system

Abstract

We provide the system. [Solution] A means for recording evaluation data acquired from a communication terminal, A means for calculating the degree of growth by analyzing multiple quantities from the recorded evaluation data mentioned above, A means of quantifying the degree of growth and the degree of user motivation based on the analyzed quantities, A means of generating suggestions for improving training content based on quantified information, A means of outputting the generated information to a communication terminal, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern education and training programs, it is difficult to accurately grasp the growth and motivation of individual participants. With conventional methods, the effects of training cannot be comprehensively evaluated, and feedback according to the situation of each participant cannot be provided promptly. Due to such problems, there are issues that the effects of training cannot be fully obtained and it is difficult to sustain the motivation of participants.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides a system that records evaluation data acquired from a communication terminal, analyzes that data, and quantifies the degree of growth and motivation. This system can immediately transmit feedback generated based on the analysis results to the communication terminal and notify the user. This makes it possible to accurately grasp the training status of each participant and make appropriate improvement suggestions, thereby maximizing the effectiveness of the training.

[0006] A "communication terminal" is an electronic device used to receive user input and transmit data to a server.

[0007] "Evaluation data" refers to information obtained from test results and survey results as a result of users undergoing training.

[0008] A "means of recording" refers to a system component that has the function of saving data transmitted from a communication terminal.

[0009] "Means of analysis" refer to system components used to process recorded data and derive trends and characteristics.

[0010] "Growth rate" is a numerical measure that shows the progress and skill improvement of users through training.

[0011] "Motivation level" is a numerical measure that indicates the level of enthusiasm and interest a user has in the training.

[0012] "Feedback" refers to information generated based on analysis results, including specific advice and suggestions for the user. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the language used in the following description will be explained.

[0016] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between 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), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is a system for improving the effectiveness of training by having users transmit the results of their training using a communication terminal after they have participated, and quantifying their level of growth and motivation.

[0035] System configuration:

[0036] After users complete a training quiz and questionnaire, they input their results into a communication terminal. This terminal transmits the entered data to a server. The data received by the terminal is processed on the server and used to analyze their progress and motivation. The server analyzes this data and generates personalized feedback for each user. This feedback is then provided to the user again via the communication terminal.

[0037] Program processing:

[0038] When a user operates a communication terminal and inputs data, the terminal sends this information to a server. The server records the data in a database and sends it to an analysis module. The analysis module compares the current data with past data to evaluate the degree of growth and uses text analysis technology to determine positive or negative opinions from open-ended responses in questionnaires. The analysis results are returned to the server as quantified growth and motivation levels. Based on this information, the server generates a feedback message for the user. The feedback includes specific advice to help the user continuously improve and can be viewed by receiving it on the communication terminal.

[0039] Specific example:

[0040] If a user undergoes training for new business software and their test scores improve from 80 to 85 to 90 points, the data is entered via the terminal, and the server determines that their progress is high. On the other hand, if the user frequently answers "easy to understand" and "useful in real life" in a survey, their motivation level is also quantified as high. Based on this, the server generates feedback such as, "You understand the training content very well. We recommend the next level of training to further improve your skills," and presents it to the user.

[0041] Thus, the system of the present invention can support the growth of participants by individually analyzing training results and providing accurate feedback.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] Users complete the training test and enter their test results via a terminal. They also answer a training-related questionnaire and enter the results into the terminal in the same way.

[0045] Step 2:

[0046] The terminal formats the test results and survey results entered by the user and sends the data to the server using a secure communication protocol.

[0047] Step 3:

[0048] The server receives evaluation data sent from the terminal. After confirming receipt of the data, it saves the data to the database.

[0049] Step 4:

[0050] The server launches an analysis module on the saved data, compares the test results history, and calculates the degree of growth.

[0051] Step 5:

[0052] The server analyzes the survey results as text and determines whether they are positive or negative. It analyzes the responses, quantifies them, and calculates the degree of motivation.

[0053] Step 6:

[0054] The server generates feedback messages for users based on their progress and motivation level. This feedback includes suggestions for improving the training and advice for the next steps.

[0055] Step 7:

[0056] The server sends the generated feedback to the device. The device notifies the user of the received feedback and displays it through an application or email.

[0057] Step 8:

[0058] Users review feedback on their devices to understand their training performance and future guidance. They then plan their next training session as needed.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] Traditional training systems have made it difficult to objectively and immediately evaluate the growth and motivation of trainees and provide specific feedback. Therefore, it has been challenging to provide appropriate improvement measures tailored to individual participants, making it difficult to maximize the effectiveness of the training.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for storing data acquired from a communication device, means for transmitting the stored data to an analysis module and evaluating the degree of growth, and means for text analysis of free-response answers from questionnaires using natural language processing technology and determining emotions. This makes it possible to immediately and objectively evaluate the user's degree of growth and motivation and provide individually optimized feedback.

[0064] A "communication device" is an electronic device used by users to input data and exchange information with a server.

[0065] "Data storage" is the process of securely storing acquired user information.

[0066] An "analysis module" is a program or algorithm used to analyze stored data and evaluate user growth and motivation.

[0067] "Natural language processing technology" is a technology that uses computers to process and analyze natural language used by humans.

[0068] "Feedback generation" is the process of creating specific improvement suggestions and evaluations for users based on the analysis results.

[0069] "Growth rate" is a numerical indicator that shows how much a user's skills and knowledge have improved.

[0070] "Motivation level" refers to a numerical value or percentage that evaluates the user's willingness and proactiveness towards training.

[0071] This invention is a system designed to improve the effectiveness of training, and it relies on data exchange between three parties: the user, the terminal, and the server. First, the user completes the training and then answers a confirmation test and questionnaire. These results are entered using a terminal (smartphone, tablet, PC, etc.) as a communication device. The terminal then transmits this data to the server.

[0072] The server receives data and saves its contents to a database. Database management systems such as MySQL® or PostgreSQL are used for this data storage. The saved data is sent to an analysis module for detailed analysis. This analysis module is built in a programming language such as Python and uses natural language processing technology to analyze the open-ended responses of the survey. Specifically, natural language processing libraries such as NLTK and spaCy are used to perform sentiment analysis of the responses.

[0073] The results of the analysis are quantified as growth rate and motivation level. This quantification involves analyzing correlations and trends between data using generative AI models. OpenAI's GPT series and other large-scale language models are used as generative AI models.

[0074] User feedback is automatically generated by the server. This generation process involves inputting prompts using a generation AI model. For example, a prompt such as "The user's progress is high; we will provide detailed advice on the next training step" is input to create individual user feedback.

[0075] Finally, the generated feedback is sent back to the device and displayed to the user. This allows the user to see their own progress and increases their motivation to take the next step. This system not only records data but also provides a mechanism to continuously support the user's growth.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] After training, users input their answers to a confirmation test and questionnaire using a communication device. The data entered includes test scores, questionnaire answer choices, and free-response answers.

[0079] Step 2:

[0080] The terminal sends the data entered by the user to the server. This transmission uses the HTTPS protocol to ensure data integrity and security, preventing data tampering.

[0081] Step 3:

[0082] The server records the received data in the database. At this stage, SQL INSERT queries are used to save the data to the database in the appropriate format.

[0083] Step 4:

[0084] The server's analysis module acquires data and performs trend analysis of test scores and sentiment analysis of questionnaires. Specifically, it calculates the degree of growth by comparing it with past test data and extracts positive and negative opinions from open-ended responses using natural language processing technology.

[0085] Step 5:

[0086] The analysis results are quantified on the server and summarized as growth rate and motivation level. This allows users' progress and motivation to be expressed in concrete numerical terms.

[0087] Step 6:

[0088] The server inputs prompt messages into the generated AI model, which then generates user-specific feedback. These prompt messages create specific advice tailored to the user's level of progress.

[0089] Step 7:

[0090] The server generates a feedback message and sends it to the terminal. The sent message can be viewed by the user through a communication device.

[0091] Step 8:

[0092] The device displays feedback to the user and suggests specific actions. This allows the user to evaluate their own progress and gain guidance for taking the next step.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] It is difficult to digitize the evaluation of education or training via communication devices and efficiently quantify user growth and motivation. Furthermore, there is a lack of guidance content based on appropriate improvement measures for users, so there is a need to maximize the effectiveness of education by utilizing evaluation data.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes means for recording evaluation values ​​obtained from communication equipment, means for analyzing multiple indicators from the recorded evaluation values ​​to calculate the degree of growth, and means for presenting improvement measures for the user based on the quantified degree of growth and motivation. This makes it possible to effectively utilize the evaluation of education or training and to immediately and appropriately improve the content of instruction that reflects the user's growth and motivation.

[0098] "Communication equipment" refers to devices used to transmit or receive data.

[0099] "Rating scores" are numerical data collected to indicate evaluations related to education and training.

[0100] "Means of recording" refers to a function or device for storing acquired data.

[0101] "Means for analyzing indicators and calculating the degree of growth" refers to a process or device that analyzes recorded data to quantify the user's improvement in ability.

[0102] "Motivation level" is an index that indicates the user's willingness and proactiveness to achieve their goals.

[0103] "Improvement measures" are specific strategies aimed at further enhancing the abilities and motivation of users.

[0104] "Improving instructional content" refers to improving programs and methods to enhance the quality of education and training.

[0105] The system for carrying out this invention mainly consists of a server, communication equipment, and an analysis module.

[0106] The server retrieves evaluation scores from communication devices and records them in a database. The communication devices transmit test results and survey results entered by users after training. The server then passes the recorded data to an analysis module. The analysis module uses numerical and text analysis libraries to quantify growth and motivation levels using historical data and free-response evaluations. Specific libraries such as TextBlob are likely to be used.

[0107] The analyzed numerical information is used by the server to generate specific improvement measures to promote user growth. User feedback includes advice on motivation for the next step and ways to enhance learning. This information is provided to the user via communication devices, such as smartphones and tablets.

[0108] As a concrete example, this system could be implemented in a training program for customer support staff at an e-commerce site. Staff test scores and satisfaction survey results would be analyzed, and they could receive customized advice to improve their response skills. An example of a prompt to the generating AI model in this case would be, "Please provide more effective feedback in our customer support training program. We want to quantify the staff's growth and motivation levels."

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] Users input their training test results and survey findings using communication devices. The input data is transmitted to the server via the communication device. Examples of input include test scores and free-form comments such as "The training was helpful." This allows the server to receive the user's rating.

[0112] Step 2:

[0113] The server records the received data in a database. The database stores user history and serves as foundational data for subsequent analysis. This lays the foundation for understanding how current test results are positioned in comparison to past data.

[0114] Step 3:

[0115] The server sends data to the analysis module, which then begins processing the data based on the rating scores. The analysis module uses a text analysis library such as TextBlob to analyze free-form comments and determine whether the sentiment is positive or negative. For numerical data, it calculates the average score and trends to quantify the degree of growth and motivation. At this time, it compares past exercise results with current data to evaluate the user's progress.

[0116] Step 4:

[0117] Based on the analysis results, the server uses a generative AI model to generate improvement measures for the user. Appropriate prompt sentences are input into the AI ​​model to obtain generated feedback and advice for the next steps. An example of a prompt sentence might be: "Please provide more effective feedback in our customer service training program. We want to quantify staff growth and motivation."

[0118] Step 5:

[0119] The server sends the generated feedback to the communication device so that the user can review it. Users can receive personalized feedback based on their training results and use it to motivate themselves for their next learning activities. In this step, mobile devices and tablets function as devices for displaying the results.

[0120] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0121] This invention is a system that improves the effectiveness of training by allowing users to participate in training, input and transmit the results and their emotions via a communication terminal, and then analyze their growth and motivation levels in more detail. By incorporating an emotion engine, this system enables the analysis of the user's emotional state and provides a comprehensive evaluation.

