System

Abstract

An object of the system according to the embodiment is to enable a shop crew to efficiently learn the latest fee plan and terminal information.SOLUTION: A system includes an information collection unit, an analysis unit, and a test generation unit. The information collection unit collects information using the generated AI. The analysis unit analyzes the information collected by the information collection unit. The test generation unit generates a confirmation test based on the information analyzed by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem that it is difficult for shop staff to efficiently learn the latest pricing plans and terminal information.

[0005] The system according to the embodiment aims to enable shop crew members to efficiently learn the latest pricing plans and terminal information. [Means for solving the problem]

[0006] The system according to the embodiment includes an information collection unit, an analysis unit, and a test generation unit. The information collection unit collects information using a generation AI. The analysis unit analyzes the information collected by the information collection unit. The test generation unit generates a verification test based on the information analyzed by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment allows shop staff to efficiently learn the latest pricing plans and terminal information. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) The learning support system according to an embodiment of the present invention is a system in which a generation AI generates constantly updated confirmation tests, contributing to the improvement of crew skills. This allows crew members to efficiently learn the latest pricing plans and device information and improve their skills.

[0029] A learning support system according to an embodiment includes an information collection unit, an analysis unit, and a test generation unit. The information collection unit uses a generation AI to collect the latest pricing plans and device information. For example, the information collection unit collects information from telecommunications companies' official websites, product catalogs, and news releases. The information collection unit can also automatically collect information using web scraping technology. The information collection unit can also acquire information using an API. For example, the information collection unit collects the latest pricing plans from telecommunications companies' official websites and acquires new device information from product catalogs. Web scraping technology analyzes the content of web pages and extracts necessary information. An API is an interface for acquiring data from specific services, and the information collection unit uses it to efficiently collect information. The analysis unit analyzes the information collected by the information collection unit. For example, the analysis unit analyzes changes in pricing plans using data mining technology. The analysis unit can also extract characteristics of device information using text analysis technology. The analysis unit can also predict future trends using machine learning algorithms. For example, the analysis unit predicts potential next plans based on data from past pricing plans. Text analysis technology uses natural language processing technology to analyze text data and extract important information. Machine learning algorithms learn from large amounts of data and find patterns to predict future trends. The test generation unit generates a confirmation test based on the information analyzed by the analysis unit. For example, the test generation unit generates questions about new pricing plans. The test generation unit can also generate multiple-choice questions about device information. The test generation unit can also generate scenario-based questions. For example, the test generation unit generates questions asking about the features of new pricing plans and creates multiple-choice questions about device information. Scenario-based questions are questions that simulate actual work situations and ask crew members how to respond to those situations. This allows the learning support system according to the embodiment to enable crew members to efficiently learn about the latest pricing plans and device information and improve their skills.For example, crew members can take regular confirmation tests to stay up-to-date and provide accurate information to customers. Test results can be used to evaluate the crew members' learning progress and encourage them to retake the course if necessary.

[0030] The information collecting unit can collect information from the official website, product catalog, and news releases of the telecommunications company. For example, the information collecting unit collects the latest pricing plans from the official website of the telecommunications company. For example, the information collecting unit accesses the official website of the telecommunications company to obtain the latest pricing plans. The information collecting unit also collects new device information from product catalogs. For example, the information collecting unit downloads the product catalog and obtains the specifications and features of the device. The information collecting unit also collects the latest information from news releases. For example, the information collecting unit monitors news releases of the telecommunications company and obtains information when new pricing plans or device information is announced. This allows the latest pricing plans and device information to be accurately collected.

[0031] The test generation unit can add scenario-based questions to the generated confirmation test. For example, the generation AI generates scenario-based questions based on the latest pricing plans and device information. For example, the test generation unit sets up a situation in which a customer selects a specific pricing plan and creates questions asking how to respond to that situation. The test generation unit also analyzes past customer interaction data to generate scenario-based questions based on actual work situations. For example, the test generation unit sets up a situation in which a customer handles a complaint and creates questions asking how to resolve that situation. The test generation unit also generates scenario-based questions based on industry trends and news. For example, the test generation unit sets up a customer interaction situation following the release of a new device and creates questions asking how to respond to that situation. This promotes learning that is tailored to actual work situations.

[0032] The test generation unit can incorporate interactive elements into the generated confirmation tests. For example, the generation AI generates drag-and-drop questions based on the latest pricing plans and device information. For example, the test generation unit creates questions that require users to drag and drop pricing plan features to classify them into the correct category. The test generation unit also analyzes past customer interaction data to generate multiple-choice questions. For example, the test generation unit creates questions that require users to select the optimal pricing plan based on their needs. The test generation unit also generates questions that incorporate interactive elements based on industry trends and news. For example, the test generation unit creates questions that require users to drag and drop the features of a new device to place them in the correct position. This can improve the effectiveness of learning.

[0033] The test generation unit can add questions in different languages ​​to the generated confirmation test. For example, the generation AI generates questions in different languages ​​based on the latest pricing plans and device information. For example, the test generation unit creates questions about pricing plans in English and Chinese. The test generation unit also analyzes past customer interaction data to generate questions in different languages. For example, the test generation unit sets up situations involving interaction with foreign customers and creates questions asking how to respond. The test generation unit also generates questions in different languages ​​based on industry trends and news. For example, the test generation unit creates questions that explain the features of a new device in multiple languages. This makes it possible to support multiple languages.

[0034] The test generation unit can add visual or audio questions to the generated confirmation test. For example, the test generation unit uses a generation AI to generate visual and audio questions based on the latest pricing plans and device information. For example, the test generation unit watches an explanatory video for a pricing plan and creates questions related to the content. The test generation unit also analyzes past customer interaction data and generates visual and audio questions. For example, the test generation unit listens to audio recordings of customer interactions and creates questions asking about how to respond. The test generation unit also generates visual and audio questions based on industry trends and news. For example, the test generation unit watches a promotional video for a new device and creates questions asking about its features. This promotes multimodal learning.

