal delivered to the terminal.

[0294] Step 6:

[0295] The user reviews the proposed plan using their device and requests approval or a revised proposal. Specifically, the user views the proposal on the device's interface and clicks a selection button to determine the next action. The input for this step is the proposal from the server, and the output is the user's request for approval or a revised proposal.

[0296] Step 7:

[0297] The server confirms the order upon user approval and manages its progress. Specifically, the server monitors the order's progress and takes steps to quickly address any problems that arise. The input for this step is the user's actions, and the output is the confirmed order and its monitoring information.

[0298] Step 8:

[0299] The server collects evaluation information from customers using a feedback collection mechanism after the order is completed. Specifically, the server generates a questionnaire and sends it along with the completion notification to request feedback. The input for this step is the completed order information, and the output is customer feedback data.

[0300] (Application Example 1)

[0301] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0302] Modern consumers want to efficiently and quickly select from a wide variety of goods and services, but information overload often makes the selection process time-consuming. Furthermore, while they desire to shop while receiving abundant visual information, traditional methods have presented challenges in quickly suggesting products that meet customer needs.

[0303] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0304] In this invention, the server includes an input means for receiving information from the customer, an operation means for processing customer requests in real time via voice input and presenting information visually, and a means for presenting a proposed plan on the customer's visual display device and obtaining approval. This enables the customer to efficiently select products and obtain information in real time through a visually assisted shopping assistant.

[0305] "Customer information" is a general term for personal data provided by customers and data related to their requests.

[0306] "Natural language processing technology" is a technology used by computers to understand and process human language, and is used to analyze text data and extract keywords.

[0307] "Plan generation means" is a function that executes a process of automatically selecting an optimal product or service plan according to customer requests based on the analyzed information.

[0308] "Visual display device" is a device for displaying electronically generated information in the user's field of vision, including smart glasses, etc.

[0309] "Voice input means" is a device or function that receives the user's voice as a digital signal and converts it into analyzable text data.

[0310] "Generated AI model" is an artificial intelligence model used to process customer information in real time using machine learning and select appropriate products and services.

[0311] "Prompt text" is a text instruction input into the generated AI model, which functions as a guideline for performing specific analysis and generation tasks.

[0312] In this invention, the following configuration is adopted to realize a visual assistance shopping assistant system. Mainly, a visual display device such as smart glasses and a server cooperate to operate.

[0313] The server receives requests from users through voice input. At this stage, the voice data is converted into text data using speech recognition technology such as the Google Speech-to-Text API. This text data is then analyzed using natural language processing techniques such as the Python libraries SpaCy and NLTK. From the analyzed information, keywords and intentions related to the user's request are extracted and processed using machine learning models (using TensorFlow or PyTorch) to select appropriate products and services.

[0314] The visual display device overlays information transmitted from the server onto the user's field of view. This allows the user to check selected product information in real time. Furthermore, to collect user feedback, a generative AI model is used to analyze user evaluations using prompt messages and generate insights.

[0315] For example, if a user gives a voice command such as "I'm looking for lightweight running shoes," the server analyzes the request and displays potential products on the glasses' display. The user can then view detailed information about the selected products and proceed with the purchase.

[0316] An example of a prompt to be input into the generating AI model would be: "Develop an algorithm that uses an AI agent to analyze the user's intent from their voice input and select products that match that intent." This would enable a system that allows users to more smoothly select the products they need and streamline the purchase process.

[0317] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0318] Step 1:

[0319] The user speaks their request through the voice input feature of their smart glasses. The voice data is input and converted into text data by the Google Speech-to-Text API. This input text data is used for natural language processing in the next step.

[0320] Step 2:

[0321] The server receives text data and performs natural language processing using Python libraries such as SpaCy and NLTK. The analysis extracts keywords and user intent from the text data, and these analysis results are output in the next step as information that forms the basis for product selection.

[0322] Step 3:

[0323] Based on the analysis results, the server searches the product database using a machine learning model based on TensorFlow or PyTorch to select products that match the user's needs. The product information selected by this generative AI model is output within the system and used for visual presentation in the next step.

[0324] Step 4:

[0325] The device (smart glasses) receives the selected product information and displays it as an overlay on the user's screen. Specifically, it displays detailed information such as the product name, price, and image within the user's field of view. This allows the user to easily and visually confirm the product.

[0326] Step 5:

[0327] Users select products of interest based on the visually displayed information and proceed to view further details or complete the purchase process. This input is sent to the server as feedback and used to improve subsequent services.

[0328] Step 6:

[0329] The server analyzes the collected feedback based on a generating AI model and uses prompt messages to generate insights from the feedback. Through this process, the system continuously learns, understands user preferences and behavioral patterns, and improves the service.

[0330] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0331] This invention relates to an AI agent system that automates the order acceptance process for customer data communication services by combining it with an emotion engine. In addition to basic functions such as receiving, analyzing, suggesting, and managing customer information, this system can recognize user emotions using the emotion engine and improve the service experience.

[0332] When a user initiates a service order, data such as the text entered and the tone of voice are sent to the server via the terminal, along with the necessary information. The server analyzes this data through natural language processing and simultaneously detects the user's emotional state using an emotion engine. For example, it can accurately recognize emotions such as positive, negative, or neutral from the tone of the text and the choice of words.

[0333] Based on the customer's emotional state, the server utilizes a plan generation mechanism to propose the most suitable data communication plan, and in some cases, offers customized suggestions tailored to the customer's mood. This allows customers to easily select a service that is more appropriate to their emotional state.

[0334] Furthermore, as the user accepts the proposal and the order progresses, progress management tools constantly monitor the process, and the emotion engine tracks emotional fluctuations in real time. For example, if a customer becomes stressed along the way, the server can immediately respond and provide support or make alternative suggestions.

[0335] Furthermore, after an order is completed, feedback is collected from the user through feedback collection methods. This feedback includes the results of the emotion engine analysis and plays a role in providing valuable insights for service improvement.

[0336] For example, if a user is dissatisfied with their internet speed, the server can analyze their feelings using an emotion engine and immediately provide additional information about high-speed plans or discount offers, thereby improving the user experience and increasing customer satisfaction. Implementing such a system allows for more personalized and rapid responses compared to traditional methods.

[0337] The following describes the processing flow.

[0338] Step 1:

[0339] The user accesses a form on their device, enters information about their desired data communication service, and sends it as a text or voice message.

[0340] Step 2:

[0341] The terminal receives user input information as digital data, converts it into a format that can be processed by the emotion engine and analysis tools, and then sends it to the server.

[0342] Step 3:

[0343] The server first passes the received data to the emotion engine, which analyzes the user's emotional state from their input. During this process, it analyzes the emotional nuances of the text and the tone of voice to identify emotions such as "positive" or "negative."

[0344] Step 4:

[0345] In parallel, the server uses natural language processing technology to analyze user information and extract specific requests and requirements. For example, it identifies keywords such as "high-speed internet is needed."

[0346] Step 5:

[0347] The server integrates the results of sentiment analysis and natural language processing, and uses a plan generation mechanism to automatically generate the optimal data communication plan that matches the user's emotional state, and sends it to the terminal.

[0348] Step 6:

[0349] The terminal displays plan proposals from the server to the user, allowing the user to view them. The user can review the proposal and either approve it or request a revised proposal.

[0350] Step 7:

[0351] If approval is obtained, the server confirms the order and monitors its progress using progress management tools. If the emotion engine detects user stress or dissatisfaction along the way, it quickly considers countermeasures and provides suggested changes and support.

[0352] Step 8:

[0353] After all orders are completed, the server uses various feedback collection methods to obtain feedback from the user. During this process, changes in the user's emotional state are also recorded and used to improve the service and refine future suggestions.

[0354] (Example 2)

[0355] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0356] In data communication services, there is a problem in that customers have difficulty quickly and accurately selecting the optimal plan that suits their emotions and needs. Furthermore, the inability to track and appropriately respond to changes in customer emotions during service use has prevented improvements in the quality of the service experience. In addition, there has been a lack of systematic methods for utilizing feedback after order completion to improve the service.

[0357] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0358] In this invention, the server includes an information analysis device, a plan generation device, and an emotion detection device. This enables automatic proposal of data communication plans that take customer emotions into consideration, and real-time responses to changes in emotions. Furthermore, a feedback collection device allows for systematic analysis of customer opinions, enabling continuous improvement of the service.

[0359] An "information input device" is a device used to collect necessary information from customers and transmit it to the system.

[0360] An "information analysis device" is a device that analyzes received customer information using natural language processing technology.

[0361] A "plan generation device" is a device that generates the optimal data communication plan for a customer based on analyzed information.

[0362] A "presentation device" is a device used to present the generated plan to the customer and obtain their approval.