[0122] System configuration:

[0123] After users complete the training, they use a communication terminal to input their test results and questionnaire responses. The terminal is equipped with an emotion engine that recognizes the user's emotions through voice data and facial recognition data. This recognition result is also sent to the server. The server uses the test results, questionnaire responses, and emotion data sent from the terminal to perform a detailed analysis of each individual's level of growth and motivation.

[0124] Program processing:

[0125] After the user completes the training, they input their results into a communication terminal. The terminal collects voice and facial recognition data, and an emotion engine analyzes this data to generate emotion data. This emotion data, along with other evaluation data, is formatted and sent from the terminal to the server. The server records this data, and an analysis module calculates the degree of growth and quantifies the level of motivation. Furthermore, using the emotion data, it generates feedback that takes into account the emotional changes of each individual user. This feedback includes advice and suggestions for the next steps, based on their emotional state. The generated feedback is provided to the user via the communication terminal.

[0126] Specific example:

[0127] For example, if a user participates in training and their test scores improve from 70 to 75 to 80 points, the emotion engine will recognize an emotion such as "increased confidence." The server will determine this to be a high level of growth and, along with the level of motivation, generate more positive feedback. The user will then receive a message such as, "Your confidence in the training has increased significantly. We recommend that you tackle practical tasks next."

[0128] In this way, by utilizing the emotion engine, it is possible to evaluate the user's training progress from multiple perspectives and provide more accurate feedback.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] After the user completes the training, they use a communication device to input test results and questionnaire responses. Additionally, the device's camera and microphone capture audio and facial data.

[0132] Step 2:

[0133] The emotion engine built into the device analyzes the collected voice data and facial recognition data. The emotion engine analyzes the user's tone of voice and facial expressions to determine their current emotional state.

[0134] Step 3:

[0135] The device integrates and formats test results, survey results, and sentiment data, and sends it to the server.

[0136] Step 4:

[0137] The server receives data sent from the terminal and records it in storage. It then launches an analysis module to calculate the growth rate from the recorded data.

[0138] Step 5:

[0139] The server's analysis module calculates growth by comparing it to past test results. It also quantifies motivation levels from questionnaires and sentiment data. By analyzing sentiment data, it evaluates emotional changes and positive / negative tendencies.

[0140] Step 6:

[0141] The server generates feedback messages for the user based on the analysis results. These feedback messages include specific suggestions for improvement in the training content and emotional support for the next steps.

[0142] Step 7:

[0143] The generated feedback is sent from the server to the terminal. The terminal receives the feedback, notifies the user, and displays it within the application. The user reviews this feedback and plans future training activities based on the feedback received.

[0144] (Example 2)

[0145] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0146] Traditional training systems have faced challenges in accurately assessing participants' growth and motivation levels, resulting in ineffective feedback. Furthermore, they lack comprehensive evaluations that consider emotional shifts, making it difficult to provide individualized feedback.

[0147] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0148] In this invention, the server includes means for recording evaluation data acquired from a communication terminal, means for analyzing multiple quantities from the evaluation data to calculate the degree of growth, means for quantifying the degree of growth and the user's motivation level, and processing means for generating individual feedback based on emotional data. This makes it possible to provide comprehensive and individualized feedback that includes the emotional state of the participants.

[0149] A "communication terminal" is an electronic device that allows users to input information or receive data.

[0150] "Evaluation data" refers to information about the results and responses that users obtained during training or other activities.

[0151] "Growth rate" is a value that indicates the degree of improvement in the user's abilities and skills, as revealed by analyzing the acquired evaluation data.

[0152] "Motivation level" is a numerical representation of the user's level of intrinsic motivation.

[0153] "Emotional processing means" refers to a device or function that analyzes voice data and facial data collected by the user and performs processing to recognize the user's emotional state.

[0154] A "feedback generation method" is a function that processes data based on analysis to generate appropriate advice and suggestions for the next action to be provided to the user.

[0155] To implement this invention, a communication terminal primarily used by the training recipients and a server that interacts with it are required.

[0156] First, users use a communication terminal to input evaluation data (test results and questionnaire responses) obtained after the training is completed. The communication terminal is equipped with a microphone to collect the user's voice and a camera to analyze their facial expressions. These devices are integrated with software that acts as an emotion processing tool, allowing emotional data to be extracted from the user's voice tone and facial expressions.

[0157] Next, the collected data is formatted and sent to the server via a secure communication method. The server is equipped with a high-speed processor and sufficient database capacity, enabling it to efficiently process and store large amounts of data. On the server side, an analysis module runs to analyze the acquired evaluation data and quantify the user's growth and motivation level. This module implements algorithms for comparison with past history, allowing for precise monitoring of the user's progress.

[0158] Furthermore, the server can use a generative AI model to generate feedback based on sentiment data. This feedback includes meaningful advice and recommendations for the next steps for the user, and is provided to the user via a communication terminal.

[0159] As a concrete example, suppose a user takes a training course on "Performance Management in Training." If their test score starts at 70 points and rises to 80 points, the emotion engine recognizes that "confidence has increased." Upon receiving this information, the server determines that the user is seeking further challenges and prepares and provides feedback suggesting "the next task to take on."

[0160] An example of a prompt message could be: "Analyze this user's performance and emotional data and create a suggestion for the next training session. User data: {Performance: 70, 80, Emotion: Increased confidence}". In this way, accurate feedback based on the user's performance and emotional state can be provided, improving the quality of training.

[0161] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0162] Step 1:

[0163] After the user completes the training, an input screen appears on the communication terminal. The user enters test results and questionnaire responses on this screen. Voice input is also used, and the terminal's microphone captures the voice. The entered data is digitized and formatted as text data. In addition, the voice data is recorded in real time and used as input for sentiment analysis in the next step.

[0164] Step 2:

[0165] The device uses its camera to collect the user's facial expression data. The collected audio and facial expression data are analyzed by a built-in emotion processing system. Specifically, the analysis algorithm detects the tone of voice and subtle facial movements, and outputs the user's current emotional state as labels such as "confidence," "anxiety," and "joy." This output is formatted and prepared to be sent to the server along with other evaluation data.

[0166] Step 3:

[0167] The device transmits formatted test results, survey responses, and sentiment data to the server via a secure communication protocol. The transmitted data is received by the server and stored in a database. Error checking codes may be added to prevent data loss during transmission.

[0168] Step 4:

[0169] The server passes the received data to the analysis module. The analysis module compares it with historical data to calculate the user's growth and motivation level. For example, it compares past test results with current results to calculate the growth rate. Furthermore, sentiment data is also taken into consideration, and an output is generated that adjusts the analysis results based on this data.

[0170] Step 5:

[0171] The server uses a generative AI model to generate optimal feedback. The prompt is given analysis results and sentiment data as input, and the generative AI model outputs the next steps and advice appropriate for the user. This feedback includes specific and actionable content to increase the user's motivation.

[0172] Step 6:

[0173] The generated feedback is sent from the server to the communication terminal. The terminal displays the received feedback to the user. The display format, including text, images, and videos, is optimized according to the user's settings and communication environment. The user can review the feedback and use it to improve future training or activities.

[0174] (Application Example 2)

[0175] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0176] In modern factories, improving worker skills and maintaining motivation are crucial challenges, but traditional training and evaluation methods make it difficult to accurately grasp workers' psychological states and growth levels. Furthermore, there is a lack of mechanisms to provide immediate feedback that takes each worker's emotional state into account, enabling efficient and effective work processes.

[0177] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0178] In this invention, the server includes means for recording evaluation data acquired from a communication terminal, means for collecting the worker's facial expressions and vocalizations and analyzing their emotional state, and means for quantifying the degree of growth and motivation based on this data, generating feedback, and displaying it on a visual device. This makes it possible to provide accurate feedback that takes into account the emotional state of each individual worker in real time, thereby achieving skill improvement and motivation maintenance.

[0179] A "communication terminal" is an electronic device used for recording, transmitting, and receiving data.

[0180] "Evaluation data" refers to information based on the results of training and surveys received by workers.

[0181] "Growth rate" is an indicator that shows the progress of workers' abilities and skills, calculated based on evaluation data.

[0182] "Motivation level" is a numerical representation of a worker's enthusiasm and interest in their work.

[0183] "Improvement suggestions" refer to proposals for optimizing training and work content based on analysis results.

[0184] A "visual device" is an electronic device used to display information and provide it to workers visually.

[0185] "Facial expression" refers to the visual expression of emotion formed by the movement of facial muscles.

[0186] "Vocalization sounds" refer to audio data contained in the voices of workers, and are used for analyzing their emotional states.

[0187] "Emotional state" refers to the results obtained through the analysis of facial expressions and vocalizations, which indicate the psychological tendencies and mood of the worker at that particular time.

[0188] "Feedback" refers to informational and advisable advice given to an employee based on their level of growth, motivation, and emotional state.

[0189] The system for realizing this invention comprises a communication terminal, a visual device, and a server as its main components. The communication terminal records evaluation data, including the training results and survey results of workers. The visual device, shaped like eyeglasses, has the function of collecting the facial expressions and vocalizations of workers and transmits this data to the server.

[0190] The server analyzes the emotional state of workers using an emotion analysis engine based on data acquired from communication terminals and visual devices. This emotion analysis engine evaluates the mental state of workers using speech recognition and facial recognition technologies. The analyzed data is used to calculate the level of worker growth and motivation.

[0191] The server generates feedback based on the analysis results. This feedback includes appropriate advice and suggestions for the next steps, tailored to each worker's emotional state. This feedback information is provided to workers in real time through visual devices, allowing them to properly understand the situation during training and proceed efficiently.

[0192] For example, if a visual device detects high levels of tension in a worker's facial expression and tone of voice while they are being trained to operate a new machine, the server can use that information to provide feedback such as, "Please stay calm and continue working slowly."

[0193] An example of a prompt message might be, "Based on the user's emotional data and work progress, generate specific feedback to improve the user's motivation." Thus, the present invention is a comprehensive system for supporting the emotions and growth of workers.

[0194] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0195] Step 1:

[0196] The user puts on a visual device and begins the training. The visual device collects the user's facial expressions and vocalizations in real time and transmits this data to a communication terminal.

[0197] Input: User facial expression data, vocalization data

[0198] Output: Data transmission to communication terminal

[0199] Step 2:

[0200] The communication terminal records the acquired facial expression data and vocalization data and sends it to the server. The server receives this data and inputs it into the emotion analysis engine.

[0201] Input: Facial expression data, vocalization data

[0202] Output: Data transfer to the emotion analysis engine

[0203] Step 3:

[0204] The server's emotion analysis engine analyzes facial expression data and vocalization data to evaluate the user's emotional state. This analysis uses speech recognition and facial recognition algorithms.

[0205] Input: Facial expression data, vocalization data

[0206] Data processing: Applying speech recognition and facial recognition algorithms.

[0207] Output: Emotional state data

[0208] Step 4:

[0209] The server combines emotional state data, past training history, and test results to calculate growth and motivation levels.

[0210] Input: Emotional state data, training history, test results

[0211] Data calculation: Calculation of growth rate and motivation level

[0212] Output: Quantified growth and motivation levels

[0213] Step 5:

[0214] The server generates feedback using a generative AI model based on quantified growth and motivation levels. This feedback includes advice that takes emotional state into consideration and suggestions for the next steps.

[0215] Input: Growth rate, level of motivation

[0216] Data processing: Feedback generation using a generative AI model.

[0217] Output: Feedback data

[0218] Step 6:

[0219] The server transmits the generated feedback to a visual device via a communication terminal and displays it to the user. The user visually confirms the feedback and takes appropriate action.

[0220] Input: Feedback data

[0221] Output: Display of feedback to the user

[0222] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0223] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0224] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0225] [Second Embodiment]

[0226] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0227] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0228] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0229] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0230] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0231] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0232] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0233] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0234] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0235] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0236] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0237] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0238] This invention is a system for improving the effectiveness of training by having users transmit the results of their training using a communication terminal after they have participated, and quantifying their level of growth and motivation.