[0035] The analysis unit can predict future trends by analyzing changes in pricing plans and device information over time based on the collected information. For example, the analysis unit organizes pricing plans and device information collected by the generation AI from telecommunications companies' official websites and product catalogs in chronological order and compares it with past data to predict future trends. For example, the analysis unit analyzes changes in pricing plans over the past few years to predict what plans will be introduced next. The analysis unit also analyzes changes in pricing plans and device information over time based on information collected from news releases and industry reports to predict future trends. For example, the analysis unit predicts the impact of the introduction of new technologies on pricing plans. The analysis unit also analyzes changes in pricing plans and device information over time based on user feedback collected from social media and forums to predict future trends. For example, the analysis unit predicts the emergence of new pricing plans that reflect user opinions. This enables future trends to be predicted and appropriate responses to be taken.

[0036] The analysis unit can analyze competitors' pricing plans and device information based on the collected information and perform a comparative analysis. For example, the analysis unit analyzes competitors' pricing plans and device information based on information collected by the generation AI from telecommunications companies' official websites and product catalogs, and performs a comparative analysis. For example, the analysis unit clarifies the features and differences of each company's pricing plans. The analysis unit also analyzes competitors' pricing plans and device information based on information collected from news releases and industry reports, and performs a comparative analysis. For example, the analysis unit compares the introduction timing and features of new pricing plans. The analysis unit also analyzes competitors' pricing plans and device information based on user feedback collected from social media and forums, and performs a comparative analysis. For example, the analysis unit compares user satisfaction and dissatisfaction. This enables comparative analysis with competitors.

[0037] The analysis unit can propose new plans based on pricing plans and service models from different industries. For example, the analysis unit uses the generative AI to collect and analyze pricing plans and service models from official websites and product catalogs outside the telecommunications industry. For example, the analysis unit proposes a new pricing plan based on a subscription model. The analysis unit also collects and analyzes pricing plans and service models from news releases and industry reports from different industries. For example, the analysis unit proposes a new plan based on pricing plans from the fitness industry. The analysis unit also collects user feedback from social media and forums in different industries and analyzes pricing plans and service models. For example, the analysis unit proposes a new plan based on service models from the entertainment industry. This makes it possible to propose new plans that utilize knowledge from different industries.

[0038] The analysis unit analyzes the crew's test results, identifies individual weaknesses, and allows them to focus their learning. For example, the analysis unit uses the generative AI to analyze the crew's test answer data and identify questions that were answered incorrectly or took a long time. For example, if many crew members answered incorrectly on questions related to a specific pricing plan, the analysis unit will suggest additional learning related to that plan. The analysis unit also analyzes the crew's past test results and identifies individual weaknesses. For example, the analysis unit will suggest focused learning related to a specific device for a crew member who lacks knowledge about that device. The analysis unit will also analyze the crew's answer patterns and suggest customized learning plans tailored to their individual learning needs. For example, the analysis unit will provide additional learning materials related to a crew member who has a low level of understanding in a specific area. This allows the crew's weaknesses to be identified and their learning to be focused.

[0039] The analysis unit can compare the crew's performance with that of other crews based on their test results and display a ranking to enhance their competitive spirit. For example, the analysis unit uses a generation AI to analyze the crew's test results and compare their performance with that of other crews. For example, the analysis unit creates and displays a ranking based on each crew's score and correct answer rate. The analysis unit also compares the crew's performance based on past test results and displays a ranking to enhance their competitive spirit. For example, the analysis unit displays a monthly performance ranking. The analysis unit also analyzes the crew's performance in real time and displays the ranking immediately after the test is completed. For example, the analysis unit displays the crew's performance immediately after the test is completed to enhance their competitive spirit. This can enhance the crew's competitive spirit and improve their motivation to learn.

[0040] The analysis unit can propose individual study plans based on the crew's test results. For example, the analysis unit uses a generative AI to analyze the crew's test results and propose a customized study plan based on each crew member's performance. For example, the analysis unit provides additional study materials related to a particular field for a crew member with low understanding in that field. The analysis unit also proposes an individual study plan based on the crew member's performance based on past test results and study history. For example, the analysis unit suggests focused study related to a particular pricing plan for a crew member who lacks knowledge about that plan. The analysis unit also analyzes the crew member's performance and proposes a customized study plan according to each crew member's learning needs. For example, the analysis unit provides additional study materials related to a particular device for a crew member who lacks knowledge about that device. This makes it possible to propose a study plan according to each crew member's learning needs.

[0041] The analysis unit can analyze the test results and provide detailed explanations for any questions that were answered incorrectly and related additional learning materials. For example, the analysis unit analyzes the crew's test results using a generation AI and provides detailed explanations for any questions that were answered incorrectly. For example, if the analysis unit gets an error on a calculation question about a pricing plan, the analysis unit will provide a detailed explanation of the calculation steps. The analysis unit also analyzes the crew's test results and provides additional learning materials related to any questions that were answered incorrectly. For example, if the analysis unit gets an error on a question about the features of a new device, the analysis unit will provide detailed information about the device. The analysis unit also analyzes the crew's test results and provides detailed explanations for any questions that were answered incorrectly and related additional learning materials. For example, if the analysis unit gets an error on a question about a specific pricing plan, the analysis unit will provide a detailed explanation and additional learning materials about that plan. This allows the crew to deepen their understanding of the questions that they answered incorrectly.

[0042] The analysis unit can analyze the crew's learning history based on the test results and evaluate the long-term learning effect. For example, the analysis unit uses a generation AI to analyze the crew's test results and learning history and evaluate the long-term learning effect. For example, the analysis unit compares past test results with current grades and evaluates the progress of learning. The analysis unit also evaluates the long-term learning effect based on the crew's learning history. For example, the analysis unit evaluates the extent to which understanding in a particular field has improved. The analysis unit also analyzes the crew's test results and learning history and evaluates the long-term learning effect. For example, the analysis unit compares past test results with current grades and evaluates the progress of learning. This makes it possible to evaluate the crew's long-term learning effect.

