System

Abstract

A system is provided.SOLUTION: The system includes a teacher terminal means for inputting a target and an evaluation criterion of a lesson, a student terminal means for inputting an answer from a student, a server means for receiving data from the teacher terminal means and the student terminal means, an evaluation means for performing natural language processing based on the target and the evaluation criterion of the lesson inputted in the server means and evaluating a degree of achievement, a feedback means for feeding back the evaluation result to the teacher terminal means and the student terminal means, and an accumulation / learning means for accumulating evaluation data in the long term and learning an evaluation model.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional educational evaluation systems primarily rely on test scores, making it difficult to qualitatively assess students' thinking abilities and independent learning. As a result, they were unable to adequately capture the broader and deeper aspects of learning that students demonstrate during class, such as their understanding of knowledge, the expression of opinions, and their proposals for action. Another problem was that evaluation standards were inconsistent and heavily reliant on the evaluator's subjectivity. Furthermore, evaluation results were not accumulated over the long term, making it difficult to track continuous growth and learning outcomes. A new evaluation system is needed to address these issues. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following system. First, it comprises teacher terminal means for teachers to input lesson goals and evaluation criteria. It also comprises student terminal means for students to input answers during lessons. Data from these terminals is sent to server means, which includes evaluation means that uses natural language processing to evaluate achievement based on the lesson goals and evaluation criteria. Evaluation results are returned to the teacher terminal means and student terminal means via feedback means. Furthermore, the system also incorporates accumulation and learning means for accumulating evaluation data over the long term and learning an evaluation model. This enables qualitative evaluation of thinking ability and independent learning, and allows long-term growth to be tracked.

[0006] "Teacher terminal means" refers to electronic equipment used by teachers to input lesson goals and evaluation criteria.

[0007] "Student terminal means" refers to electronic devices that students use during class to input answers and opinions.

[0008] The "server means" is a computer system for receiving and processing data sent from the teacher terminal means and the student terminal means.

[0009] The "evaluation means" is a function that performs natural language processing based on the lesson goals and evaluation criteria input into the server means, and evaluates the achievement level of students.

[0010] The "feedback means" is a function for returning the evaluation results to the teacher terminal means and the student terminal means.

[0011] "Storage and learning means" is a function for accumulating evaluation data over the long term and learning the evaluation model.

[0012] "Natural language processing" is a technology that allows computers to analyze and understand human language.

[0013] "Achievement assessment" is the assessment of the extent to which students meet the course objectives and assessment criteria.

[0014] "Feedback" is information provided to teachers and students based on the evaluation results that is useful for improvement and future instruction.

[0015] An "assessment model" is a set of algorithms and rules used in assessment tools to quantitatively and qualitatively determine student achievement. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The system of the present invention uses an evaluation generation AI to qualitatively evaluate students' thinking ability and independent learning based on goals and evaluation criteria set by teachers during lessons. This system includes teacher terminal means, student terminal means, server means, and evaluation means. Specific embodiments of the system are described below.

[0038] Teacher terminal means

[0039] The user (teacher) inputs the lesson goals and evaluation criteria using the teacher's terminal means. For example, evaluation criteria such as "understanding environmental issues," "own opinions," and "action proposals" are set in advance. This data is sent to the server means via the interface.

[0040] Student terminal means

[0041] Students use the student terminal means to input assignments and comments during class. For example, if student A inputs, "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle," this data is transmitted from the student terminal means to the server means.

[0042] Server Means

[0043] The server means receives data transmitted from the teacher terminal means and the student terminal means, and stores the received data in a database.

[0044] Evaluation methods

[0045] The server incorporates an evaluation system that uses natural language processing to analyze students' responses based on lesson objectives and evaluation criteria, and evaluates their level of achievement. Specifically, the system extracts from the responses parts that correspond to "understanding environmental issues," "personal opinions," and "action proposals," and assigns a score to each part.

[0046] Feedback Methods

[0047] The evaluation results generated by the evaluation means are sent back to the teacher terminal means and the student terminal means via the feedback means. For example, the evaluation results for Student A's answer are displayed on the teacher terminal means and the student terminal means. This feedback information is useful for the teacher when giving the next instruction.

[0048] Accumulation and learning means

[0049] Furthermore, the storage and learning means in the server means stores the evaluation data over the long term and updates the evaluation model, thereby continuously improving the system's evaluation accuracy.

[0050] Specific examples

[0051] As a concrete example, consider the case where a teacher is giving a "lesson on environmental issues." The teacher inputs the lesson's objectives and evaluation criteria (e.g., understanding of environmental issues, personal opinions, action proposals) into the teacher's terminal means. During the lesson, students input their answers to assignments into the student's terminal means, and this data is sent to the server means. The server analyzes the response data and scores the level of achievement for each item based on the evaluation criteria. The evaluation results are fed back to the teacher and students, and the evaluation data is accumulated over the long term and used to train the evaluation model. This makes qualitative evaluation possible, allowing the thinking ability and independent learning of students to be accurately grasped.

[0052] In this way, the present invention provides an effective means for assessing thinking ability and independent learning, and is a solution to overcome the limitations of traditional assessment methods that rely on test scores.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] The user (teacher) inputs the lesson goals and evaluation criteria into the teacher's terminal. For example, the user sets evaluation items such as "understanding environmental issues," "personal opinions," and "action proposals."

[0056] Step 2:

[0057] The terminal transmits the input lesson objectives and evaluation criteria to the server means, and the teacher terminal means converts the data into packets via the interface and transfers them to the server via the network.

[0058] Step 3:

[0059] The server receives the lesson objectives and evaluation criteria data and stores them in a database. The database management system within the server ensures data integrity while storing the data.

[0060] Step 4:

[0061] Students use student terminals to input answers to assignments during class. For example, they input sentences such as, "I think we need to learn more about environmental issues. For example, I think we should recycle more."

[0062] Step 5:

[0063] The terminal sends the students' answer data to the server means. The input text data is formatted, organized into packets, and sent to the server via the Internet.

[0064] Step 6:

[0065] The server stores the received student response data in a database, ready to be analyzed by the evaluation means.

[0066] Step 7:

[0067] The server's evaluation tool analyzes students' response data using a natural language processing engine, extracting and categorizing keywords and phrases from the text based on the evaluation criteria.

[0068] Step 8:

[0069] The assessment tool calculates a score for each item according to the lesson objectives and assessment criteria. For example, 10 points are assigned to "understanding environmental issues," 8 points to "your own opinion," and 9 points to "suggestions for action."

[0070] Step 9:

[0071] The server compiles the evaluation results and generates feedback data for each student in JSON format.

[0072] Step 10:

[0073] The server transmits feedback data to the teacher terminal means and the student terminal means, and the transmitted data is displayed on the interface of each terminal.

[0074] Step 11:

[0075] The device displays the evaluation results. The user (teacher) can check the evaluation results and use them to plan the next lesson. Students can also check their own evaluations and reflect on their learning.

[0076] Step 12:

[0077] The server stores the evaluation data in the storage and learning means. By accumulating data over the long term, the accuracy of the evaluation model will be improved in the future.

[0078] Step 13:

[0079] The server's storage and learning means trains the evaluation model. Using the accumulated data, machine learning algorithms are applied to improve evaluation accuracy.

[0080] Example 1

[0081] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0082] In the traditional education system, there was a lack of qualitative methods for evaluating students' thinking ability and independent learning. As a result, teachers had no choice but to rely on test scores, making it difficult to accurately evaluate each student's growth and depth of learning. Furthermore, there was a lack of effective methods for providing feedback on the results of evaluations and using them to improve future instruction.

[0083] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0084] In this invention, the server includes teacher terminal means for inputting lesson goals and evaluation criteria, student terminal means for students to input their answers, server means for receiving data from the teacher terminal means and the student terminal means and storing it in a database, evaluation means for performing natural language processing on the server means based on the lesson goals and evaluation criteria inputted and evaluating the level of achievement, feedback means for feeding back the evaluation results to the teacher terminal means and the student terminal means, storage and learning means for accumulating evaluation data over the long term and learning an evaluation model, technical means for analyzing students' answers using natural language processing and assigning scores to specific evaluation criteria, and display means for displaying the generated evaluation results on the teacher terminal and the student terminal. This makes it possible to qualitatively evaluate students' thinking abilities and independent learning, allowing teachers to provide more effective instruction based on the evaluation results.

[0085] "Teacher terminal means" refers to a device used by a teacher to input lesson objectives and evaluation criteria.

[0086] "Student terminal means" refers to a device used by students during class to input answers to assignments and comments.

[0087] The term "server means" refers to a computer system used to receive data sent from the teacher terminal means and the student terminal means, and to store and process the data.

[0088] "Database" refers to a system located within the server means for storing received data in a structured format.

[0089] "Natural language processing" refers to the technology that enables computers to understand, analyze, and process human language.

[0090] "Evaluation means" refers to a function for analyzing students' responses using natural language processing based on lesson goals and evaluation criteria input into the server means, and evaluating their level of achievement.

[0091] The "feedback means" refers to a function for returning the evaluation results generated by the evaluation means to the teacher terminal means and the student terminal means.

[0092] "Storage and learning means" refers to a system for storing evaluation data over the long term and for learning and updating generative AI models.

[0093] "Technical means" refers to the technical components used to analyze student responses using natural language processing and assign scores against specific assessment criteria.

[0094] "Display means" refers to a function for displaying the generated evaluation results on the teacher terminal and the student terminal.

[0095] The system of the present invention qualitatively evaluates students' thinking ability and independent learning based on goals and evaluation criteria set by educators during lessons. The system includes teacher terminal means, student terminal means, server means, evaluation means, feedback means, storage and learning means, technical means, and display means.

[0096] Teacher terminal means

[0097] The user (teacher) uses the teacher's terminal means to input the lesson's goals and evaluation criteria. Specifically, the teacher starts a dedicated application and inputs the goals and evaluation criteria (e.g., "Understanding environmental issues," "Own opinion," "Proposed action"). Once the input is complete, the teacher clicks the "Send" button to send the setting data to the server means.

[0098] Student terminal means

[0099] Students use student terminal means to input answers to assignments and comments during class. Students start a dedicated application, enter their answers to assignments in an input form, and submit. For example, Student A might enter, "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle." Once the input is complete, the data is sent to the server means.

[0100] Server Means

[0101] The server receives data sent from the teacher terminal means and student terminal means and stores it in a database. The server listens to the data and stores the received data in a structured format in the database. It also sends a data reception confirmation back to each terminal. The received data is analyzed using the evaluation means based on the lesson goals and evaluation criteria.

[0102] Evaluation methods

[0103] The evaluation tool on the server uses natural language processing (NLP) to analyze students' answers based on the evaluation criteria set by the teacher. Specific APIs such as Python's NLTK and SpaCy are used to extract the parts of the answers that correspond to "understanding environmental issues," "personal opinions," and "action proposals," and assign scores to each. For example, the following prompt is input into the generative AI model:

[0104] Example prompt:

[0105] "Analyze the student's response according to the assessment criteria of 'Understanding environmental issues,' 'Own opinions,' and 'Suggested actions,' and rate each one accordingly. For example, here is a response such as, 'I think we need to learn more about environmental issues. For example, I think we should try harder to recycle.'"

[0106] Feedback Methods

[0107] The evaluation results generated by the evaluation means are sent back to the teacher terminal means and the student terminal means via the feedback means. The evaluation results are displayed on each terminal, allowing teachers to use this information for their next instruction and students to check the evaluation of their own learning.

[0108] Accumulation and learning means

[0109] The server's storage and learning means stores the evaluation data over the long term and updates the evaluation model to operate and improve the generative AI model.The model is retrained based on the evaluation data, and the system's evaluation accuracy is continuously improved.

[0110] technical means

[0111] Natural language processing is used to analyze student responses and assign scores against specific assessment criteria, allowing for detailed analysis and accurate assessment of each criterion.

[0112] Display means

[0113] The system includes a display means for displaying the generated evaluation results on the teacher's terminal and the student's terminal. By displaying the evaluation results, the transparency of the evaluation content is increased, and the quality of learning for students can be improved.

[0114] In this way, the system of the present invention provides an effective means for accurately assessing students' thinking ability and independent learning in educational settings, thereby overcoming the limitations of traditional assessment methods that rely on test scores.

[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0116] Step 1:

[0117] The user (teacher) uses the teacher's terminal means to input the lesson's goals and evaluation criteria. Specific inputs include evaluation criteria such as "understanding environmental issues," "personal opinions," and "action proposals." The terminal sends this setting data to the server means.

[0118] Input: Course objectives and assessment criteria

[0119] Output: Sending configuration data to the server

[0120] Specific behavior:

[0121] 1. The teacher launches the dedicated application.

[0122] 2. Enter your goals and evaluation criteria into the application form.

[0123] 3. Once you have completed the input, click the "Submit" button to send the setting data to the server.

[0124] Step 2:

[0125] Students use the student terminal means to input assignments and comments during class. For example, Student A inputs, "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle." The terminal sends this data to the server means.

[0126] Input: Answers to assignments and comments

[0127] Output: Sending response data to the server

[0128] Specific behavior:

[0129] 1. The student launches the dedicated application.

[0130] 2. Enter your answers to the assignment in the application form.

[0131] 3. Once you have completed entering the information, click the "Submit" button to send the response data to the server.

[0132] Step 3:

[0133] The server receives the data transmitted from the teacher terminal means and the student terminal means and stores it in a database, whereby lesson objectives, assessment criteria data, and answer data are stored in a structured format.

[0134] Input: Data sent from the teacher's device and student's device

[0135] Output: Data stored in the database

[0136] Specific behavior:

[0137] 1. The server listens to data sent from teacher and student devices.

[0138] 2. Receive the data and store it in a structured format in a database.

[0139] 3. A confirmation of data receipt is sent back to each terminal.

[0140] Step 4:

[0141] The server's internal evaluation tool uses natural language processing (NLP) to analyze students' responses based on the evaluation criteria set by the teacher. Using APIs such as Python's NLTK and SpaCy, it extracts parts of the responses that correspond to "understanding environmental issues," "personal opinions," and "action suggestions," and assigns a score to each criterion.

[0142] Input: Lesson objectives, assessment criteria, and response data stored in a database

[0143] Output: Scores corresponding to each criterion

[0144] Specific behavior:

[0145] 1. The server retrieves the criteria and response data.

[0146] 2. Perform text analysis using natural language processing tools (NLTK or SpaCy).

[0147] 3. Automatically identify the parts that fall under each evaluation criterion and calculate the corresponding score.

[0148] Step 5:

[0149] The evaluation results generated by the evaluation means are sent back to the teacher terminal means and the student terminal means via the feedback means. The evaluation results are displayed on each terminal, and can be viewed by the users.

[0150] Input: Evaluation results obtained by analysis

[0151] Output: Sending and displaying the evaluation results to the teacher and student devices

[0152] Specific behavior:

[0153] 1. The server generates the evaluation result.

[0154] 2. Send the evaluation results to the teacher and student devices.

[0155] 3. The evaluation results received by each device are displayed on the user interface.

[0156] Step 6:

[0157] The server's storage and learning means stores the evaluation data over the long term and retrains the evaluation model to operate and improve the generative AI model, thereby continuously improving the system's evaluation accuracy.

[0158] Input: Evaluation result data

[0159] Output: A trained evaluation model

[0160] Specific behavior:

[0161] 1. Accumulate evaluation data in a database.

[0162] 2. Retrain the generative AI model based on the evaluation data at regular intervals.

[0163] 3. The retrained model is applied to the system and used for subsequent evaluations.

[0164] (Application example 1)

[0165] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0166] Traditional teacher-student communication and assessment methods lack effective means for qualitatively evaluating students' thinking skills and independent learning. Furthermore, systems for monitoring the safety of elderly people and home security have difficulty immediately detecting abnormal behavior or dangerous situations and providing appropriate feedback. This creates many challenges for educational and home security.

[0167] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0168] In this invention, the server includes an educational terminal means for inputting lesson goals and evaluation criteria, a learning terminal means for students to input their answers, an information processing means for receiving data from the educational terminal means and the learning terminal means, an evaluation means for analyzing and processing the lesson goals and evaluation criteria input to the information processing means to evaluate the level of achievement, a feedback means for feeding back the evaluation results to the educational terminal means and the learning terminal means, a storage and learning means for storing evaluation data over the long term and learning an evaluation model, a sensor means for acquiring monitoring data, an anomaly detection means for detecting abnormal behavior based on the monitoring data, and a warning means for issuing a warning in response to abnormal behavior detected by the anomaly detection means. This makes it possible to accurately evaluate students' thinking abilities and independent learning, and to improve the safety of the elderly and homes.

[0169] "Educational terminal means" refers to a dedicated device or software that allows a teacher to input lesson objectives and evaluation criteria.

[0170] "Learning terminal means" refers to a device or software that allows students to input their answers and assignments.

[0171] The "information processing means" is a system for receiving, storing, and analyzing data from the education terminal means and the learning terminal means.

[0172] "Evaluation tools" are functions that use natural language processing to evaluate students' achievement levels based on the input lesson goals and evaluation criteria.

[0173] The "feedback means" is a system for returning the evaluation results generated by the evaluation means to the education terminal means and the learning terminal means.

[0174] The "accumulation and learning means" is a function that stores evaluation data over the long term and uses the accumulated data to improve the accuracy of the evaluation model.

[0175] "Sensor means" refers to a device for acquiring monitoring data, and may include, for example, a camera or various sensors.

[0176] The "abnormality detection means" is a system for analyzing and detecting abnormal behavior and dangerous situations based on data acquired from the sensor means.

[0177] The "warning means" is a function for issuing a warning to the user in response to abnormal behavior detected by the abnormality detection means.

[0178] MODE FOR CARRYING OUT THE INVENTION

[0179] The present invention is a system that includes an education terminal means, a learning terminal means, an information processing means, an evaluation means, a feedback means, a storage and learning means, a sensor means, an anomaly detection means, and a warning means. Specific embodiments of the system are described below.