[0239] System configuration:

[0240] After users complete a training quiz and questionnaire, they input their results into a communication terminal. This terminal transmits the entered data to a server. The data received by the terminal is processed on the server and used to analyze their progress and motivation. The server analyzes this data and generates personalized feedback for each user. This feedback is then provided to the user again via the communication terminal.

[0241] Program processing:

[0242] When a user operates a communication terminal and inputs data, the terminal sends this information to a server. The server records the data in a database and sends it to an analysis module. The analysis module compares the current data with past data to evaluate the degree of growth and uses text analysis technology to determine positive or negative opinions from open-ended responses in questionnaires. The analysis results are returned to the server as quantified growth and motivation levels. Based on this information, the server generates a feedback message for the user. The feedback includes specific advice to help the user continuously improve and can be viewed by receiving it on the communication terminal.

[0243] Specific example:

[0244] If a user undergoes training for new business software and their test scores improve from 80 to 85 to 90 points, the data is entered via the terminal, and the server determines that their progress is high. On the other hand, if the user frequently answers "easy to understand" and "useful in real life" in a survey, their motivation level is also quantified as high. Based on this, the server generates feedback such as, "You understand the training content very well. We recommend the next level of training to further improve your skills," and presents it to the user.

[0245] Thus, the system of the present invention can support the growth of participants by individually analyzing training results and providing accurate feedback.

[0246] The following describes the processing flow.

[0247] Step 1:

[0248] Users complete the training test and enter their test results via a terminal. They also answer a training-related questionnaire and enter the results into the terminal in the same way.

[0249] Step 2:

[0250] The terminal formats the test results and survey results entered by the user and sends the data to the server using a secure communication protocol.

[0251] Step 3:

[0252] The server receives evaluation data sent from the terminal. After confirming receipt of the data, it saves the data to the database.

[0253] Step 4:

[0254] The server launches an analysis module on the saved data, compares the test results history, and calculates the degree of growth.

[0255] Step 5:

[0256] The server analyzes the survey results as text and determines whether they are positive or negative. It analyzes the responses, quantifies them, and calculates the degree of motivation.

[0257] Step 6:

[0258] The server generates feedback messages for users based on their progress and motivation level. This feedback includes suggestions for improving the training and advice for the next steps.

[0259] Step 7:

[0260] The server sends the generated feedback to the device. The device notifies the user of the received feedback and displays it through an application or email.

[0261] Step 8:

[0262] Users review feedback on their devices to understand their training performance and future guidance. They then plan their next training session as needed.

[0263] (Example 1)

[0264] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0265] Traditional training systems have made it difficult to objectively and immediately evaluate the growth and motivation of trainees and provide specific feedback. Therefore, it has been challenging to provide appropriate improvement measures tailored to individual participants, making it difficult to maximize the effectiveness of the training.

[0266] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0267] In this invention, the server includes means for storing data acquired from a communication device, means for transmitting the stored data to an analysis module and evaluating the degree of growth, and means for text analysis of free-response answers from questionnaires using natural language processing technology and determining emotions. This makes it possible to immediately and objectively evaluate the user's degree of growth and motivation and provide individually optimized feedback.

[0268] A "communication device" is an electronic device used by users to input data and exchange information with a server.

[0269] "Data storage" is the process of securely storing acquired user information.

[0270] An "analysis module" is a program or algorithm used to analyze stored data and evaluate user growth and motivation.

[0271] "Natural language processing technology" is a technology that uses computers to process and analyze natural language used by humans.

[0272] "Feedback generation" is the process of creating specific improvement suggestions and evaluations for users based on the analysis results.

[0273] "Growth rate" is a numerical indicator that shows how much a user's skills and knowledge have improved.

[0274] "Motivation level" refers to a numerical value or percentage that evaluates the user's willingness and proactiveness towards training.

[0275] This invention is a system designed to improve the effectiveness of training, and it relies on data exchange between three parties: the user, the terminal, and the server. First, the user completes the training and then answers a confirmation test and questionnaire. These results are entered using a terminal (smartphone, tablet, PC, etc.) as a communication device. The terminal then transmits this data to the server.

[0276] The server receives data and saves its contents to a database. Database management systems such as MySQL or PostgreSQL are used for this data storage. The saved data is sent to an analysis module for detailed analysis. This analysis module is built in a programming language such as Python and uses natural language processing techniques to analyze the open-ended responses of the survey. Specifically, natural language processing libraries such as NLTK and spaCy are used to perform sentiment analysis of the responses.

[0277] The results of the analysis are quantified as the degree of growth and motivation. For this quantification, the correlation and trends between data are analyzed using a generative AI model. As the generative AI model, the GPT series of OpenAI and other large language models are used.

[0278] Feedback for the user is automatically generated by the server. For this generation, input of a prompt sentence using a generative AI model is performed. For example, a prompt sentence such as "The user's growth degree is high, and provide detailed advice to recommend the next training step" is input to create user-specific feedback.

[0279] Finally, the generated feedback is sent back to the terminal and displayed to the user. As a result, the user can confirm their own growth and enhance the motivation to proceed to the next step. This system not only simply records data but also provides a mechanism to continuously support the growth of the user.

[0280] The flow of the specific process in Example 1 will be described using FIG. 11.

[0281] Step 1:

[0282] After the user's training, the user inputs the answers to the confirmation test and questionnaire using a communication device. The data to be input are the test scores, questionnaire options, and free-form answers.

[0283] Step 2:

[0284] The terminal sends the data input by the user to the server. For this transmission, the HTTPS protocol is used to ensure the integrity and security of the data, and the data is sent so that it cannot be tampered with.

[0285] Step 3:

[0286] The server records the received data in the database. At this stage, the SQL INSERT query is used to save the data in the appropriate format in the database.

[0287] Step 4:

[0288] The server's analysis module retrieves the data and performs trend analysis on the test scores and sentiment analysis on the questionnaires. Specifically, it calculates the growth rate by comparing with past test data and extracts positive and negative opinions from the free responses using natural language processing technology.

[0289] Step 5:

[0290] The server quantifies the analysis results and summarizes them as the growth rate and motivation level. As a result, the user's progress and motivation are expressed in specific numerical values.

[0291] Step 6:

[0292] The server inputs the prompt text into the generated AI model to generate individual user feedback. Based on this prompt text, specific advice corresponding to the user's growth rate is created.

[0293] Step 7:

[0294] The server sends the generated feedback message to the terminal. The sent message can be confirmed by the user through the communication device.

[0295] Step 8:

[0296] The terminal displays the feedback to the user and presents specific actions. As a result, the user can evaluate their own growth and obtain a guideline for proceeding to the next step.

[0297] (Application Example 1)

[0298] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0299] It is difficult to digitize the evaluation of education or training via communication devices and efficiently quantify user growth and motivation. Furthermore, there is a lack of guidance content based on appropriate improvement measures for users, so there is a need to maximize the effectiveness of education by utilizing evaluation data.

[0300] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0301] In this invention, the server includes means for recording evaluation values ​​obtained from communication equipment, means for analyzing multiple indicators from the recorded evaluation values ​​to calculate the degree of growth, and means for presenting improvement measures for the user based on the quantified degree of growth and motivation. This makes it possible to effectively utilize the evaluation of education or training and to immediately and appropriately improve the content of instruction that reflects the user's growth and motivation.

[0302] "Communication equipment" refers to devices used to transmit or receive data.

[0303] "Rating scores" are numerical data collected to indicate evaluations related to education and training.

[0304] "Means of recording" refers to a function or device for storing acquired data.

[0305] "Means for analyzing indicators and calculating the degree of growth" refers to a process or device that analyzes recorded data to quantify the user's improvement in ability.

[0306] "Motivation level" is an index that indicates the user's willingness and proactiveness to achieve their goals.

[0307] "Upward measures" refer to specific measures to further enhance the capabilities and motivation of users.

[0308] "Improvement of guidance content" refers to the improvement of programs and methods for enhancing the quality of education and training.

[0309] The system for implementing this invention mainly consists of a server, communication devices, and an analysis module.

[0310] The server acquires evaluation values from the communication devices and records them in the database. The communication devices are responsible for transmitting the test results and survey results input by the users after training. Also, the server passes the recorded data to the analysis module. The analysis module uses numerical analysis libraries and text analysis libraries to quantify the degree of growth and motivation using past historical data and the evaluation of the input free descriptions. As specific libraries, it is conceivable that TextBlob, etc. may be used.

[0311] The analyzed numerical information is used for the server to generate specific improvement measures to promote the growth of the users. The feedback for the users includes advice on motivation for the next steps and strengthening of learning. This information is provided to the users through the communication devices, and for example, smartphones and tablets serve as output devices.

[0312] As a specific example, this system may be introduced into the training program received by the customer support staff of an e-commerce site. The test scores and satisfaction survey results of the staff are analyzed, and customized advice for improving corresponding skills can be received. An example of the prompt sentence for the generation AI model in this case is, "In the customer service training program, please provide more effective feedback. I want to quantify the degree of growth and motivation of the staff."

[0313] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0314] Step 1:

[0315] Users input their training test results and survey findings using communication devices. The input data is transmitted to the server via the communication device. Examples of input include test scores and free-form comments such as "The training was helpful." This allows the server to receive the user's rating.

[0316] Step 2:

[0317] The server records the received data in a database. The database stores user history and serves as foundational data for subsequent analysis. This lays the foundation for understanding how current test results are positioned in comparison to past data.

[0318] Step 3:

[0319] The server sends data to the analysis module, which then begins processing the data based on the rating scores. The analysis module uses a text analysis library such as TextBlob to analyze free-form comments and determine whether the sentiment is positive or negative. For numerical data, it calculates the average score and trends to quantify the degree of growth and motivation. At this time, it compares past exercise results with current data to evaluate the user's progress.

[0320] Step 4:

[0321] Based on the analysis results, the server uses a generative AI model to generate improvement measures for the user. Appropriate prompt sentences are input into the AI ​​model to obtain generated feedback and advice for the next steps. An example of a prompt sentence might be: "Please provide more effective feedback in our customer service training program. We want to quantify staff growth and motivation."

[0322] Step 5:

[0323] The server sends the generated feedback to the communication device so that the user can review it. Users can receive personalized feedback based on their training results and use it to motivate themselves for their next learning activities. In this step, mobile devices and tablets function as devices for displaying the results.

[0324] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0325] This invention is a system that improves the effectiveness of training by allowing users to participate in training, input and transmit the results and their emotions via a communication terminal, and then analyze their growth and motivation levels in more detail. By incorporating an emotion engine, this system enables the analysis of the user's emotional state and provides a comprehensive evaluation.

[0326] System configuration:

[0327] After users complete the training, they use a communication terminal to input their test results and questionnaire responses. The terminal is equipped with an emotion engine that recognizes the user's emotions through voice data and facial recognition data. This recognition result is also sent to the server. The server uses the test results, questionnaire responses, and emotion data sent from the terminal to perform a detailed analysis of each individual's level of growth and motivation.

[0328] Program processing:

[0329] After the user completes the training, they input their results into a communication terminal. The terminal collects voice and facial recognition data, and an emotion engine analyzes this data to generate emotion data. This emotion data, along with other evaluation data, is formatted and sent from the terminal to the server. The server records this data, and an analysis module calculates the degree of growth and quantifies the level of motivation. Furthermore, using the emotion data, it generates feedback that takes into account the emotional changes of each individual user. This feedback includes advice and suggestions for the next steps, based on their emotional state. The generated feedback is provided to the user via the communication terminal.

[0330] Specific example:

[0331] For example, if a user participates in training and their test scores improve from 70 to 75 to 80 points, the emotion engine will recognize an emotion such as "increased confidence." The server will determine this to be a high level of growth and, along with the level of motivation, generate more positive feedback. The user will then receive a message such as, "Your confidence in the training has increased significantly. We recommend that you tackle practical tasks next."

[0332] In this way, by utilizing the emotion engine, it is possible to evaluate the user's training progress from multiple perspectives and provide more accurate feedback.

[0333] The following describes the processing flow.