[0043] The analysis unit can suggest a collaborative learning session with other crew members based on the test results, thereby promoting mutual learning. For example, the analysis unit uses a generative AI to analyze the crew's test results and suggest a collaborative learning session with other crew members. For example, the analysis unit groups crew members who have a low level of understanding in a particular field together to promote collaborative learning. The analysis unit also suggests a collaborative learning session to promote mutual learning based on the crew's test results. For example, the analysis unit groups crew members who lack knowledge about a particular pricing plan together to promote collaborative learning. The analysis unit also analyzes the crew's test results and suggests a collaborative learning session with other crew members. For example, the analysis unit groups crew members who lack knowledge about a particular device together to promote collaborative learning. This can promote mutual learning among the crew members.

[0044] The analysis unit can provide relearning plans that correspond to different learning styles based on the test results. For example, the analysis unit uses a generation AI to analyze the crew's test results and provide relearning plans that correspond to different learning styles. For example, the analysis unit provides learning materials using diagrams and graphs to crew members who are good at visual learning. The analysis unit also provides relearning plans that correspond to different learning styles based on the crew's learning history. For example, the analysis unit provides audio commentary to crew members who are good at audio learning. The analysis unit also analyzes the crew's test results and provides relearning plans that correspond to different learning styles. For example, the analysis unit provides detailed text materials to crew members who are good at text learning. This makes it possible to provide relearning plans that correspond to the crew's learning style.

[0045] The analysis unit can analyze the crew's learning progress and propose an optimal learning schedule according to each individual's learning pace. For example, the analysis unit uses a generation AI to analyze the crew's learning progress in real time and propose an optimal learning schedule according to each individual's learning pace. For example, the analysis unit proposes additional study time for crew members who are lagging behind in their studies. The analysis unit also proposes an optimal learning schedule according to each individual's learning pace based on the crew's past learning history. For example, the analysis unit proposes an early next step for crew members who are fast learners. The analysis unit also analyzes the crew's learning progress and proposes an optimal learning schedule according to each individual's learning pace. For example, the analysis unit proposes a schedule that focuses on a particular area for crew members who have a low level of understanding in that area. This makes it possible to propose an optimal learning schedule according to the crew's learning pace.

[0046] The analysis unit can predict future learning needs based on the crew's learning history and prepare learning plans in advance. For example, the analysis unit uses a generative AI to analyze the crew's learning history and predict future learning needs. For example, the analysis unit identifies the next area to learn based on past learning data and prepares a learning plan in advance. The analysis unit also predicts future learning needs based on the crew's test results and prepares a learning plan in advance. For example, the analysis unit prepares a learning plan for a particular area for a crew member with low understanding of that area. The analysis unit also analyzes the crew's learning history and predicts future learning needs. For example, the analysis unit prepares a learning plan for new pricing plans or device information before those contents are announced. This makes it possible to predict future learning needs and prepare learning plans in advance.

[0047] The analysis unit can evaluate the crew's aptitude for different work tasks based on their learning progress and propose optimal work assignments. In the analysis unit, for example, the generation AI analyzes the crew's learning progress and evaluates their aptitude for different work tasks. For example, the analysis unit assigns a crew member with extensive knowledge of a specific pricing plan to work related to that plan. The analysis unit also evaluates the crew's aptitude for different work tasks based on their past learning history and proposes optimal work assignments. For example, the analysis unit assigns a crew member with extensive knowledge of a new device to work related to that device. The analysis unit also analyzes the crew's learning progress and evaluates their aptitude for different work tasks. For example, the analysis unit assigns a crew member with a high level of understanding in a particular field to work related to that field. This makes it possible to propose optimal work assignments based on the crew's aptitudes.

[0048] The analysis unit can suggest pair learning or group learning with other crew members based on the crew member's learning progress, thereby building a cooperative learning environment. For example, the analysis unit uses a generative AI to analyze the crew member's learning progress and suggest pair learning with other crew members. For example, the analysis unit pairs crew members with high and low levels of understanding in a particular field to promote learning. The analysis unit also suggests group learning based on the crew member's past learning history. For example, the analysis unit groups crew members with high levels of understanding in different fields to promote mutual learning. The analysis unit also analyzes the crew member's learning progress and suggests pair learning or group learning with other crew members. For example, the analysis unit groups crew members who lack knowledge about a particular pricing plan to promote joint learning. This makes it possible to build a cooperative learning environment among crew members.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The analysis unit can propose customized learning plans based on the crew's learning history, tailored to each individual's learning style. For example, the analysis unit can provide learning materials using diagrams and graphs to crew members who are good at visual learning. It can also provide audio commentary to crew members who are good at audio learning. It can also provide detailed text materials to crew members who are good at text learning. This makes it possible to provide optimal learning plans tailored to each crew member's learning style, maximizing the learning effect.

[0051] The analysis unit can suggest joint learning sessions with other crew members based on the crew member's learning progress and promote mutual learning. For example, it can group crew members who have a low level of understanding in a particular field together to promote joint learning. It can also group crew members who lack knowledge about a particular pricing plan together to promote joint learning. It can also group crew members who lack knowledge about a particular device together to promote joint learning. This can promote mutual learning among crew members and improve learning effectiveness.

[0052] The analysis unit can compare the crew's performance with that of other crews based on their test results and display rankings to foster a sense of competition. For example, it can create and display rankings based on each crew's score and correct answer rate. It can also display monthly performance rankings. It can also display the crew's performance immediately after the test to foster a sense of competition. This can foster a sense of competition among crew members and improve their motivation to learn.