[0180] Educational terminal means

[0181] This is a device or software that teachers use to input lesson goals and evaluation criteria. For example, teachers use a tablet or PC to input evaluation criteria such as "understanding environmental issues," "personal opinions," and "suggested actions." This data is sent to a server through an interface.

[0182] Learning terminal means

[0183] This is the device or software that students use to enter their answers and assignments during class. For example, a student might type into their tablet, "I think we need to learn more about environmental issues. For example, I think we should recycle more." This data is sent to a server.

[0184] Information Processing Means

[0185] This system receives, stores, and analyzes data from the education terminal means and learning terminal means. For example, the server stores the input data in a database and passes the data to an evaluation model or anomaly detection model as needed.

[0186] Evaluation methods

[0187] The system runs on a server and analyzes students' responses based on the lesson's goals and assessment criteria. Specifically, it uses natural language processing technology to analyze the responses and assigns scores to "understanding environmental issues," "personal opinions," and "action suggestions."

[0188] Feedback Methods

[0189] The server is used to feed back the evaluation results to the education terminal means and the learning terminal means. For example, the evaluation results for the students' answers are sent from the server to the teacher's tablet and the student's tablet. This allows the teacher to provide appropriate feedback.

[0190] Accumulation and learning means

[0191] This system stores evaluation data over the long term and improves the accuracy of the evaluation model based on the accumulated data. For example, the server periodically learns from the data and updates the evaluation model, enabling more accurate evaluations.

[0192] Sensor Means

[0193] A device that acquires monitoring data. For example, it monitors the situation inside and outside the home using IP cameras and various sensors.

[0194] Anomaly detection means

[0195] This system analyzes and detects abnormal behavior and dangerous situations based on data acquired from sensors. For example, it can detect abnormalities such as when an elderly person collapses or a suspicious person enters a building.

[0196] warning means

[0197] This function alerts users to any abnormal behavior detected by the anomaly detection method. For example, it can immediately notify users of the abnormality by sending a push notification to their smartphone.

[0198] Specific examples

[0199] Scenario 1: A teacher is teaching a lesson about environmental issues.

[0200] Device use: Teachers input lesson goals and assessment criteria into tablets.

[0201] Evaluation process: Students enter their answers into a tablet, and the server analyzes the answers using natural language processing and generates a score.

[0202] Feedback: Evaluation results are fed back to teachers and students to guide further instruction.

[0203] Scenario 2: Monitoring the safety of elderly people.

[0204] Device use: IP cameras and sensors installed inside and outside the home.

[0205] Anomaly detection process: The server analyzes video data to detect falls by elderly people or intrusions by suspicious individuals.

[0206] Warning: When an abnormality is detected, a push notification such as "Fall detected!" or "Intruder detected!" will be sent to your smartphone.

[0207] Prompt Sentence Examples

[0208] "Create an algorithm that detects whether an elderly person is sitting or slumped in their living room."

[0209] "Explain how to train a model to detect if there is an intruder outside your home."

[0210] Thus, the present invention provides a system that is useful for both education and security purposes.

[0211] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0212] Step 1:

[0213] The teacher inputs the lesson goals and evaluation criteria into the educational terminal means. The input data includes "understanding of environmental issues," "personal opinions," "action proposals," etc. This input data is sent to the server.

[0214] Step 2:

[0215] During class, students input their answers and assignments into the learning terminal means. For example, a student might input an answer such as, "I think we need to learn more about environmental issues. For example, I think we should recycle more." This data is also sent to the server.

[0216] Step 3:

[0217] The server receives input data from the education terminal means and the learning terminal means, and stores the data in a database using the information processing means. This stored data is the basis for analysis.

[0218] Step 4:

[0219] The server uses the evaluation tools based on the received data and performs natural language processing based on the lesson goals and evaluation criteria entered. Specifically, it uses a generative AI model to analyze the answers and assign scores to "understanding environmental issues," "personal opinions," and "suggested actions."

[0220] Step 5:

[0221] The analysis results are sent back to the education terminal means and the learning terminal means via the feedback means. For example, the server sends the scores generated by the evaluation means to the terminals of the teacher and students and displays them on the screen.

[0222] Step 6:

[0223] The server processes data over the long term using a storage and learning method, storing the evaluation data over the long term and using this data to train the evaluation model, thereby continuously improving the system's evaluation accuracy.

[0224] Step 7:

[0225] To obtain the monitoring data, the sensor means obtains data from various sensors and IP cameras inside and outside the home, for example, a camera captures video of the living room.

[0226] Step 8:

[0227] The server receives the data sent from the sensor means and uses the anomaly detection means to analyze and detect abnormal behavior or dangerous situations, such as when an elderly person collapses or a suspicious person enters the building.

[0228] Step 9:

[0229] If an abnormality is detected, the server will immediately send alert information to the user's smartphone or device using an alerting method, such as a push notification saying "Fall detected!" or "Intruder detected!"

[0230] By taking these steps, it is possible to build a system that simultaneously improves the accuracy of evaluations in educational settings and strengthens security within the home.

[0231] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0232] The system of the present invention utilizes an evaluation generation AI and an emotion engine to qualitatively evaluate students' thinking ability and independent learning based on goals and evaluation criteria set by teachers during lessons. This system includes teacher terminal means, student terminal means, server means, evaluation means, feedback means, an emotion engine, and storage and learning means. Specific embodiments of the system are described below.

[0233] Teacher terminal means

[0234] The user (teacher) inputs the lesson goals and evaluation criteria using the teacher's terminal means. For example, the user sets evaluation items such as "understanding environmental issues," "personal opinions," and "action proposals." This data is sent to the server means via the interface.

[0235] Student terminal means

[0236] Students use the student terminal means to input answers to assignments during class. For example, if student A inputs "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle," this data is transmitted from the student terminal means to the server means.

[0237] Server Means

[0238] The server means receives data transmitted from the teacher terminal means and the student terminal means, and stores the received data in a database.

[0239] Evaluation methods

[0240] The server incorporates an evaluation system that uses natural language processing to analyze students' responses based on lesson objectives and evaluation criteria, and evaluates their level of achievement. Specifically, the system extracts from the responses parts that correspond to "understanding environmental issues," "personal opinions," and "action proposals," and assigns a score to each part.

[0241] Emotion Engine

[0242] The emotion engine analyzes students' responses and their behavior when entering answers to recognize their emotions. For example, through text analysis, it can identify emotions such as joy, anger, sadness, and happiness contained in the responses. The emotion data recognized by the emotion engine is provided to the evaluation tool and reflected in the achievement evaluation.

[0243] Feedback Methods

[0244] The evaluation results and emotion data generated by the evaluation means and emotion engine are sent back to the teacher terminal means and student terminal means via the feedback means. For example, the evaluation results and emotion evaluations for Student A's answer are displayed on the teacher terminal means and student terminal means. This feedback information is useful for the teacher when providing the next instruction.

[0245] Accumulation and learning means

[0246] Furthermore, the storage and learning means in the server means stores the evaluation data and emotion data over the long term and updates the evaluation model, thereby continuously improving the system's evaluation accuracy.

[0247] Specific examples

[0248] As a concrete example, consider the case where a teacher is giving a "lesson on environmental issues." The teacher inputs the lesson's goals and evaluation criteria (e.g., understanding of environmental issues, personal opinions, action suggestions) into the teacher's terminal means. During the lesson, students input their answers to assignments into the student's terminal means, and the data is sent to the server means. The server analyzes the answer data and scores the level of achievement for each item based on the evaluation criteria. Furthermore, an emotion engine analyzes the answers, recognizes emotions, and provides the results to the evaluation means. The evaluation results and emotion data are fed back to the teacher and students, and the evaluation data and emotion data are accumulated over the long term and used to train the evaluation model. This makes qualitative evaluation possible, allowing the thinking ability and independent learning of students to be accurately captured.

[0249] In this way, the present invention provides an effective means for assessing students' emotional aspects in addition to their thinking ability and independent learning, thereby realizing a more comprehensive educational evaluation.

[0250] The processing flow will be explained below.

[0251] Step 1:

[0252] The user (teacher) inputs the lesson goals and evaluation criteria into the teacher's terminal. For example, the user sets evaluation items such as "understanding environmental issues," "personal opinions," and "action proposals."

[0253] Step 2:

[0254] The terminal transmits the input lesson objectives and evaluation criteria to the server means, and the teacher terminal means converts the data into packets via the interface and transfers them to the server via the network.

[0255] Step 3:

[0256] The server receives the lesson objectives and evaluation criteria data and stores them in a database. The database management system within the server ensures data integrity while storing the data.

[0257] Step 4:

[0258] Students use student terminals to input answers to assignments during class. For example, Student A inputs a sentence such as, "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle."

[0259] Step 5:

[0260] The terminal sends the students' answer data to the server means. The input text data is formatted, organized into packets, and sent to the server via the Internet.

[0261] Step 6:

[0262] The server stores the received student response data in a database, ready to be analyzed by the evaluation tool and emotion engine.

[0263] Step 7:

[0264] The server's emotion engine analyzes students' response data and recognizes emotions from the text content. For example, emotions such as joy, anger, sadness, and happiness are identified based on positive and negative expressions in the text.

[0265] Step 8:

[0266] The server's evaluation means incorporates the emotional data analyzed by the emotion engine into the evaluation, and also uses a natural language processing engine to analyze the response content based on the evaluation criteria. Specifically, it extracts and classifies the parts of the text that correspond to "understanding," "opinion," and "suggestion."

[0267] Step 9:

[0268] The assessment tool calculates a score for each item according to the lesson objectives and assessment criteria. For example, 10 points are assigned to "understanding environmental issues," 8 points to "personal opinions," and 9 points to "action suggestions," and these are adjusted based on emotional data.

[0269] Step 10:

[0270] The server compiles the evaluation results and emotion data and generates feedback data. The evaluation results are generated as JSON format data for each student.

[0271] Step 11:

[0272] The server transmits feedback data to the teacher terminal means and the student terminal means, and the transmitted data is displayed on the interface of each terminal.

[0273] Step 12:

[0274] The device displays the evaluation results and emotional data. The user (teacher) can check the evaluation results and emotional data and use them to plan the next lesson. Students can also check their own evaluations and reflect on their learning.

[0275] Step 13:

[0276] The server stores the evaluation data and emotion data in the storage and learning means. By accumulating data over the long term, the accuracy of the evaluation model will be improved in the future.

[0277] Step 14:

[0278] The server's storage and learning means trains the evaluation model. Using the accumulated data, machine learning algorithms are applied to improve evaluation accuracy.

[0279] Example 2

[0280] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0281] Conventional educational evaluation systems are limited to quantitative assessment of students' thinking ability and independent learning, making it difficult to comprehensively evaluate students' emotional aspects. Furthermore, there is insufficient long-term data accumulation and learning to continuously improve the accuracy of evaluation models. As a result, there is a lack of information that contributes to the reliability of evaluation results and the improvement of teachers' teaching strategies.

[0282] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0283] In this invention, the server includes a data receiving means, an evaluation means, an emotion analysis means, a feedback means, and an accumulation and learning means. This allows for analysis and evaluation of students' answers using natural language processing, and for identifying emotions to provide a comprehensive evaluation. Furthermore, by accumulating evaluation data and emotion data over the long term and continuously learning the evaluation model, the accuracy of the evaluation can be improved.

[0284] "Educator terminal means" means an electronic device used by an educator to input lesson objectives and assessment criteria.

[0285] "Student terminal means" refers to an electronic device used by a student to input answers to assignments during class.

[0286] The "data receiving means" is a device having the function of receiving data transmitted from the teacher terminal means and the student terminal means.

[0287] The "server means" is a central processing unit that includes a data receiving means and has the function of analyzing and storing received data.

[0288] An "assessment tool" is a device or program that performs natural language processing based on the lesson's objectives and evaluation criteria and has the function of evaluating the learner's achievement.

[0289] "Emotion analysis means" refers to a device or program that has the function of analyzing the content of a learner's answers and their behavior when entering answers, and identifying their emotions.

[0290] The "feedback means" is a device or program that has the function of returning the evaluation results and emotion data to the educator terminal means and the learner terminal means.

[0291] "Storage and learning means" refers to a device or program that has the function of storing evaluation data and emotion data over the long term and continuously learning the evaluation model.

[0292] The system of the present invention includes educator terminal means, learner terminal means, server means, evaluation means, emotion analysis means, feedback means, and accumulation and learning means. This system utilizes generative AI and natural language processing technology to evaluate learners' thinking ability and independent learning, and analyze their emotions.

[0293] System configuration

[0294] Educator terminal means

[0295] The user (educator) uses an educator's terminal to input lesson goals and evaluation criteria. This terminal is a personal computer or tablet equipped with a standard web browser, and the user inputs the goals and evaluation criteria through a dedicated interface. For example, the user inputs data such as: "Understanding environmental issues," "Own opinion," and "Proposed actions." The input data is sent to the server via an HTTP request.

[0296] Learner terminal means

[0297] Learners use learner terminals to input answers to assignments during class. These terminals are also personal computers or tablets equipped with a web browser. For example, if Learner A inputs, "I think we need to learn more about environmental issues. For example, I think we should recycle more," this data is sent to the server.

[0298] Server Means

[0299] The server means receives the data transmitted from the teacher terminal and the student terminal and stores it in a database. This server uses database software such as MySQL (registered trademark) or PostgreSQL. Based on the received and stored data, the server performs data analysis using the evaluation means.

[0300] Evaluation methods

[0301] The evaluation method within the server analyzes the data using a generative AI model and a natural language processing library (e.g., NLTK or spaCy). Specifically, it extracts the parts of the response that correspond to "understanding environmental issues," "personal opinions," and "action proposals," and assigns a score to each. For example, it assigns a score to each evaluation item for Learner A's response and evaluates the level of achievement.

[0302] Emotion analysis means

[0303] The server uses a sentiment analysis tool to analyze the learner's responses and input behavior to identify emotions. This analysis utilizes text analysis tools (e.g., Affectiva and IBM Watson (registered trademark) Natural Language Understanding). For example, from the phrase "I need to learn more," the server can identify emotions such as "motivation" and "responsibility."

[0304] Feedback Methods

[0305] The results generated by the evaluation means and emotion analysis means are sent back to the teacher's terminal and the student's terminal via the feedback means. For example, the evaluation result for Student A's answer is scored and displayed on the screen. The identified emotion is also displayed.

[0306] Accumulation and learning means

[0307] Evaluation data and emotion data are stored over the long term using a storage and learning method. Based on the stored data, a machine learning algorithm continuously trains the evaluation model. This process is performed periodically as a batch process, contributing to improving the performance of the entire system.

[0308] Specific examples

[0309] For example, if a teacher is giving a lesson on environmental issues, he or she would follow these steps:

[0310] 1. The educator uses the educator terminal to enter the evaluation criteria.

[0311] Examples: "Understanding environmental issues," "Your own opinion," "Proposals for action."

[0312] 2. During class, students enter their answers to the assignments through their student devices.

[0313] Example: Learner A types, "I think I need to learn more about environmental issues. For example, I think we should recycle more."

[0314] 3. The server receives the data and stores it in a database.

[0315] 4. The evaluation instrument analyzes the data and assigns a score to each evaluation item.

[0316] 5. A sentiment analyzer analyzes the responses and identifies the sentiment.

[0317] For example, identify "motivation" and "responsibility."

[0318] 6. The results of the evaluation and sentiment analysis measures are fed back to the teacher's terminal and the student's terminal.

[0319] Prompt Sentence Examples

[0320] Here's an example prompt to input to the generative AI model:

[0321] Example prompt 1: "Analyze Student A's answer, 'I think we need to learn more about environmental issues. For example, I think we should recycle more.'" and evaluate it in terms of 'Understanding of environmental issues,' 'Own opinion,' and 'Suggested actions.'

[0322] Example prompt 2: "Identify the emotion in this passage and rate it as 'happy,' 'anger,' 'sad,' or 'surprise.'"

[0323] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0324] Step 1:

[0325] The user (educator) uses an educator terminal to input lesson goals and evaluation criteria.

[0326] Specific actions: Evaluation items such as "understanding of environmental issues," "own opinion," and "suggested actions" are entered into a dedicated interface displayed in the web browser on the educator's device.

[0327] Input: Course objectives and assessment criteria

[0328] Output: Assessment item data sent to the server

[0329] Step 2:

[0330] The server receives the evaluation item data sent from the teacher's terminal and stores it in a database.

[0331] Specific operation: The server receives the data sent through the HTTP request and uses database software (e.g., MySQL, PostgreSQL) to issue an INSERT statement to the database to store the data.

[0332] Input: Evaluation item data

[0333] Output: Evaluation item data stored in a database

[0334] Step 3:

[0335] The learner uses the learner's terminal to input answers to the assignment.

[0336] Specific actions: Learner A enters "I think we need to learn more about environmental issues. For example, I think we should recycle more" into the input form on the learner's device and clicks the send button.

[0337] Input: Learner's response data

[0338] Output: Learner's response data sent to the server

[0339] Step 4:

[0340] The server receives the response data sent from the learner's terminal and stores it in a database.

[0341] Specific operation: The server receives the data sent through the HTTP request, issues an INSERT statement to the database, and saves it. At the same time, it logs that the receiving process has been completed.

[0342] Input: Learner's response data

[0343] Output: Learner response data stored in a database

[0344] Step 5:

[0345] The server uses the evaluation means to analyze and evaluate the stored data.

[0346] Specific operation: The server analyzes the saved response data using generative AI models and natural language processing libraries (NLTK, spaCy, etc.). It generates prompt sentences and assigns scores to each evaluation item. Example: "Student A's response, 'I think we need to learn more about environmental issues. For example, I think we should recycle more,' is analyzed and evaluated in terms of 'Understanding environmental issues,' 'Own opinion,' and 'Suggested actions.'"

[0347] Input: Learner's response data

[0348] Output: Evaluation result score data

[0349] Step 6:

[0350] The server uses emotion analysis means to analyze the content of the learner's answers and identify their emotions.

[0351] Specific behavior: Use text analysis tools (such as Affectiva or IBM Watson Natural Language Understanding) to identify emotions such as joy, anger, sadness, and happiness contained in the response data using emotion analysis methods. Example: "Identify the emotion contained in this sentence and rate it as 'joy,' 'anger,' 'sadness,' or 'surprise.'"