[0334] Step 1:

[0335] After the user completes the training, they use a communication device to input test results and questionnaire responses. Additionally, the device's camera and microphone capture audio and facial data.

[0336] Step 2:

[0337] The emotion engine built into the device analyzes the collected voice data and facial recognition data. The emotion engine analyzes the user's tone of voice and facial expressions to determine their current emotional state.

[0338] Step 3:

[0339] The device integrates and formats test results, survey results, and sentiment data, and sends it to the server.

[0340] Step 4:

[0341] The server receives data sent from the terminal and records it in storage. It then launches an analysis module to calculate the growth rate from the recorded data.

[0342] Step 5:

[0343] The server's analysis module calculates growth by comparing it to past test results. It also quantifies motivation levels from questionnaires and sentiment data. By analyzing sentiment data, it evaluates emotional changes and positive / negative tendencies.

[0344] Step 6:

[0345] The server generates feedback messages for the user based on the analysis results. These feedback messages include specific suggestions for improvement in the training content and emotional support for the next steps.

[0346] Step 7:

[0347] The generated feedback is sent from the server to the terminal. The terminal receives the feedback, notifies the user, and displays it within the application. The user reviews this feedback and plans future training activities based on the feedback received.

[0348] (Example 2)

[0349] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0350] Traditional training systems have faced challenges in accurately assessing participants' growth and motivation levels, resulting in ineffective feedback. Furthermore, they lack comprehensive evaluations that consider emotional shifts, making it difficult to provide individualized feedback.

[0351] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0352] In this invention, the server includes means for recording evaluation data acquired from a communication terminal, means for analyzing multiple quantities from the evaluation data to calculate the degree of growth, means for quantifying the degree of growth and the user's motivation level, and processing means for generating individual feedback based on emotional data. This makes it possible to provide comprehensive and individualized feedback that includes the emotional state of the participants.

[0353] A "communication terminal" is an electronic device that allows users to input information or receive data.

[0354] "Evaluation data" refers to information about the results and responses that users obtained during training or other activities.

[0355] "Growth rate" is a value that indicates the degree of improvement in the user's abilities and skills, as revealed by analyzing the acquired evaluation data.

[0356] "Motivation level" is a numerical representation of the user's level of intrinsic motivation.

[0357] "Emotional processing means" refers to a device or function that analyzes voice data and facial data collected by the user and performs processing to recognize the user's emotional state.

[0358] A "feedback generation method" is a function that processes data based on analysis to generate appropriate advice and suggestions for the next action to be provided to the user.

[0359] To implement this invention, a communication terminal primarily used by the training recipients and a server that interacts with it are required.

[0360] First, users use a communication terminal to input evaluation data (test results and questionnaire responses) obtained after the training is completed. The communication terminal is equipped with a microphone to collect the user's voice and a camera to analyze their facial expressions. These devices are integrated with software that acts as an emotion processing tool, allowing emotional data to be extracted from the user's voice tone and facial expressions.

[0361] Next, the collected data is formatted and sent to the server via a secure communication method. The server is equipped with a high-speed processor and sufficient database capacity, enabling it to efficiently process and store large amounts of data. On the server side, an analysis module runs to analyze the acquired evaluation data and quantify the user's growth and motivation level. This module implements algorithms for comparison with past history, allowing for precise monitoring of the user's progress.

[0362] Furthermore, the server can use a generative AI model to generate feedback based on sentiment data. This feedback includes meaningful advice and recommendations for the next steps for the user, and is provided to the user via a communication terminal.

[0363] As a concrete example, suppose a user takes a training course on "Performance Management in Training." If their test score starts at 70 points and rises to 80 points, the emotion engine recognizes that "confidence has increased." Upon receiving this information, the server determines that the user is seeking further challenges and prepares and provides feedback suggesting "the next task to take on."

[0364] An example of a prompt message could be: "Analyze this user's performance and emotional data and create a suggestion for the next training session. User data: {Performance: 70, 80, Emotion: Increased confidence}". In this way, accurate feedback based on the user's performance and emotional state can be provided, improving the quality of training.

[0365] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0366] Step 1:

[0367] After the user completes the training, an input screen appears on the communication terminal. The user enters test results and questionnaire responses on this screen. Voice input is also used, and the terminal's microphone captures the voice. The entered data is digitized and formatted as text data. In addition, the voice data is recorded in real time and used as input for sentiment analysis in the next step.

[0368] Step 2:

[0369] The device uses its camera to collect the user's facial expression data. The collected audio and facial expression data are analyzed by a built-in emotion processing system. Specifically, the analysis algorithm detects the tone of voice and subtle facial movements, and outputs the user's current emotional state as labels such as "confidence," "anxiety," and "joy." This output is formatted and prepared to be sent to the server along with other evaluation data.

[0370] Step 3:

[0371] The device transmits formatted test results, survey responses, and sentiment data to the server via a secure communication protocol. The transmitted data is received by the server and stored in a database. Error checking codes may be added to prevent data loss during transmission.

[0372] Step 4:

[0373] The server passes the received data to the analysis module. The analysis module compares it with historical data to calculate the user's growth and motivation level. For example, it compares past test results with current results to calculate the growth rate. Furthermore, sentiment data is also taken into consideration, and an output is generated that adjusts the analysis results based on this data.

[0374] Step 5:

[0375] The server uses a generative AI model to generate optimal feedback. The prompt is given analysis results and sentiment data as input, and the generative AI model outputs the next steps and advice appropriate for the user. This feedback includes specific and actionable content to increase the user's motivation.

[0376] Step 6:

[0377] The generated feedback is sent from the server to the communication terminal. The terminal displays the received feedback to the user. The display format, including text, images, and videos, is optimized according to the user's settings and communication environment. The user can review the feedback and use it to improve future training or activities.

[0378] (Application Example 2)

[0379] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0380] In modern factories, improving worker skills and maintaining motivation are crucial challenges, but traditional training and evaluation methods make it difficult to accurately grasp workers' psychological states and growth levels. Furthermore, there is a lack of mechanisms to provide immediate feedback that takes each worker's emotional state into account, enabling efficient and effective work processes.

[0381] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0382] In this invention, the server includes means for recording evaluation data acquired from a communication terminal, means for collecting the worker's facial expressions and vocalizations and analyzing their emotional state, and means for quantifying the degree of growth and motivation based on this data, generating feedback, and displaying it on a visual device. This makes it possible to provide accurate feedback that takes into account the emotional state of each individual worker in real time, thereby achieving skill improvement and motivation maintenance.

[0383] A "communication terminal" is an electronic device used for recording, transmitting, and receiving data.

[0384] "Evaluation data" refers to information based on the results of training and surveys received by workers.

[0385] "Growth rate" is an indicator that shows the progress of workers' abilities and skills, calculated based on evaluation data.

[0386] "Motivation level" is a numerical representation of a worker's enthusiasm and interest in their work.

[0387] "Improvement suggestions" refer to proposals for optimizing training and work content based on analysis results.

[0388] A "visual device" is an electronic device used to display information and provide it to workers visually.

[0389] "Facial expression" refers to the visual expression of emotion formed by the movement of facial muscles.

[0390] "Vocalization sounds" refer to audio data contained in the voices of workers, and are used for analyzing their emotional states.

[0391] "Emotional state" refers to the results obtained through the analysis of facial expressions and vocalizations, which indicate the psychological tendencies and mood of the worker at that particular time.

[0392] "Feedback" refers to informational and advisable advice given to an employee based on their level of growth, motivation, and emotional state.

[0393] The system for realizing this invention comprises a communication terminal, a visual device, and a server as its main components. The communication terminal records evaluation data, including the training results and survey results of workers. The visual device, shaped like eyeglasses, has the function of collecting the facial expressions and vocalizations of workers and transmits this data to the server.

[0394] The server analyzes the emotional state of workers using an emotion analysis engine based on data acquired from communication terminals and visual devices. This emotion analysis engine evaluates the mental state of workers using speech recognition and facial recognition technologies. The analyzed data is used to calculate the level of worker growth and motivation.

[0395] The server generates feedback based on the analysis results. This feedback includes appropriate advice and suggestions for the next steps, tailored to each worker's emotional state. This feedback information is provided to workers in real time through visual devices, allowing them to properly understand the situation during training and proceed efficiently.

[0396] For example, if a visual device detects high levels of tension in a worker's facial expression and tone of voice while they are being trained to operate a new machine, the server can use that information to provide feedback such as, "Please stay calm and continue working slowly."

[0397] An example of a prompt message might be, "Based on the user's emotional data and work progress, generate specific feedback to improve the user's motivation." Thus, the present invention is a comprehensive system for supporting the emotions and growth of workers.

[0398] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0399] Step 1:

[0400] The user puts on a visual device and begins the training. The visual device collects the user's facial expressions and vocalizations in real time and transmits this data to a communication terminal.

[0401] Input: User facial expression data, vocalization data

[0402] Output: Data transmission to communication terminal

[0403] Step 2:

[0404] The communication terminal records the acquired facial expression data and vocalization data and sends it to the server. The server receives this data and inputs it into the emotion analysis engine.

[0405] Input: Facial expression data, vocalization data

[0406] Output: Data transfer to the emotion analysis engine

[0407] Step 3:

[0408] The server's emotion analysis engine analyzes facial expression data and vocalization data to evaluate the user's emotional state. This analysis uses speech recognition and facial recognition algorithms.

[0409] Input: Facial expression data, vocalization data

[0410] Data processing: Applying speech recognition and facial recognition algorithms.

[0411] Output: Emotional state data

[0412] Step 4:

[0413] The server combines emotional state data, past training history, and test results to calculate growth and motivation levels.

[0414] Input: Emotional state data, training history, test results

[0415] Data calculation: Calculation of growth rate and motivation level

[0416] Output: Quantified growth and motivation levels

[0417] Step 5:

[0418] The server generates feedback using a generative AI model based on quantified growth and motivation levels. This feedback includes advice that takes emotional state into consideration and suggestions for the next steps.

[0419] Input: Growth rate, level of motivation

[0420] Data processing: Feedback generation using a generative AI model.

[0421] Output: Feedback data

[0422] Step 6:

[0423] The server transmits the generated feedback to a visual device via a communication terminal and displays it to the user. The user visually confirms the feedback and takes appropriate action.

[0424] Input: Feedback data

[0425] Output: Display of feedback to the user

[0426] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0427] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0428] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0429] [Third Embodiment]

[0430] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0431] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0432] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0433] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0434] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0435] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0436] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0437] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0438] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0439] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0440] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0441] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0442] This invention is a system for improving the effectiveness of training by having users transmit the results of their training using a communication terminal after they have participated, and quantifying their level of growth and motivation.

[0443] System configuration:

[0444] After users complete a training quiz and questionnaire, they input their results into a communication terminal. This terminal transmits the entered data to a server. The data received by the terminal is processed on the server and used to analyze their progress and motivation. The server analyzes this data and generates personalized feedback for each user. This feedback is then provided to the user again via the communication terminal.

[0445] Program processing:

[0446] When a user operates a communication terminal and inputs data, the terminal sends this information to a server. The server records the data in a database and sends it to an analysis module. The analysis module compares the current data with past data to evaluate the degree of growth and uses text analysis technology to determine positive or negative opinions from open-ended responses in questionnaires. The analysis results are returned to the server as quantified growth and motivation levels. Based on this information, the server generates a feedback message for the user. The feedback includes specific advice to help the user continuously improve and can be viewed by receiving it on the communication terminal.

[0447] Specific example:

[0448] If a user undergoes training for new business software and their test scores improve from 80 to 85 to 90 points, the data is entered via the terminal, and the server determines that their progress is high. On the other hand, if the user frequently answers "easy to understand" and "useful in real life" in a survey, their motivation level is also quantified as high. Based on this, the server generates feedback such as, "You understand the training content very well. We recommend the next level of training to further improve your skills," and presents it to the user.

[0449] Thus, the system of the present invention can support the growth of participants by individually analyzing training results and providing accurate feedback.