[0053] The analysis unit can evaluate the crew's aptitude for different work tasks based on their learning progress and propose optimal work assignments. For example, a crew member with extensive knowledge of a particular pricing plan can be assigned to work related to that plan. A crew member with extensive knowledge of a new terminal can also be assigned to work related to that terminal. Furthermore, a crew member with a high level of understanding in a particular field can be assigned to work related to that field. This makes it possible to propose optimal work assignments based on the crew's aptitudes and improve work efficiency.

[0054] Based on the crew's learning progress, the analysis unit can suggest paired or group learning with other crew members, creating a cooperative learning environment. For example, it can pair crew members with high and low levels of understanding in a particular field to promote learning. It can also group crew members with high levels of understanding in different fields to promote mutual learning. It can also group crew members who lack knowledge about a particular pricing plan to promote collaborative learning. This creates a cooperative learning environment among crew members, improving learning effectiveness.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The information collection unit uses generation AI to collect the latest pricing plans and device information. For example, the information collection unit may collect information from the official websites, product catalogs, and news releases of telecommunications companies. The information collection unit may also collect information automatically using web scraping technology. Furthermore, the information collection unit may also obtain information using an API. Step 2: The analysis unit analyzes the information collected by the information collection unit. For example, the analysis unit may use data mining technology to analyze changes in pricing plans. The analysis unit may also use text analysis technology to extract characteristics of device information. Furthermore, the analysis unit may use machine learning algorithms to predict future trends. Step 3: The test generator generates a confirmation test based on the information analyzed by the analyzer. For example, the test generator generates questions about a new pricing plan. The test generator can also generate multiple-choice questions about device information. Furthermore, the test generator can also generate scenario-based questions.

[0057] (Example 2) The learning support system according to an embodiment of the present invention is a system in which a generation AI generates constantly updated confirmation tests, contributing to the improvement of crew skills. This allows crew members to efficiently learn the latest pricing plans and device information and improve their skills.

[0058] A learning support system according to an embodiment includes an information collection unit, an analysis unit, and a test generation unit. The information collection unit uses a generation AI to collect the latest pricing plans and device information. For example, the information collection unit collects information from telecommunications companies' official websites, product catalogs, and news releases. The information collection unit can also automatically collect information using web scraping technology. The information collection unit can also acquire information using an API. For example, the information collection unit collects the latest pricing plans from telecommunications companies' official websites and acquires new device information from product catalogs. Web scraping technology analyzes the content of web pages and extracts necessary information. An API is an interface for acquiring data from specific services, and the information collection unit uses it to efficiently collect information. The analysis unit analyzes the information collected by the information collection unit. For example, the analysis unit analyzes changes in pricing plans using data mining technology. The analysis unit can also extract characteristics of device information using text analysis technology. The analysis unit can also predict future trends using machine learning algorithms. For example, the analysis unit predicts potential next plans based on data from past pricing plans. Text analysis technology uses natural language processing technology to analyze text data and extract important information. Machine learning algorithms learn from large amounts of data and find patterns to predict future trends. The test generation unit generates a confirmation test based on the information analyzed by the analysis unit. For example, the test generation unit generates questions about new pricing plans. The test generation unit can also generate multiple-choice questions about device information. The test generation unit can also generate scenario-based questions. For example, the test generation unit generates questions asking about the features of new pricing plans and creates multiple-choice questions about device information. Scenario-based questions are questions that simulate actual work situations and ask crew members how to respond to those situations. This allows the learning support system according to the embodiment to enable crew members to efficiently learn about the latest pricing plans and device information and improve their skills.For example, crew members can take regular confirmation tests to stay up-to-date and provide accurate information to customers. Test results can be used to evaluate the crew members' learning progress and encourage them to retake the course if necessary.

[0059] The information collecting unit can collect information from the official website, product catalog, and news releases of the telecommunications company. For example, the information collecting unit collects the latest pricing plans from the official website of the telecommunications company. For example, the information collecting unit accesses the official website of the telecommunications company to obtain the latest pricing plans. The information collecting unit also collects new device information from product catalogs. For example, the information collecting unit downloads the product catalog and obtains the specifications and features of the device. The information collecting unit also collects the latest information from news releases. For example, the information collecting unit monitors news releases of the telecommunications company and obtains information when new pricing plans or device information is announced. This allows the latest pricing plans and device information to be accurately collected.

[0060] The test generation unit can add scenario-based questions to the generated confirmation test. For example, the generation AI generates scenario-based questions based on the latest pricing plans and device information. For example, the test generation unit sets up a situation in which a customer selects a specific pricing plan and creates questions asking how to respond to that situation. The test generation unit also analyzes past customer interaction data to generate scenario-based questions based on actual work situations. For example, the test generation unit sets up a situation in which a customer handles a complaint and creates questions asking how to resolve that situation. The test generation unit also generates scenario-based questions based on industry trends and news. For example, the test generation unit sets up a customer interaction situation following the release of a new device and creates questions asking how to respond to that situation. This promotes learning that is tailored to actual work situations.

[0061] The test generation unit can incorporate interactive elements into the generated confirmation tests. For example, the generation AI generates drag-and-drop questions based on the latest pricing plans and device information. For example, the test generation unit creates questions that require users to drag and drop pricing plan features to classify them into the correct category. The test generation unit also analyzes past customer interaction data to generate multiple-choice questions. For example, the test generation unit creates questions that require users to select the optimal pricing plan based on their needs. The test generation unit also generates questions that incorporate interactive elements based on industry trends and news. For example, the test generation unit creates questions that require users to drag and drop the features of a new device to place them in the correct position. This can improve the effectiveness of learning.

[0062] The test generation unit can add questions in different languages ​​to the generated confirmation test. For example, the generation AI generates questions in different languages ​​based on the latest pricing plans and device information. For example, the test generation unit creates questions about pricing plans in English and Chinese. The test generation unit also analyzes past customer interaction data to generate questions in different languages. For example, the test generation unit sets up situations involving interaction with foreign customers and creates questions asking how to respond. The test generation unit also generates questions in different languages ​​based on industry trends and news. For example, the test generation unit creates questions that explain the features of a new device in multiple languages. This makes it possible to support multiple languages.