[0363] A "progress management device" is a device used to monitor the progress of an order, detect problems, and provide solutions.

[0364] A "feedback collection device" is a device used to collect feedback from customers after an order is completed and to use that feedback to improve services.

[0365] An "emotion detection device" is a device that uses emotion analysis technology to detect a customer's emotional state and reflect that in service proposals.

[0366] An "emotion tracking device" is a device that tracks customer emotional fluctuations in real time and provides support as needed.

[0367] This system consists of multiple devices designed to improve the user experience in data communication services. The server plays a central role in processing information transmitted from the terminal. The user first inputs the necessary information through the terminal. This information input device collects information in the form of text input or voice commands and sends it to the server.

[0368] The server processes the received information using an information analysis device and utilizes natural language processing technology to deepen its understanding of user requests. This process employs machine learning models, specifically using the Google Cloud Natural Language API. Based on the analyzed data, a plan generation device automatically creates the optimal data communication plan.

[0369] Furthermore, the server analyzes the user's emotional state through an emotion detection device. This emotion analysis uses techniques including contextual understanding and tone analysis to track the user's emotions in real time. Tools such as Microsoft Azure's Text Analytics are used for this task. This enables personalized plan suggestions based on emotions, improving user satisfaction.

[0370] The progress management system monitors the order's progress in real time, and the emotion tracking system automatically adjusts support when it detects changes in emotion. This allows, for example, the server to immediately suggest countermeasures if a user experiences stress during the process.

[0371] After an order is completed, user feedback is collected by a feedback collection device and used, along with sentiment analysis results, to improve future services. The insights gained from this feedback enable continuous improvement of service quality.

[0372] For example, if a user expresses dissatisfaction when selecting a communication plan, the server prompts the generated AI model with the message, "Please provide a method for suggesting an appropriate communication plan based on the information entered by the new user," thereby providing the user with a better suggestion. In this way, optimized customer service tailored to the environment becomes possible.

[0373] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0374] Step 1:

[0375] The user uses a terminal to input the necessary information into the information input device. This information includes text data and voice data. Through the user interface, the user can input, for example, their name, contact information, and desired services. The entered information is sent from the terminal to the server.

[0376] Step 2:

[0377] The server receives information transmitted from the terminal and initiates natural language processing using an information analysis device. The input data is text-based, and the server performs keyword extraction and semantic analysis on this data. Machine learning techniques are used to effectively interpret customer needs and requests from the input information.

[0378] Step 3:

[0379] Based on the analysis results, the server designs the optimal data communication plan using a plan generation device. It receives output from the information analysis device and customizes the plan by taking into account past data and market information. For example, the initial proposed plan is the one best suited to the customer's usage history and requests.

[0380] Step 4:

[0381] The server utilizes an emotion detection device to analyze the user's emotions from the wording and context in the input data. In this process, an emotion analysis model is used to accurately determine positive, negative, or neutral emotional states. An emotional evaluation is generated as output, which is then used to create the plan for the next step.

[0382] Step 5:

[0383] The server uses a plan generator to fine-tune the plan based on the user's emotional data. It provides personalized suggestions while taking emotional states into consideration. For example, if negative emotions are detected, the server will offer the customer a plan with more flexible terms or discounts.

[0384] Step 6:

[0385] The server continuously monitors the progress of orders through a progress management device. During this time, an emotion tracking device tracks customer emotional changes in real time and deploys prompt support as needed. If an emotional change is detected, an alert is immediately sent to support staff, and appropriate assistance is provided to the customer.

[0386] Step 7:

[0387] Once a user completes an order, the server collects feedback using a feedback collection device. The collected opinions and evaluation data are evaluated along with sentiment analysis to derive insights for service improvement. The opinions obtained from the feedback analysis will be used for future service development and improvement measures.

[0388] (Application Example 2)

[0389] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0390] In today's e-commerce industry, it is considered difficult to provide personalized experiences based on individual customer emotions and needs when customers make online purchases. This can lead to increased customer dissatisfaction and abandonment of the purchase process, potentially resulting in decreased customer loyalty. This invention aims to improve the user experience by analyzing customer emotions in real time and making optimal product and service recommendations based on that analysis.

[0391] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0392] In this invention, the server includes an information input means, an information analysis means, a plan generation means, a presentation means, a progress management means, an opinion collection means, and an emotion recognition and suggestion means. This enables the analysis of the customer's emotional state and the suggestion of corresponding product information and discount information in real time, thereby improving customer satisfaction and optimizing the purchase process.

[0393] An "information input means" is a component that receives data provided by a customer and performs the initial process necessary for further analysis or processing within the system.

[0394] "Information analysis means" refers to a device or program that uses natural language processing technology to interpret received customer data and analyze its contents.

[0395] A "plan generation means" is a component for automatically creating the most appropriate information and communication plan based on the analyzed information.

[0396] A "presentation method" refers to a configuration that has the function of displaying the generated information and communication plan to the customer in an easy-to-understand manner and encouraging approval or selection.

[0397] A "progress management system" is a mechanism that monitors the progress of an order, detects problems as needed, and implements a process to provide solutions.

[0398] "Methods for gathering feedback" refer to components used to obtain feedback from customers after an order is completed and to gain insights for service improvement based on that feedback.

[0399] "Emotion recognition suggestion means" refers to a device or function that detects a customer's emotions in real time and dynamically suggests product information and discount information based on those emotions.

[0400] This system has a configuration that transfers data obtained from customers through an information input means to a server, which then supports subsequent processing. The server has powerful information analysis capabilities and analyzes the received data using natural language processing technology. Specifically, it receives voice data and text data and uses a pre-trained machine learning model to determine the customer's emotions. The analysis results are then used by a plan generation means to create an optimal information and communication plan that matches the customer's emotions and needs.

[0401] In this system, emotion recognition and suggestion mechanisms play a crucial role. Using these mechanisms, the server monitors customer emotions in real time and, based on those emotions, presents personalized product and discount information to each individual customer. This allows users to have a more personalized and enriching experience, much like window shopping.

[0402] For example, if voice and text analysis reveals that a user is interested in a product but dissatisfied with its price, the system recognizes this sentiment and suggests relevant discount information or alternative products. Furthermore, if a customer encounters a problem during the purchase process, a progress management system detects this and immediately provides a solution.

[0403] An example of a prompt using a generative AI model is as follows: In response to customer feedback that "this smartphone is a little expensive," consider an approach that offers alternatives or discounts.

[0404] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0405] Step 1:

[0406] The terminal receives voice and text data from the user. This input data includes the user's wishes and opinions. The terminal converts this data into a digital format and sends it to the server.

[0407] Step 2:

[0408] The server analyzes the received audio and text data using information analysis tools. This analysis process applies natural language processing techniques to extract specific keywords and emotional nuances from the data. The analysis results include information about the user's emotions and desires.

[0409] Step 3:

[0410] The server uses a plan generation means to create an optimal information and communication plan based on the analysis results. In this step, emotion recognition suggestion means are utilized, and the generating AI model personalizes the suggested content. The generated plan includes suggestions that reflect the user's emotional state and preferences.

[0411] Step 4:

[0412] The server sends the information and communication plan created by the plan generation means back to the terminal via the presentation means. The terminal presents this information to the user, allows them to review the proposal, and requests approval. Based on the user's response, final adjustments to the plan may be made.

[0413] Step 5:

[0414] After the user approves the information and communication plan, the server continues to monitor the order status using progress management tools. If necessary, it detects problems, primarily using generative AI models, and dynamically provides solutions.

[0415] Step 6:

[0416] Once the process is complete, the server collects feedback from users through feedback collection mechanisms. This feedback is analyzed by the server and used to gain insights for service improvement. The generated insights are then used in the next optimization process.

[0417] 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.

[0418] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0419] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0420] [Third Embodiment]

[0421] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0422] 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.

[0423] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0424] 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.

[0425] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0426] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0427] 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.

[0428] 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.

[0429] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0430] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0431] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0432] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0433] This invention provides an AI agent system that automates the acceptance of data communication service orders from customers. Specific embodiments thereof are described below.

[0434] First, when a user initiates a new service order, the terminal's user interface opens, and the customer enters the necessary information. The input device then sends this information to the server as structured data.

[0435] Next, the server uses natural language processing technology to analyze the received data and accurately understand customer requests and needs. This analysis employs machine learning and dictionary-based methods to extract keywords from the input text and grasp customer expectations.

[0436] Based on the analysis results, the server automatically selects the optimal data communication service plan for the customer via a plan generation mechanism. A proposal for the selected plan is generated, and this information is sent to the terminal.

[0437] Customers can view the proposed plan through the interface on their device and either approve it or request a revised proposal. If approved, the server confirms the order and continuously monitors the order's execution status using progress management tools. If any problems arise along the way, the server immediately identifies the problem and notifies the user or relevant technical staff of the solution.