[0352] Input: Learner's response data

[0353] Output: Sentiment analysis result data

[0354] Step 7:

[0355] The server feeds back the evaluation results and emotion data to the teacher's terminal and the student's terminal.

[0356] Specific operation: Evaluation results and sentiment analysis results are sent in real time using feedback tools and displayed on the screens of the teacher's and learner's devices. Real-time notifications are sent using WebSocket.

[0357] Input: Evaluation results and sentiment analysis results

[0358] Output: Feedback information displayed on teacher and student devices

[0359] Step 8:

[0360] The server stores the rating data and emotion data for a long period of time and updates the rating model.

[0361] Specific operation: Using the accumulation and learning method, the evaluation data and emotion data are stored in a database, and the evaluation model is updated periodically by applying a machine learning algorithm. This is executed periodically as a batch process using a scheduler.

[0362] Input: Evaluation results and sentiment analysis results

[0363] Output: Updated valuation model

[0364] This allows the system to comprehensively evaluate students' thinking abilities and independent learning, and supports teachers' teaching strategies.

[0365] (Application example 2)

[0366] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0367] Traditional education systems lack effective means for qualitatively evaluating students' thinking skills and independent learning. Furthermore, in the field of customer service, there are few systems for real-time emotion recognition and providing appropriate feedback, making it difficult to improve customer satisfaction. These issues are barriers to comprehensive evaluation and improvement of satisfaction in education and customer service.

[0368] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a teacher terminal means for inputting lesson goals and evaluation criteria; a student terminal means for inputting answers by students; a server means for receiving data from the teacher terminal means and the student terminal means; an evaluation means for performing natural language processing based on the lesson goals and evaluation criteria input to the server means and evaluating the level of achievement; a feedback means for feeding back the evaluation results to the teacher terminal means and the student terminal means; a storage and learning means for accumulating evaluation data over the long term and learning an evaluation model; an evaluation means for analyzing customer input text in real time and identifying customer emotions; and a feedback means for providing appropriate feedback based on the identified emotions. This makes it possible to qualitatively evaluate students' thinking abilities and independent learning while recognizing customer emotions in real time and providing appropriate feedback.

[0369] The "teacher terminal means" is a device for inputting lesson goals and evaluation criteria.

[0370] "Student terminal means" refers to a device that allows students to input answers to assignments during class.

[0371] The "server means" is a central system that receives and processes data sent from the teacher terminal means and the student terminal means.

[0372] The "evaluation means" is a device that has the function of performing natural language processing based on the lesson goals and evaluation criteria input in the server means, and evaluating the degree of achievement.

[0373] The "feedback means" is a mechanism for returning the evaluation results to the teacher terminal means and the student terminal means.

[0374] The "accumulation and learning means" is a mechanism for storing evaluation data over the long term and updating the evaluation model.

[0375] "Customer input text" is text data provided by a customer when using a service.

[0376] "Real-time analysis" is the process of processing data as soon as it is entered.

[0377] The "emotion identification evaluation means" is a device that has the function of recognizing and evaluating emotions from input text.

[0378] "Appropriate feedback" refers to advice and information returned to the user based on the evaluation results and emotional data.

[0379] The present invention is a system that can be effectively used in educational settings and virtual stores. Specific embodiments will be described below.

[0380] 1. System configuration:

[0381] This system includes a teacher terminal means, a student terminal means, a server means, an evaluation means, a feedback means, a storage and learning means, and an evaluation means for emotion recognition. The detailed configuration of each element is as follows:

[0382] 2. Teacher terminal means:

[0383] The teacher terminal means is a device that allows teachers to input lesson goals and evaluation criteria. Specifically, the teacher uses a tablet or PC to input goals and criteria through an interface.

[0384] 3. Student Devices:

[0385] The student terminal means is a device that students use to input answers during class. Students use tablets or PCs to input answers to assignments.

[0386] 4. Server means:

[0387] The server means is a central system that receives data sent from the teacher terminal means and the student terminal means, and performs natural language processing based on the input lesson goals and evaluation criteria.

[0388] 5. Evaluation method:

[0389] The evaluation means is a device that has the function of analyzing the answers of students in the server means and evaluating their achievement. Specifically, it uses a natural language processing model to extract parts of the answers that correspond to the evaluation items and assign a score to each item.

[0390] 6. Feedback methods:

[0391] The feedback means is a mechanism for returning the evaluation results to the teacher terminal means and the student terminal means, allowing students to check their own evaluation results and use them as a guide for their next learning.

[0392] 7. Storage and learning methods:

[0393] The accumulation and learning method is a mechanism for storing evaluation data over the long term and updating the evaluation model, which allows the accuracy of the evaluation model to be continuously improved.

[0394] 8. Customer Emotion Recognition:

[0395] When dealing with customers in a virtual store, the system analyzes the text entered by the customer in real time and has an evaluation method to identify emotions. Specifically, it uses smart glasses to capture the customer's text input, then recognizes their emotions through an emotion engine and provides feedback.

[0396] Hardware and software used:

[0397] Hardware: smart glasses (e.g., Google® Glass®), servers (for data processing and storage)

[0398] Software: Transformer model library (Hugging Face), emotion engine

[0399] The server analyzes the input text data of the customer in real time and identifies the emotion using the evaluation means, after which appropriate feedback is provided through the feedback means.

[0400] Examples:

[0401] If a customer says in-store, "I think this product is great, but it's too expensive," the emotion engine will analyze this and conclude, "That's a positive sentiment, but there's also dissatisfaction with the price." Staff can then immediately recommend specific discounts to improve customer satisfaction.

[0402] Example prompt sentence:

[0403] "Customer utterances are fed into the following sentiment analysis model to determine real-time sentiment as feedback. Example: 'I love the new features, but the price is too high.'"

[0404] This allows the system to provide more comprehensive and effective evaluation and feedback in both training and customer interactions.

[0405] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0406] Step 1:

[0407] The teacher uses the teacher's terminal means to input lesson goals and evaluation criteria. The input data is sent from the teacher's terminal means to the server means. Specifically, the teacher inputs evaluation items and criteria (e.g., understanding of environmental issues, personal opinions, action proposals).

[0408] Input: Text data of evaluation items and criteria

[0409] Output: Data sent from the teacher's computer to the server

[0410] Step 2:

[0411] Students use the student terminal means to input answers to assignments during class, and the answer data is transmitted from the student terminal means to the server means.

[0412] Input: Text data of student responses

[0413] Output: Data sent from student devices to the server

[0414] Step 3:

[0415] The server means stores the data received from the teacher terminal means and the student terminal means, and stores lesson goals, evaluation criteria, and student response data in a database.

[0416] Input: Data submitted by teachers and students

[0417] Output: Data stored in the database

[0418] Step 4:

[0419] The server uses the evaluation means to perform natural language processing based on the input data and evaluates the level of achievement based on the lesson goals and evaluation criteria. Specifically, it extracts parts of the answer sentence that correspond to the evaluation items and assigns a score to each.

[0420] Input: lesson goals and evaluation criteria, student response data

[0421] Output: Scored evaluation data

[0422] Step 5:

[0423] The server uses an emotion engine to analyze the content of students' responses and recognize their emotions. It identifies emotions such as joy, anger, sadness, and happiness from the text data and generates emotion data.

[0424] Input: Text data of student responses

[0425] Output: Emotion data

[0426] Step 6:

[0427] The server sends the evaluation results and emotion data back to the teacher terminal means and the student terminal means via the feedback means, and the teacher and students can check the evaluation results and emotion evaluations on their terminals.

[0428] Input: scored evaluation data, sentiment data

[0429] Output: Feedback information to teacher and student devices

[0430] Step 7:

[0431] The server uses an accumulation and learning method to store evaluation data and emotion data over the long term and update the evaluation model.

[0432] Input: Rating data and emotion data

[0433] Output: Updated valuation model

[0434] Step 8:

[0435] Smart glasses are used to capture customer input text, which is then sent to the server in real time.

[0436] Input: Customer text data

[0437] Output: Customer data sent to server

[0438] Step 9:

[0439] The server analyzes the customer's input text in real time and identifies emotions using evaluation means. Emotions are recognized through an emotion engine.

[0440] Input: Customer text data

[0441] Output: Identified emotion data

[0442] Step 10:

[0443] The server uses a feedback means to provide appropriate feedback based on the identified emotion, and presents information to customer care staff.

[0444] Input: Identified emotion data

[0445] Output: Feedback information for customer service staff

[0446] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0447] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0448] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0449] [Second embodiment]

[0450] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0451] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0452] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0453] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0454] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0455] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0456] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0457] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0458] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0459] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0460] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0461] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0462] The system of the present invention uses an evaluation generation AI to qualitatively evaluate students' thinking ability and independent learning based on goals and evaluation criteria set by teachers during lessons. This system includes teacher terminal means, student terminal means, server means, and evaluation means. Specific embodiments of the system are described below.

[0463] Teacher terminal means

[0464] The user (teacher) inputs the lesson goals and evaluation criteria using the teacher's terminal means. For example, evaluation criteria such as "understanding environmental issues," "own opinions," and "action proposals" are set in advance. This data is sent to the server means via the interface.

[0465] Student terminal means

[0466] Students use the student terminal means to input assignments and comments during class. For example, if student A inputs, "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle," this data is transmitted from the student terminal means to the server means.

[0467] Server Means

[0468] The server means receives data transmitted from the teacher terminal means and the student terminal means, and stores the received data in a database.

[0469] Evaluation methods

[0470] The server incorporates an evaluation system that uses natural language processing to analyze students' responses based on lesson objectives and evaluation criteria, and evaluates their level of achievement. Specifically, the system extracts from the responses parts that correspond to "understanding environmental issues," "personal opinions," and "action proposals," and assigns a score to each part.

[0471] Feedback Methods

[0472] The evaluation results generated by the evaluation means are sent back to the teacher terminal means and the student terminal means via the feedback means. For example, the evaluation results for Student A's answer are displayed on the teacher terminal means and the student terminal means. This feedback information is useful for the teacher when giving the next instruction.

[0473] Accumulation and learning means

[0474] Furthermore, the storage and learning means in the server means stores the evaluation data over the long term and updates the evaluation model, thereby continuously improving the system's evaluation accuracy.

[0475] Specific examples

[0476] As a concrete example, consider the case where a teacher is giving a "lesson on environmental issues." The teacher inputs the lesson's objectives and evaluation criteria (e.g., understanding of environmental issues, personal opinions, action proposals) into the teacher's terminal means. During the lesson, students input their answers to assignments into the student's terminal means, and this data is sent to the server means. The server analyzes the response data and scores the level of achievement for each item based on the evaluation criteria. The evaluation results are fed back to the teacher and students, and the evaluation data is accumulated over the long term and used to train the evaluation model. This makes qualitative evaluation possible, allowing the thinking ability and independent learning of students to be accurately grasped.

[0477] In this way, the present invention provides an effective means for assessing thinking ability and independent learning, and is a solution to overcome the limitations of traditional assessment methods that rely on test scores.

[0478] The processing flow will be explained below.

[0479] Step 1:

[0480] The user (teacher) inputs the lesson goals and evaluation criteria into the teacher's terminal. For example, the user sets evaluation items such as "understanding environmental issues," "personal opinions," and "action proposals."

[0481] Step 2:

[0482] The terminal transmits the input lesson objectives and evaluation criteria to the server means, and the teacher terminal means converts the data into packets via the interface and transfers them to the server via the network.

[0483] Step 3:

[0484] The server receives the lesson objectives and evaluation criteria data and stores them in a database. The database management system within the server ensures data integrity while storing the data.

[0485] Step 4:

[0486] Students use student terminals to input answers to assignments during class. For example, they input sentences such as, "I think we need to learn more about environmental issues. For example, I think we should recycle more."

[0487] Step 5:

[0488] The terminal sends the students' answer data to the server means. The input text data is formatted, organized into packets, and sent to the server via the Internet.

[0489] Step 6:

[0490] The server stores the received student response data in a database, ready to be analyzed by the evaluation means.

[0491] Step 7:

[0492] The server's evaluation tool analyzes students' response data using a natural language processing engine, extracting and categorizing keywords and phrases from the text based on the evaluation criteria.

[0493] Step 8:

[0494] The assessment tool calculates a score for each item according to the lesson objectives and assessment criteria. For example, 10 points are assigned to "understanding environmental issues," 8 points to "your own opinion," and 9 points to "suggestions for action."

[0495] Step 9:

[0496] The server compiles the evaluation results and generates feedback data for each student in JSON format.

[0497] Step 10:

[0498] The server transmits feedback data to the teacher terminal means and the student terminal means, and the transmitted data is displayed on the interface of each terminal.

[0499] Step 11:

[0500] The device displays the evaluation results. The user (teacher) can check the evaluation results and use them to plan the next lesson. Students can also check their own evaluations and reflect on their learning.

[0501] Step 12:

[0502] The server stores the evaluation data in the storage and learning means. By accumulating data over the long term, the accuracy of the evaluation model will be improved in the future.

[0503] Step 13:

[0504] The server's storage and learning means trains the evaluation model. Using the accumulated data, machine learning algorithms are applied to improve evaluation accuracy.

[0505] Example 1

[0506] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0507] In the traditional education system, there was a lack of qualitative methods for evaluating students' thinking ability and independent learning. As a result, teachers had no choice but to rely on test scores, making it difficult to accurately evaluate each student's growth and depth of learning. Furthermore, there was a lack of effective methods for providing feedback on the results of evaluations and using them to improve future instruction.

[0508] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0509] In this invention, the server includes teacher terminal means for inputting lesson goals and evaluation criteria, student terminal means for students to input their answers, server means for receiving data from the teacher terminal means and the student terminal means and storing it in a database, evaluation means for performing natural language processing on the server means based on the lesson goals and evaluation criteria inputted and evaluating the level of achievement, feedback means for feeding back the evaluation results to the teacher terminal means and the student terminal means, storage and learning means for accumulating evaluation data over the long term and learning an evaluation model, technical means for analyzing students' answers using natural language processing and assigning scores to specific evaluation criteria, and display means for displaying the generated evaluation results on the teacher terminal and the student terminal. This makes it possible to qualitatively evaluate students' thinking abilities and independent learning, allowing teachers to provide more effective instruction based on the evaluation results.

[0510] "Teacher terminal means" refers to a device used by a teacher to input lesson objectives and evaluation criteria.

[0511] "Student terminal means" refers to a device used by students during class to input answers to assignments and comments.

[0512] The term "server means" refers to a computer system used to receive data sent from the teacher terminal means and the student terminal means, and to store and process the data.

[0513] "Database" refers to a system located within the server means for storing received data in a structured format.

[0514] "Natural language processing" refers to the technology that enables computers to understand, analyze, and process human language.

[0515] "Evaluation means" refers to a function for analyzing students' responses using natural language processing based on lesson goals and evaluation criteria input into the server means, and evaluating their level of achievement.

[0516] The "feedback means" refers to a function for returning the evaluation results generated by the evaluation means to the teacher terminal means and the student terminal means.

[0517] "Storage and learning means" refers to a system for storing evaluation data over the long term and for learning and updating generative AI models.

[0518] "Technical means" refers to the technical components used to analyze student responses using natural language processing and assign scores against specific assessment criteria.

[0519] "Display means" refers to a function for displaying the generated evaluation results on the teacher terminal and the student terminal.

[0520] The system of the present invention qualitatively evaluates students' thinking ability and independent learning based on goals and evaluation criteria set by educators during lessons. The system includes teacher terminal means, student terminal means, server means, evaluation means, feedback means, storage and learning means, technical means, and display means.

[0521] Teacher terminal means

[0522] The user (teacher) uses the teacher's terminal means to input the lesson's goals and evaluation criteria. Specifically, the teacher starts a dedicated application and inputs the goals and evaluation criteria (e.g., "Understanding environmental issues," "Own opinion," "Proposed action"). Once the input is complete, the teacher clicks the "Send" button to send the setting data to the server means.

[0523] Student terminal means

[0524] Students use student terminal means to input answers to assignments and comments during class. Students start a dedicated application, enter their answers to assignments in an input form, and submit. For example, Student A might enter, "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle." Once the input is complete, the data is sent to the server means.

[0525] Server Means

[0526] The server receives data sent from the teacher terminal means and student terminal means and stores it in a database. The server listens to the data and stores the received data in a structured format in the database. It also sends a data reception confirmation back to each terminal. The received data is analyzed using the evaluation means based on the lesson goals and evaluation criteria.

[0527] Evaluation methods

[0528] The evaluation tool on the server uses natural language processing (NLP) to analyze students' answers based on the evaluation criteria set by the teacher. Specific APIs such as Python's NLTK and SpaCy are used to extract the parts of the answers that correspond to "understanding environmental issues," "personal opinions," and "action proposals," and assign scores to each. For example, the following prompt is input into the generative AI model:

[0529] Example prompt:

[0530] "Analyze the student's response according to the assessment criteria of 'Understanding environmental issues,' 'Own opinions,' and 'Suggested actions,' and rate each one accordingly. For example, here is a response such as, 'I think we need to learn more about environmental issues. For example, I think we should try harder to recycle.'"

[0531] Feedback Methods

[0532] The evaluation results generated by the evaluation means are sent back to the teacher terminal means and the student terminal means via the feedback means. The evaluation results are displayed on each terminal, allowing teachers to use this information for their next instruction and students to check the evaluation of their own learning.

[0533] Accumulation and learning means

[0534] The server's storage and learning means stores the evaluation data over the long term and updates the evaluation model to operate and improve the generative AI model.The model is retrained based on the evaluation data, and the system's evaluation accuracy is continuously improved.

[0535] technical means

[0536] Natural language processing is used to analyze student responses and assign scores against specific assessment criteria, allowing for detailed analysis and accurate assessment of each criterion.

[0537] Display means

[0538] The system includes a display means for displaying the generated evaluation results on the teacher's terminal and the student's terminal. By displaying the evaluation results, the transparency of the evaluation content is increased, and the quality of learning for students can be improved.