[0450] The following describes the processing flow.

[0451] Step 1:

[0452] Users complete the training test and enter their test results via a terminal. They also answer a training-related questionnaire and enter the results into the terminal in the same way.

[0453] Step 2:

[0454] The terminal formats the test results and survey results entered by the user and sends the data to the server using a secure communication protocol.

[0455] Step 3:

[0456] The server receives evaluation data sent from the terminal. After confirming receipt of the data, it saves the data to the database.

[0457] Step 4:

[0458] The server launches an analysis module on the saved data, compares the test results history, and calculates the degree of growth.

[0459] Step 5:

[0460] The server analyzes the survey results as text and determines whether they are positive or negative. It analyzes the responses, quantifies them, and calculates the degree of motivation.

[0461] Step 6:

[0462] The server generates feedback messages for users based on their progress and motivation level. This feedback includes suggestions for improving the training and advice for the next steps.

[0463] Step 7:

[0464] The server sends the generated feedback to the device. The device notifies the user of the received feedback and displays it through an application or email.

[0465] Step 8:

[0466] Users review feedback on their devices to understand their training performance and future guidance. They then plan their next training session as needed.

[0467] (Example 1)

[0468] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0469] Traditional training systems have made it difficult to objectively and immediately evaluate the growth and motivation of trainees and provide specific feedback. Therefore, it has been challenging to provide appropriate improvement measures tailored to individual participants, making it difficult to maximize the effectiveness of the training.

[0470] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0471] In this invention, the server includes means for storing data acquired from a communication device, means for transmitting the stored data to an analysis module and evaluating the degree of growth, and means for text analysis of free-response answers from questionnaires using natural language processing technology and determining emotions. This makes it possible to immediately and objectively evaluate the user's degree of growth and motivation and provide individually optimized feedback.

[0472] A "communication device" is an electronic device used by users to input data and exchange information with a server.

[0473] "Data storage" is the process of securely storing acquired user information.

[0474] An "analysis module" is a program or algorithm used to analyze stored data and evaluate user growth and motivation.

[0475] "Natural language processing technology" is a technology that uses computers to process and analyze natural language used by humans.

[0476] "Feedback generation" is the process of creating specific improvement suggestions and evaluations for users based on the analysis results.

[0477] "Growth rate" is a numerical indicator that shows how much a user's skills and knowledge have improved.

[0478] "Motivation level" refers to a numerical value or percentage that evaluates the user's willingness and proactiveness towards training.

[0479] This invention is a system designed to improve the effectiveness of training, and it relies on data exchange between three parties: the user, the terminal, and the server. First, the user completes the training and then answers a confirmation test and questionnaire. These results are entered using a terminal (smartphone, tablet, PC, etc.) as a communication device. The terminal then transmits this data to the server.

[0480] The server receives data and saves its contents to a database. Database management systems such as MySQL or PostgreSQL are used for this data storage. The saved data is sent to an analysis module for detailed analysis. This analysis module is built in a programming language such as Python and uses natural language processing techniques to analyze the open-ended responses of the survey. Specifically, natural language processing libraries such as NLTK and spaCy are used to perform sentiment analysis of the responses.

[0481] The results of the analysis are quantified as growth rate and motivation level. This quantification involves analyzing correlations and trends between data using generative AI models. OpenAI's GPT series and other large-scale language models are used as generative AI models.

[0482] User feedback is automatically generated by the server. This generation process involves inputting prompts using a generation AI model. For example, a prompt such as "The user's progress is high; we will provide detailed advice on the next training step" is input to create individual user feedback.

[0483] Finally, the generated feedback is sent back to the device and displayed to the user. This allows the user to see their own progress and increases their motivation to take the next step. This system not only records data but also provides a mechanism to continuously support the user's growth.

[0484] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0485] Step 1:

[0486] After training, users input their answers to a confirmation test and questionnaire using a communication device. The data entered includes test scores, questionnaire answer choices, and free-response answers.

[0487] Step 2:

[0488] The terminal sends the data entered by the user to the server. This transmission uses the HTTPS protocol to ensure data integrity and security, preventing data tampering.

[0489] Step 3:

[0490] The server records the received data in the database. At this stage, SQL INSERT queries are used to save the data to the database in the appropriate format.

[0491] Step 4:

[0492] The server's analysis module acquires data and performs trend analysis of test scores and sentiment analysis of questionnaires. Specifically, it calculates the degree of growth by comparing it with past test data and extracts positive and negative opinions from open-ended responses using natural language processing technology.

[0493] Step 5:

[0494] The analysis results are quantified on the server and summarized as growth rate and motivation level. This allows users' progress and motivation to be expressed in concrete numerical terms.

[0495] Step 6:

[0496] The server inputs prompt messages into the generated AI model, which then generates user-specific feedback. These prompt messages create specific advice tailored to the user's level of progress.

[0497] Step 7:

[0498] The server generates a feedback message and sends it to the terminal. The sent message can be viewed by the user through a communication device.

[0499] Step 8:

[0500] The device displays feedback to the user and suggests specific actions. This allows the user to evaluate their own progress and gain guidance for taking the next step.

[0501] (Application Example 1)

[0502] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0503] It is difficult to digitize the evaluation of education or training via communication devices and efficiently quantify user growth and motivation. Furthermore, there is a lack of guidance content based on appropriate improvement measures for users, so there is a need to maximize the effectiveness of education by utilizing evaluation data.

[0504] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0505] In this invention, the server includes means for recording evaluation values ​​obtained from communication equipment, means for analyzing multiple indicators from the recorded evaluation values ​​to calculate the degree of growth, and means for presenting improvement measures for the user based on the quantified degree of growth and motivation. This makes it possible to effectively utilize the evaluation of education or training and to immediately and appropriately improve the content of instruction that reflects the user's growth and motivation.

[0506] "Communication equipment" refers to devices used to transmit or receive data.

[0507] "Rating scores" are numerical data collected to indicate evaluations related to education and training.

[0508] "Means of recording" refers to a function or device for storing acquired data.

[0509] "Means for analyzing indicators and calculating the degree of growth" refers to a process or device that analyzes recorded data to quantify the user's improvement in ability.

[0510] "Motivation level" is an index that indicates the user's willingness and proactiveness to achieve their goals.

[0511] "Improvement measures" are specific strategies aimed at further enhancing the abilities and motivation of users.

[0512] "Improving instructional content" refers to improving programs and methods to enhance the quality of education and training.

[0513] The system for carrying out this invention mainly consists of a server, communication equipment, and an analysis module.

[0514] The server retrieves evaluation scores from communication devices and records them in a database. The communication devices transmit test results and survey results entered by users after training. The server then passes the recorded data to an analysis module. The analysis module uses numerical and text analysis libraries to quantify growth and motivation levels using historical data and free-response evaluations. Specific libraries such as TextBlob are likely to be used.

[0515] The analyzed numerical information is used by the server to generate specific improvement measures to promote user growth. User feedback includes advice on motivation for the next step and ways to enhance learning. This information is provided to the user via communication devices, such as smartphones and tablets.

[0516] As a concrete example, this system could be implemented in a training program for customer support staff at an e-commerce site. Staff test scores and satisfaction survey results would be analyzed, and they could receive customized advice to improve their response skills. An example of a prompt to the generating AI model in this case would be, "Please provide more effective feedback in our customer support training program. We want to quantify the staff's growth and motivation levels."

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

[0518] Step 1:

[0519] Users input their training test results and survey findings using communication devices. The input data is transmitted to the server via the communication device. Examples of input include test scores and free-form comments such as "The training was helpful." This allows the server to receive the user's rating.

[0520] Step 2:

[0521] The server records the received data in a database. The database stores user history and serves as foundational data for subsequent analysis. This lays the foundation for understanding how current test results are positioned in comparison to past data.

[0522] Step 3:

[0523] The server sends data to the analysis module, which then begins processing the data based on the rating scores. The analysis module uses a text analysis library such as TextBlob to analyze free-form comments and determine whether the sentiment is positive or negative. For numerical data, it calculates the average score and trends to quantify the degree of growth and motivation. At this time, it compares past exercise results with current data to evaluate the user's progress.

[0524] Step 4:

[0525] Based on the analysis results, the server uses a generative AI model to generate improvement measures for the user. Appropriate prompt sentences are input into the AI ​​model to obtain generated feedback and advice for the next steps. An example of a prompt sentence might be: "Please provide more effective feedback in our customer service training program. We want to quantify staff growth and motivation."

[0526] Step 5:

[0527] The server sends the generated feedback to the communication device so that the user can review it. Users can receive personalized feedback based on their training results and use it to motivate themselves for their next learning activities. In this step, mobile devices and tablets function as devices for displaying the results.

[0528] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0529] This invention is a system that improves the effectiveness of training by allowing users to participate in training, input and transmit the results and their emotions via a communication terminal, and then analyze their growth and motivation levels in more detail. By incorporating an emotion engine, this system enables the analysis of the user's emotional state and provides a comprehensive evaluation.

[0530] System configuration:

[0531] After users complete the training, they use a communication terminal to input their test results and questionnaire responses. The terminal is equipped with an emotion engine that recognizes the user's emotions through voice data and facial recognition data. This recognition result is also sent to the server. The server uses the test results, questionnaire responses, and emotion data sent from the terminal to perform a detailed analysis of each individual's level of growth and motivation.

[0532] Program processing:

[0533] After the user completes the training, they input their results into a communication terminal. The terminal collects voice and facial recognition data, and an emotion engine analyzes this data to generate emotion data. This emotion data, along with other evaluation data, is formatted and sent from the terminal to the server. The server records this data, and an analysis module calculates the degree of growth and quantifies the level of motivation. Furthermore, using the emotion data, it generates feedback that takes into account the emotional changes of each individual user. This feedback includes advice and suggestions for the next steps, based on their emotional state. The generated feedback is provided to the user via the communication terminal.

[0534] Specific example:

[0535] For example, if a user participates in training and their test scores improve from 70 to 75 to 80 points, the emotion engine will recognize an emotion such as "increased confidence." The server will determine this to be a high level of growth and, along with the level of motivation, generate more positive feedback. The user will then receive a message such as, "Your confidence in the training has increased significantly. We recommend that you tackle practical tasks next."

[0536] In this way, by utilizing the emotion engine, it is possible to evaluate the user's training progress from multiple perspectives and provide more accurate feedback.

[0537] The following describes the processing flow.

[0538] Step 1:

[0539] After the user completes the training, they use a communication device to input test results and questionnaire responses. Additionally, the device's camera and microphone capture audio and facial data.

[0540] Step 2:

[0541] The emotion engine built into the device analyzes the collected voice data and facial recognition data. The emotion engine analyzes the user's tone of voice and facial expressions to determine their current emotional state.

[0542] Step 3:

[0543] The device integrates and formats test results, survey results, and sentiment data, and sends it to the server.

[0544] Step 4:

[0545] The server receives data sent from the terminal and records it in storage. It then launches an analysis module to calculate the growth rate from the recorded data.

[0546] Step 5:

[0547] The server's analysis module calculates growth by comparing it to past test results. It also quantifies motivation levels from questionnaires and sentiment data. By analyzing sentiment data, it evaluates emotional changes and positive / negative tendencies.

[0548] Step 6:

[0549] The server generates feedback messages for the user based on the analysis results. These feedback messages include specific suggestions for improvement in the training content and emotional support for the next steps.

[0550] Step 7:

[0551] The generated feedback is sent from the server to the terminal. The terminal receives the feedback, notifies the user, and displays it within the application. The user reviews this feedback and plans future training activities based on the feedback received.

[0552] (Example 2)

[0553] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0554] Traditional training systems have faced challenges in accurately assessing participants' growth and motivation levels, resulting in ineffective feedback. Furthermore, they lack comprehensive evaluations that consider emotional shifts, making it difficult to provide individualized feedback.