[0438] Finally, once the order is complete, we use feedback collection methods to gather customer opinions and requests. This feedback is used to improve our service and help enhance the quality of future interactions.

[0439] For example, if a user requests a "high-speed internet plan for business," the system will immediately suggest a plan that meets their needs, simplifying the process. This is expected to significantly reduce time and costs compared to traditional manual processes, as well as improve user satisfaction.

[0440] The following describes the processing flow.

[0441] Step 1:

[0442] The user accesses the service order interface, fills in the required information in the form to start a new order, and clicks the submit button.

[0443] Step 2:

[0444] The terminal receives the information entered by the user as digital data and completes the process of sending it to the server as structured data.

[0445] Step 3:

[0446] The server begins processing the data received from the terminal using analysis tools. Specifically, it uses a natural language processing model to extract keywords and phrases from the data and accurately identify customer requests.

[0447] Step 4:

[0448] Based on the analysis results, the server selects the most suitable data communication service plan from among several options and creates a proposed message using a plan generation method.

[0449] Step 5:

[0450] The server sends the generated proposal message to the terminal, preparing it for presentation to the user. The proposal includes plan details, pricing, and terms and conditions.

[0451] Step 6:

[0452] Users view the proposed plan via their device, click the approve button if they are satisfied with the content, and configure their settings on their device if they require a revised proposal.

[0453] Step 7:

[0454] The terminal sends the user's selection to the server, which then processes the order accordingly. If approved, the order moves to the execution phase.

[0455] Step 8:

[0456] The server uses progress management tools to monitor the progress of orders and updates statuses such as "Currently processing" and "Technical team is working on it" in real time.

[0457] Step 9:

[0458] If a problem occurs in the order process, the server will immediately detect the anomaly and notify the user or technical staff of the steps and recommended actions for resolving the problem.

[0459] Step 10:

[0460] After an order is completed, the server collects user ratings and comments through feedback collection mechanisms and saves this data as material for service improvement.

[0461] (Example 1)

[0462] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0463] Modern communication services require efficient and accurate responses to diverse customer needs. However, traditional manual order processing and plan proposals are time-consuming and may not fully achieve customer satisfaction. Furthermore, there are challenges in managing order progress, responding quickly to problems, and collecting feedback for service improvement.

[0464] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0465] In this invention, the server includes an input means for acquiring customer information as structured data, a means for analyzing the received information using natural language processing technology, and a means for generating an optimal data communication service plan based on the analysis results. This enables rapid understanding of customer needs and provision of appropriate plans, continuous order management and problem handling, and collection of feedback for improving service quality.

[0466] "Input method" refers to a method for obtaining necessary information from customers and inputting it into the system in a format that can be processed.

[0467] "Communication means" refers to a means of transmitting data from a terminal to a server, and involves transferring structured data according to a predetermined protocol.

[0468] "Analysis means" refers to the process of analyzing received information using natural language processing technology to extract customer needs.

[0469] The "plan generation method" is a method for generating a data communication service plan that is suitable for the customer's needs based on the analysis results.

[0470] A "proposal presentation method" refers to a means of presenting the generated plan to the customer as a proposal and receiving requests for approval or revisions.

[0471] A "progress management system" is a process for monitoring the progress of an order and taking immediate action if a problem arises.

[0472] A "feedback collection method" is a method of gathering evaluation information from customers after an order is completed and using that information to improve the service.

[0473] A "generative AI model" is an artificial intelligence model that uses machine learning techniques to analyze data and select the optimal service plan.

[0474] A "prompt message" is a sentence used to give instructions or requests to an AI system, and is used when processing data or proposing services.

[0475] The embodiments for carrying out the present invention will be described in detail.

[0476] This AI agent system is designed to efficiently obtain data communication service orders from customers and provide appropriate plans. The system primarily functions through the cooperation of users, terminals, and servers.

[0477] The user initiates an order for a data communication service using a terminal. They input the necessary information into the terminal's user interface and transmit it. The input information is converted into structured data by the terminal and sent to the server.

[0478] The terminal is responsible for packaging user input data into a standard data format such as JSON and sending it to the server using an HTTP POST request. In this process, the terminal maintains the accuracy and integrity of the data.

[0479] The server uses natural language processing techniques to analyze the received data. Specifically, it extracts customer needs from text data using Python's NLTK library and generative AI models. Based on the results, the server generates an appropriate data communication service plan. The generated plan is then constructed as a proposal by a template engine and sent to the terminal.

[0480] Once a plan is presented to the user, they can review the proposed plan on their device and either approve it or request a revised proposal. The server confirms the order based on this response and monitors the order's progress. In case of any problems, the server identifies the issue and notifies the user or relevant technical staff of the necessary information.

[0481] Finally, once the order is completed, the server uses feedback collection tools to gather evaluation information from the customer. This feedback data is analyzed using AI models to help improve future services.

[0482] As a concrete example, consider a case where a user requests a "high-speed internet plan for business." An example of a prompt message for this system would be, "I would like high-speed internet service for business. Please suggest a recommended plan." This allows the system to quickly and accurately suggest a plan that meets the user's needs, thereby improving service efficiency and customer satisfaction.

[0483] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0484] Step 1:

[0485] The user initiates an order for a data communication service and enters the necessary information into the user interface on the terminal. Specifically, the user enters data such as their name, contact information, and desired service into a form. The input in this step is data entered by the user, and the output is structured data on the terminal.

[0486] Step 2:

[0487] The terminal packages the user's input data as structured data and sends it to the server. Specifically, the terminal converts the input data into JSON format and sends it to the server via an HTTP POST request. In this step, the input is the structured data received from the user interface, and the output is the data sent to the server.

[0488] Step 3:

[0489] The server analyzes the received structured data using natural language processing techniques. Specifically, the server uses generative AI models and natural language tools to analyze text data and extract customer needs and expectations. The input for this step is data sent from the terminal, and the output is the analyzed needs information.

[0490] Step 4:

[0491] The server generates an appropriate data communication service plan based on the analysis results. Specifically, the server utilizes a generation AI model to construct a plan based on customer needs and selects the most suitable option from its internal database. The input for this step is the analyzed needs information, and the output is a proposed plan.

[0492] Step 5:

[0493] The server sends the generated plan proposal to the terminal. Specifically, the server generates the proposal in HTML or PDF format and sends it to the terminal via real-time notification or email. The input for this step is the generated plan proposal, and the output is the proposal delivered to the terminal.

[0494] Step 6:

[0495] The user reviews the proposed plan using their device and requests approval or a revised proposal. Specifically, the user views the proposal on the device's interface and clicks a selection button to determine the next action. The input for this step is the proposal from the server, and the output is the user's request for approval or a revised proposal.

[0496] Step 7:

[0497] The server confirms the order upon user approval and manages its progress. Specifically, the server monitors the order's progress and takes steps to quickly address any problems that arise. The input for this step is the user's actions, and the output is the confirmed order and its monitoring information.

[0498] Step 8:

[0499] The server collects evaluation information from customers using a feedback collection mechanism after the order is completed. Specifically, the server generates a questionnaire and sends it along with the completion notification to request feedback. The input for this step is the completed order information, and the output is customer feedback data.

[0500] (Application Example 1)

[0501] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0502] Modern consumers want to efficiently and quickly select from a wide variety of goods and services, but information overload often makes the selection process time-consuming. Furthermore, while they desire to shop while receiving abundant visual information, traditional methods have presented challenges in quickly suggesting products that meet customer needs.

[0503] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0504] In this invention, the server includes an input means for receiving information from the customer, an operation means for processing customer requests in real time via voice input and presenting information visually, and a means for presenting a proposed plan on the customer's visual display device and obtaining approval. This enables the customer to efficiently select products and obtain information in real time through a visually assisted shopping assistant.

[0505] "Customer information" is a general term for personal data and data related to requests provided by customers.

[0506] "Natural language processing technology" refers to the technology used by computers to understand and process human language, and involves analyzing text data and extracting keywords.

[0507] A "plan generation method" is a function that automatically selects the optimal product or service plan in response to customer requests based on the analyzed information.

[0508] A "visual display device" is a device that displays electronically generated information in the user's field of vision, and includes smart glasses, among other things.

[0509] "Voice input means" refers to a device or function that receives the user's voice as a digital signal and converts it into analyzable text data.

[0510] A "generative AI model" is an artificial intelligence model that uses machine learning to process customer information in real time and select appropriate products and services.

[0511] A "prompt" is a text instruction input into a generative AI model, serving as a guideline for performing specific analysis or generation tasks.

[0512] This invention adopts the following configuration to realize a visually assisted shopping assistant system. A visual display device, such as smart glasses, and a server work together in cooperation.