[0063] The test generation unit can add visual or audio questions to the generated confirmation test. For example, the test generation unit uses a generation AI to generate visual and audio questions based on the latest pricing plans and device information. For example, the test generation unit watches an explanatory video for a pricing plan and creates questions related to the content. The test generation unit also analyzes past customer interaction data and generates visual and audio questions. For example, the test generation unit listens to audio recordings of customer interactions and creates questions asking about how to respond. The test generation unit also generates visual and audio questions based on industry trends and news. For example, the test generation unit watches a promotional video for a new device and creates questions asking about its features. This promotes multimodal learning.

[0064] The analysis unit can predict future trends by analyzing changes in pricing plans and device information over time based on the collected information. For example, the analysis unit organizes pricing plans and device information collected by the generation AI from telecommunications companies' official websites and product catalogs in chronological order and compares it with past data to predict future trends. For example, the analysis unit analyzes changes in pricing plans over the past few years to predict what plans will be introduced next. The analysis unit also analyzes changes in pricing plans and device information over time based on information collected from news releases and industry reports to predict future trends. For example, the analysis unit predicts the impact of the introduction of new technologies on pricing plans. The analysis unit also analyzes changes in pricing plans and device information over time based on user feedback collected from social media and forums to predict future trends. For example, the analysis unit predicts the emergence of new pricing plans that reflect user opinions. This enables future trends to be predicted and appropriate responses to be taken.

[0065] The analysis unit can analyze competitors' pricing plans and device information based on the collected information and perform a comparative analysis. For example, the analysis unit analyzes competitors' pricing plans and device information based on information collected by the generation AI from telecommunications companies' official websites and product catalogs, and performs a comparative analysis. For example, the analysis unit clarifies the features and differences of each company's pricing plans. The analysis unit also analyzes competitors' pricing plans and device information based on information collected from news releases and industry reports, and performs a comparative analysis. For example, the analysis unit compares the introduction timing and features of new pricing plans. The analysis unit also analyzes competitors' pricing plans and device information based on user feedback collected from social media and forums, and performs a comparative analysis. For example, the analysis unit compares user satisfaction and dissatisfaction. This enables comparative analysis with competitors.

[0066] The analysis unit can use the emotion estimation function to analyze user feedback or reviews and identify areas for improvement in pricing plans or device information. For example, the analysis unit can use the emotion estimation function to analyze user feedback collected by the generation AI from social media or review sites and identify areas for improvement in pricing plans or device information. For example, the analysis unit can extract points of dissatisfaction among users and propose improvements. The analysis unit can also use the emotion estimation function to analyze user feedback collected from forums or customer support records and identify areas for improvement in pricing plans or device information. For example, the analysis unit can strengthen points that users highly evaluate. The analysis unit can also use the emotion estimation function to analyze user feedback collected from survey results or survey reports and identify areas for improvement in pricing plans or device information. For example, the analysis unit can propose a new pricing plan that meets the user's needs. This makes it possible to identify areas for improvement in pricing plans or device information based on user feedback.

[0067] The analysis unit can propose new plans based on pricing plans and service models from different industries. For example, the analysis unit uses the generative AI to collect and analyze pricing plans and service models from official websites and product catalogs outside the telecommunications industry. For example, the analysis unit proposes a new pricing plan based on a subscription model. The analysis unit also collects and analyzes pricing plans and service models from news releases and industry reports from different industries. For example, the analysis unit proposes a new plan based on pricing plans from the fitness industry. The analysis unit also collects user feedback from social media and forums in different industries and analyzes pricing plans and service models. For example, the analysis unit proposes a new plan based on service models from the entertainment industry. This makes it possible to propose new plans that utilize knowledge from different industries.

[0068] The analysis unit can analyze users' emotional responses to information collected using the emotion estimation function and suggest methods of providing information that will elicit positive responses. For example, the analysis unit can analyze user feedback collected by the generative AI from social media and review sites using the emotion estimation function and suggest methods of providing information that will elicit positive responses. For example, the analysis unit can identify expressions and wording preferred by users. The analysis unit can also analyze user feedback collected from forums and customer support records using the emotion estimation function and suggest methods of providing information that will elicit positive responses. For example, the analysis unit can identify the timing for providing information that users will rate highly. The analysis unit can also analyze user feedback collected from survey results and research reports using the emotion estimation function and suggest methods of providing information that will elicit positive responses. For example, the analysis unit can identify methods of customizing information to meet user needs. This can suggest methods of providing information that will elicit positive responses from users.

[0069] The test generation unit can adjust the difficulty level according to the crew member's emotional state using the emotion estimation function. For example, the test generation unit uses a generation AI to analyze the crew member's emotional state in real time and adjust the difficulty level. For example, the test generation unit lowers the difficulty level if the crew member is feeling stressed and raises the difficulty level if the crew member is relaxed. The test generation unit also adjusts the difficulty level according to the crew member's emotional state based on past test results and emotional data. For example, the test generation unit prioritizes questions in areas that the crew member previously struggled with. The test generation unit also maintains the crew member's motivation to learn by analyzing the crew member's emotional state and adjusting the difficulty level. For example, the test generation unit gradually increases the difficulty level of questions that the crew member rated highly. This makes it possible to adjust the difficulty level according to the crew member's emotional state.

[0070] The test generation unit can generate questions based on topics that interest the crew most. For example, the generation AI analyzes the emotional state of the crew and generates questions based on the topics that interest them most. For example, the test generation unit creates questions about a new device that the crew has shown interest in. The test generation unit also generates questions based on topics that interest the crew most based on past test results and emotional data. For example, the test generation unit prioritizes questions about topics that the crew has rated highly. The test generation unit also increases motivation to learn by analyzing the emotional state of the crew and generating questions based on topics that interest them most. For example, the test generation unit creates questions about a new pricing plan that the crew has shown interest in. This can pique the crew's interest and increase their motivation to learn.