[0539] In this way, the system of the present invention provides an effective means for accurately assessing students' thinking ability and independent learning in educational settings, thereby overcoming the limitations of traditional assessment methods that rely on test scores.

[0540] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0541] Step 1:

[0542] The user (teacher) uses the teacher's terminal means to input the lesson's goals and evaluation criteria. Specific inputs include evaluation criteria such as "understanding environmental issues," "personal opinions," and "action proposals." The terminal sends this setting data to the server means.

[0543] Input: Course objectives and assessment criteria

[0544] Output: Sending configuration data to the server

[0545] Specific behavior:

[0546] 1. The teacher launches the dedicated application.

[0547] 2. Enter your goals and evaluation criteria into the application form.

[0548] 3. Once you have completed the input, click the "Submit" button to send the setting data to the server.

[0549] Step 2:

[0550] Students use the student terminal means to input assignments and comments during class. For example, Student A inputs, "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle." The terminal sends this data to the server means.

[0551] Input: Answers to assignments and comments

[0552] Output: Sending response data to the server

[0553] Specific behavior:

[0554] 1. The student launches the dedicated application.

[0555] 2. Enter your answers to the assignment in the application form.

[0556] 3. Once you have completed entering the information, click the "Submit" button to send the response data to the server.

[0557] Step 3:

[0558] The server receives the data transmitted from the teacher terminal means and the student terminal means and stores it in a database, whereby lesson objectives, assessment criteria data, and answer data are stored in a structured format.

[0559] Input: Data sent from the teacher's device and student's device

[0560] Output: Data stored in the database

[0561] Specific behavior:

[0562] 1. The server listens to data sent from teacher and student devices.

[0563] 2. Receive the data and store it in a structured format in a database.

[0564] 3. A confirmation of data receipt is sent back to each terminal.

[0565] Step 4:

[0566] The server's internal evaluation tool uses natural language processing (NLP) to analyze students' responses based on the evaluation criteria set by the teacher. Using APIs such as Python's NLTK and SpaCy, it extracts parts of the responses that correspond to "understanding environmental issues," "personal opinions," and "action suggestions," and assigns a score to each criterion.

[0567] Input: Lesson objectives, assessment criteria, and response data stored in a database

[0568] Output: Scores corresponding to each criterion

[0569] Specific behavior:

[0570] 1. The server retrieves the criteria and response data.

[0571] 2. Perform text analysis using natural language processing tools (NLTK or SpaCy).

[0572] 3. Automatically identify the parts that fall under each evaluation criterion and calculate the corresponding score.

[0573] Step 5:

[0574] The evaluation results generated by the evaluation means are sent back to the teacher terminal means and the student terminal means via the feedback means. The evaluation results are displayed on each terminal, and can be viewed by the users.

[0575] Input: Evaluation results obtained by analysis

[0576] Output: Sending and displaying the evaluation results to the teacher and student devices

[0577] Specific behavior:

[0578] 1. The server generates the evaluation result.

[0579] 2. Send the evaluation results to the teacher and student devices.

[0580] 3. The evaluation results received by each device are displayed on the user interface.

[0581] Step 6:

[0582] The server's storage and learning means stores the evaluation data over the long term and retrains the evaluation model to operate and improve the generative AI model, thereby continuously improving the system's evaluation accuracy.

[0583] Input: Evaluation result data

[0584] Output: A trained evaluation model

[0585] Specific behavior:

[0586] 1. Accumulate evaluation data in a database.

[0587] 2. Retrain the generative AI model based on the evaluation data at regular intervals.

[0588] 3. The retrained model is applied to the system and used for subsequent evaluations.

[0589] (Application example 1)

[0590] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0591] Traditional teacher-student communication and assessment methods lack effective means for qualitatively evaluating students' thinking skills and independent learning. Furthermore, systems for monitoring the safety of elderly people and home security have difficulty immediately detecting abnormal behavior or dangerous situations and providing appropriate feedback. This creates many challenges for educational and home security.

[0592] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0593] In this invention, the server includes an educational terminal means for inputting lesson goals and evaluation criteria, a learning terminal means for students to input their answers, an information processing means for receiving data from the educational terminal means and the learning terminal means, an evaluation means for analyzing and processing the lesson goals and evaluation criteria input to the information processing means to evaluate the level of achievement, a feedback means for feeding back the evaluation results to the educational terminal means and the learning terminal means, a storage and learning means for storing evaluation data over the long term and learning an evaluation model, a sensor means for acquiring monitoring data, an anomaly detection means for detecting abnormal behavior based on the monitoring data, and a warning means for issuing a warning in response to abnormal behavior detected by the anomaly detection means. This makes it possible to accurately evaluate students' thinking abilities and independent learning, and to improve the safety of the elderly and homes.

[0594] "Educational terminal means" refers to a dedicated device or software that allows a teacher to input lesson objectives and evaluation criteria.

[0595] "Learning terminal means" refers to a device or software that allows students to input their answers and assignments.

[0596] The "information processing means" is a system for receiving, storing, and analyzing data from the education terminal means and the learning terminal means.

[0597] "Evaluation tools" are functions that use natural language processing to evaluate students' achievement levels based on the input lesson goals and evaluation criteria.

[0598] The "feedback means" is a system for returning the evaluation results generated by the evaluation means to the education terminal means and the learning terminal means.

[0599] The "accumulation and learning means" is a function that stores evaluation data over the long term and uses the accumulated data to improve the accuracy of the evaluation model.

[0600] "Sensor means" refers to a device for acquiring monitoring data, and may include, for example, a camera or various sensors.

[0601] The "abnormality detection means" is a system for analyzing and detecting abnormal behavior and dangerous situations based on data acquired from the sensor means.

[0602] The "warning means" is a function for issuing a warning to the user in response to abnormal behavior detected by the abnormality detection means.

[0603] MODE FOR CARRYING OUT THE INVENTION

[0604] The present invention is a system that includes an education terminal means, a learning terminal means, an information processing means, an evaluation means, a feedback means, a storage and learning means, a sensor means, an anomaly detection means, and a warning means. Specific embodiments of the system are described below.

[0605] Educational terminal means

[0606] This is a device or software that teachers use to input lesson goals and evaluation criteria. For example, teachers use a tablet or PC to input evaluation criteria such as "understanding environmental issues," "personal opinions," and "suggested actions." This data is sent to a server through an interface.

[0607] Learning terminal means

[0608] This is the device or software that students use to enter their answers and assignments during class. For example, a student might type into their tablet, "I think we need to learn more about environmental issues. For example, I think we should recycle more." This data is sent to a server.

[0609] Information Processing Means

[0610] This system receives, stores, and analyzes data from the education terminal means and learning terminal means. For example, the server stores the input data in a database and passes the data to an evaluation model or anomaly detection model as needed.

[0611] Evaluation methods

[0612] The system runs on a server and analyzes students' responses based on the lesson's goals and assessment criteria. Specifically, it uses natural language processing technology to analyze the responses and assigns scores to "understanding environmental issues," "personal opinions," and "action suggestions."

[0613] Feedback Methods

[0614] The server is used to feed back the evaluation results to the education terminal means and the learning terminal means. For example, the evaluation results for the students' answers are sent from the server to the teacher's tablet and the student's tablet. This allows the teacher to provide appropriate feedback.

[0615] Accumulation and learning means

[0616] This system stores evaluation data over the long term and improves the accuracy of the evaluation model based on the accumulated data. For example, the server periodically learns from the data and updates the evaluation model, enabling more accurate evaluations.

[0617] Sensor Means

[0618] A device that acquires monitoring data. For example, it monitors the situation inside and outside the home using IP cameras and various sensors.

[0619] Anomaly detection means

[0620] This system analyzes and detects abnormal behavior and dangerous situations based on data acquired from sensors. For example, it can detect abnormalities such as when an elderly person collapses or a suspicious person enters a building.

[0621] warning means

[0622] This function alerts users to any abnormal behavior detected by the anomaly detection method. For example, it can immediately notify users of the abnormality by sending a push notification to their smartphone.

[0623] Specific examples

[0624] Scenario 1: A teacher is teaching a lesson about environmental issues.

[0625] Device use: Teachers input lesson goals and assessment criteria into tablets.

[0626] Evaluation process: Students enter their answers into a tablet, and the server analyzes the answers using natural language processing and generates a score.

[0627] Feedback: Evaluation results are fed back to teachers and students to guide further instruction.

[0628] Scenario 2: Monitoring the safety of elderly people.

[0629] Device use: IP cameras and sensors installed inside and outside the home.

[0630] Anomaly detection process: The server analyzes video data to detect falls by elderly people or intrusions by suspicious individuals.

[0631] Warning: When an abnormality is detected, a push notification such as "Fall detected!" or "Intruder detected!" will be sent to your smartphone.

[0632] Prompt Sentence Examples

[0633] "Create an algorithm that detects whether an elderly person is sitting or slumped in their living room."

[0634] "Explain how to train a model to detect if there is an intruder outside your home."

[0635] Thus, the present invention provides a system that is useful for both education and security purposes.

[0636] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0637] Step 1:

[0638] The teacher inputs the lesson goals and evaluation criteria into the educational terminal means. The input data includes "understanding of environmental issues," "personal opinions," "action proposals," etc. This input data is sent to the server.

[0639] Step 2:

[0640] During class, students input their answers and assignments into the learning terminal means. For example, a student might input an answer such as, "I think we need to learn more about environmental issues. For example, I think we should recycle more." This data is also sent to the server.

[0641] Step 3:

[0642] The server receives input data from the education terminal means and the learning terminal means, and stores the data in a database using the information processing means. This stored data is the basis for analysis.

[0643] Step 4:

[0644] The server uses the evaluation tools based on the received data and performs natural language processing based on the lesson goals and evaluation criteria entered. Specifically, it uses a generative AI model to analyze the answers and assign scores to "understanding environmental issues," "personal opinions," and "suggested actions."

[0645] Step 5:

[0646] The analysis results are sent back to the education terminal means and the learning terminal means via the feedback means. For example, the server sends the scores generated by the evaluation means to the terminals of the teacher and students and displays them on the screen.

[0647] Step 6:

[0648] The server processes data over the long term using a storage and learning method, storing the evaluation data over the long term and using this data to train the evaluation model, thereby continuously improving the system's evaluation accuracy.

[0649] Step 7:

[0650] To obtain the monitoring data, the sensor means obtains data from various sensors and IP cameras inside and outside the home, for example, a camera captures video of the living room.

[0651] Step 8:

[0652] The server receives the data sent from the sensor means and uses the anomaly detection means to analyze and detect abnormal behavior or dangerous situations, such as when an elderly person collapses or a suspicious person enters the building.

[0653] Step 9:

[0654] If an abnormality is detected, the server will immediately send alert information to the user's smartphone or device using an alerting method, such as a push notification saying "Fall detected!" or "Intruder detected!"

[0655] By taking these steps, it is possible to build a system that simultaneously improves the accuracy of evaluations in educational settings and strengthens security within the home.

[0656] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0657] The system of the present invention utilizes an evaluation generation AI and an emotion engine to qualitatively evaluate students' thinking ability and independent learning based on goals and evaluation criteria set by teachers during lessons. This system includes teacher terminal means, student terminal means, server means, evaluation means, feedback means, an emotion engine, and storage and learning means. Specific embodiments of the system are described below.

[0658] Teacher terminal means

[0659] The user (teacher) inputs the lesson goals and evaluation criteria using the teacher's terminal means. For example, the user sets evaluation items such as "understanding environmental issues," "personal opinions," and "action proposals." This data is sent to the server means via the interface.

[0660] Student terminal means

[0661] Students use the student terminal means to input answers to assignments during class. For example, if student A inputs "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle," this data is transmitted from the student terminal means to the server means.

[0662] Server Means

[0663] The server means receives data transmitted from the teacher terminal means and the student terminal means, and stores the received data in a database.

[0664] Evaluation methods

[0665] The server incorporates an evaluation system that uses natural language processing to analyze students' responses based on lesson objectives and evaluation criteria, and evaluates their level of achievement. Specifically, the system extracts from the responses parts that correspond to "understanding environmental issues," "personal opinions," and "action proposals," and assigns a score to each part.

[0666] Emotion Engine

[0667] The emotion engine analyzes students' responses and their behavior when entering answers to recognize their emotions. For example, through text analysis, it can identify emotions such as joy, anger, sadness, and happiness contained in the responses. The emotion data recognized by the emotion engine is provided to the evaluation tool and reflected in the achievement evaluation.

[0668] Feedback Methods

[0669] The evaluation results and emotion data generated by the evaluation means and emotion engine are sent back to the teacher terminal means and student terminal means via the feedback means. For example, the evaluation results and emotion evaluations for Student A's answer are displayed on the teacher terminal means and student terminal means. This feedback information is useful for the teacher when providing the next instruction.

[0670] Accumulation and learning means

[0671] Furthermore, the storage and learning means in the server means stores the evaluation data and emotion data over the long term and updates the evaluation model, thereby continuously improving the system's evaluation accuracy.

[0672] Specific examples

[0673] As a concrete example, consider the case where a teacher is giving a "lesson on environmental issues." The teacher inputs the lesson's goals and evaluation criteria (e.g., understanding of environmental issues, personal opinions, action suggestions) into the teacher's terminal means. During the lesson, students input their answers to assignments into the student's terminal means, and the data is sent to the server means. The server analyzes the answer data and scores the level of achievement for each item based on the evaluation criteria. Furthermore, an emotion engine analyzes the answers, recognizes emotions, and provides the results to the evaluation means. The evaluation results and emotion data are fed back to the teacher and students, and the evaluation data and emotion data are accumulated over the long term and used to train the evaluation model. This makes qualitative evaluation possible, allowing the thinking ability and independent learning of students to be accurately captured.

[0674] In this way, the present invention provides an effective means for assessing students' emotional aspects in addition to their thinking ability and independent learning, thereby realizing a more comprehensive educational evaluation.

[0675] The processing flow will be explained below.

[0676] Step 1:

[0677] The user (teacher) inputs the lesson goals and evaluation criteria into the teacher's terminal. For example, the user sets evaluation items such as "understanding environmental issues," "personal opinions," and "action proposals."

[0678] Step 2:

[0679] The terminal transmits the input lesson objectives and evaluation criteria to the server means, and the teacher terminal means converts the data into packets via the interface and transfers them to the server via the network.

[0680] Step 3:

[0681] The server receives the lesson objectives and evaluation criteria data and stores them in a database. The database management system within the server ensures data integrity while storing the data.

[0682] Step 4:

[0683] Students use student terminals to input answers to assignments during class. For example, Student A inputs a sentence such as, "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle."

[0684] Step 5:

[0685] The terminal sends the students' answer data to the server means. The input text data is formatted, organized into packets, and sent to the server via the Internet.

[0686] Step 6:

[0687] The server stores the received student response data in a database, ready to be analyzed by the evaluation tool and emotion engine.

[0688] Step 7:

[0689] The server's emotion engine analyzes students' response data and recognizes emotions from the text content. For example, emotions such as joy, anger, sadness, and happiness are identified based on positive and negative expressions in the text.

[0690] Step 8:

[0691] The server's evaluation means incorporates the emotional data analyzed by the emotion engine into the evaluation, and also uses a natural language processing engine to analyze the response content based on the evaluation criteria. Specifically, it extracts and classifies the parts of the text that correspond to "understanding," "opinion," and "suggestion."

[0692] Step 9:

[0693] The assessment tool calculates a score for each item according to the lesson objectives and assessment criteria. For example, 10 points are assigned to "understanding environmental issues," 8 points to "personal opinions," and 9 points to "action suggestions," and these are adjusted based on emotional data.

[0694] Step 10:

[0695] The server compiles the evaluation results and emotion data and generates feedback data. The evaluation results are generated as JSON format data for each student.

[0696] Step 11:

[0697] The server transmits feedback data to the teacher terminal means and the student terminal means, and the transmitted data is displayed on the interface of each terminal.

[0698] Step 12:

[0699] The device displays the evaluation results and emotional data. The user (teacher) can check the evaluation results and emotional data and use them to plan the next lesson. Students can also check their own evaluations and reflect on their learning.

[0700] Step 13:

[0701] The server stores the evaluation data and emotion data in the storage and learning means. By accumulating data over the long term, the accuracy of the evaluation model will be improved in the future.

[0702] Step 14:

[0703] The server's storage and learning means trains the evaluation model. Using the accumulated data, machine learning algorithms are applied to improve evaluation accuracy.

[0704] Example 2

[0705] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0706] Conventional educational evaluation systems are limited to quantitative assessment of students' thinking ability and independent learning, making it difficult to comprehensively evaluate students' emotional aspects. Furthermore, there is insufficient long-term data accumulation and learning to continuously improve the accuracy of evaluation models. As a result, there is a lack of information that contributes to the reliability of evaluation results and the improvement of teachers' teaching strategies.

[0707] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0708] In this invention, the server includes a data receiving means, an evaluation means, an emotion analysis means, a feedback means, and an accumulation and learning means. This allows for analysis and evaluation of students' answers using natural language processing, and for identifying emotions to provide a comprehensive evaluation. Furthermore, by accumulating evaluation data and emotion data over the long term and continuously learning the evaluation model, the accuracy of the evaluation can be improved.

[0709] "Educator terminal means" means an electronic device used by an educator to input lesson objectives and assessment criteria.

[0710] "Student terminal means" refers to an electronic device used by a student to input answers to assignments during class.

[0711] The "data receiving means" is a device having the function of receiving data transmitted from the teacher terminal means and the student terminal means.

[0712] The "server means" is a central processing unit that includes a data receiving means and has the function of analyzing and storing received data.

[0713] An "assessment tool" is a device or program that performs natural language processing based on the lesson's objectives and evaluation criteria and has the function of evaluating the learner's achievement.

[0714] "Emotion analysis means" refers to a device or program that has the function of analyzing the content of a learner's answers and their behavior when entering answers, and identifying their emotions.

[0715] The "feedback means" is a device or program that has the function of returning the evaluation results and emotion data to the educator terminal means and the learner terminal means.