[0513] The server receives requests from users through voice input. At this stage, the voice data is converted into text data using speech recognition technology such as the Google Speech-to-Text API. This text data is then analyzed using natural language processing techniques such as the Python libraries SpaCy and NLTK. From the analyzed information, keywords and intentions related to the user's request are extracted and processed using machine learning models (using TensorFlow or PyTorch) to select appropriate products and services.

[0514] The visual display device overlays information transmitted from the server onto the user's field of view. This allows the user to check selected product information in real time. Furthermore, to collect user feedback, a generative AI model is used to analyze user evaluations using prompt messages and generate insights.

[0515] For example, if a user gives a voice command such as "I'm looking for lightweight running shoes," the server analyzes the request and displays potential products on the glasses' display. The user can then view detailed information about the selected products and proceed with the purchase.

[0516] An example of a prompt to be input into the generating AI model would be: "Develop an algorithm that uses an AI agent to analyze the user's intent from their voice input and select products that match that intent." This would enable a system that allows users to more smoothly select the products they need and streamline the purchase process.

[0517] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0518] Step 1:

[0519] The user speaks their request through the voice input feature of their smart glasses. The voice data is input and converted into text data by the Google Speech-to-Text API. This input text data is used for natural language processing in the next step.

[0520] Step 2:

[0521] The server receives text data and performs natural language processing using Python libraries such as SpaCy and NLTK. The analysis extracts keywords and user intent from the text data, and these analysis results are output in the next step as information that forms the basis for product selection.

[0522] Step 3:

[0523] Based on the analysis results, the server searches the product database using a machine learning model based on TensorFlow or PyTorch to select products that match the user's needs. The product information selected by this generative AI model is output within the system and used for visual presentation in the next step.

[0524] Step 4:

[0525] The device (smart glasses) receives the selected product information and displays it as an overlay on the user's screen. Specifically, it displays detailed information such as the product name, price, and image within the user's field of view. This allows the user to easily and visually confirm the product.

[0526] Step 5:

[0527] Users select products of interest based on the visually displayed information and proceed to view further details or complete the purchase process. This input is sent to the server as feedback and used to improve subsequent services.

[0528] Step 6:

[0529] The server analyzes the collected feedback based on a generating AI model and uses prompt messages to generate insights from the feedback. Through this process, the system continuously learns, understands user preferences and behavioral patterns, and improves the service.

[0530] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0531] This invention relates to an AI agent system that automates the order acceptance process for customer data communication services by combining it with an emotion engine. In addition to basic functions such as receiving, analyzing, suggesting, and managing customer information, this system can recognize user emotions using the emotion engine and improve the service experience.

[0532] When a user initiates a service order, data such as the text entered and the tone of voice are sent to the server via the terminal, along with the necessary information. The server analyzes this data through natural language processing and simultaneously detects the user's emotional state using an emotion engine. For example, it can accurately recognize emotions such as positive, negative, or neutral from the tone of the text and the choice of words.

[0533] Based on the customer's emotional state, the server utilizes a plan generation mechanism to propose the most suitable data communication plan, and in some cases, offers customized suggestions tailored to the customer's mood. This allows customers to easily select a service that is more appropriate to their emotional state.

[0534] Furthermore, as the user accepts the proposal and the order progresses, progress management tools constantly monitor the process, and the emotion engine tracks emotional fluctuations in real time. For example, if a customer becomes stressed along the way, the server can immediately respond and provide support or make alternative suggestions.

[0535] Furthermore, after an order is completed, feedback is collected from the user through feedback collection methods. This feedback includes the results of the emotion engine analysis and plays a role in providing valuable insights for service improvement.

[0536] For example, if a user is dissatisfied with their internet speed, the server can analyze their feelings using an emotion engine and immediately provide additional information about high-speed plans or discount offers, thereby improving the user experience and increasing customer satisfaction. Implementing such a system allows for more personalized and rapid responses compared to traditional methods.

[0537] The following describes the processing flow.

[0538] Step 1:

[0539] The user accesses a form on their device, enters information about their desired data communication service, and sends it as a text or voice message.

[0540] Step 2:

[0541] The terminal receives user input information as digital data, converts it into a format that can be processed by the emotion engine and analysis tools, and then sends it to the server.

[0542] Step 3:

[0543] The server first passes the received data to the emotion engine, which analyzes the user's emotional state from their input. During this process, it analyzes the emotional nuances of the text and the tone of voice to identify emotions such as "positive" or "negative."

[0544] Step 4:

[0545] In parallel, the server uses natural language processing technology to analyze user information and extract specific requests and requirements. For example, it identifies keywords such as "high-speed internet is needed."

[0546] Step 5:

[0547] The server integrates the results of sentiment analysis and natural language processing, and uses a plan generation mechanism to automatically generate the optimal data communication plan that matches the user's emotional state, and sends it to the terminal.

[0548] Step 6:

[0549] The terminal displays plan proposals from the server to the user, allowing the user to view them. The user can review the proposal and either approve it or request a revised proposal.

[0550] Step 7:

[0551] If approval is obtained, the server confirms the order and monitors its progress using progress management tools. If the emotion engine detects user stress or dissatisfaction along the way, it quickly considers countermeasures and provides suggested changes and support.

[0552] Step 8:

[0553] After all orders are completed, the server uses various feedback collection methods to obtain feedback from the user. During this process, changes in the user's emotional state are also recorded and used to improve the service and refine future suggestions.

[0554] (Example 2)

[0555] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0556] In data communication services, there is a problem in that customers have difficulty quickly and accurately selecting the optimal plan that suits their emotions and needs. Furthermore, the inability to track and appropriately respond to changes in customer emotions during service use has prevented improvements in the quality of the service experience. In addition, there has been a lack of systematic methods for utilizing feedback after order completion to improve the service.

[0557] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0558] In this invention, the server includes an information analysis device, a plan generation device, and an emotion detection device. This enables automatic proposal of data communication plans that take customer emotions into consideration, and real-time responses to changes in emotions. Furthermore, a feedback collection device allows for systematic analysis of customer opinions, enabling continuous improvement of the service.

[0559] An "information input device" is a device used to collect necessary information from customers and transmit it to the system.

[0560] An "information analysis device" is a device that analyzes received customer information using natural language processing technology.

[0561] A "plan generation device" is a device that generates the optimal data communication plan for a customer based on analyzed information.

[0562] A "presentation device" is a device used to present the generated plan to the customer and obtain their approval.

[0563] A "progress management device" is a device used to monitor the progress of an order, detect problems, and provide solutions.

[0564] A "feedback collection device" is a device used to collect feedback from customers after an order is completed and to use that feedback to improve services.

[0565] An "emotion detection device" is a device that uses emotion analysis technology to detect a customer's emotional state and reflect that in service proposals.

[0566] An "emotion tracking device" is a device that tracks customer emotional fluctuations in real time and provides support as needed.

[0567] This system consists of multiple devices designed to improve the user experience in data communication services. The server plays a central role in processing information transmitted from the terminal. The user first inputs the necessary information through the terminal. This information input device collects information in the form of text input or voice commands and sends it to the server.

[0568] The server processes the received information using an information analysis device and utilizes natural language processing technology to deepen its understanding of user requests. This process employs machine learning models, specifically using the Google Cloud Natural Language API. Based on the analyzed data, a plan generation device automatically creates the optimal data communication plan.

[0569] Furthermore, the server analyzes the user's emotional state through an emotion detection device. This emotion analysis uses techniques including contextual understanding and tone analysis to track the user's emotions in real time. Tools such as Microsoft Azure's Text Analytics are used for this task. This enables personalized plan suggestions based on emotions, improving user satisfaction.

[0570] The progress management system monitors the order's progress in real time, and the emotion tracking system automatically adjusts support when it detects changes in emotion. This allows, for example, the server to immediately suggest countermeasures if a user experiences stress during the process.

[0571] After an order is completed, user feedback is collected by a feedback collection device and used, along with sentiment analysis results, to improve future services. The insights gained from this feedback enable continuous improvement of service quality.

[0572] For example, if a user expresses dissatisfaction when selecting a communication plan, the server prompts the generated AI model with the message, "Please provide a method for suggesting an appropriate communication plan based on the information entered by the new user," thereby providing the user with a better suggestion. In this way, optimized customer service tailored to the environment becomes possible.

[0573] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0574] Step 1:

[0575] The user uses a terminal to input the necessary information into the information input device. This information includes text data and voice data. Through the user interface, the user can input, for example, their name, contact information, and desired services. The entered information is sent from the terminal to the server.

[0576] Step 2:

[0577] The server receives information transmitted from the terminal and initiates natural language processing using an information analysis device. The input data is text-based, and the server performs keyword extraction and semantic analysis on this data. Machine learning techniques are used to effectively interpret customer needs and requests from the input information.