[0071] The analysis unit analyzes the crew's test results, identifies individual weaknesses, and allows them to focus their learning. For example, the analysis unit uses the generative AI to analyze the crew's test answer data and identify questions that were answered incorrectly or took a long time. For example, if many crew members answered incorrectly on questions related to a specific pricing plan, the analysis unit will suggest additional learning related to that plan. The analysis unit also analyzes the crew's past test results and identifies individual weaknesses. For example, the analysis unit will suggest focused learning related to a specific device for a crew member who lacks knowledge about that device. The analysis unit will also analyze the crew's answer patterns and suggest customized learning plans tailored to their individual learning needs. For example, the analysis unit will provide additional learning materials related to a crew member who has a low level of understanding in a specific area. This allows the crew's weaknesses to be identified and their learning to be focused.

[0072] The analysis unit can compare the crew's performance with that of other crews based on their test results and display a ranking to enhance their competitive spirit. For example, the analysis unit uses a generation AI to analyze the crew's test results and compare their performance with that of other crews. For example, the analysis unit creates and displays a ranking based on each crew's score and correct answer rate. The analysis unit also compares the crew's performance based on past test results and displays a ranking to enhance their competitive spirit. For example, the analysis unit displays a monthly performance ranking. The analysis unit also analyzes the crew's performance in real time and displays the ranking immediately after the test is completed. For example, the analysis unit displays the crew's performance immediately after the test is completed to enhance their competitive spirit. This can enhance the crew's competitive spirit and improve their motivation to learn.

[0073] The analysis unit can propose individual study plans based on the crew's test results. For example, the analysis unit uses a generative AI to analyze the crew's test results and propose a customized study plan based on each crew member's performance. For example, the analysis unit provides additional study materials related to a particular field for a crew member with low understanding in that field. The analysis unit also proposes an individual study plan based on the crew member's performance based on past test results and study history. For example, the analysis unit suggests focused study related to a particular pricing plan for a crew member who lacks knowledge about that plan. The analysis unit also analyzes the crew member's performance and proposes a customized study plan according to each crew member's learning needs. For example, the analysis unit provides additional study materials related to a particular device for a crew member who lacks knowledge about that device. This makes it possible to propose a study plan according to each crew member's learning needs.

[0074] The analysis unit can use the emotion estimation function to provide feedback according to the crew member's emotional state and promote a positive learning experience. For example, the analysis unit uses a generative AI to analyze the crew member's emotional state in real time and provide positive feedback. For example, the analysis unit displays an encouraging message when the crew member gets the answer correct. The analysis unit also provides feedback according to the crew member's emotional state based on the crew member's past test results and emotional data. For example, the analysis unit displays a gentle, encouraging message when the crew member makes a mistake. The analysis unit also analyzes the crew member's emotional state and provides feedback to promote a positive learning experience. For example, the analysis unit displays a praising message for questions that the crew member received a high score on. This can promote a positive learning experience for the crew member.

[0075] The analysis unit can analyze the test results and provide detailed explanations for any questions that were answered incorrectly and related additional learning materials. For example, the analysis unit analyzes the crew's test results using a generation AI and provides detailed explanations for any questions that were answered incorrectly. For example, if the analysis unit gets an error on a calculation question about a pricing plan, the analysis unit will provide a detailed explanation of the calculation steps. The analysis unit also analyzes the crew's test results and provides additional learning materials related to any questions that were answered incorrectly. For example, if the analysis unit gets an error on a question about the features of a new device, the analysis unit will provide detailed information about the device. The analysis unit also analyzes the crew's test results and provides detailed explanations for any questions that were answered incorrectly and related additional learning materials. For example, if the analysis unit gets an error on a question about a specific pricing plan, the analysis unit will provide a detailed explanation and additional learning materials about that plan. This allows the crew to deepen their understanding of the questions that they answered incorrectly.

[0076] The analysis unit can analyze the crew's learning history based on the test results and evaluate the long-term learning effect. For example, the analysis unit uses a generation AI to analyze the crew's test results and learning history and evaluate the long-term learning effect. For example, the analysis unit compares past test results with current grades and evaluates the progress of learning. The analysis unit also evaluates the long-term learning effect based on the crew's learning history. For example, the analysis unit evaluates the extent to which understanding in a particular field has improved. The analysis unit also analyzes the crew's test results and learning history and evaluates the long-term learning effect. For example, the analysis unit compares past test results with current grades and evaluates the progress of learning. This makes it possible to evaluate the crew's long-term learning effect.

[0077] The analysis unit can suggest a collaborative learning session with other crew members based on the test results, thereby promoting mutual learning. For example, the analysis unit uses a generative AI to analyze the crew's test results and suggest a collaborative learning session with other crew members. For example, the analysis unit groups crew members who have a low level of understanding in a particular field together to promote collaborative learning. The analysis unit also suggests a collaborative learning session to promote mutual learning based on the crew's test results. For example, the analysis unit groups crew members who lack knowledge about a particular pricing plan together to promote collaborative learning. The analysis unit also analyzes the crew's test results and suggests a collaborative learning session with other crew members. For example, the analysis unit groups crew members who lack knowledge about a particular device together to promote collaborative learning. This can promote mutual learning among the crew members.

[0078] The analysis unit can provide relearning plans that correspond to different learning styles based on the test results. For example, the analysis unit uses a generation AI to analyze the crew's test results and provide relearning plans that correspond to different learning styles. For example, the analysis unit provides learning materials using diagrams and graphs to crew members who are good at visual learning. The analysis unit also provides relearning plans that correspond to different learning styles based on the crew's learning history. For example, the analysis unit provides audio commentary to crew members who are good at audio learning. The analysis unit also analyzes the crew's test results and provides relearning plans that correspond to different learning styles. For example, the analysis unit provides detailed text materials to crew members who are good at text learning. This makes it possible to provide relearning plans that correspond to the crew's learning style.