[0716] "Storage and learning means" refers to a device or program that has the function of storing evaluation data and emotion data over the long term and continuously learning the evaluation model.

[0717] The system of the present invention includes educator terminal means, learner terminal means, server means, evaluation means, emotion analysis means, feedback means, and accumulation and learning means. This system utilizes generative AI and natural language processing technology to evaluate learners' thinking ability and independent learning, and analyze their emotions.

[0718] System configuration

[0719] Educator terminal means

[0720] The user (educator) uses an educator's terminal to input lesson goals and evaluation criteria. This terminal is a personal computer or tablet equipped with a standard web browser, and the user inputs the goals and evaluation criteria through a dedicated interface. For example, the user inputs data such as: "Understanding environmental issues," "Own opinion," and "Proposed actions." The input data is sent to the server via an HTTP request.

[0721] Learner terminal means

[0722] Learners use learner terminals to input answers to assignments during class. These terminals are also personal computers or tablets equipped with a web browser. For example, if Learner A inputs, "I think we need to learn more about environmental issues. For example, I think we should recycle more," this data is sent to the server.

[0723] Server Means

[0724] The server means receives the data sent from the teacher's terminal and the student's terminal and stores it in a database. This server uses database software such as MySQL or PostgreSQL. Based on the received and stored data, the server performs data analysis using the evaluation means.

[0725] Evaluation methods

[0726] The evaluation method within the server analyzes the data using a generative AI model and a natural language processing library (e.g., NLTK or spaCy). Specifically, it extracts the parts of the response that correspond to "understanding environmental issues," "personal opinions," and "action proposals," and assigns a score to each. For example, it assigns a score to each evaluation item for Learner A's response and evaluates the level of achievement.

[0727] Emotion analysis means

[0728] The server uses a sentiment analysis method to analyze the learner's responses and input behavior to identify emotions. This analysis utilizes text analysis tools (e.g., Affectiva and IBM Watson Natural Language Understanding). For example, from the phrase "I need to learn more," it identifies emotions such as "motivation" and "responsibility."

[0729] Feedback Methods

[0730] The results generated by the evaluation means and emotion analysis means are sent back to the teacher's terminal and the student's terminal via the feedback means. For example, the evaluation result for Student A's answer is scored and displayed on the screen. The identified emotion is also displayed.

[0731] Accumulation and learning means

[0732] Evaluation data and emotion data are stored over the long term using a storage and learning method. Based on the stored data, a machine learning algorithm continuously trains the evaluation model. This process is performed periodically as a batch process, contributing to improving the performance of the entire system.

[0733] Specific examples

[0734] For example, if a teacher is giving a lesson on environmental issues, he or she would follow these steps:

[0735] 1. The educator uses the educator terminal to enter the evaluation criteria.

[0736] Examples: "Understanding environmental issues," "Your own opinion," "Proposals for action."

[0737] 2. During class, students enter their answers to the assignments through their student devices.

[0738] Example: Learner A types, "I think I need to learn more about environmental issues. For example, I think we should recycle more."

[0739] 3. The server receives the data and stores it in a database.

[0740] 4. The evaluation instrument analyzes the data and assigns a score to each evaluation item.

[0741] 5. A sentiment analyzer analyzes the responses and identifies the sentiment.

[0742] For example, identify "motivation" and "responsibility."

[0743] 6. The results of the evaluation and sentiment analysis measures are fed back to the teacher's terminal and the student's terminal.

[0744] Prompt Sentence Examples

[0745] Here's an example prompt to input to the generative AI model:

[0746] Example prompt 1: "Analyze Student A's answer, 'I think we need to learn more about environmental issues. For example, I think we should recycle more.'" and evaluate it in terms of 'Understanding of environmental issues,' 'Own opinion,' and 'Suggested actions.'

[0747] Example prompt 2: "Identify the emotion in this passage and rate it as 'happy,' 'anger,' 'sad,' or 'surprise.'"

[0748] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0749] Step 1:

[0750] The user (educator) uses an educator terminal to input lesson goals and evaluation criteria.

[0751] Specific actions: Evaluation items such as "understanding of environmental issues," "own opinion," and "suggested actions" are entered into a dedicated interface displayed in the web browser on the educator's device.

[0752] Input: Course objectives and assessment criteria

[0753] Output: Assessment item data sent to the server

[0754] Step 2:

[0755] The server receives the evaluation item data sent from the teacher's terminal and stores it in a database.

[0756] Specific operation: The server receives the data sent through the HTTP request and uses database software (e.g., MySQL, PostgreSQL) to issue an INSERT statement to the database to store the data.

[0757] Input: Evaluation item data

[0758] Output: Evaluation item data stored in a database

[0759] Step 3:

[0760] The learner uses the learner's terminal to input answers to the assignment.

[0761] Specific actions: Learner A enters "I think we need to learn more about environmental issues. For example, I think we should recycle more" into the input form on the learner's device and clicks the send button.

[0762] Input: Learner's response data

[0763] Output: Learner's response data sent to the server

[0764] Step 4:

[0765] The server receives the response data sent from the learner's terminal and stores it in a database.

[0766] Specific operation: The server receives the data sent through the HTTP request, issues an INSERT statement to the database, and saves it. At the same time, it logs that the receiving process has been completed.

[0767] Input: Learner's response data

[0768] Output: Learner response data stored in a database

[0769] Step 5:

[0770] The server uses the evaluation means to analyze and evaluate the stored data.

[0771] Specific operation: The server analyzes the saved response data using generative AI models and natural language processing libraries (NLTK, spaCy, etc.). It generates prompt sentences and assigns scores to each evaluation item. Example: "Student A's response, 'I think we need to learn more about environmental issues. For example, I think we should recycle more,' is analyzed and evaluated in terms of 'Understanding environmental issues,' 'Own opinion,' and 'Suggested actions.'"

[0772] Input: Learner's response data

[0773] Output: Evaluation result score data

[0774] Step 6:

[0775] The server uses emotion analysis means to analyze the content of the learner's answers and identify their emotions.

[0776] Specific behavior: Use text analysis tools (such as Affectiva or IBM Watson Natural Language Understanding) to identify emotions such as joy, anger, sadness, and happiness contained in the response data using emotion analysis methods. Example: "Identify the emotion contained in this sentence and rate it as 'joy,' 'anger,' 'sadness,' or 'surprise.'"

[0777] Input: Learner's response data

[0778] Output: Sentiment analysis result data

[0779] Step 7:

[0780] The server feeds back the evaluation results and emotion data to the teacher's terminal and the student's terminal.

[0781] Specific operation: Evaluation results and sentiment analysis results are sent in real time using feedback tools and displayed on the screens of the teacher's and learner's devices. Real-time notifications are sent using WebSocket.

[0782] Input: Evaluation results and sentiment analysis results

[0783] Output: Feedback information displayed on teacher and student devices

[0784] Step 8:

[0785] The server stores the rating data and emotion data for a long period of time and updates the rating model.

[0786] Specific operation: Using the accumulation and learning method, the evaluation data and emotion data are stored in a database, and the evaluation model is updated periodically by applying a machine learning algorithm. This is executed periodically as a batch process using a scheduler.

[0787] Input: Evaluation results and sentiment analysis results

[0788] Output: Updated valuation model

[0789] This allows the system to comprehensively evaluate students' thinking abilities and independent learning, and supports teachers' teaching strategies.

[0790] (Application example 2)

[0791] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0792] Traditional education systems lack effective means for qualitatively evaluating students' thinking skills and independent learning. Furthermore, in the field of customer service, there are few systems for real-time emotion recognition and providing appropriate feedback, making it difficult to improve customer satisfaction. These issues are barriers to comprehensive evaluation and improvement of satisfaction in education and customer service.

[0793] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a teacher terminal means for inputting lesson goals and evaluation criteria; a student terminal means for inputting answers by students; a server means for receiving data from the teacher terminal means and the student terminal means; an evaluation means for performing natural language processing based on the lesson goals and evaluation criteria input to the server means and evaluating the level of achievement; a feedback means for feeding back the evaluation results to the teacher terminal means and the student terminal means; a storage and learning means for accumulating evaluation data over the long term and learning an evaluation model; an evaluation means for analyzing customer input text in real time and identifying customer emotions; and a feedback means for providing appropriate feedback based on the identified emotions. This makes it possible to qualitatively evaluate students' thinking abilities and independent learning while recognizing customer emotions in real time and providing appropriate feedback.

[0794] The "teacher terminal means" is a device for inputting lesson goals and evaluation criteria.

[0795] "Student terminal means" refers to a device that allows students to input answers to assignments during class.

[0796] The "server means" is a central system that receives and processes data sent from the teacher terminal means and the student terminal means.

[0797] The "evaluation means" is a device that has the function of performing natural language processing based on the lesson goals and evaluation criteria input in the server means, and evaluating the degree of achievement.

[0798] The "feedback means" is a mechanism for returning the evaluation results to the teacher terminal means and the student terminal means.

[0799] The "accumulation and learning means" is a mechanism for storing evaluation data over the long term and updating the evaluation model.

[0800] "Customer input text" is text data provided by a customer when using a service.

[0801] "Real-time analysis" is the process of processing data as soon as it is entered.

[0802] The "emotion identification evaluation means" is a device that has the function of recognizing and evaluating emotions from input text.

[0803] "Appropriate feedback" refers to advice and information returned to the user based on the evaluation results and emotional data.

[0804] The present invention is a system that can be effectively used in educational settings and virtual stores. Specific embodiments will be described below.

[0805] 1. System configuration:

[0806] This system includes a teacher terminal means, a student terminal means, a server means, an evaluation means, a feedback means, a storage and learning means, and an evaluation means for emotion recognition. The detailed configuration of each element is as follows:

[0807] 2. Teacher terminal means:

[0808] The teacher terminal means is a device that allows teachers to input lesson goals and evaluation criteria. Specifically, the teacher uses a tablet or PC to input goals and criteria through an interface.

[0809] 3. Student Devices:

[0810] The student terminal means is a device that students use to input answers during class. Students use tablets or PCs to input answers to assignments.

[0811] 4. Server means:

[0812] The server means is a central system that receives data sent from the teacher terminal means and the student terminal means, and performs natural language processing based on the input lesson goals and evaluation criteria.

[0813] 5. Evaluation method:

[0814] The evaluation means is a device that has the function of analyzing the answers of students in the server means and evaluating their achievement. Specifically, it uses a natural language processing model to extract parts of the answers that correspond to the evaluation items and assign a score to each item.

[0815] 6. Feedback methods:

[0816] The feedback means is a mechanism for returning the evaluation results to the teacher terminal means and the student terminal means, allowing students to check their own evaluation results and use them as a guide for their next learning.

[0817] 7. Storage and learning methods:

[0818] The accumulation and learning method is a mechanism for storing evaluation data over the long term and updating the evaluation model, which allows the accuracy of the evaluation model to be continuously improved.

[0819] 8. Customer Emotion Recognition:

[0820] When dealing with customers in a virtual store, the system analyzes the text entered by the customer in real time and has an evaluation method to identify emotions. Specifically, it uses smart glasses to capture the customer's text input, then recognizes their emotions through an emotion engine and provides feedback.

[0821] Hardware and software used:

[0822] Hardware: smart glasses (e.g., Google Glass), servers (for data processing and storage)

[0823] Software: Transformer model library (Hugging Face), emotion engine

[0824] The server analyzes the input text data of the customer in real time and identifies the emotion using the evaluation means, after which appropriate feedback is provided through the feedback means.

[0825] Examples:

[0826] If a customer says in-store, "I think this product is great, but it's too expensive," the emotion engine will analyze this and conclude, "That's a positive sentiment, but there's also dissatisfaction with the price." Staff can then immediately recommend specific discounts to improve customer satisfaction.

[0827] Example prompt sentence:

[0828] "Customer utterances are fed into the following sentiment analysis model to determine real-time sentiment as feedback. Example: 'I love the new features, but the price is too high.'"

[0829] This allows the system to provide more comprehensive and effective evaluation and feedback in both training and customer interactions.

[0830] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0831] Step 1:

[0832] The teacher uses the teacher's terminal means to input lesson goals and evaluation criteria. The input data is sent from the teacher's terminal means to the server means. Specifically, the teacher inputs evaluation items and criteria (e.g., understanding of environmental issues, personal opinions, action proposals).

[0833] Input: Text data of evaluation items and criteria

[0834] Output: Data sent from the teacher's computer to the server

[0835] Step 2:

[0836] Students use the student terminal means to input answers to assignments during class, and the answer data is transmitted from the student terminal means to the server means.

[0837] Input: Text data of student responses

[0838] Output: Data sent from student devices to the server

[0839] Step 3:

[0840] The server means stores the data received from the teacher terminal means and the student terminal means, and stores lesson goals, evaluation criteria, and student response data in a database.

[0841] Input: Data submitted by teachers and students

[0842] Output: Data stored in the database

[0843] Step 4:

[0844] The server uses the evaluation means to perform natural language processing based on the input data and evaluates the level of achievement based on the lesson goals and evaluation criteria. Specifically, it extracts parts of the answer sentence that correspond to the evaluation items and assigns a score to each.

[0845] Input: lesson goals and evaluation criteria, student response data

[0846] Output: Scored evaluation data

[0847] Step 5:

[0848] The server uses an emotion engine to analyze the content of students' responses and recognize their emotions. It identifies emotions such as joy, anger, sadness, and happiness from the text data and generates emotion data.

[0849] Input: Text data of student responses

[0850] Output: Emotion data

[0851] Step 6:

[0852] The server sends the evaluation results and emotion data back to the teacher terminal means and the student terminal means via the feedback means, and the teacher and students can check the evaluation results and emotion evaluations on their terminals.

[0853] Input: scored evaluation data, sentiment data

[0854] Output: Feedback information to teacher and student devices

[0855] Step 7:

[0856] The server uses an accumulation and learning method to store evaluation data and emotion data over the long term and update the evaluation model.

[0857] Input: Rating data and emotion data

[0858] Output: Updated valuation model

[0859] Step 8:

[0860] Smart glasses are used to capture customer input text, which is then sent to the server in real time.

[0861] Input: Customer text data

[0862] Output: Customer data sent to server

[0863] Step 9:

[0864] The server analyzes the customer's input text in real time and identifies emotions using evaluation means. Emotions are recognized through an emotion engine.

[0865] Input: Customer text data

[0866] Output: Identified emotion data

[0867] Step 10:

[0868] The server uses a feedback means to provide appropriate feedback based on the identified emotion, and presents information to customer care staff.

[0869] Input: Identified emotion data

[0870] Output: Feedback information for customer service staff

[0871] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0872] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0873] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0874] [Third embodiment]

[0875] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0876] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0877] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0878] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0879] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0880] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0881] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0882] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0883] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0884] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0885] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0886] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0887] The system of the present invention uses an evaluation generation AI to qualitatively evaluate students' thinking ability and independent learning based on goals and evaluation criteria set by teachers during lessons. This system includes teacher terminal means, student terminal means, server means, and evaluation means. Specific embodiments of the system are described below.

[0888] Teacher terminal means

[0889] The user (teacher) inputs the lesson goals and evaluation criteria using the teacher's terminal means. For example, evaluation criteria such as "understanding environmental issues," "own opinions," and "action proposals" are set in advance. This data is sent to the server means via the interface.

[0890] Student terminal means

[0891] Students use the student terminal means to input assignments and comments during class. For example, if student A inputs, "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle," this data is transmitted from the student terminal means to the server means.

[0892] Server Means

[0893] The server means receives data transmitted from the teacher terminal means and the student terminal means, and stores the received data in a database.

[0894] Evaluation methods

[0895] The server incorporates an evaluation system that uses natural language processing to analyze students' responses based on lesson objectives and evaluation criteria, and evaluates their level of achievement. Specifically, the system extracts from the responses parts that correspond to "understanding environmental issues," "personal opinions," and "action proposals," and assigns a score to each part.

[0896] Feedback Methods

[0897] The evaluation results generated by the evaluation means are sent back to the teacher terminal means and the student terminal means via the feedback means. For example, the evaluation results for Student A's answer are displayed on the teacher terminal means and the student terminal means. This feedback information is useful for the teacher when giving the next instruction.

[0898] Accumulation and learning means

[0899] Furthermore, the storage and learning means in the server means stores the evaluation data over the long term and updates the evaluation model, thereby continuously improving the system's evaluation accuracy.

[0900] Specific examples

[0901] As a concrete example, consider the case where a teacher is giving a "lesson on environmental issues." The teacher inputs the lesson's objectives and evaluation criteria (e.g., understanding of environmental issues, personal opinions, action proposals) into the teacher's terminal means. During the lesson, students input their answers to assignments into the student's terminal means, and this data is sent to the server means. The server analyzes the response data and scores the level of achievement for each item based on the evaluation criteria. The evaluation results are fed back to the teacher and students, and the evaluation data is accumulated over the long term and used to train the evaluation model. This makes qualitative evaluation possible, allowing the thinking ability and independent learning of students to be accurately grasped.

[0902] In this way, the present invention provides an effective means for assessing thinking ability and independent learning, and is a solution to overcome the limitations of traditional assessment methods that rely on test scores.

[0903] The processing flow will be explained below.

[0904] Step 1:

[0905] The user (teacher) inputs the lesson goals and evaluation criteria into the teacher's terminal. For example, the user sets evaluation items such as "understanding environmental issues," "personal opinions," and "action proposals."

[0906] Step 2:

[0907] The terminal transmits the input lesson objectives and evaluation criteria to the server means, and the teacher terminal means converts the data into packets via the interface and transfers them to the server via the network.

[0908] Step 3:

[0909] The server receives the lesson objectives and evaluation criteria data and stores them in a database. The database management system within the server ensures data integrity while storing the data.

[0910] Step 4:

[0911] Students use student terminals to input answers to assignments during class. For example, they input sentences such as, "I think we need to learn more about environmental issues. For example, I think we should recycle more."

[0912] Step 5:

[0913] The terminal sends the students' answer data to the server means. The input text data is formatted, organized into packets, and sent to the server via the Internet.