[0578] Step 3:

[0579] Based on the analysis results, the server designs the optimal data communication plan using a plan generation device. It receives output from the information analysis device and customizes the plan by taking into account past data and market information. For example, the initial proposed plan is the one best suited to the customer's usage history and requests.

[0580] Step 4:

[0581] The server utilizes an emotion detection device to analyze the user's emotions from the wording and context in the input data. In this process, an emotion analysis model is used to accurately determine positive, negative, or neutral emotional states. An emotional evaluation is generated as output, which is then used to create the plan for the next step.

[0582] Step 5:

[0583] The server uses a plan generator to fine-tune the plan based on the user's emotional data. It provides personalized suggestions while taking emotional states into consideration. For example, if negative emotions are detected, the server will offer the customer a plan with more flexible terms or discounts.

[0584] Step 6:

[0585] The server continuously monitors the progress of orders through a progress management device. During this time, an emotion tracking device tracks customer emotional changes in real time and deploys prompt support as needed. If an emotional change is detected, an alert is immediately sent to support staff, and appropriate assistance is provided to the customer.

[0586] Step 7:

[0587] Once a user completes an order, the server collects feedback using a feedback collection device. The collected opinions and evaluation data are evaluated along with sentiment analysis to derive insights for service improvement. The opinions obtained from the feedback analysis will be used for future service development and improvement measures.

[0588] (Application Example 2)

[0589] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0590] In today's e-commerce industry, it is considered difficult to provide personalized experiences based on individual customer emotions and needs when customers make online purchases. This can lead to increased customer dissatisfaction and abandonment of the purchase process, potentially resulting in decreased customer loyalty. This invention aims to improve the user experience by analyzing customer emotions in real time and making optimal product and service recommendations based on that analysis.

[0591] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0592] In this invention, the server includes an information input means, an information analysis means, a plan generation means, a presentation means, a progress management means, an opinion collection means, and an emotion recognition and suggestion means. This enables the analysis of the customer's emotional state and the suggestion of corresponding product information and discount information in real time, thereby improving customer satisfaction and optimizing the purchase process.

[0593] An "information input means" is a component that receives data provided by a customer and performs the initial process necessary for further analysis or processing within the system.

[0594] "Information analysis means" refers to a device or program that uses natural language processing technology to interpret received customer data and analyze its contents.

[0595] A "plan generation means" is a component for automatically creating the most appropriate information and communication plan based on the analyzed information.

[0596] A "presentation method" refers to a configuration that has the function of displaying the generated information and communication plan to the customer in an easy-to-understand manner and encouraging approval or selection.

[0597] A "progress management system" is a mechanism that monitors the progress of an order, detects problems as needed, and implements a process to provide solutions.

[0598] "Methods for gathering feedback" refer to components used to obtain feedback from customers after an order is completed and to gain insights for service improvement based on that feedback.

[0599] "Emotion recognition suggestion means" refers to a device or function that detects a customer's emotions in real time and dynamically suggests product information and discount information based on those emotions.

[0600] This system has a configuration that transfers data obtained from customers through an information input means to a server, which then supports subsequent processing. The server has powerful information analysis capabilities and analyzes the received data using natural language processing technology. Specifically, it receives voice data and text data and uses a pre-trained machine learning model to determine the customer's emotions. The analysis results are then used by a plan generation means to create an optimal information and communication plan that matches the customer's emotions and needs.

[0601] In this system, emotion recognition and suggestion mechanisms play a crucial role. Using these mechanisms, the server monitors customer emotions in real time and, based on those emotions, presents personalized product and discount information to each individual customer. This allows users to have a more personalized and enriching experience, much like window shopping.

[0602] For example, if voice and text analysis reveals that a user is interested in a product but dissatisfied with its price, the system recognizes this sentiment and suggests relevant discount information or alternative products. Furthermore, if a customer encounters a problem during the purchase process, a progress management system detects this and immediately provides a solution.

[0603] An example of a prompt using a generative AI model is as follows: In response to customer feedback that "this smartphone is a little expensive," consider an approach that offers alternatives or discounts.

[0604] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0605] Step 1:

[0606] The terminal receives voice and text data from the user. This input data includes the user's wishes and opinions. The terminal converts this data into a digital format and sends it to the server.

[0607] Step 2:

[0608] The server analyzes the received audio and text data using information analysis tools. This analysis process applies natural language processing techniques to extract specific keywords and emotional nuances from the data. The analysis results include information about the user's emotions and desires.

[0609] Step 3:

[0610] The server uses a plan generation means to create an optimal information and communication plan based on the analysis results. In this step, emotion recognition suggestion means are utilized, and the generating AI model personalizes the suggested content. The generated plan includes suggestions that reflect the user's emotional state and preferences.

[0611] Step 4:

[0612] The server sends the information and communication plan created by the plan generation means back to the terminal via the presentation means. The terminal presents this information to the user, allows them to review the proposal, and requests approval. Based on the user's response, final adjustments to the plan may be made.

[0613] Step 5:

[0614] After the user approves the information and communication plan, the server continues to monitor the order status using progress management tools. If necessary, it detects problems, primarily using generative AI models, and dynamically provides solutions.

[0615] Step 6:

[0616] Once the process is complete, the server collects feedback from users through feedback collection mechanisms. This feedback is analyzed by the server and used to gain insights for service improvement. The generated insights are then used in the next optimization process.

[0617] 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.

[0618] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0619] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0620] [Fourth Embodiment]

[0621] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0622] 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.

[0623] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0624] 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.

[0625] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0626] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0627] 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.

[0628] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0629] 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.

[0630] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0631] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0632] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0633] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0634] This invention provides an AI agent system that automates the acceptance of data communication service orders from customers. Specific embodiments thereof are described below.

[0635] First, when a user initiates a new service order, the terminal's user interface opens, and the customer enters the necessary information. The input device then sends this information to the server as structured data.

[0636] Next, the server uses natural language processing technology to analyze the received data and accurately understand customer requests and needs. This analysis employs machine learning and dictionary-based methods to extract keywords from the input text and grasp customer expectations.

[0637] Based on the analysis results, the server automatically selects the optimal data communication service plan for the customer via a plan generation mechanism. A proposal for the selected plan is generated, and this information is sent to the terminal.

[0638] Customers can view the proposed plan through the interface on their device and either approve it or request a revised proposal. If approved, the server confirms the order and continuously monitors the order's execution status using progress management tools. If any problems arise along the way, the server immediately identifies the problem and notifies the user or relevant technical staff of the solution.

[0639] Finally, once the order is complete, we use feedback collection methods to gather customer opinions and requests. This feedback is used to improve our service and help enhance the quality of future interactions.

[0640] For example, if a user requests a "high-speed internet plan for business," the system will immediately suggest a plan that meets their needs, simplifying the process. This is expected to significantly reduce time and costs compared to traditional manual processes, as well as improve user satisfaction.

[0641] The following describes the processing flow.

[0642] Step 1:

[0643] The user accesses the service order interface, fills in the required information in the form to start a new order, and clicks the submit button.

[0644] Step 2:

[0645] The terminal receives the information entered by the user as digital data and completes the process of sending it to the server as structured data.

[0646] Step 3:

[0647] The server begins processing the data received from the terminal using analysis tools. Specifically, it uses a natural language processing model to extract keywords and phrases from the data and accurately identify customer requests.

[0648] Step 4:

[0649] Based on the analysis results, the server selects the most suitable data communication service plan from among several options and creates a proposed message using a plan generation method.

[0650] Step 5:

[0651] The server sends the generated proposal message to the terminal, preparing it for presentation to the user. The proposal includes plan details, pricing, and terms and conditions.

[0652] Step 6:

[0653] Users view the proposed plan via their device, click the approve button if they are satisfied with the content, and configure their settings on their device if they require a revised proposal.

[0654] Step 7:

[0655] The terminal sends the user's selection to the server, which then processes the order accordingly. If approved, the order moves to the execution phase.

[0656] Step 8:

[0657] The server uses progress management tools to monitor the progress of orders and updates statuses such as "Currently processing" and "Technical team is working on it" in real time.

[0658] Step 9:

[0659] If a problem occurs in the order process, the server will immediately detect the anomaly and notify the user or technical staff of the steps and recommended actions for resolving the problem.

[0660] Step 10:

[0661] After an order is completed, the server collects user ratings and comments through feedback collection mechanisms and saves this data as material for service improvement.

[0662] (Example 1)

[0663] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0664] Modern communication services require efficient and accurate responses to diverse customer needs. However, traditional manual order processing and plan proposals are time-consuming and may not fully achieve customer satisfaction. Furthermore, there are challenges in managing order progress, responding quickly to problems, and collecting feedback for service improvement.