[0079] The analysis unit uses the emotion estimation function to suggest the timing for relearning according to the crew's emotional state, thereby promoting effective learning. For example, the analysis unit uses a generation AI to analyze the crew's emotional state in real time and suggest the optimal timing for relearning. For example, the analysis unit encourages relearning when the crew is relaxed. The analysis unit also suggests the timing for relearning based on the crew's past test results and emotional data. For example, the analysis unit encourages relearning during times when the crew is most likely to concentrate. The analysis unit also promotes effective learning by analyzing the crew's emotional state and suggesting the timing for relearning. For example, the analysis unit encourages relearning when the crew is feeling positive emotions. This makes it possible to suggest the timing for relearning according to the crew's emotional state.

[0080] The analysis unit can analyze the crew's learning progress and propose an optimal learning schedule according to each individual's learning pace. For example, the analysis unit uses a generation AI to analyze the crew's learning progress in real time and propose an optimal learning schedule according to each individual's learning pace. For example, the analysis unit proposes additional study time for crew members who are lagging behind in their studies. The analysis unit also proposes an optimal learning schedule according to each individual's learning pace based on the crew's past learning history. For example, the analysis unit proposes an early next step for crew members who are fast learners. The analysis unit also analyzes the crew's learning progress and proposes an optimal learning schedule according to each individual's learning pace. For example, the analysis unit proposes a schedule that focuses on a particular area for crew members who have a low level of understanding in that area. This makes it possible to propose an optimal learning schedule according to the crew's learning pace.

[0081] The analysis unit can predict future learning needs based on the crew's learning history and prepare learning plans in advance. For example, the analysis unit uses a generative AI to analyze the crew's learning history and predict future learning needs. For example, the analysis unit identifies the next area to learn based on past learning data and prepares a learning plan in advance. The analysis unit also predicts future learning needs based on the crew's test results and prepares a learning plan in advance. For example, the analysis unit prepares a learning plan for a particular area for a crew member with low understanding of that area. The analysis unit also analyzes the crew's learning history and predicts future learning needs. For example, the analysis unit prepares a learning plan for new pricing plans or device information before those contents are announced. This makes it possible to predict future learning needs and prepare learning plans in advance.

[0082] The analysis unit uses the emotion estimation function to provide feedback on learning progress according to the crew's emotional state, thereby maintaining motivation to learn. For example, the analysis unit uses a generation AI to analyze the crew's emotional state in real time and provide feedback according to their learning progress. For example, the analysis unit displays a praising message when the crew is feeling positive. The analysis unit also provides feedback according to their learning progress based on the crew's past test results and emotional data. For example, the analysis unit displays an encouraging message for questions that the crew answered incorrectly. The analysis unit also maintains motivation to learn by analyzing the crew's emotional state and providing feedback according to their learning progress. For example, the analysis unit displays a positive message for questions that the crew received a high score on. This makes it possible to provide feedback to maintain the crew's motivation to learn.

[0083] The analysis unit can evaluate the crew's aptitude for different work tasks based on their learning progress and propose optimal work assignments. In the analysis unit, for example, the generation AI analyzes the crew's learning progress and evaluates their aptitude for different work tasks. For example, the analysis unit assigns a crew member with extensive knowledge of a specific pricing plan to work related to that plan. The analysis unit also evaluates the crew's aptitude for different work tasks based on their past learning history and proposes optimal work assignments. For example, the analysis unit assigns a crew member with extensive knowledge of a new device to work related to that device. The analysis unit also analyzes the crew's learning progress and evaluates their aptitude for different work tasks. For example, the analysis unit assigns a crew member with a high level of understanding in a particular field to work related to that field. This makes it possible to propose optimal work assignments based on the crew's aptitudes.

[0084] The analysis unit can suggest pair learning or group learning with other crew members based on the crew member's learning progress, thereby building a cooperative learning environment. For example, the analysis unit uses a generative AI to analyze the crew member's learning progress and suggest pair learning with other crew members. For example, the analysis unit pairs crew members with high and low levels of understanding in a particular field to promote learning. The analysis unit also suggests group learning based on the crew member's past learning history. For example, the analysis unit groups crew members with high levels of understanding in different fields to promote mutual learning. The analysis unit also analyzes the crew member's learning progress and suggests pair learning or group learning with other crew members. For example, the analysis unit groups crew members who lack knowledge about a particular pricing plan to promote joint learning. This makes it possible to build a cooperative learning environment among crew members.

[0085] The analysis unit uses the emotion estimation function to suggest a method for managing learning progress according to the crew's emotional state, allowing them to progress with learning while reducing stress. For example, the analysis unit uses a generation AI to analyze the crew's emotional state in real time and suggest a method for managing learning progress. For example, the analysis unit adjusts the learning pace if the crew is feeling stressed. The analysis unit also suggests a method for managing learning progress based on the crew's past test results and emotional data. For example, the analysis unit suggests that the crew should progress with learning when they are relaxed. The analysis unit also analyzes the crew's emotional state and suggests a method for managing learning progress, allowing them to progress with learning while reducing stress. For example, the analysis unit suggests that the crew should progress with learning when they are feeling positive emotions. This allows the crew to progress with learning while reducing stress.

[0086] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0087] The analysis unit can propose customized learning plans based on the crew's learning history, tailored to each individual's learning style. For example, the analysis unit can provide learning materials using diagrams and graphs to crew members who are good at visual learning. It can also provide audio commentary to crew members who are good at audio learning. It can also provide detailed text materials to crew members who are good at text learning. This makes it possible to provide optimal learning plans tailored to each crew member's learning style, maximizing the learning effect.

[0088] The analysis unit can suggest joint learning sessions with other crew members based on the crew member's learning progress and promote mutual learning. For example, it can group crew members who have a low level of understanding in a particular field together to promote joint learning. It can also group crew members who lack knowledge about a particular pricing plan together to promote joint learning. It can also group crew members who lack knowledge about a particular device together to promote joint learning. This can promote mutual learning among crew members and improve learning effectiveness.