[0555] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0556] In this invention, the server includes means for recording evaluation data acquired from a communication terminal, means for analyzing multiple quantities from the evaluation data to calculate the degree of growth, means for quantifying the degree of growth and the user's motivation level, and processing means for generating individual feedback based on emotional data. This makes it possible to provide comprehensive and individualized feedback that includes the emotional state of the participants.

[0557] A "communication terminal" is an electronic device that allows users to input information or receive data.

[0558] "Evaluation data" refers to information about the results and responses that users obtained during training or other activities.

[0559] "Growth rate" is a value that indicates the degree of improvement in the user's abilities and skills, as revealed by analyzing the acquired evaluation data.

[0560] "Motivation level" is a numerical representation of the user's level of intrinsic motivation.

[0561] "Emotional processing means" refers to a device or function that analyzes voice data and facial data collected by the user and performs processing to recognize the user's emotional state.

[0562] A "feedback generation method" is a function that processes data based on analysis to generate appropriate advice and suggestions for the next action to be provided to the user.

[0563] To implement this invention, a communication terminal primarily used by the training recipients and a server that interacts with it are required.

[0564] First, users use a communication terminal to input evaluation data (test results and questionnaire responses) obtained after the training is completed. The communication terminal is equipped with a microphone to collect the user's voice and a camera to analyze their facial expressions. These devices are integrated with software that acts as an emotion processing tool, allowing emotional data to be extracted from the user's voice tone and facial expressions.

[0565] Next, the collected data is formatted and sent to the server via a secure communication method. The server is equipped with a high-speed processor and sufficient database capacity, enabling it to efficiently process and store large amounts of data. On the server side, an analysis module runs to analyze the acquired evaluation data and quantify the user's growth and motivation level. This module implements algorithms for comparison with past history, allowing for precise monitoring of the user's progress.

[0566] Furthermore, the server can use a generative AI model to generate feedback based on sentiment data. This feedback includes meaningful advice and recommendations for the next steps for the user, and is provided to the user via a communication terminal.

[0567] As a concrete example, suppose a user takes a training course on "Performance Management in Training." If their test score starts at 70 points and rises to 80 points, the emotion engine recognizes that "confidence has increased." Upon receiving this information, the server determines that the user is seeking further challenges and prepares and provides feedback suggesting "the next task to take on."

[0568] An example of a prompt message could be: "Analyze this user's performance and emotional data and create a suggestion for the next training session. User data: {Performance: 70, 80, Emotion: Increased confidence}". In this way, accurate feedback based on the user's performance and emotional state can be provided, improving the quality of training.

[0569] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0570] Step 1:

[0571] After the user completes the training, an input screen appears on the communication terminal. The user enters test results and questionnaire responses on this screen. Voice input is also used, and the terminal's microphone captures the voice. The entered data is digitized and formatted as text data. In addition, the voice data is recorded in real time and used as input for sentiment analysis in the next step.

[0572] Step 2:

[0573] The device uses its camera to collect the user's facial expression data. The collected audio and facial expression data are analyzed by a built-in emotion processing system. Specifically, the analysis algorithm detects the tone of voice and subtle facial movements, and outputs the user's current emotional state as labels such as "confidence," "anxiety," and "joy." This output is formatted and prepared to be sent to the server along with other evaluation data.

[0574] Step 3:

[0575] The device transmits formatted test results, survey responses, and sentiment data to the server via a secure communication protocol. The transmitted data is received by the server and stored in a database. Error checking codes may be added to prevent data loss during transmission.

[0576] Step 4:

[0577] The server passes the received data to the analysis module. The analysis module compares it with historical data to calculate the user's growth and motivation level. For example, it compares past test results with current results to calculate the growth rate. Furthermore, sentiment data is also taken into consideration, and an output is generated that adjusts the analysis results based on this data.

[0578] Step 5:

[0579] The server uses a generative AI model to generate optimal feedback. The prompt is given analysis results and sentiment data as input, and the generative AI model outputs the next steps and advice appropriate for the user. This feedback includes specific and actionable content to increase the user's motivation.

[0580] Step 6:

[0581] The generated feedback is sent from the server to the communication terminal. The terminal displays the received feedback to the user. The display format, including text, images, and videos, is optimized according to the user's settings and communication environment. The user can review the feedback and use it to improve future training or activities.

[0582] (Application Example 2)

[0583] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0584] In modern factories, improving worker skills and maintaining motivation are crucial challenges, but traditional training and evaluation methods make it difficult to accurately grasp workers' psychological states and growth levels. Furthermore, there is a lack of mechanisms to provide immediate feedback that takes each worker's emotional state into account, enabling efficient and effective work processes.

[0585] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0586] In this invention, the server includes means for recording evaluation data acquired from a communication terminal, means for collecting the worker's facial expressions and vocalizations and analyzing their emotional state, and means for quantifying the degree of growth and motivation based on this data, generating feedback, and displaying it on a visual device. This makes it possible to provide accurate feedback that takes into account the emotional state of each individual worker in real time, thereby achieving skill improvement and motivation maintenance.

[0587] A "communication terminal" is an electronic device used for recording, transmitting, and receiving data.

[0588] "Evaluation data" refers to information based on the results of training and surveys received by workers.

[0589] "Growth rate" is an indicator that shows the progress of workers' abilities and skills, calculated based on evaluation data.

[0590] "Motivation level" is a numerical representation of a worker's enthusiasm and interest in their work.

[0591] "Improvement suggestions" refer to proposals for optimizing training and work content based on analysis results.

[0592] A "visual device" is an electronic device used to display information and provide it to workers visually.

[0593] "Facial expression" refers to the visual expression of emotion formed by the movement of facial muscles.

[0594] "Vocalization sounds" refer to audio data contained in the voices of workers, and are used for analyzing their emotional states.

[0595] "Emotional state" refers to the results obtained through the analysis of facial expressions and vocalizations, which indicate the psychological tendencies and mood of the worker at that particular time.

[0596] "Feedback" refers to informational and advisable advice given to an employee based on their level of growth, motivation, and emotional state.

[0597] The system for realizing this invention comprises a communication terminal, a visual device, and a server as its main components. The communication terminal records evaluation data, including the training results and survey results of workers. The visual device, shaped like eyeglasses, has the function of collecting the facial expressions and vocalizations of workers and transmits this data to the server.

[0598] The server analyzes the emotional state of workers using an emotion analysis engine based on data acquired from communication terminals and visual devices. This emotion analysis engine evaluates the mental state of workers using speech recognition and facial recognition technologies. The analyzed data is used to calculate the level of worker growth and motivation.

[0599] The server generates feedback based on the analysis results. This feedback includes appropriate advice and suggestions for the next steps, tailored to each worker's emotional state. This feedback information is provided to workers in real time through visual devices, allowing them to properly understand the situation during training and proceed efficiently.

[0600] For example, if a visual device detects high levels of tension in a worker's facial expression and tone of voice while they are being trained to operate a new machine, the server can use that information to provide feedback such as, "Please stay calm and continue working slowly."

[0601] An example of a prompt message might be, "Based on the user's emotional data and work progress, generate specific feedback to improve the user's motivation." Thus, the present invention is a comprehensive system for supporting the emotions and growth of workers.

[0602] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0603] Step 1:

[0604] The user puts on a visual device and begins the training. The visual device collects the user's facial expressions and vocalizations in real time and transmits this data to a communication terminal.

[0605] Input: User facial expression data, vocalization data

[0606] Output: Data transmission to communication terminal

[0607] Step 2:

[0608] The communication terminal records the acquired facial expression data and vocalization data and sends it to the server. The server receives this data and inputs it into the emotion analysis engine.

[0609] Input: Facial expression data, vocalization data

[0610] Output: Data transfer to the emotion analysis engine

[0611] Step 3:

[0612] The server's emotion analysis engine analyzes facial expression data and vocalization data to evaluate the user's emotional state. This analysis uses speech recognition and facial recognition algorithms.

[0613] Input: Facial expression data, vocalization data

[0614] Data processing: Applying speech recognition and facial recognition algorithms.

[0615] Output: Emotional state data

[0616] Step 4:

[0617] The server combines emotional state data, past training history, and test results to calculate growth and motivation levels.

[0618] Input: Emotional state data, training history, test results

[0619] Data calculation: Calculation of growth rate and motivation level

[0620] Output: Quantified growth and motivation levels

[0621] Step 5:

[0622] The server generates feedback using a generative AI model based on quantified growth and motivation levels. This feedback includes advice that takes emotional state into consideration and suggestions for the next steps.

[0623] Input: Growth rate, level of motivation

[0624] Data processing: Feedback generation using a generative AI model.

[0625] Output: Feedback data

[0626] Step 6:

[0627] The server transmits the generated feedback to a visual device via a communication terminal and displays it to the user. The user visually confirms the feedback and takes appropriate action.

[0628] Input: Feedback data

[0629] Output: Display of feedback to the user

[0630] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0631] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0632] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0633] [Fourth Embodiment]

[0634] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0635] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0636] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0637] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0638] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0639] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0640] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0641] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0642] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0643] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0644] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0645] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0646] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0647] This invention is a system for improving the effectiveness of training by having users transmit the results of their training using a communication terminal after they have participated, and quantifying their level of growth and motivation.

[0648] System configuration:

[0649] After users complete a training quiz and questionnaire, they input their results into a communication terminal. This terminal transmits the entered data to a server. The data received by the terminal is processed on the server and used to analyze their progress and motivation. The server analyzes this data and generates personalized feedback for each user. This feedback is then provided to the user again via the communication terminal.

[0650] Program processing:

[0651] When a user operates a communication terminal and inputs data, the terminal sends this information to a server. The server records the data in a database and sends it to an analysis module. The analysis module compares the current data with past data to evaluate the degree of growth and uses text analysis technology to determine positive or negative opinions from open-ended responses in questionnaires. The analysis results are returned to the server as quantified growth and motivation levels. Based on this information, the server generates a feedback message for the user. The feedback includes specific advice to help the user continuously improve and can be viewed by receiving it on the communication terminal.

[0652] Specific example:

[0653] If a user undergoes training for new business software and their test scores improve from 80 to 85 to 90 points, the data is entered via the terminal, and the server determines that their progress is high. On the other hand, if the user frequently answers "easy to understand" and "useful in real life" in a survey, their motivation level is also quantified as high. Based on this, the server generates feedback such as, "You understand the training content very well. We recommend the next level of training to further improve your skills," and presents it to the user.

[0654] Thus, the system of the present invention can support the growth of participants by individually analyzing training results and providing accurate feedback.

[0655] The following describes the processing flow.

[0656] Step 1:

[0657] Users complete the training test and enter their test results via a terminal. They also answer a training-related questionnaire and enter the results into the terminal in the same way.

[0658] Step 2:

[0659] The terminal formats the test results and survey results entered by the user and sends the data to the server using a secure communication protocol.

[0660] Step 3:

[0661] The server receives evaluation data sent from the terminal. After confirming receipt of the data, it saves the data to the database.

[0662] Step 4:

[0663] The server launches an analysis module on the saved data, compares the test results history, and calculates the degree of growth.

[0664] Step 5:

[0665] The server analyzes the survey results as text and determines whether they are positive or negative. It analyzes the responses, quantifies them, and calculates the degree of motivation.

[0666] Step 6:

[0667] The server generates feedback messages for users based on their progress and motivation level. This feedback includes suggestions for improving the training and advice for the next steps.

[0668] Step 7:

[0669] The server sends the generated feedback to the device. The device notifies the user of the received feedback and displays it through an application or email.

[0670] Step 8:

[0671] Users review feedback on their devices to understand their training performance and future guidance. They then plan their next training session as needed.

[0672] (Example 1)

[0673] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0674] Traditional training systems have made it difficult to objectively and immediately evaluate the growth and motivation of trainees and provide specific feedback. Therefore, it has been challenging to provide appropriate improvement measures tailored to individual participants, making it difficult to maximize the effectiveness of the training.