[0665] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0666] In this invention, the server includes an input means for acquiring customer information as structured data, a means for analyzing the received information using natural language processing technology, and a means for generating an optimal data communication service plan based on the analysis results. This enables rapid understanding of customer needs and provision of appropriate plans, continuous order management and problem handling, and collection of feedback for improving service quality.

[0667] "Input method" refers to a method for obtaining necessary information from customers and inputting it into the system in a format that can be processed.

[0668] "Communication means" refers to a means of transmitting data from a terminal to a server, and involves transferring structured data according to a predetermined protocol.

[0669] "Analysis means" refers to the process of analyzing received information using natural language processing technology to extract customer needs.

[0670] The "plan generation method" is a method for generating a data communication service plan that is suitable for the customer's needs based on the analysis results.

[0671] A "proposal presentation method" refers to a means of presenting the generated plan to the customer as a proposal and receiving requests for approval or revisions.

[0672] A "progress management system" is a process for monitoring the progress of an order and taking immediate action if a problem arises.

[0673] A "feedback collection method" is a method of gathering evaluation information from customers after an order is completed and using that information to improve the service.

[0674] A "generative AI model" is an artificial intelligence model that uses machine learning techniques to analyze data and select the optimal service plan.

[0675] A "prompt message" is a sentence used to give instructions or requests to an AI system, and is used when processing data or proposing services.

[0676] The embodiments for carrying out the present invention will be described in detail.

[0677] This AI agent system is designed to efficiently obtain data communication service orders from customers and provide appropriate plans. The system primarily functions through the cooperation of users, terminals, and servers.

[0678] The user initiates an order for a data communication service using a terminal. They input the necessary information into the terminal's user interface and transmit it. The input information is converted into structured data by the terminal and sent to the server.

[0679] The terminal is responsible for packaging user input data into a standard data format such as JSON and sending it to the server using an HTTP POST request. In this process, the terminal maintains the accuracy and integrity of the data.

[0680] The server uses natural language processing techniques to analyze the received data. Specifically, it extracts customer needs from text data using Python's NLTK library and generative AI models. Based on the results, the server generates an appropriate data communication service plan. The generated plan is then constructed as a proposal by a template engine and sent to the terminal.

[0681] Once a plan is presented to the user, they can review the proposed plan on their device and either approve it or request a revised proposal. The server confirms the order based on this response and monitors the order's progress. In case of any problems, the server identifies the issue and notifies the user or relevant technical staff of the necessary information.

[0682] Finally, once the order is completed, the server uses feedback collection tools to gather evaluation information from the customer. This feedback data is analyzed using AI models to help improve future services.

[0683] As a concrete example, consider a case where a user requests a "high-speed internet plan for business." An example of a prompt message for this system would be, "I would like high-speed internet service for business. Please suggest a recommended plan." This allows the system to quickly and accurately suggest a plan that meets the user's needs, thereby improving service efficiency and customer satisfaction.

[0684] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0685] Step 1:

[0686] The user initiates an order for a data communication service and enters the necessary information into the user interface on the terminal. Specifically, the user enters data such as their name, contact information, and desired service into a form. The input in this step is data entered by the user, and the output is structured data on the terminal.

[0687] Step 2:

[0688] The terminal packages the user's input data as structured data and sends it to the server. Specifically, the terminal converts the input data into JSON format and sends it to the server via an HTTP POST request. In this step, the input is the structured data received from the user interface, and the output is the data sent to the server.

[0689] Step 3:

[0690] The server analyzes the received structured data using natural language processing techniques. Specifically, the server uses generative AI models and natural language tools to analyze text data and extract customer needs and expectations. The input for this step is data sent from the terminal, and the output is the analyzed needs information.

[0691] Step 4:

[0692] The server generates an appropriate data communication service plan based on the analysis results. Specifically, the server utilizes a generation AI model to construct a plan based on customer needs and selects the most suitable option from its internal database. The input for this step is the analyzed needs information, and the output is a proposed plan.

[0693] Step 5:

[0694] The server sends the generated plan proposal to the terminal. Specifically, the server generates the proposal in HTML or PDF format and sends it to the terminal via real-time notification or email. The input for this step is the generated plan proposal, and the output is the proposal delivered to the terminal.

[0695] Step 6:

[0696] The user reviews the proposed plan using their device and requests approval or a revised proposal. Specifically, the user views the proposal on the device's interface and clicks a selection button to determine the next action. The input for this step is the proposal from the server, and the output is the user's request for approval or a revised proposal.

[0697] Step 7:

[0698] The server confirms the order upon user approval and manages its progress. Specifically, the server monitors the order's progress and takes steps to quickly address any problems that arise. The input for this step is the user's actions, and the output is the confirmed order and its monitoring information.

[0699] Step 8:

[0700] The server collects evaluation information from customers using a feedback collection mechanism after the order is completed. Specifically, the server generates a questionnaire and sends it along with the completion notification to request feedback. The input for this step is the completed order information, and the output is customer feedback data.

[0701] (Application Example 1)

[0702] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0703] Modern consumers want to efficiently and quickly select from a wide variety of goods and services, but information overload often makes the selection process time-consuming. Furthermore, while they desire to shop while receiving abundant visual information, traditional methods have presented challenges in quickly suggesting products that meet customer needs.

[0704] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0705] In this invention, the server includes an input means for receiving information from the customer, an operation means for processing customer requests in real time via voice input and presenting information visually, and a means for presenting a proposed plan on the customer's visual display device and obtaining approval. This enables the customer to efficiently select products and obtain information in real time through a visually assisted shopping assistant.

[0706] "Customer information" is a general term for personal data and data related to requests provided by customers.

[0707] "Natural language processing technology" refers to the technology used by computers to understand and process human language, and involves analyzing text data and extracting keywords.

[0708] A "plan generation method" is a function that automatically selects the optimal product or service plan in response to customer requests based on the analyzed information.

[0709] A "visual display device" is a device that displays electronically generated information in the user's field of vision, and includes smart glasses, among other things.

[0710] "Voice input means" refers to a device or function that receives the user's voice as a digital signal and converts it into analyzable text data.

[0711] A "generative AI model" is an artificial intelligence model that uses machine learning to process customer information in real time and select appropriate products and services.

[0712] A "prompt" is a text instruction input into a generative AI model, serving as a guideline for performing specific analysis or generation tasks.

[0713] This invention adopts the following configuration to realize a visually assisted shopping assistant system. A visual display device, such as smart glasses, and a server work together in cooperation.

[0714] The server receives requests from users through voice input. At this stage, the voice data is converted into text data using speech recognition technology such as the Google Speech-to-Text API. This text data is then analyzed using natural language processing techniques such as the Python libraries SpaCy and NLTK. From the analyzed information, keywords and intentions related to the user's request are extracted and processed using machine learning models (using TensorFlow or PyTorch) to select appropriate products and services.

[0715] The visual display device overlays information transmitted from the server onto the user's field of view. This allows the user to check selected product information in real time. Furthermore, to collect user feedback, a generative AI model is used to analyze user evaluations using prompt messages and generate insights.

[0716] For example, if a user gives a voice command such as "I'm looking for lightweight running shoes," the server analyzes the request and displays potential products on the glasses' display. The user can then view detailed information about the selected products and proceed with the purchase.

[0717] An example of a prompt to be input into the generating AI model would be: "Develop an algorithm that uses an AI agent to analyze the user's intent from their voice input and select products that match that intent." This would enable a system that allows users to more smoothly select the products they need and streamline the purchase process.

[0718] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0719] Step 1:

[0720] The user speaks their request through the voice input feature of their smart glasses. The voice data is input and converted into text data by the Google Speech-to-Text API. This input text data is used for natural language processing in the next step.

[0721] Step 2:

[0722] The server receives text data and performs natural language processing using Python libraries such as SpaCy and NLTK. The analysis extracts keywords and user intent from the text data, and these analysis results are output in the next step as information that forms the basis for product selection.

[0723] Step 3:

[0724] Based on the analysis results, the server searches the product database using a machine learning model based on TensorFlow or PyTorch to select products that match the user's needs. The product information selected by this generative AI model is output within the system and used for visual presentation in the next step.

[0725] Step 4:

[0726] The device (smart glasses) receives the selected product information and displays it as an overlay on the user's screen. Specifically, it displays detailed information such as the product name, price, and image within the user's field of view. This allows the user to easily and visually confirm the product.

[0727] Step 5:

[0728] Users select products of interest based on the visually displayed information and proceed to view further details or complete the purchase process. This input is sent to the server as feedback and used to improve subsequent services.

[0729] Step 6:

[0730] The server analyzes the collected feedback based on a generating AI model and uses prompt messages to generate insights from the feedback. Through this process, the system continuously learns, understands user preferences and behavioral patterns, and improves the service.