[0914] Step 6:

[0915] The server stores the received student response data in a database, ready to be analyzed by the evaluation means.

[0916] Step 7:

[0917] The server's evaluation tool analyzes students' response data using a natural language processing engine, extracting and categorizing keywords and phrases from the text based on the evaluation criteria.

[0918] Step 8:

[0919] The assessment tool calculates a score for each item according to the lesson objectives and assessment criteria. For example, 10 points are assigned to "understanding environmental issues," 8 points to "your own opinion," and 9 points to "suggestions for action."

[0920] Step 9:

[0921] The server compiles the evaluation results and generates feedback data for each student in JSON format.

[0922] Step 10:

[0923] The server transmits feedback data to the teacher terminal means and the student terminal means, and the transmitted data is displayed on the interface of each terminal.

[0924] Step 11:

[0925] The device displays the evaluation results. The user (teacher) can check the evaluation results and use them to plan the next lesson. Students can also check their own evaluations and reflect on their learning.

[0926] Step 12:

[0927] The server stores the evaluation data in the storage and learning means. By accumulating data over the long term, the accuracy of the evaluation model will be improved in the future.

[0928] Step 13:

[0929] The server's storage and learning means trains the evaluation model. Using the accumulated data, machine learning algorithms are applied to improve evaluation accuracy.

[0930] Example 1

[0931] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0932] In the traditional education system, there was a lack of qualitative methods for evaluating students' thinking ability and independent learning. As a result, teachers had no choice but to rely on test scores, making it difficult to accurately evaluate each student's growth and depth of learning. Furthermore, there was a lack of effective methods for providing feedback on the results of evaluations and using them to improve future instruction.

[0933] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0934] In this invention, the server includes teacher terminal means for inputting lesson goals and evaluation criteria, student terminal means for students to input their answers, server means for receiving data from the teacher terminal means and the student terminal means and storing it in a database, evaluation means for performing natural language processing on the server means based on the lesson goals and evaluation criteria inputted and evaluating the level of achievement, feedback means for feeding back the evaluation results to the teacher terminal means and the student terminal means, storage and learning means for accumulating evaluation data over the long term and learning an evaluation model, technical means for analyzing students' answers using natural language processing and assigning scores to specific evaluation criteria, and display means for displaying the generated evaluation results on the teacher terminal and the student terminal. This makes it possible to qualitatively evaluate students' thinking abilities and independent learning, allowing teachers to provide more effective instruction based on the evaluation results.

[0935] "Teacher terminal means" refers to a device used by a teacher to input lesson objectives and evaluation criteria.

[0936] "Student terminal means" refers to a device used by students during class to input answers to assignments and comments.

[0937] The term "server means" refers to a computer system used to receive data sent from the teacher terminal means and the student terminal means, and to store and process the data.

[0938] "Database" refers to a system located within the server means for storing received data in a structured format.

[0939] "Natural language processing" refers to the technology that enables computers to understand, analyze, and process human language.

[0940] "Evaluation means" refers to a function for analyzing students' responses using natural language processing based on lesson goals and evaluation criteria input into the server means, and evaluating their level of achievement.

[0941] The "feedback means" refers to a function for returning the evaluation results generated by the evaluation means to the teacher terminal means and the student terminal means.

[0942] "Storage and learning means" refers to a system for storing evaluation data over the long term and for learning and updating generative AI models.

[0943] "Technical means" refers to the technical components used to analyze student responses using natural language processing and assign scores against specific assessment criteria.

[0944] "Display means" refers to a function for displaying the generated evaluation results on the teacher terminal and the student terminal.

[0945] The system of the present invention qualitatively evaluates students' thinking ability and independent learning based on goals and evaluation criteria set by educators during lessons. The system includes teacher terminal means, student terminal means, server means, evaluation means, feedback means, storage and learning means, technical means, and display means.

[0946] Teacher terminal means

[0947] The user (teacher) uses the teacher's terminal means to input the lesson's goals and evaluation criteria. Specifically, the teacher starts a dedicated application and inputs the goals and evaluation criteria (e.g., "Understanding environmental issues," "Own opinion," "Proposed action"). Once the input is complete, the teacher clicks the "Send" button to send the setting data to the server means.

[0948] Student terminal means

[0949] Students use student terminal means to input answers to assignments and comments during class. Students start a dedicated application, enter their answers to assignments in an input form, and submit. For example, Student A might enter, "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle." Once the input is complete, the data is sent to the server means.

[0950] Server Means

[0951] The server receives data sent from the teacher terminal means and student terminal means and stores it in a database. The server listens to the data and stores the received data in a structured format in the database. It also sends a data reception confirmation back to each terminal. The received data is analyzed using the evaluation means based on the lesson goals and evaluation criteria.

[0952] Evaluation methods

[0953] The evaluation tool on the server uses natural language processing (NLP) to analyze students' answers based on the evaluation criteria set by the teacher. Specific APIs such as Python's NLTK and SpaCy are used to extract the parts of the answers that correspond to "understanding environmental issues," "personal opinions," and "action proposals," and assign scores to each. For example, the following prompt is input into the generative AI model:

[0954] Example prompt:

[0955] "Analyze the student's response according to the assessment criteria of 'Understanding environmental issues,' 'Own opinions,' and 'Suggested actions,' and rate each one accordingly. For example, here is a response such as, 'I think we need to learn more about environmental issues. For example, I think we should try harder to recycle.'"

[0956] Feedback Methods

[0957] The evaluation results generated by the evaluation means are sent back to the teacher terminal means and the student terminal means via the feedback means. The evaluation results are displayed on each terminal, allowing teachers to use this information for their next instruction and students to check the evaluation of their own learning.

[0958] Accumulation and learning means

[0959] The server's storage and learning means stores the evaluation data over the long term and updates the evaluation model to operate and improve the generative AI model.The model is retrained based on the evaluation data, and the system's evaluation accuracy is continuously improved.

[0960] technical means

[0961] Natural language processing is used to analyze student responses and assign scores against specific assessment criteria, allowing for detailed analysis and accurate assessment of each criterion.

[0962] Display means

[0963] The system includes a display means for displaying the generated evaluation results on the teacher's terminal and the student's terminal. By displaying the evaluation results, the transparency of the evaluation content is increased, and the quality of learning for students can be improved.

[0964] In this way, the system of the present invention provides an effective means for accurately assessing students' thinking ability and independent learning in educational settings, thereby overcoming the limitations of traditional assessment methods that rely on test scores.

[0965] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0966] Step 1:

[0967] The user (teacher) uses the teacher's terminal means to input the lesson's goals and evaluation criteria. Specific inputs include evaluation criteria such as "understanding environmental issues," "personal opinions," and "action proposals." The terminal sends this setting data to the server means.

[0968] Input: Course objectives and assessment criteria

[0969] Output: Sending configuration data to the server

[0970] Specific behavior:

[0971] 1. The teacher launches the dedicated application.

[0972] 2. Enter your goals and evaluation criteria into the application form.

[0973] 3. Once you have completed the input, click the "Submit" button to send the setting data to the server.

[0974] Step 2:

[0975] Students use the student terminal means to input assignments and comments during class. For example, Student A inputs, "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle." The terminal sends this data to the server means.

[0976] Input: Answers to assignments and comments

[0977] Output: Sending response data to the server

[0978] Specific behavior:

[0979] 1. The student launches the dedicated application.

[0980] 2. Enter your answers to the assignment in the application form.

[0981] 3. Once you have completed entering the information, click the "Submit" button to send the response data to the server.

[0982] Step 3:

[0983] The server receives the data transmitted from the teacher terminal means and the student terminal means and stores it in a database, whereby lesson objectives, assessment criteria data, and answer data are stored in a structured format.

[0984] Input: Data sent from the teacher's device and student's device

[0985] Output: Data stored in the database

[0986] Specific behavior:

[0987] 1. The server listens to data sent from teacher and student devices.

[0988] 2. Receive the data and store it in a structured format in a database.

[0989] 3. A confirmation of data receipt is sent back to each terminal.

[0990] Step 4:

[0991] The server's internal evaluation tool uses natural language processing (NLP) to analyze students' responses based on the evaluation criteria set by the teacher. Using APIs such as Python's NLTK and SpaCy, it extracts parts of the responses that correspond to "understanding environmental issues," "personal opinions," and "action suggestions," and assigns a score to each criterion.

[0992] Input: Lesson objectives, assessment criteria, and response data stored in a database

[0993] Output: Scores corresponding to each criterion

[0994] Specific behavior:

[0995] 1. The server retrieves the criteria and response data.

[0996] 2. Perform text analysis using natural language processing tools (NLTK or SpaCy).

[0997] 3. Automatically identify the parts that fall under each evaluation criterion and calculate the corresponding score.

[0998] Step 5:

[0999] The evaluation results generated by the evaluation means are sent back to the teacher terminal means and the student terminal means via the feedback means. The evaluation results are displayed on each terminal, and can be viewed by the users.

[1000] Input: Evaluation results obtained by analysis

[1001] Output: Sending and displaying the evaluation results to the teacher and student devices

[1002] Specific behavior:

[1003] 1. The server generates the evaluation result.

[1004] 2. Send the evaluation results to the teacher and student devices.

[1005] 3. The evaluation results received by each device are displayed on the user interface.

[1006] Step 6:

[1007] The server's storage and learning means stores the evaluation data over the long term and retrains the evaluation model to operate and improve the generative AI model, thereby continuously improving the system's evaluation accuracy.

[1008] Input: Evaluation result data

[1009] Output: A trained evaluation model

[1010] Specific behavior:

[1011] 1. Accumulate evaluation data in a database.

[1012] 2. Retrain the generative AI model based on the evaluation data at regular intervals.

[1013] 3. The retrained model is applied to the system and used for subsequent evaluations.

[1014] (Application example 1)

[1015] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1016] Traditional teacher-student communication and assessment methods lack effective means for qualitatively evaluating students' thinking skills and independent learning. Furthermore, systems for monitoring the safety of elderly people and home security have difficulty immediately detecting abnormal behavior or dangerous situations and providing appropriate feedback. This creates many challenges for educational and home security.

[1017] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1018] In this invention, the server includes an educational terminal means for inputting lesson goals and evaluation criteria, a learning terminal means for students to input their answers, an information processing means for receiving data from the educational terminal means and the learning terminal means, an evaluation means for analyzing and processing the lesson goals and evaluation criteria input to the information processing means to evaluate the level of achievement, a feedback means for feeding back the evaluation results to the educational terminal means and the learning terminal means, a storage and learning means for storing evaluation data over the long term and learning an evaluation model, a sensor means for acquiring monitoring data, an anomaly detection means for detecting abnormal behavior based on the monitoring data, and a warning means for issuing a warning in response to abnormal behavior detected by the anomaly detection means. This makes it possible to accurately evaluate students' thinking abilities and independent learning, and to improve the safety of the elderly and homes.

[1019] "Educational terminal means" refers to a dedicated device or software that allows a teacher to input lesson objectives and evaluation criteria.

[1020] "Learning terminal means" refers to a device or software that allows students to input their answers and assignments.

[1021] The "information processing means" is a system for receiving, storing, and analyzing data from the education terminal means and the learning terminal means.

[1022] "Evaluation tools" are functions that use natural language processing to evaluate students' achievement levels based on the input lesson goals and evaluation criteria.

[1023] The "feedback means" is a system for returning the evaluation results generated by the evaluation means to the education terminal means and the learning terminal means.

[1024] The "accumulation and learning means" is a function that stores evaluation data over the long term and uses the accumulated data to improve the accuracy of the evaluation model.

[1025] "Sensor means" refers to a device for acquiring monitoring data, and may include, for example, a camera or various sensors.

[1026] The "abnormality detection means" is a system for analyzing and detecting abnormal behavior and dangerous situations based on data acquired from the sensor means.

[1027] The "warning means" is a function for issuing a warning to the user in response to abnormal behavior detected by the abnormality detection means.

[1028] MODE FOR CARRYING OUT THE INVENTION

[1029] The present invention is a system that includes an education terminal means, a learning terminal means, an information processing means, an evaluation means, a feedback means, a storage and learning means, a sensor means, an anomaly detection means, and a warning means. Specific embodiments of the system are described below.

[1030] Educational terminal means

[1031] This is a device or software that teachers use to input lesson goals and evaluation criteria. For example, teachers use a tablet or PC to input evaluation criteria such as "understanding environmental issues," "personal opinions," and "suggested actions." This data is sent to a server through an interface.

[1032] Learning terminal means

[1033] This is the device or software that students use to enter their answers and assignments during class. For example, a student might type into their tablet, "I think we need to learn more about environmental issues. For example, I think we should recycle more." This data is sent to a server.

[1034] Information Processing Means

[1035] This system receives, stores, and analyzes data from the education terminal means and learning terminal means. For example, the server stores the input data in a database and passes the data to an evaluation model or anomaly detection model as needed.

[1036] Evaluation methods

[1037] The system runs on a server and analyzes students' responses based on the lesson's goals and assessment criteria. Specifically, it uses natural language processing technology to analyze the responses and assigns scores to "understanding environmental issues," "personal opinions," and "action suggestions."

[1038] Feedback Methods

[1039] The server is used to feed back the evaluation results to the education terminal means and the learning terminal means. For example, the evaluation results for the students' answers are sent from the server to the teacher's tablet and the student's tablet. This allows the teacher to provide appropriate feedback.

[1040] Accumulation and learning means

[1041] This system stores evaluation data over the long term and improves the accuracy of the evaluation model based on the accumulated data. For example, the server periodically learns from the data and updates the evaluation model, enabling more accurate evaluations.

[1042] Sensor Means

[1043] A device that acquires monitoring data. For example, it monitors the situation inside and outside the home using IP cameras and various sensors.

[1044] Anomaly detection means

[1045] This system analyzes and detects abnormal behavior and dangerous situations based on data acquired from sensors. For example, it can detect abnormalities such as when an elderly person collapses or a suspicious person enters a building.

[1046] warning means

[1047] This function alerts users to any abnormal behavior detected by the anomaly detection method. For example, it can immediately notify users of the abnormality by sending a push notification to their smartphone.

[1048] Specific examples

[1049] Scenario 1: A teacher is teaching a lesson about environmental issues.

[1050] Device use: Teachers input lesson goals and assessment criteria into tablets.

[1051] Evaluation process: Students enter their answers into a tablet, and the server analyzes the answers using natural language processing and generates a score.

[1052] Feedback: Evaluation results are fed back to teachers and students to guide further instruction.

[1053] Scenario 2: Monitoring the safety of elderly people.

[1054] Device use: IP cameras and sensors installed inside and outside the home.

[1055] Anomaly detection process: The server analyzes video data to detect falls by elderly people or intrusions by suspicious individuals.

[1056] Warning: When an abnormality is detected, a push notification such as "Fall detected!" or "Intruder detected!" will be sent to your smartphone.

[1057] Prompt Sentence Examples

[1058] "Create an algorithm that detects whether an elderly person is sitting or slumped in their living room."

[1059] "Explain how to train a model to detect if there is an intruder outside your home."

[1060] Thus, the present invention provides a system that is useful for both education and security purposes.

[1061] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1062] Step 1:

[1063] The teacher inputs the lesson goals and evaluation criteria into the educational terminal means. The input data includes "understanding of environmental issues," "personal opinions," "action proposals," etc. This input data is sent to the server.

[1064] Step 2:

[1065] During class, students input their answers and assignments into the learning terminal means. For example, a student might input an answer such as, "I think we need to learn more about environmental issues. For example, I think we should recycle more." This data is also sent to the server.

[1066] Step 3:

[1067] The server receives input data from the education terminal means and the learning terminal means, and stores the data in a database using the information processing means. This stored data is the basis for analysis.

[1068] Step 4:

[1069] The server uses the evaluation tools based on the received data and performs natural language processing based on the lesson goals and evaluation criteria entered. Specifically, it uses a generative AI model to analyze the answers and assign scores to "understanding environmental issues," "personal opinions," and "suggested actions."

[1070] Step 5:

[1071] The analysis results are sent back to the education terminal means and the learning terminal means via the feedback means. For example, the server sends the scores generated by the evaluation means to the terminals of the teacher and students and displays them on the screen.

[1072] Step 6:

[1073] The server processes data over the long term using a storage and learning method, storing the evaluation data over the long term and using this data to train the evaluation model, thereby continuously improving the system's evaluation accuracy.

[1074] Step 7:

[1075] To obtain the monitoring data, the sensor means obtains data from various sensors and IP cameras inside and outside the home, for example, a camera captures video of the living room.

[1076] Step 8:

[1077] The server receives the data sent from the sensor means and uses the anomaly detection means to analyze and detect abnormal behavior or dangerous situations, such as when an elderly person collapses or a suspicious person enters the building.

[1078] Step 9:

[1079] If an abnormality is detected, the server will immediately send alert information to the user's smartphone or device using an alerting method, such as a push notification saying "Fall detected!" or "Intruder detected!"

[1080] By taking these steps, it is possible to build a system that simultaneously improves the accuracy of evaluations in educational settings and strengthens security within the home.

[1081] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1082] The system of the present invention utilizes an evaluation generation AI and an emotion engine to qualitatively evaluate students' thinking ability and independent learning based on goals and evaluation criteria set by teachers during lessons. This system includes teacher terminal means, student terminal means, server means, evaluation means, feedback means, an emotion engine, and storage and learning means. Specific embodiments of the system are described below.

[1083] Teacher terminal means

[1084] The user (teacher) inputs the lesson goals and evaluation criteria using the teacher's terminal means. For example, the user sets evaluation items such as "understanding environmental issues," "personal opinions," and "action proposals." This data is sent to the server means via the interface.

[1085] Student terminal means

[1086] Students use the student terminal means to input answers to assignments during class. For example, if student A inputs "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle," this data is transmitted from the student terminal means to the server means.

[1087] Server Means

[1088] The server means receives data transmitted from the teacher terminal means and the student terminal means, and stores the received data in a database.