[0675] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0676] In this invention, the server includes means for storing data acquired from a communication device, means for transmitting the stored data to an analysis module and evaluating the degree of growth, and means for text analysis of free-response answers from questionnaires using natural language processing technology and determining emotions. This makes it possible to immediately and objectively evaluate the user's degree of growth and motivation and provide individually optimized feedback.

[0677] A "communication device" is an electronic device used by users to input data and exchange information with a server.

[0678] "Data storage" is the process of securely storing acquired user information.

[0679] An "analysis module" is a program or algorithm used to analyze stored data and evaluate user growth and motivation.

[0680] "Natural language processing technology" is a technology that uses computers to process and analyze natural language used by humans.

[0681] "Feedback generation" is the process of creating specific improvement suggestions and evaluations for users based on the analysis results.

[0682] "Growth rate" is a numerical indicator that shows how much a user's skills and knowledge have improved.

[0683] "Motivation level" refers to a numerical value or percentage that evaluates the user's willingness and proactiveness towards training.

[0684] This invention is a system designed to improve the effectiveness of training, and it relies on data exchange between three parties: the user, the terminal, and the server. First, the user completes the training and then answers a confirmation test and questionnaire. These results are entered using a terminal (smartphone, tablet, PC, etc.) as a communication device. The terminal then transmits this data to the server.

[0685] The server receives data and saves its contents to a database. Database management systems such as MySQL or PostgreSQL are used for this data storage. The saved data is sent to an analysis module for detailed analysis. This analysis module is built in a programming language such as Python and uses natural language processing techniques to analyze the open-ended responses of the survey. Specifically, natural language processing libraries such as NLTK and spaCy are used to perform sentiment analysis of the responses.

[0686] The results of the analysis are quantified as growth rate and motivation level. This quantification involves analyzing correlations and trends between data using generative AI models. OpenAI's GPT series and other large-scale language models are used as generative AI models.

[0687] User feedback is automatically generated by the server. This generation process involves inputting prompts using a generation AI model. For example, a prompt such as "The user's progress is high; we will provide detailed advice on the next training step" is input to create individual user feedback.

[0688] Finally, the generated feedback is sent back to the device and displayed to the user. This allows the user to see their own progress and increases their motivation to take the next step. This system not only records data but also provides a mechanism to continuously support the user's growth.

[0689] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0690] Step 1:

[0691] After training, users input their answers to a confirmation test and questionnaire using a communication device. The data entered includes test scores, questionnaire answer choices, and free-response answers.

[0692] Step 2:

[0693] The terminal sends the data entered by the user to the server. This transmission uses the HTTPS protocol to ensure data integrity and security, preventing data tampering.

[0694] Step 3:

[0695] The server records the received data in the database. At this stage, SQL INSERT queries are used to save the data to the database in the appropriate format.

[0696] Step 4:

[0697] The server's analysis module acquires data and performs trend analysis of test scores and sentiment analysis of questionnaires. Specifically, it calculates the degree of growth by comparing it with past test data and extracts positive and negative opinions from open-ended responses using natural language processing technology.

[0698] Step 5:

[0699] The analysis results are quantified on the server and summarized as growth rate and motivation level. This allows users' progress and motivation to be expressed in concrete numerical terms.

[0700] Step 6:

[0701] The server inputs prompt messages into the generated AI model, which then generates user-specific feedback. These prompt messages create specific advice tailored to the user's level of progress.

[0702] Step 7:

[0703] The server generates a feedback message and sends it to the terminal. The sent message can be viewed by the user through a communication device.

[0704] Step 8:

[0705] The device displays feedback to the user and suggests specific actions. This allows the user to evaluate their own progress and gain guidance for taking the next step.

[0706] (Application Example 1)

[0707] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0708] It is difficult to digitize the evaluation of education or training via communication devices and efficiently quantify user growth and motivation. Furthermore, there is a lack of guidance content based on appropriate improvement measures for users, so there is a need to maximize the effectiveness of education by utilizing evaluation data.

[0709] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0710] In this invention, the server includes means for recording evaluation values ​​obtained from communication equipment, means for analyzing multiple indicators from the recorded evaluation values ​​to calculate the degree of growth, and means for presenting improvement measures for the user based on the quantified degree of growth and motivation. This makes it possible to effectively utilize the evaluation of education or training and to immediately and appropriately improve the content of instruction that reflects the user's growth and motivation.

[0711] "Communication equipment" refers to devices used to transmit or receive data.

[0712] "Rating scores" are numerical data collected to indicate evaluations related to education and training.

[0713] "Means of recording" refers to a function or device for storing acquired data.

[0714] "Means for analyzing indicators and calculating the degree of growth" refers to a process or device that analyzes recorded data to quantify the user's improvement in ability.

[0715] "Motivation level" is an index that indicates the user's willingness and proactiveness to achieve their goals.

[0716] "Improvement measures" are specific strategies aimed at further enhancing the abilities and motivation of users.

[0717] "Improving instructional content" refers to improving programs and methods to enhance the quality of education and training.

[0718] The system for carrying out this invention mainly consists of a server, communication equipment, and an analysis module.

[0719] The server retrieves evaluation scores from communication devices and records them in a database. The communication devices transmit test results and survey results entered by users after training. The server then passes the recorded data to an analysis module. The analysis module uses numerical and text analysis libraries to quantify growth and motivation levels using historical data and free-response evaluations. Specific libraries such as TextBlob are likely to be used.

[0720] The analyzed numerical information is used by the server to generate specific improvement measures to promote user growth. User feedback includes advice on motivation for the next step and ways to enhance learning. This information is provided to the user via communication devices, such as smartphones and tablets.

[0721] As a concrete example, this system could be implemented in a training program for customer support staff at an e-commerce site. Staff test scores and satisfaction survey results would be analyzed, and they could receive customized advice to improve their response skills. An example of a prompt to the generating AI model in this case would be, "Please provide more effective feedback in our customer support training program. We want to quantify the staff's growth and motivation levels."

[0722] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0723] Step 1:

[0724] Users input their training test results and survey findings using communication devices. The input data is transmitted to the server via the communication device. Examples of input include test scores and free-form comments such as "The training was helpful." This allows the server to receive the user's rating.

[0725] Step 2:

[0726] The server records the received data in a database. The database stores user history and serves as foundational data for subsequent analysis. This lays the foundation for understanding how current test results are positioned in comparison to past data.

[0727] Step 3:

[0728] The server sends data to the analysis module, which then begins processing the data based on the rating scores. The analysis module uses a text analysis library such as TextBlob to analyze free-form comments and determine whether the sentiment is positive or negative. For numerical data, it calculates the average score and trends to quantify the degree of growth and motivation. At this time, it compares past exercise results with current data to evaluate the user's progress.

[0729] Step 4:

[0730] Based on the analysis results, the server uses a generative AI model to generate improvement measures for the user. Appropriate prompt sentences are input into the AI ​​model to obtain generated feedback and advice for the next steps. An example of a prompt sentence might be: "Please provide more effective feedback in our customer service training program. We want to quantify staff growth and motivation."

[0731] Step 5:

[0732] The server sends the generated feedback to the communication device so that the user can review it. Users can receive personalized feedback based on their training results and use it to motivate themselves for their next learning activities. In this step, mobile devices and tablets function as devices for displaying the results.

[0733] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0734] This invention is a system that improves the effectiveness of training by allowing users to participate in training, input and transmit the results and their emotions via a communication terminal, and then analyze their growth and motivation levels in more detail. By incorporating an emotion engine, this system enables the analysis of the user's emotional state and provides a comprehensive evaluation.

[0735] System configuration:

[0736] After users complete the training, they use a communication terminal to input their test results and questionnaire responses. The terminal is equipped with an emotion engine that recognizes the user's emotions through voice data and facial recognition data. This recognition result is also sent to the server. The server uses the test results, questionnaire responses, and emotion data sent from the terminal to perform a detailed analysis of each individual's level of growth and motivation.

[0737] Program processing:

[0738] After the user completes the training, they input their results into a communication terminal. The terminal collects voice and facial recognition data, and an emotion engine analyzes this data to generate emotion data. This emotion data, along with other evaluation data, is formatted and sent from the terminal to the server. The server records this data, and an analysis module calculates the degree of growth and quantifies the level of motivation. Furthermore, using the emotion data, it generates feedback that takes into account the emotional changes of each individual user. This feedback includes advice and suggestions for the next steps, based on their emotional state. The generated feedback is provided to the user via the communication terminal.

[0739] Specific example:

[0740] For example, if a user participates in training and their test scores improve from 70 to 75 to 80 points, the emotion engine will recognize an emotion such as "increased confidence." The server will determine this to be a high level of growth and, along with the level of motivation, generate more positive feedback. The user will then receive a message such as, "Your confidence in the training has increased significantly. We recommend that you tackle practical tasks next."

[0741] In this way, by utilizing the emotion engine, it is possible to evaluate the user's training progress from multiple perspectives and provide more accurate feedback.

[0742] The following describes the processing flow.

[0743] Step 1:

[0744] After the user completes the training, they use a communication device to input test results and questionnaire responses. Additionally, the device's camera and microphone capture audio and facial data.

[0745] Step 2:

[0746] The emotion engine built into the device analyzes the collected voice data and facial recognition data. The emotion engine analyzes the user's tone of voice and facial expressions to determine their current emotional state.

[0747] Step 3:

[0748] The device integrates and formats test results, survey results, and sentiment data, and sends it to the server.

[0749] Step 4:

[0750] The server receives data sent from the terminal and records it in storage. It then launches an analysis module to calculate the growth rate from the recorded data.

[0751] Step 5:

[0752] The server's analysis module calculates growth by comparing it to past test results. It also quantifies motivation levels from questionnaires and sentiment data. By analyzing sentiment data, it evaluates emotional changes and positive / negative tendencies.

[0753] Step 6:

[0754] The server generates feedback messages for the user based on the analysis results. These feedback messages include specific suggestions for improvement in the training content and emotional support for the next steps.

[0755] Step 7:

[0756] The generated feedback is sent from the server to the terminal. The terminal receives the feedback, notifies the user, and displays it within the application. The user reviews this feedback and plans future training activities based on the feedback received.

[0757] (Example 2)

[0758] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0759] Traditional training systems have faced challenges in accurately assessing participants' growth and motivation levels, resulting in ineffective feedback. Furthermore, they lack comprehensive evaluations that consider emotional shifts, making it difficult to provide individualized feedback.

[0760] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0761] In this invention, the server includes means for recording evaluation data acquired from a communication terminal, means for analyzing multiple quantities from the evaluation data to calculate the degree of growth, means for quantifying the degree of growth and the user's motivation level, and processing means for generating individual feedback based on emotional data. This makes it possible to provide comprehensive and individualized feedback that includes the emotional state of the participants.

[0762] A "communication terminal" is an electronic device that allows users to input information or receive data.

[0763] "Evaluation data" refers to information about the results and responses that users obtained during training or other activities.

[0764] "Growth rate" is a value that indicates the degree of improvement in the user's abilities and skills, as revealed by analyzing the acquired evaluation data.

[0765] "Motivation level" is a numerical representation of the user's level of intrinsic motivation.

[0766] "Emotional processing means" refers to a device or function that analyzes voice data and facial data collected by the user and performs processing to recognize the user's emotional state.

[0767] A "feedback generation method" is a function that processes data based on analysis to generate appropriate advice and suggestions for the next action to be provided to the user.

[0768] To implement this invention, a communication terminal primarily used by the training recipients and a server that interacts with it are required.

[0769] First, users use a communication terminal to input evaluation data (test results and questionnaire responses) obtained after the training is completed. The communication terminal is equipped with a microphone to collect the user's voice and a camera to analyze their facial expressions. These devices are integrated with software that acts as an emotion processing tool, allowing emotional data to be extracted from the user's voice tone and facial expressions.

[0770] Next, the collected data is formatted and sent to the server via a secure communication method. The server is equipped with a high-speed processor and sufficient database capacity, enabling it to efficiently process and store large amounts of data. On the server side, an analysis module runs to analyze the acquired evaluation data and quantify the user's growth and motivation level. This module implements algorithms for comparison with past history, allowing for precise monitoring of the user's progress.