[0731] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0732] This invention relates to an AI agent system that automates the order acceptance process for customer data communication services by combining it with an emotion engine. In addition to basic functions such as receiving, analyzing, suggesting, and managing customer information, this system can recognize user emotions using the emotion engine and improve the service experience.

[0733] When a user initiates a service order, data such as the text entered and the tone of voice are sent to the server via the terminal, along with the necessary information. The server analyzes this data through natural language processing and simultaneously detects the user's emotional state using an emotion engine. For example, it can accurately recognize emotions such as positive, negative, or neutral from the tone of the text and the choice of words.

[0734] Based on the customer's emotional state, the server utilizes a plan generation mechanism to propose the most suitable data communication plan, and in some cases, offers customized suggestions tailored to the customer's mood. This allows customers to easily select a service that is more appropriate to their emotional state.

[0735] Furthermore, as the user accepts the proposal and the order progresses, progress management tools constantly monitor the process, and the emotion engine tracks emotional fluctuations in real time. For example, if a customer becomes stressed along the way, the server can immediately respond and provide support or make alternative suggestions.

[0736] Furthermore, after an order is completed, feedback is collected from the user through feedback collection methods. This feedback includes the results of the emotion engine analysis and plays a role in providing valuable insights for service improvement.

[0737] For example, if a user is dissatisfied with their internet speed, the server can analyze their feelings using an emotion engine and immediately provide additional information about high-speed plans or discount offers, thereby improving the user experience and increasing customer satisfaction. Implementing such a system allows for more personalized and rapid responses compared to traditional methods.

[0738] The following describes the processing flow.

[0739] Step 1:

[0740] The user accesses a form on their device, enters information about their desired data communication service, and sends it as a text or voice message.

[0741] Step 2:

[0742] The terminal receives user input information as digital data, converts it into a format that can be processed by the emotion engine and analysis tools, and then sends it to the server.

[0743] Step 3:

[0744] The server first passes the received data to the emotion engine, which analyzes the user's emotional state from their input. During this process, it analyzes the emotional nuances of the text and the tone of voice to identify emotions such as "positive" or "negative."

[0745] Step 4:

[0746] In parallel, the server uses natural language processing technology to analyze user information and extract specific requests and requirements. For example, it identifies keywords such as "high-speed internet is needed."

[0747] Step 5:

[0748] The server integrates the results of sentiment analysis and natural language processing, and uses a plan generation mechanism to automatically generate the optimal data communication plan that matches the user's emotional state, and sends it to the terminal.

[0749] Step 6:

[0750] The terminal displays plan proposals from the server to the user, allowing the user to view them. The user can review the proposal and either approve it or request a revised proposal.

[0751] Step 7:

[0752] If approval is obtained, the server confirms the order and monitors its progress using progress management tools. If the emotion engine detects user stress or dissatisfaction along the way, it quickly considers countermeasures and provides suggested changes and support.

[0753] Step 8:

[0754] After all orders are completed, the server uses various feedback collection methods to obtain feedback from the user. During this process, changes in the user's emotional state are also recorded and used to improve the service and refine future suggestions.

[0755] (Example 2)

[0756] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0757] In data communication services, there is a problem in that customers have difficulty quickly and accurately selecting the optimal plan that suits their emotions and needs. Furthermore, the inability to track and appropriately respond to changes in customer emotions during service use has prevented improvements in the quality of the service experience. In addition, there has been a lack of systematic methods for utilizing feedback after order completion to improve the service.

[0758] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0759] In this invention, the server includes an information analysis device, a plan generation device, and an emotion detection device. This enables automatic proposal of data communication plans that take customer emotions into consideration, and real-time responses to changes in emotions. Furthermore, a feedback collection device allows for systematic analysis of customer opinions, enabling continuous improvement of the service.

[0760] An "information input device" is a device used to collect necessary information from customers and transmit it to the system.

[0761] An "information analysis device" is a device that analyzes received customer information using natural language processing technology.

[0762] A "plan generation device" is a device that generates the optimal data communication plan for a customer based on analyzed information.

[0763] A "presentation device" is a device used to present the generated plan to the customer and obtain their approval.

[0764] A "progress management device" is a device used to monitor the progress of an order, detect problems, and provide solutions.

[0765] A "feedback collection device" is a device used to collect feedback from customers after an order is completed and to use that feedback to improve services.

[0766] An "emotion detection device" is a device that uses emotion analysis technology to detect a customer's emotional state and reflect that in service proposals.

[0767] An "emotion tracking device" is a device that tracks customer emotional fluctuations in real time and provides support as needed.

[0768] This system consists of multiple devices designed to improve the user experience in data communication services. The server plays a central role in processing information transmitted from the terminal. The user first inputs the necessary information through the terminal. This information input device collects information in the form of text input or voice commands and sends it to the server.

[0769] The server processes the received information using an information analysis device and utilizes natural language processing technology to deepen its understanding of user requests. This process employs machine learning models, specifically using the Google Cloud Natural Language API. Based on the analyzed data, a plan generation device automatically creates the optimal data communication plan.

[0770] Furthermore, the server analyzes the user's emotional state through an emotion detection device. This emotion analysis uses techniques including contextual understanding and tone analysis to track the user's emotions in real time. Tools such as Microsoft Azure's Text Analytics are used for this task. This enables personalized plan suggestions based on emotions, improving user satisfaction.

[0771] The progress management system monitors the order's progress in real time, and the emotion tracking system automatically adjusts support when it detects changes in emotion. This allows, for example, the server to immediately suggest countermeasures if a user experiences stress during the process.

[0772] After an order is completed, user feedback is collected by a feedback collection device and used, along with sentiment analysis results, to improve future services. The insights gained from this feedback enable continuous improvement of service quality.

[0773] For example, if a user expresses dissatisfaction when selecting a communication plan, the server prompts the generated AI model with the message, "Please provide a method for suggesting an appropriate communication plan based on the information entered by the new user," thereby providing the user with a better suggestion. In this way, optimized customer service tailored to the environment becomes possible.

[0774] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0775] Step 1:

[0776] The user uses a terminal to input the necessary information into the information input device. This information includes text data and voice data. Through the user interface, the user can input, for example, their name, contact information, and desired services. The entered information is sent from the terminal to the server.

[0777] Step 2:

[0778] The server receives information transmitted from the terminal and initiates natural language processing using an information analysis device. The input data is text-based, and the server performs keyword extraction and semantic analysis on this data. Machine learning techniques are used to effectively interpret customer needs and requests from the input information.

[0779] Step 3:

[0780] Based on the analysis results, the server designs the optimal data communication plan using a plan generation device. It receives output from the information analysis device and customizes the plan by taking into account past data and market information. For example, the initial proposed plan is the one best suited to the customer's usage history and requests.

[0781] Step 4:

[0782] The server utilizes an emotion detection device to analyze the user's emotions from the wording and context in the input data. In this process, an emotion analysis model is used to accurately determine positive, negative, or neutral emotional states. An emotional evaluation is generated as output, which is then used to create the plan for the next step.

[0783] Step 5:

[0784] The server uses a plan generator to fine-tune the plan based on the user's emotional data. It provides personalized suggestions while taking emotional states into consideration. For example, if negative emotions are detected, the server will offer the customer a plan with more flexible terms or discounts.

[0785] Step 6:

[0786] The server continuously monitors the progress of orders through a progress management device. During this time, an emotion tracking device tracks customer emotional changes in real time and deploys prompt support as needed. If an emotional change is detected, an alert is immediately sent to support staff, and appropriate assistance is provided to the customer.

[0787] Step 7:

[0788] Once a user completes an order, the server collects feedback using a feedback collection device. The collected opinions and evaluation data are evaluated along with sentiment analysis to derive insights for service improvement. The opinions obtained from the feedback analysis will be used for future service development and improvement measures.

[0789] (Application Example 2)

[0790] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0791] In today's e-commerce industry, it is considered difficult to provide personalized experiences based on individual customer emotions and needs when customers make online purchases. This can lead to increased customer dissatisfaction and abandonment of the purchase process, potentially resulting in decreased customer loyalty. This invention aims to improve the user experience by analyzing customer emotions in real time and making optimal product and service recommendations based on that analysis.

[0792] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0793] In this invention, the server includes an information input means, an information analysis means, a plan generation means, a presentation means, a progress management means, an opinion collection means, and an emotion recognition and suggestion means. This enables the analysis of the customer's emotional state and the suggestion of corresponding product information and discount information in real time, thereby improving customer satisfaction and optimizing the purchase process.

[0794] An "information input means" is a component that receives data provided by a customer and performs the initial process necessary for further analysis or processing within the system.

[0795] "Information analysis means" refers to a device or program that uses natural language processing technology to interpret received customer data and analyze its contents.