[1089] Evaluation methods

[1090] The server incorporates an evaluation system that uses natural language processing to analyze students' responses based on lesson objectives and evaluation criteria, and evaluates their level of achievement. Specifically, the system extracts from the responses parts that correspond to "understanding environmental issues," "personal opinions," and "action proposals," and assigns a score to each part.

[1091] Emotion Engine

[1092] The emotion engine analyzes students' responses and their behavior when entering answers to recognize their emotions. For example, through text analysis, it can identify emotions such as joy, anger, sadness, and happiness contained in the responses. The emotion data recognized by the emotion engine is provided to the evaluation tool and reflected in the achievement evaluation.

[1093] Feedback Methods

[1094] The evaluation results and emotion data generated by the evaluation means and emotion engine are sent back to the teacher terminal means and student terminal means via the feedback means. For example, the evaluation results and emotion evaluations for Student A's answer are displayed on the teacher terminal means and student terminal means. This feedback information is useful for the teacher when providing the next instruction.

[1095] Accumulation and learning means

[1096] Furthermore, the storage and learning means in the server means stores the evaluation data and emotion data over the long term and updates the evaluation model, thereby continuously improving the system's evaluation accuracy.

[1097] Specific examples

[1098] As a concrete example, consider the case where a teacher is giving a "lesson on environmental issues." The teacher inputs the lesson's goals and evaluation criteria (e.g., understanding of environmental issues, personal opinions, action suggestions) into the teacher's terminal means. During the lesson, students input their answers to assignments into the student's terminal means, and the data is sent to the server means. The server analyzes the answer data and scores the level of achievement for each item based on the evaluation criteria. Furthermore, an emotion engine analyzes the answers, recognizes emotions, and provides the results to the evaluation means. The evaluation results and emotion data are fed back to the teacher and students, and the evaluation data and emotion data are accumulated over the long term and used to train the evaluation model. This makes qualitative evaluation possible, allowing the thinking ability and independent learning of students to be accurately captured.

[1099] In this way, the present invention provides an effective means for assessing students' emotional aspects in addition to their thinking ability and independent learning, thereby realizing a more comprehensive educational evaluation.

[1100] The processing flow will be explained below.

[1101] Step 1:

[1102] The user (teacher) inputs the lesson goals and evaluation criteria into the teacher's terminal. For example, the user sets evaluation items such as "understanding environmental issues," "personal opinions," and "action proposals."

[1103] Step 2:

[1104] The terminal transmits the input lesson objectives and evaluation criteria to the server means, and the teacher terminal means converts the data into packets via the interface and transfers them to the server via the network.

[1105] Step 3:

[1106] The server receives the lesson objectives and evaluation criteria data and stores them in a database. The database management system within the server ensures data integrity while storing the data.

[1107] Step 4:

[1108] Students use student terminals to input answers to assignments during class. For example, Student A inputs a sentence such as, "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle."

[1109] Step 5:

[1110] The terminal sends the students' answer data to the server means. The input text data is formatted, organized into packets, and sent to the server via the Internet.

[1111] Step 6:

[1112] The server stores the received student response data in a database, ready to be analyzed by the evaluation tool and emotion engine.

[1113] Step 7:

[1114] The server's emotion engine analyzes students' response data and recognizes emotions from the text content. For example, emotions such as joy, anger, sadness, and happiness are identified based on positive and negative expressions in the text.

[1115] Step 8:

[1116] The server's evaluation means incorporates the emotional data analyzed by the emotion engine into the evaluation, and also uses a natural language processing engine to analyze the response content based on the evaluation criteria. Specifically, it extracts and classifies the parts of the text that correspond to "understanding," "opinion," and "suggestion."

[1117] Step 9:

[1118] The assessment tool calculates a score for each item according to the lesson objectives and assessment criteria. For example, 10 points are assigned to "understanding environmental issues," 8 points to "personal opinions," and 9 points to "action suggestions," and these are adjusted based on emotional data.

[1119] Step 10:

[1120] The server compiles the evaluation results and emotion data and generates feedback data. The evaluation results are generated as JSON format data for each student.

[1121] Step 11:

[1122] The server transmits feedback data to the teacher terminal means and the student terminal means, and the transmitted data is displayed on the interface of each terminal.

[1123] Step 12:

[1124] The device displays the evaluation results and emotional data. The user (teacher) can check the evaluation results and emotional data and use them to plan the next lesson. Students can also check their own evaluations and reflect on their learning.

[1125] Step 13:

[1126] The server stores the evaluation data and emotion data in the storage and learning means. By accumulating data over the long term, the accuracy of the evaluation model will be improved in the future.

[1127] Step 14:

[1128] The server's storage and learning means trains the evaluation model. Using the accumulated data, machine learning algorithms are applied to improve evaluation accuracy.

[1129] Example 2

[1130] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1131] Conventional educational evaluation systems are limited to quantitative assessment of students' thinking ability and independent learning, making it difficult to comprehensively evaluate students' emotional aspects. Furthermore, there is insufficient long-term data accumulation and learning to continuously improve the accuracy of evaluation models. As a result, there is a lack of information that contributes to the reliability of evaluation results and the improvement of teachers' teaching strategies.

[1132] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1133] In this invention, the server includes a data receiving means, an evaluation means, an emotion analysis means, a feedback means, and an accumulation and learning means. This allows for analysis and evaluation of students' answers using natural language processing, and for identifying emotions to provide a comprehensive evaluation. Furthermore, by accumulating evaluation data and emotion data over the long term and continuously learning the evaluation model, the accuracy of the evaluation can be improved.

[1134] "Educator terminal means" means an electronic device used by an educator to input lesson objectives and assessment criteria.

[1135] "Student terminal means" refers to an electronic device used by a student to input answers to assignments during class.

[1136] The "data receiving means" is a device having the function of receiving data transmitted from the teacher terminal means and the student terminal means.

[1137] The "server means" is a central processing unit that includes a data receiving means and has the function of analyzing and storing received data.

[1138] An "assessment tool" is a device or program that performs natural language processing based on the lesson's objectives and evaluation criteria and has the function of evaluating the learner's achievement.

[1139] "Emotion analysis means" refers to a device or program that has the function of analyzing the content of a learner's answers and their behavior when entering answers, and identifying their emotions.

[1140] The "feedback means" is a device or program that has the function of returning the evaluation results and emotion data to the educator terminal means and the learner terminal means.

[1141] "Storage and learning means" refers to a device or program that has the function of storing evaluation data and emotion data over the long term and continuously learning the evaluation model.

[1142] The system of the present invention includes educator terminal means, learner terminal means, server means, evaluation means, emotion analysis means, feedback means, and accumulation and learning means. This system utilizes generative AI and natural language processing technology to evaluate learners' thinking ability and independent learning, and analyze their emotions.

[1143] System configuration

[1144] Educator terminal means

[1145] The user (educator) uses an educator's terminal to input lesson goals and evaluation criteria. This terminal is a personal computer or tablet equipped with a standard web browser, and the user inputs the goals and evaluation criteria through a dedicated interface. For example, the user inputs data such as: "Understanding environmental issues," "Own opinion," and "Proposed actions." The input data is sent to the server via an HTTP request.

[1146] Learner terminal means

[1147] Learners use learner terminals to input answers to assignments during class. These terminals are also personal computers or tablets equipped with a web browser. For example, if Learner A inputs, "I think we need to learn more about environmental issues. For example, I think we should recycle more," this data is sent to the server.

[1148] Server Means

[1149] The server means receives the data sent from the teacher's terminal and the student's terminal and stores it in a database. This server uses database software such as MySQL or PostgreSQL. Based on the received and stored data, the server performs data analysis using the evaluation means.

[1150] Evaluation methods

[1151] The evaluation method within the server analyzes the data using a generative AI model and a natural language processing library (e.g., NLTK or spaCy). Specifically, it extracts the parts of the response that correspond to "understanding environmental issues," "personal opinions," and "action proposals," and assigns a score to each. For example, it assigns a score to each evaluation item for Learner A's response and evaluates the level of achievement.

[1152] Emotion analysis means

[1153] The server uses a sentiment analysis method to analyze the learner's responses and input behavior to identify emotions. This analysis utilizes text analysis tools (e.g., Affectiva and IBM Watson Natural Language Understanding). For example, from the phrase "I need to learn more," it identifies emotions such as "motivation" and "responsibility."

[1154] Feedback Methods

[1155] The results generated by the evaluation means and emotion analysis means are sent back to the teacher's terminal and the student's terminal via the feedback means. For example, the evaluation result for Student A's answer is scored and displayed on the screen. The identified emotion is also displayed.

[1156] Accumulation and learning means

[1157] Evaluation data and emotion data are stored over the long term using a storage and learning method. Based on the stored data, a machine learning algorithm continuously trains the evaluation model. This process is performed periodically as a batch process, contributing to improving the performance of the entire system.

[1158] Specific examples

[1159] For example, if a teacher is giving a lesson on environmental issues, he or she would follow these steps:

[1160] 1. The educator uses the educator terminal to enter the evaluation criteria.

[1161] Examples: "Understanding environmental issues," "Your own opinion," "Proposals for action."

[1162] 2. During class, students enter their answers to the assignments through their student devices.

[1163] Example: Learner A types, "I think I need to learn more about environmental issues. For example, I think we should recycle more."

[1164] 3. The server receives the data and stores it in a database.

[1165] 4. The evaluation instrument analyzes the data and assigns a score to each evaluation item.

[1166] 5. A sentiment analyzer analyzes the responses and identifies the sentiment.

[1167] For example, identify "motivation" and "responsibility."

[1168] 6. The results of the evaluation and sentiment analysis measures are fed back to the teacher's terminal and the student's terminal.

[1169] Prompt Sentence Examples

[1170] Here's an example prompt to input to the generative AI model:

[1171] Example prompt 1: "Analyze Student A's answer, 'I think we need to learn more about environmental issues. For example, I think we should recycle more.'" and evaluate it in terms of 'Understanding of environmental issues,' 'Own opinion,' and 'Suggested actions.'

[1172] Example prompt 2: "Identify the emotion in this passage and rate it as 'happy,' 'anger,' 'sad,' or 'surprise.'"

[1173] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1174] Step 1:

[1175] The user (educator) uses an educator terminal to input lesson goals and evaluation criteria.

[1176] Specific actions: Evaluation items such as "understanding of environmental issues," "own opinion," and "suggested actions" are entered into a dedicated interface displayed in the web browser on the educator's device.

[1177] Input: Course objectives and assessment criteria

[1178] Output: Assessment item data sent to the server

[1179] Step 2:

[1180] The server receives the evaluation item data sent from the teacher's terminal and stores it in a database.

[1181] Specific operation: The server receives the data sent through the HTTP request and uses database software (e.g., MySQL, PostgreSQL) to issue an INSERT statement to the database to store the data.

[1182] Input: Evaluation item data

[1183] Output: Evaluation item data stored in a database

[1184] Step 3:

[1185] The learner uses the learner's terminal to input answers to the assignment.

[1186] Specific actions: Learner A enters "I think we need to learn more about environmental issues. For example, I think we should recycle more" into the input form on the learner's device and clicks the send button.

[1187] Input: Learner's response data

[1188] Output: Learner's response data sent to the server

[1189] Step 4:

[1190] The server receives the response data sent from the learner's terminal and stores it in a database.

[1191] Specific operation: The server receives the data sent through the HTTP request, issues an INSERT statement to the database, and saves it. At the same time, it logs that the receiving process has been completed.

[1192] Input: Learner's response data

[1193] Output: Learner response data stored in a database

[1194] Step 5:

[1195] The server uses the evaluation means to analyze and evaluate the stored data.

[1196] Specific operation: The server analyzes the saved response data using generative AI models and natural language processing libraries (NLTK, spaCy, etc.). It generates prompt sentences and assigns scores to each evaluation item. Example: "Student A's response, 'I think we need to learn more about environmental issues. For example, I think we should recycle more,' is analyzed and evaluated in terms of 'Understanding environmental issues,' 'Own opinion,' and 'Suggested actions.'"

[1197] Input: Learner's response data

[1198] Output: Evaluation result score data

[1199] Step 6:

[1200] The server uses emotion analysis means to analyze the content of the learner's answers and identify their emotions.

[1201] Specific behavior: Use text analysis tools (such as Affectiva or IBM Watson Natural Language Understanding) to identify emotions such as joy, anger, sadness, and happiness contained in the response data using emotion analysis methods. Example: "Identify the emotion contained in this sentence and rate it as 'joy,' 'anger,' 'sadness,' or 'surprise.'"

[1202] Input: Learner's response data

[1203] Output: Sentiment analysis result data

[1204] Step 7:

[1205] The server feeds back the evaluation results and emotion data to the teacher's terminal and the student's terminal.

[1206] Specific operation: Evaluation results and sentiment analysis results are sent in real time using feedback tools and displayed on the screens of the teacher's and learner's devices. Real-time notifications are sent using WebSocket.

[1207] Input: Evaluation results and sentiment analysis results

[1208] Output: Feedback information displayed on teacher and student devices

[1209] Step 8:

[1210] The server stores the rating data and emotion data for a long period of time and updates the rating model.

[1211] Specific operation: Using the accumulation and learning method, the evaluation data and emotion data are stored in a database, and the evaluation model is updated periodically by applying a machine learning algorithm. This is executed periodically as a batch process using a scheduler.

[1212] Input: Evaluation results and sentiment analysis results

[1213] Output: Updated valuation model

[1214] This allows the system to comprehensively evaluate students' thinking abilities and independent learning, and supports teachers' teaching strategies.

[1215] (Application example 2)

[1216] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1217] Traditional education systems lack effective means for qualitatively evaluating students' thinking skills and independent learning. Furthermore, in the field of customer service, there are few systems for real-time emotion recognition and providing appropriate feedback, making it difficult to improve customer satisfaction. These issues are barriers to comprehensive evaluation and improvement of satisfaction in education and customer service.

[1218] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a teacher terminal means for inputting lesson goals and evaluation criteria; a student terminal means for inputting answers by students; a server means for receiving data from the teacher terminal means and the student terminal means; an evaluation means for performing natural language processing based on the lesson goals and evaluation criteria input to the server means and evaluating the level of achievement; a feedback means for feeding back the evaluation results to the teacher terminal means and the student terminal means; a storage and learning means for accumulating evaluation data over the long term and learning an evaluation model; an evaluation means for analyzing customer input text in real time and identifying customer emotions; and a feedback means for providing appropriate feedback based on the identified emotions. This makes it possible to qualitatively evaluate students' thinking abilities and independent learning while recognizing customer emotions in real time and providing appropriate feedback.

[1219] The "teacher terminal means" is a device for inputting lesson goals and evaluation criteria.

[1220] "Student terminal means" refers to a device that allows students to input answers to assignments during class.

[1221] The "server means" is a central system that receives and processes data sent from the teacher terminal means and the student terminal means.

[1222] The "evaluation means" is a device that has the function of performing natural language processing based on the lesson goals and evaluation criteria input in the server means, and evaluating the degree of achievement.

[1223] The "feedback means" is a mechanism for returning the evaluation results to the teacher terminal means and the student terminal means.

[1224] The "accumulation and learning means" is a mechanism for storing evaluation data over the long term and updating the evaluation model.

[1225] "Customer input text" is text data provided by a customer when using a service.

[1226] "Real-time analysis" is the process of processing data as soon as it is entered.

[1227] The "emotion identification evaluation means" is a device that has the function of recognizing and evaluating emotions from input text.

[1228] "Appropriate feedback" refers to advice and information returned to the user based on the evaluation results and emotional data.

[1229] The present invention is a system that can be effectively used in educational settings and virtual stores. Specific embodiments will be described below.

[1230] 1. System configuration:

[1231] This system includes a teacher terminal means, a student terminal means, a server means, an evaluation means, a feedback means, a storage and learning means, and an evaluation means for emotion recognition. The detailed configuration of each element is as follows:

[1232] 2. Teacher terminal means:

[1233] The teacher terminal means is a device that allows teachers to input lesson goals and evaluation criteria. Specifically, the teacher uses a tablet or PC to input goals and criteria through an interface.

[1234] 3. Student Devices:

[1235] The student terminal means is a device that students use to input answers during class. Students use tablets or PCs to input answers to assignments.

[1236] 4. Server means:

[1237] The server means is a central system that receives data sent from the teacher terminal means and the student terminal means, and performs natural language processing based on the input lesson goals and evaluation criteria.

[1238] 5. Evaluation method:

[1239] The evaluation means is a device that has the function of analyzing the answers of students in the server means and evaluating their achievement. Specifically, it uses a natural language processing model to extract parts of the answers that correspond to the evaluation items and assign a score to each item.

[1240] 6. Feedback methods:

[1241] The feedback means is a mechanism for returning the evaluation results to the teacher terminal means and the student terminal means, allowing students to check their own evaluation results and use them as a guide for their next learning.

[1242] 7. Storage and learning methods:

[1243] The accumulation and learning method is a mechanism for storing evaluation data over the long term and updating the evaluation model, which allows the accuracy of the evaluation model to be continuously improved.

[1244] 8. Customer Emotion Recognition:

[1245] When dealing with customers in a virtual store, the system analyzes the text entered by the customer in real time and has an evaluation method to identify emotions. Specifically, it uses smart glasses to capture the customer's text input, then recognizes their emotions through an emotion engine and provides feedback.

[1246] Hardware and software used:

[1247] Hardware: smart glasses (e.g., Google Glass), servers (for data processing and storage)

[1248] Software: Transformer model library (Hugging Face), emotion engine

[1249] The server analyzes the input text data of the customer in real time and identifies the emotion using the evaluation means, after which appropriate feedback is provided through the feedback means.

[1250] Examples:

[1251] If a customer says in-store, "I think this product is great, but it's too expensive," the emotion engine will analyze this and conclude, "That's a positive sentiment, but there's also dissatisfaction with the price." Staff can then immediately recommend specific discounts to improve customer satisfaction.

[1252] Example prompt sentence:

[1253] "Customer utterances are fed into the following sentiment analysis model to determine real-time sentiment as feedback. Example: 'I love the new features, but the price is too high.'"

[1254] This allows the system to provide more comprehensive and effective evaluation and feedback in both training and customer interactions.