[0771] Furthermore, the server can use a generative AI model to generate feedback based on sentiment data. This feedback includes meaningful advice and recommendations for the next steps for the user, and is provided to the user via a communication terminal.

[0772] As a concrete example, suppose a user takes a training course on "Performance Management in Training." If their test score starts at 70 points and rises to 80 points, the emotion engine recognizes that "confidence has increased." Upon receiving this information, the server determines that the user is seeking further challenges and prepares and provides feedback suggesting "the next task to take on."

[0773] An example of a prompt message could be: "Analyze this user's performance and emotional data and create a suggestion for the next training session. User data: {Performance: 70, 80, Emotion: Increased confidence}". In this way, accurate feedback based on the user's performance and emotional state can be provided, improving the quality of training.

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

[0775] Step 1:

[0776] After the user completes the training, an input screen appears on the communication terminal. The user enters test results and questionnaire responses on this screen. Voice input is also used, and the terminal's microphone captures the voice. The entered data is digitized and formatted as text data. In addition, the voice data is recorded in real time and used as input for sentiment analysis in the next step.

[0777] Step 2:

[0778] The device uses its camera to collect the user's facial expression data. The collected audio and facial expression data are analyzed by a built-in emotion processing system. Specifically, the analysis algorithm detects the tone of voice and subtle facial movements, and outputs the user's current emotional state as labels such as "confidence," "anxiety," and "joy." This output is formatted and prepared to be sent to the server along with other evaluation data.

[0779] Step 3:

[0780] The device transmits formatted test results, survey responses, and sentiment data to the server via a secure communication protocol. The transmitted data is received by the server and stored in a database. Error checking codes may be added to prevent data loss during transmission.

[0781] Step 4:

[0782] The server passes the received data to the analysis module. The analysis module compares it with historical data to calculate the user's growth and motivation level. For example, it compares past test results with current results to calculate the growth rate. Furthermore, sentiment data is also taken into consideration, and an output is generated that adjusts the analysis results based on this data.

[0783] Step 5:

[0784] The server uses a generative AI model to generate optimal feedback. The prompt is given analysis results and sentiment data as input, and the generative AI model outputs the next steps and advice appropriate for the user. This feedback includes specific and actionable content to increase the user's motivation.

[0785] Step 6:

[0786] The generated feedback is sent from the server to the communication terminal. The terminal displays the received feedback to the user. The display format, including text, images, and videos, is optimized according to the user's settings and communication environment. The user can review the feedback and use it to improve future training or activities.

[0787] (Application Example 2)

[0788] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0789] In modern factories, improving worker skills and maintaining motivation are crucial challenges, but traditional training and evaluation methods make it difficult to accurately grasp workers' psychological states and growth levels. Furthermore, there is a lack of mechanisms to provide immediate feedback that takes each worker's emotional state into account, enabling efficient and effective work processes.

[0790] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0791] In this invention, the server includes means for recording evaluation data acquired from a communication terminal, means for collecting the worker's facial expressions and vocalizations and analyzing their emotional state, and means for quantifying the degree of growth and motivation based on this data, generating feedback, and displaying it on a visual device. This makes it possible to provide accurate feedback that takes into account the emotional state of each individual worker in real time, thereby achieving skill improvement and motivation maintenance.

[0792] A "communication terminal" is an electronic device used for recording, transmitting, and receiving data.

[0793] "Evaluation data" refers to information based on the results of training and surveys received by workers.

[0794] "Growth rate" is an indicator that shows the progress of workers' abilities and skills, calculated based on evaluation data.

[0795] "Motivation level" is a numerical representation of a worker's enthusiasm and interest in their work.

[0796] "Improvement suggestions" refer to proposals for optimizing training and work content based on analysis results.

[0797] A "visual device" is an electronic device used to display information and provide it to workers visually.

[0798] "Facial expression" refers to the visual expression of emotion formed by the movement of facial muscles.

[0799] "Vocalization sounds" refer to audio data contained in the voices of workers, and are used for analyzing their emotional states.

[0800] "Emotional state" refers to the results obtained through the analysis of facial expressions and vocalizations, which indicate the psychological tendencies and mood of the worker at that particular time.

[0801] "Feedback" refers to informational and advisable advice given to an employee based on their level of growth, motivation, and emotional state.

[0802] The system for realizing this invention comprises a communication terminal, a visual device, and a server as its main components. The communication terminal records evaluation data, including the training results and survey results of workers. The visual device, shaped like eyeglasses, has the function of collecting the facial expressions and vocalizations of workers and transmits this data to the server.

[0803] The server analyzes the emotional state of workers using an emotion analysis engine based on data acquired from communication terminals and visual devices. This emotion analysis engine evaluates the mental state of workers using speech recognition and facial recognition technologies. The analyzed data is used to calculate the level of worker growth and motivation.

[0804] The server generates feedback based on the analysis results. This feedback includes appropriate advice and suggestions for the next steps, tailored to each worker's emotional state. This feedback information is provided to workers in real time through visual devices, allowing them to properly understand the situation during training and proceed efficiently.

[0805] For example, if a visual device detects high levels of tension in a worker's facial expression and tone of voice while they are being trained to operate a new machine, the server can use that information to provide feedback such as, "Please stay calm and continue working slowly."

[0806] An example of a prompt message might be, "Based on the user's emotional data and work progress, generate specific feedback to improve the user's motivation." Thus, the present invention is a comprehensive system for supporting the emotions and growth of workers.

[0807] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0808] Step 1:

[0809] The user puts on a visual device and begins the training. The visual device collects the user's facial expressions and vocalizations in real time and transmits this data to a communication terminal.

[0810] Input: User facial expression data, vocalization data

[0811] Output: Data transmission to communication terminal

[0812] Step 2:

[0813] The communication terminal records the acquired facial expression data and vocalization data and sends it to the server. The server receives this data and inputs it into the emotion analysis engine.

[0814] Input: Facial expression data, vocalization data

[0815] Output: Data transfer to the emotion analysis engine

[0816] Step 3:

[0817] The server's emotion analysis engine analyzes facial expression data and vocalization data to evaluate the user's emotional state. This analysis uses speech recognition and facial recognition algorithms.

[0818] Input: Facial expression data, vocalization data

[0819] Data processing: Applying speech recognition and facial recognition algorithms.

[0820] Output: Emotional state data

[0821] Step 4:

[0822] The server combines emotional state data, past training history, and test results to calculate growth and motivation levels.

[0823] Input: Emotional state data, training history, test results

[0824] Data calculation: Calculation of growth rate and motivation level

[0825] Output: Quantified growth and motivation levels

[0826] Step 5:

[0827] The server generates feedback using a generative AI model based on quantified growth and motivation levels. This feedback includes advice that takes emotional state into consideration and suggestions for the next steps.

[0828] Input: Growth rate, level of motivation

[0829] Data processing: Feedback generation using a generative AI model.

[0830] Output: Feedback data

[0831] Step 6:

[0832] The server transmits the generated feedback to a visual device via a communication terminal and displays it to the user. The user visually confirms the feedback and takes appropriate action.

[0833] Input: Feedback data

[0834] Output: Display of feedback to the user

[0835] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0836] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0837] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0838] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0839] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0840] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0841] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0842] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0843] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0844] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0845] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0846] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0847] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0848] 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.

[0849] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0850] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0851] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0852] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0853] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0854] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0855] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0856] The following is further disclosed regarding the embodiments described above.

[0857] (Claim 1)

[0858] A means for recording evaluation data acquired from a communication terminal,

[0859] A means for calculating the degree of growth by analyzing multiple quantities from the recorded evaluation data mentioned above,

[0860] A means of quantifying the degree of growth and the degree of user motivation based on the analyzed quantities,

[0861] A means of generating suggestions for improving training content based on quantified information,

[0862] A means of outputting the generated information to a communication terminal,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, wherein the above evaluation data are test results and survey results.

[0866] (Claim 3)

[0867] The system according to claim 1, wherein the means for performing the above analysis is based on comparative analysis with past history.

[0868] "Example 1"

[0869] (Claim 1)

[0870] A means of storing data acquired from a communication device,

[0871] A means for sending the stored data to an analysis module and evaluating the degree of growth,

[0872] A method for analyzing open-ended responses in a survey using natural language processing technology to determine emotions,

[0873] A means of quantifying the user's growth and motivation level based on analytical data,

[0874] A means of generating feedback using a generative AI model based on quantified information,

[0875] A means for transmitting and displaying the generated feedback to a communication device,

[0876] A system that includes this.

[0877] (Claim 2)

[0878] The system according to claim 1, wherein the acquired data consists of test results and survey results.

[0879] (Claim 3)

[0880] The system according to claim 1, wherein the analysis module performs analysis by comparing it with past records.

[0881] "Application Example 1"

[0882] (Claim 1)

[0883] A means for recording evaluation values ​​obtained from communication equipment,

[0884] A means for analyzing multiple indicators from the recorded evaluation values ​​mentioned above to calculate the degree of growth,

[0885] A means of quantifying the degree of growth and the user's motivation based on the analyzed indicators,

[0886] A means of generating suggestions for improving instructional content based on quantified information,

[0887] A means for outputting the generated information to a communication device,

[0888] A means of presenting improvement measures for users based on quantified growth levels and motivation levels,

[0889] A system that includes this.

[0890] (Claim 2)

[0891] The system according to claim 1, where the above evaluation coefficient is the test result and the survey result.

[0892] (Claim 3)

[0893] The system according to claim 1, wherein the means for performing the above analysis is based on comparative analysis with existing history.

[0894] "Example 2 of combining an emotion engine"

[0895] (Claim 1)

[0896] A means for recording evaluation data acquired from a communication terminal,

[0897] A means for calculating the degree of growth by analyzing multiple quantities from the recorded evaluation data mentioned above,

[0898] A means of quantifying the degree of growth and the degree of user motivation based on the analyzed quantities,

[0899] A means of generating suggestions for improving training content based on quantified information,

[0900] A means of outputting the generated information to a communication terminal,

[0901] An emotion processing means for analyzing the user's voice data and facial data,

[0902] A processing means for generating individual feedback based on emotional data,

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, wherein the above evaluation data are the test results and survey results.

[0906] (Claim 3)

[0907] The system according to claim 1, wherein the means for performing the above analysis is based on comparative analysis with past history.

[0908] "Application example 2 when combining with an emotional engine"

[0909] (Claim 1)

[0910] A means for recording evaluation data acquired from a communication terminal,

[0911] A means for calculating the degree of growth by analyzing multiple quantities from the recorded evaluation data mentioned above,

[0912] A means of quantifying the degree of growth and the degree of user motivation based on the analyzed quantities,

[0913] A means of generating suggestions for improving work processes based on quantified information,

[0914] A means for outputting the generated information to the worker's visual device,

[0915] A means of collecting workers' facial expressions and vocalizations through a visual device and analyzing their emotional state,

[0916] A means for generating feedback based on emotional state and displaying it on a visual device,

[0917] A system that includes this.

[0918] (Claim 2)

[0919] The system according to claim 1, wherein the above evaluation data consists of test results and survey results, and also includes emotional state data.

[0920] (Claim 3)

[0921] The system according to claim 1, wherein the means of analysis described above is based on comparative analysis with past history and includes comparison with emotional patterns. [Explanation of Symbols]

[0922] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for recording evaluation data acquired from a communication terminal, A means for calculating the degree of growth by analyzing multiple quantities from the recorded evaluation data mentioned above, A means of quantifying the degree of growth and the degree of user motivation based on the analyzed quantities, A means of generating suggestions for improving training content based on quantified information, A means of outputting the generated information to a communication terminal, A system that includes this.

2. The system according to claim 1, wherein the above evaluation data are test results and survey results.

3. The system according to claim 1, wherein the means for performing the above analysis is based on comparative analysis with past history.

Images