[0089] The analysis unit can compare the crew's performance with that of other crews based on their test results and display rankings to foster a sense of competition. For example, it can create and display rankings based on each crew's score and correct answer rate. It can also display monthly performance rankings. It can also display the crew's performance immediately after the test to foster a sense of competition. This can foster a sense of competition among crew members and improve their motivation to learn.

[0090] The analysis unit can evaluate the crew's aptitude for different work tasks based on their learning progress and propose optimal work assignments. For example, a crew member with extensive knowledge of a particular pricing plan can be assigned to work related to that plan. A crew member with extensive knowledge of a new terminal can also be assigned to work related to that terminal. Furthermore, a crew member with a high level of understanding in a particular field can be assigned to work related to that field. This makes it possible to propose optimal work assignments based on the crew's aptitudes and improve work efficiency.

[0091] Based on the crew's learning progress, the analysis unit can suggest paired or group learning with other crew members, creating a cooperative learning environment. For example, it can pair crew members with high and low levels of understanding in a particular field to promote learning. It can also group crew members with high levels of understanding in different fields to promote mutual learning. It can also group crew members who lack knowledge about a particular pricing plan to promote collaborative learning. This creates a cooperative learning environment among crew members, improving learning effectiveness.

[0092] The analysis unit can use the emotion estimation function to provide feedback according to the crew member's emotional state, promoting a positive learning experience. For example, it can display an encouraging message if the crew member gets the answer right. It can also display a gentle, encouraging message if the crew member gets the answer wrong. It can also display a message of praise for questions the crew member received a high evaluation for. This promotes a positive learning experience for the crew member and increases their motivation to learn.

[0093] The test generator can use the emotion estimation function to adjust the difficulty of questions according to the crew's emotional state. For example, it can lower the difficulty if the crew is feeling stressed and raise the difficulty if they are relaxed. It can also adjust the difficulty according to the crew's emotional state based on past test results and emotional data. It can also gradually increase the difficulty of questions that crew members have rated highly. This makes it possible to adjust the difficulty according to the crew's emotional state, thereby improving learning effectiveness.

[0094] The analysis unit can analyze the user's emotional response to the collected information using the emotion estimation function and suggest a method of providing information that will elicit a positive response. For example, it can identify expressions and wording that the user prefers. It can also identify the timing for providing information that the user will rate highly. It can also identify a method of customizing information according to the user's needs. This makes it possible to suggest a method of providing information that will elicit a positive response from the user and improve customer satisfaction.

[0095] The analysis unit uses the emotion estimation function to provide feedback on the crew's learning progress according to their emotional state, thereby maintaining their motivation to learn. For example, it can display a praising message when the crew is feeling positive. It can also display an encouraging message for questions the crew got wrong. It can also display a positive message for questions the crew received a high evaluation for. This provides feedback to maintain the crew's motivation to learn, improving the effectiveness of learning.

[0096] The analysis unit uses the emotion estimation function to suggest ways to manage learning progress according to the crew's emotional state, allowing them to progress with learning while reducing stress. For example, if the crew is feeling stressed, the analysis unit can adjust the learning pace. It can also suggest that the crew progress with learning when they are relaxed. It can also suggest that the crew progress with learning when they are feeling positive. This allows the crew to progress with learning while reducing stress, improving learning effectiveness.

[0097] The processing flow of the second embodiment will be briefly explained below.

[0098] Step 1: The information collection unit uses generation AI to collect the latest pricing plans and device information. For example, the information collection unit may collect information from the official websites, product catalogs, and news releases of telecommunications companies. The information collection unit may also collect information automatically using web scraping technology. Furthermore, the information collection unit may also obtain information using an API. Step 2: The analysis unit analyzes the information collected by the information collection unit. For example, the analysis unit may use data mining technology to analyze changes in pricing plans. The analysis unit may also use text analysis technology to extract characteristics of device information. Furthermore, the analysis unit may use machine learning algorithms to predict future trends. Step 3: The test generator generates a confirmation test based on the information analyzed by the analyzer. For example, the test generator generates questions about a new pricing plan. The test generator can also generate multiple-choice questions about device information. Furthermore, the test generator can also generate scenario-based questions.

[0099] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0100] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0101] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0102] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0103] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0104] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0105] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0106] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0107] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0108] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0109] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0110] 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.

[0111] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0112] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0113] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0114] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0115] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0116] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0117] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0118] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0119] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0120] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0121] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0123] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0124] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] 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.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0127] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0131] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0133] 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.

[0134] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0135] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0136] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0138] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0139] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0140] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0141] 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.

[0142] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0143] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0144] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0145] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0146] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0147] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0148] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0149] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0150] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0151] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0152] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0153] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0154] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0155] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0156] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0157] 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.

[0158] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0159] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0160] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0161] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0162] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0163] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0164] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0165] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0166] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. An information gathering unit using generative AI, an analysis unit that analyzes the information collected by the information collection unit; a test generation unit that generates a verification test based on the information analyzed by the analysis unit. A system characterized by:

2. The information collecting unit Gather information from official carrier websites, product catalogs, and news releases 2. The system of claim 1.

3. The test generator Adding questions in different languages ​​to generated validation tests 2. The system of claim 1.

4. The analysis unit Analyze crew test results to identify individual weaknesses and focus on them for learning.

2. The system of claim 1.

5. The analysis unit Analyze your test results and provide detailed explanations and relevant additional study materials for any questions you get wrong 2. The system of claim 1.

6. The analysis unit Expand the scope of information collected to include international pricing plans and device information 2. The system of claim 1.

7. The test generator Adjust the difficulty according to the crew's emotional state 2. The system of claim 1.

8. The analysis unit Providing feedback on learning progress according to the crew's emotional state to maintain motivation to learn The system of claim 1 .

Images