[0796] A "plan generation means" is a component for automatically creating the most appropriate information and communication plan based on the analyzed information.

[0797] A "presentation method" refers to a configuration that has the function of displaying the generated information and communication plan to the customer in an easy-to-understand manner and encouraging approval or selection.

[0798] A "progress management system" is a mechanism that monitors the progress of an order, detects problems as needed, and implements a process to provide solutions.

[0799] "Methods for gathering feedback" refer to components used to obtain feedback from customers after an order is completed and to gain insights for service improvement based on that feedback.

[0800] "Emotion recognition suggestion means" refers to a device or function that detects a customer's emotions in real time and dynamically suggests product information and discount information based on those emotions.

[0801] This system has a configuration that transfers data obtained from customers through an information input means to a server, which then supports subsequent processing. The server has powerful information analysis capabilities and analyzes the received data using natural language processing technology. Specifically, it receives voice data and text data and uses a pre-trained machine learning model to determine the customer's emotions. The analysis results are then used by a plan generation means to create an optimal information and communication plan that matches the customer's emotions and needs.

[0802] In this system, emotion recognition and suggestion mechanisms play a crucial role. Using these mechanisms, the server monitors customer emotions in real time and, based on those emotions, presents personalized product and discount information to each individual customer. This allows users to have a more personalized and enriching experience, much like window shopping.

[0803] For example, if voice and text analysis reveals that a user is interested in a product but dissatisfied with its price, the system recognizes this sentiment and suggests relevant discount information or alternative products. Furthermore, if a customer encounters a problem during the purchase process, a progress management system detects this and immediately provides a solution.

[0804] An example of a prompt using a generative AI model is as follows: In response to customer feedback that "this smartphone is a little expensive," consider an approach that offers alternatives or discounts.

[0805] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0806] Step 1:

[0807] The terminal receives voice and text data from the user. This input data includes the user's wishes and opinions. The terminal converts this data into a digital format and sends it to the server.

[0808] Step 2:

[0809] The server analyzes the received audio and text data using information analysis tools. This analysis process applies natural language processing techniques to extract specific keywords and emotional nuances from the data. The analysis results include information about the user's emotions and desires.

[0810] Step 3:

[0811] The server uses a plan generation means to create an optimal information and communication plan based on the analysis results. In this step, emotion recognition suggestion means are utilized, and the generating AI model personalizes the suggested content. The generated plan includes suggestions that reflect the user's emotional state and preferences.

[0812] Step 4:

[0813] The server sends the information and communication plan created by the plan generation means back to the terminal via the presentation means. The terminal presents this information to the user, allows them to review the proposal, and requests approval. Based on the user's response, final adjustments to the plan may be made.

[0814] Step 5:

[0815] After the user approves the information and communication plan, the server continues to monitor the order status using progress management tools. If necessary, it detects problems, primarily using generative AI models, and dynamically provides solutions.

[0816] Step 6:

[0817] Once the process is complete, the server collects feedback from users through feedback collection mechanisms. This feedback is analyzed by the server and used to gain insights for service improvement. The generated insights are then used in the next optimization process.

[0818] 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.

[0819] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0820] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0821] 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.

[0822] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0823] 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.

[0824] 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.

[0825] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0826] 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."

[0827] 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.

[0828] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0829] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0838] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0839] The following is further disclosed regarding the embodiments described above.

[0840] (Claim 1)

[0841] An input method for receiving information from customers,

[0842] An analysis means for analyzing the received information using natural language processing technology,

[0843] A plan generation means that proposes an optimal data communication service plan based on the analyzed information,

[0844] A means of presenting the proposed plan to the customer and obtaining their approval,

[0845] A progress management system that monitors order progress, detects problems, and provides solutions,

[0846] A feedback collection method that collects customer feedback after an order is completed and uses it to improve the service,

[0847] A system that includes this.

[0848] (Claim 2)

[0849] The system according to claim 1, characterized in that the natural language processing technology uses a machine learning model to analyze customer information.

[0850] (Claim 3)

[0851] The system according to claim 1, characterized in that the feedback collection means analyzes customer evaluation data to generate insights for service improvement.

[0852] "Example 1"

[0853] (Claim 1)

[0854] An input method for obtaining information from customers,

[0855] A communication means for transmitting the acquired information as structured data to a server,

[0856] An analysis means for analyzing the received information using natural language processing technology,

[0857] A plan generation means that generates an optimal data communication service means based on the analyzed information,

[0858] The generated plan is presented to the customer as a proposal, and a means is provided for receiving approval or a revised proposal.

[0859] A progress management means for monitoring the progress of the approved order, detecting problems, and notifying solutions,

[0860] A feedback collection method that collects evaluation information from customers after an order is completed and generates insights for service improvement,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, characterized in that the natural language processing technology analyzes customer information using a generative AI model.

[0864] (Claim 3)

[0865] The system according to claim 1, characterized in that the feedback collection means analyzes customer evaluation data to generate insights for service improvement and utilizes them in the next plan proposal.

[0866] "Application Example 1"

[0867] (Claim 1)

[0868] An input method for receiving information from customers,

[0869] An analysis means for analyzing the received information using natural language processing technology,

[0870] A plan generation means that proposes an optimal product or service plan based on the analyzed information,

[0871] A means of presenting the proposed plan on the customer's visual display device and obtaining their approval,

[0872] A progress management system that monitors order progress, detects problems, and provides solutions,

[0873] An operating means that processes customer requests in real time via voice input and presents information visually,

[0874] A feedback collection method that collects customer feedback after an order is completed and uses it to improve the service,

[0875] A system that includes this.

[0876] (Claim 2)

[0877] The system according to claim 1, characterized in that the natural language processing technology analyzes customer information using a machine learning model, and the analysis means selects products using a generative AI model.

[0878] (Claim 3)

[0879] The system according to claim 1, characterized in that the feedback collection means analyzes customer evaluation data to generate insights for service improvement, and includes a function to learn from feedback using a generation AI model with prompt sentences as input.

[0880] "Example 2 of combining an emotion engine"

[0881] (Claim 1)

[0882] An information input device that receives information from customers,

[0883] An information analysis device that analyzes the received information using natural language processing technology,

[0884] A plan generation device that generates an optimal data communication plan based on the analyzed information,

[0885] A presentation device for presenting the generated plan to the customer and obtaining their approval,

[0886] A progress management device that monitors the progress of orders and provides problem detection and solutions,

[0887] A feedback collection device that collects customer feedback after an order is completed and uses it to improve the service,

[0888] An emotion detection device that uses emotion analysis technology to detect the emotional state of customers and reflect it in service proposals,

[0889] An emotion tracking device that tracks customer emotional fluctuations in real time and provides support as needed,

[0890] A system that includes this.

[0891] (Claim 2)

[0892] The system according to claim 1, characterized in that the natural language processing technology uses a machine learning model to analyze customer information.

[0893] (Claim 3)

[0894] The system according to claim 1, characterized in that the feedback collection device analyzes customer evaluation information to generate insights for service improvement.

[0895] "Application example 2 when combining with an emotional engine"

[0896] (Claim 1)

[0897] A means of receiving information from customers,

[0898] Information analysis means for analyzing the received information using natural language processing technology,

[0899] A plan generation means that proposes an optimal information and communication plan based on the analyzed information,

[0900] A means of presenting the proposed plan to the customer and obtaining their approval,

[0901] A progress management system that monitors the status of ongoing orders, detects problems, and provides solutions,

[0902] A method for collecting customer feedback after an order is completed and using it to improve the service,

[0903] An emotion recognition suggestion means that detects the customer's emotional state and dynamically suggests product information or discount information based on that emotion,

[0904] A system that includes this.

[0905] (Claim 2)

[0906] The system according to claim 1, characterized in that the natural language processing technology analyzes customer information using a learning machine model.

[0907] (Claim 3)

[0908] The system according to claim 1, characterized in that the opinion collection means analyzes customer evaluation data to generate insights for service improvement. [Explanation of Symbols]

[0909] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. An input method for receiving information from customers, An analysis means for analyzing the received information using natural language processing technology, A plan generation means that proposes an optimal product or service plan based on the analyzed information, A means of presenting the proposed plan on the customer's visual display device and obtaining their approval, A progress management system that monitors order progress, detects problems, and provides solutions, An operating means that processes customer requests in real time via voice input and presents information visually, A feedback collection method that gathers customer feedback after an order is completed and uses it to improve the service, A system that includes this.

2. The system according to claim 1, characterized in that the natural language processing technology analyzes customer information using a machine learning model, and the analysis means selects products using a generative AI model.

3. The system according to claim 1, characterized in that the feedback collection means analyzes customer evaluation data to generate insights for service improvement, and includes a function to learn from feedback using a generation AI model with prompt text as input.

Images