[1255] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1256] Step 1:

[1257] The teacher uses the teacher's terminal means to input lesson goals and evaluation criteria. The input data is sent from the teacher's terminal means to the server means. Specifically, the teacher inputs evaluation items and criteria (e.g., understanding of environmental issues, personal opinions, action proposals).

[1258] Input: Text data of evaluation items and criteria

[1259] Output: Data sent from the teacher's computer to the server

[1260] Step 2:

[1261] Students use the student terminal means to input answers to assignments during class, and the answer data is transmitted from the student terminal means to the server means.

[1262] Input: Text data of student responses

[1263] Output: Data sent from student devices to the server

[1264] Step 3:

[1265] The server means stores the data received from the teacher terminal means and the student terminal means, and stores lesson goals, evaluation criteria, and student response data in a database.

[1266] Input: Data submitted by teachers and students

[1267] Output: Data stored in the database

[1268] Step 4:

[1269] The server uses the evaluation means to perform natural language processing based on the input data and evaluates the level of achievement based on the lesson goals and evaluation criteria. Specifically, it extracts parts of the answer sentence that correspond to the evaluation items and assigns a score to each.

[1270] Input: lesson goals and evaluation criteria, student response data

[1271] Output: Scored evaluation data

[1272] Step 5:

[1273] The server uses an emotion engine to analyze the content of students' responses and recognize their emotions. It identifies emotions such as joy, anger, sadness, and happiness from the text data and generates emotion data.

[1274] Input: Text data of student responses

[1275] Output: Emotion data

[1276] Step 6:

[1277] The server sends the evaluation results and emotion data back to the teacher terminal means and the student terminal means via the feedback means, and the teacher and students can check the evaluation results and emotion evaluations on their terminals.

[1278] Input: scored evaluation data, sentiment data

[1279] Output: Feedback information to teacher and student devices

[1280] Step 7:

[1281] The server uses an accumulation and learning method to store evaluation data and emotion data over the long term and update the evaluation model.

[1282] Input: Rating data and emotion data

[1283] Output: Updated valuation model

[1284] Step 8:

[1285] Smart glasses are used to capture customer input text, which is then sent to the server in real time.

[1286] Input: Customer text data

[1287] Output: Customer data sent to server

[1288] Step 9:

[1289] The server analyzes the customer's input text in real time and identifies emotions using evaluation means. Emotions are recognized through an emotion engine.

[1290] Input: Customer text data

[1291] Output: Identified emotion data

[1292] Step 10:

[1293] The server uses a feedback means to provide appropriate feedback based on the identified emotion, and presents information to customer care staff.

[1294] Input: Identified emotion data

[1295] Output: Feedback information for customer service staff

[1296] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1297] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1298] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1299] [Fourth embodiment]

[1300] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1301] 7, a 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.

[1302] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1303] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1304] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1305] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1306] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1307] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1308] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1309] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1310] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1311] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1312] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1313] The system of the present invention uses an evaluation generation AI to qualitatively evaluate students' thinking ability and independent learning based on goals and evaluation criteria set by teachers during lessons. This system includes teacher terminal means, student terminal means, server means, and evaluation means. Specific embodiments of the system are described below.

[1314] Teacher terminal means

[1315] The user (teacher) inputs the lesson goals and evaluation criteria using the teacher's terminal means. For example, evaluation criteria such as "understanding environmental issues," "own opinions," and "action proposals" are set in advance. This data is sent to the server means via the interface.

[1316] Student terminal means

[1317] Students use the student terminal means to input assignments and comments during class. For example, if student A inputs, "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle," this data is transmitted from the student terminal means to the server means.

[1318] Server Means

[1319] The server means receives data transmitted from the teacher terminal means and the student terminal means, and stores the received data in a database.

[1320] Evaluation methods

[1321] The server incorporates an evaluation system that uses natural language processing to analyze students' responses based on lesson objectives and evaluation criteria, and evaluates their level of achievement. Specifically, the system extracts from the responses parts that correspond to "understanding environmental issues," "personal opinions," and "action proposals," and assigns a score to each part.

[1322] Feedback Methods

[1323] The evaluation results generated by the evaluation means are sent back to the teacher terminal means and the student terminal means via the feedback means. For example, the evaluation results for Student A's answer are displayed on the teacher terminal means and the student terminal means. This feedback information is useful for the teacher when giving the next instruction.

[1324] Accumulation and learning means

[1325] Furthermore, the storage and learning means in the server means stores the evaluation data over the long term and updates the evaluation model, thereby continuously improving the system's evaluation accuracy.

[1326] Specific examples

[1327] As a concrete example, consider the case where a teacher is giving a "lesson on environmental issues." The teacher inputs the lesson's objectives and evaluation criteria (e.g., understanding of environmental issues, personal opinions, action proposals) into the teacher's terminal means. During the lesson, students input their answers to assignments into the student's terminal means, and this data is sent to the server means. The server analyzes the response data and scores the level of achievement for each item based on the evaluation criteria. The evaluation results are fed back to the teacher and students, and the evaluation data is accumulated over the long term and used to train the evaluation model. This makes qualitative evaluation possible, allowing the thinking ability and independent learning of students to be accurately grasped.

[1328] In this way, the present invention provides an effective means for assessing thinking ability and independent learning, and is a solution to overcome the limitations of traditional assessment methods that rely on test scores.

[1329] The processing flow will be explained below.

[1330] Step 1:

[1331] The user (teacher) inputs the lesson goals and evaluation criteria into the teacher's terminal. For example, the user sets evaluation items such as "understanding environmental issues," "personal opinions," and "action proposals."

[1332] Step 2:

[1333] The terminal transmits the input lesson objectives and evaluation criteria to the server means, and the teacher terminal means converts the data into packets via the interface and transfers them to the server via the network.

[1334] Step 3:

[1335] The server receives the lesson objectives and evaluation criteria data and stores them in a database. The database management system within the server ensures data integrity while storing the data.

[1336] Step 4:

[1337] Students use student terminals to input answers to assignments during class. For example, they input sentences such as, "I think we need to learn more about environmental issues. For example, I think we should recycle more."

[1338] Step 5:

[1339] The terminal sends the students' answer data to the server means. The input text data is formatted, organized into packets, and sent to the server via the Internet.

[1340] Step 6:

[1341] The server stores the received student response data in a database, ready to be analyzed by the evaluation means.

[1342] Step 7:

[1343] The server's evaluation tool analyzes students' response data using a natural language processing engine, extracting and categorizing keywords and phrases from the text based on the evaluation criteria.

[1344] Step 8:

[1345] The assessment tool calculates a score for each item according to the lesson objectives and assessment criteria. For example, 10 points are assigned to "understanding environmental issues," 8 points to "your own opinion," and 9 points to "suggestions for action."

[1346] Step 9:

[1347] The server compiles the evaluation results and generates feedback data for each student in JSON format.

[1348] Step 10:

[1349] The server transmits feedback data to the teacher terminal means and the student terminal means, and the transmitted data is displayed on the interface of each terminal.

[1350] Step 11:

[1351] The device displays the evaluation results. The user (teacher) can check the evaluation results and use them to plan the next lesson. Students can also check their own evaluations and reflect on their learning.

[1352] Step 12:

[1353] The server stores the evaluation data in the storage and learning means. By accumulating data over the long term, the accuracy of the evaluation model will be improved in the future.

[1354] Step 13:

[1355] The server's storage and learning means trains the evaluation model. Using the accumulated data, machine learning algorithms are applied to improve evaluation accuracy.

[1356] Example 1

[1357] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1358] In the traditional education system, there was a lack of qualitative methods for evaluating students' thinking ability and independent learning. As a result, teachers had no choice but to rely on test scores, making it difficult to accurately evaluate each student's growth and depth of learning. Furthermore, there was a lack of effective methods for providing feedback on the results of evaluations and using them to improve future instruction.

[1359] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1360] In this invention, the server includes teacher terminal means for inputting lesson goals and evaluation criteria, student terminal means for students to input their answers, server means for receiving data from the teacher terminal means and the student terminal means and storing it in a database, evaluation means for performing natural language processing on the server means based on the lesson goals and evaluation criteria inputted and evaluating the level of achievement, feedback means for feeding back the evaluation results to the teacher terminal means and the student terminal means, storage and learning means for accumulating evaluation data over the long term and learning an evaluation model, technical means for analyzing students' answers using natural language processing and assigning scores to specific evaluation criteria, and display means for displaying the generated evaluation results on the teacher terminal and the student terminal. This makes it possible to qualitatively evaluate students' thinking abilities and independent learning, allowing teachers to provide more effective instruction based on the evaluation results.

[1361] "Teacher terminal means" refers to a device used by a teacher to input lesson objectives and evaluation criteria.

[1362] "Student terminal means" refers to a device used by students during class to input answers to assignments and comments.

[1363] The term "server means" refers to a computer system used to receive data sent from the teacher terminal means and the student terminal means, and to store and process the data.

[1364] "Database" refers to a system located within the server means for storing received data in a structured format.

[1365] "Natural language processing" refers to the technology that enables computers to understand, analyze, and process human language.

[1366] "Evaluation means" refers to a function for analyzing students' responses using natural language processing based on lesson goals and evaluation criteria input into the server means, and evaluating their level of achievement.

[1367] The "feedback means" refers to a function for returning the evaluation results generated by the evaluation means to the teacher terminal means and the student terminal means.

[1368] "Storage and learning means" refers to a system for storing evaluation data over the long term and for learning and updating generative AI models.

[1369] "Technical means" refers to the technical components used to analyze student responses using natural language processing and assign scores against specific assessment criteria.

[1370] "Display means" refers to a function for displaying the generated evaluation results on the teacher terminal and the student terminal.

[1371] The system of the present invention qualitatively evaluates students' thinking ability and independent learning based on goals and evaluation criteria set by educators during lessons. The system includes teacher terminal means, student terminal means, server means, evaluation means, feedback means, storage and learning means, technical means, and display means.

[1372] Teacher terminal means

[1373] The user (teacher) uses the teacher's terminal means to input the lesson's goals and evaluation criteria. Specifically, the teacher starts a dedicated application and inputs the goals and evaluation criteria (e.g., "Understanding environmental issues," "Own opinion," "Proposed action"). Once the input is complete, the teacher clicks the "Send" button to send the setting data to the server means.

[1374] Student terminal means

[1375] Students use student terminal means to input answers to assignments and comments during class. Students start a dedicated application, enter their answers to assignments in an input form, and submit. For example, Student A might enter, "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle." Once the input is complete, the data is sent to the server means.

[1376] Server Means

[1377] The server receives data sent from the teacher terminal means and student terminal means and stores it in a database. The server listens to the data and stores the received data in a structured format in the database. It also sends a data reception confirmation back to each terminal. The received data is analyzed using the evaluation means based on the lesson goals and evaluation criteria.

[1378] Evaluation methods

[1379] The evaluation tool on the server uses natural language processing (NLP) to analyze students' answers based on the evaluation criteria set by the teacher. Specific APIs such as Python's NLTK and SpaCy are used to extract the parts of the answers that correspond to "understanding environmental issues," "personal opinions," and "action proposals," and assign scores to each. For example, the following prompt is input into the generative AI model:

[1380] Example prompt:

[1381] "Analyze the student's response according to the assessment criteria of 'Understanding environmental issues,' 'Own opinions,' and 'Suggested actions,' and rate each one accordingly. For example, here is a response such as, 'I think we need to learn more about environmental issues. For example, I think we should try harder to recycle.'"

[1382] Feedback Methods

[1383] The evaluation results generated by the evaluation means are sent back to the teacher terminal means and the student terminal means via the feedback means. The evaluation results are displayed on each terminal, allowing teachers to use this information for their next instruction and students to check the evaluation of their own learning.

[1384] Accumulation and learning means

[1385] The server's storage and learning means stores the evaluation data over the long term and updates the evaluation model to operate and improve the generative AI model.The model is retrained based on the evaluation data, and the system's evaluation accuracy is continuously improved.

[1386] technical means

[1387] Natural language processing is used to analyze student responses and assign scores against specific assessment criteria, allowing for detailed analysis and accurate assessment of each criterion.

[1388] Display means

[1389] The system includes a display means for displaying the generated evaluation results on the teacher's terminal and the student's terminal. By displaying the evaluation results, the transparency of the evaluation content is increased, and the quality of learning for students can be improved.

[1390] In this way, the system of the present invention provides an effective means for accurately assessing students' thinking ability and independent learning in educational settings, thereby overcoming the limitations of traditional assessment methods that rely on test scores.

[1391] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1392] Step 1:

[1393] The user (teacher) uses the teacher's terminal means to input the lesson's goals and evaluation criteria. Specific inputs include evaluation criteria such as "understanding environmental issues," "personal opinions," and "action proposals." The terminal sends this setting data to the server means.

[1394] Input: Course objectives and assessment criteria

[1395] Output: Sending configuration data to the server

[1396] Specific behavior:

[1397] 1. The teacher launches the dedicated application.

[1398] 2. Enter your goals and evaluation criteria into the application form.

[1399] 3. Once you have completed the input, click the "Submit" button to send the setting data to the server.

[1400] Step 2:

[1401] Students use the student terminal means to input assignments and comments during class. For example, Student A inputs, "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle." The terminal sends this data to the server means.

[1402] Input: Answers to assignments and comments

[1403] Output: Sending response data to the server

[1404] Specific behavior:

[1405] 1. The student launches the dedicated application.

[1406] 2. Enter your answers to the assignment in the application form.

[1407] 3. Once you have completed entering the information, click the "Submit" button to send the response data to the server.

[1408] Step 3:

[1409] The server receives the data transmitted from the teacher terminal means and the student terminal means and stores it in a database, whereby lesson objectives, assessment criteria data, and answer data are stored in a structured format.

[1410] Input: Data sent from the teacher's device and student's device

[1411] Output: Data stored in the database

[1412] Specific behavior:

[1413] 1. The server listens to data sent from teacher and student devices.

[1414] 2. Receive the data and store it in a structured format in a database.

[1415] 3. A confirmation of data receipt is sent back to each terminal.

[1416] Step 4:

[1417] The server's internal evaluation tool uses natural language processing (NLP) to analyze students' responses based on the evaluation criteria set by the teacher. Using APIs such as Python's NLTK and SpaCy, it extracts parts of the responses that correspond to "understanding environmental issues," "personal opinions," and "action suggestions," and assigns a score to each criterion.

[1418] Input: Lesson objectives, assessment criteria, and response data stored in a database

[1419] Output: Scores corresponding to each criterion

[1420] Specific behavior:

[1421] 1. The server retrieves the criteria and response data.

[1422] 2. Perform text analysis using natural language processing tools (NLTK or SpaCy).

[1423] 3. Automatically identify the parts that fall under each evaluation criterion and calculate the corresponding score.

[1424] Step 5:

[1425] The evaluation results generated by the evaluation means are sent back to the teacher terminal means and the student terminal means via the feedback means. The evaluation results are displayed on each terminal, and can be viewed by the users.

[1426] Input: Evaluation results obtained by analysis

[1427] Output: Sending and displaying the evaluation results to the teacher and student devices

[1428] Specific behavior:

[1429] 1. The server generates the evaluation result.

[1430] 2. Send the evaluation results to the teacher and student devices.

[1431] 3. The evaluation results received by each device are displayed on the user interface.

[1432] Step 6:

[1433] The server's storage and learning means stores the evaluation data over the long term and retrains the evaluation model to operate and improve the generative AI model, thereby continuously improving the system's evaluation accuracy.

[1434] Input: Evaluation result data

[1435] Output: A trained evaluation model

[1436] Specific behavior:

[1437] 1. Accumulate evaluation data in a database.

[1438] 2. Retrain the generative AI model based on the evaluation data at regular intervals.

[1439] 3. The retrained model is applied to the system and used for subsequent evaluations.

[1440] (Application example 1)

[1441] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1442] Traditional teacher-student communication and assessment methods lack effective means for qualitatively evaluating students' thinking skills and independent learning. Furthermore, systems for monitoring the safety of elderly people and home security have difficulty immediately detecting abnormal behavior or dangerous situations and providing appropriate feedback. This creates many challenges for educational and home security.

[1443] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1444] In this invention, the server includes an educational terminal means for inputting lesson goals and evaluation criteria, a learning terminal means for students to input their answers, an information processing means for receiving data from the educational terminal means and the learning terminal means, an evaluation means for analyzing and processing the lesson goals and evaluation criteria input to the information processing means to evaluate the level of achievement, a feedback means for feeding back the evaluation results to the educational terminal means and the learning terminal means, a storage and learning means for storing evaluation data over the long term and learning an evaluation model, a sensor means for acquiring monitoring data, an anomaly detection means for detecting abnormal behavior based on the monitoring data, and a warning means for issuing a warning in response to abnormal behavior detected by the anomaly detection means. This makes it possible to accurately evaluate students' thinking abilities and independent learning, and to improve the safety of the elderly and homes.

[1445] "Educational terminal means" refers to a dedicated device or software that allows a teacher to input lesson objectives and evaluation criteria.

[1446] "Learning terminal means" refers to a device or software that allows students to input their answers and assignments.

[1447] The "information processing means" is a system for receiving, storing, and analyzing data from the education terminal means and the learning terminal means.

[1448] "Evaluation tools" are functions that use natural language processing to evaluate students' achievement levels based on the input lesson goals and evaluation criteria.

[1449] The "feedback means" is a system for returning the evaluation results generated by the evaluation means to the education terminal means and the learning terminal means.

[1450] The "accumulation and learning means" is a function that stores evaluation data over the long term and uses the accumulated data to improve the accuracy of the evaluation model.

[1451] "Sensor means" refers to a device for acquiring monitoring data, and may include, for example, a camera or various sensors.

[1452] The "abnormality detection means" is a system for analyzing and detecting abnormal behavior and dangerous situations based on data acquired from the sensor means.

[1453] The "warning means" is a function for issuing a warning to the user in response to abnormal behavior detected by the abnormality detection means.

[1454] MODE FOR CARRYING OUT THE INVENTION

[1455] The present invention is a system that includes an education terminal means, a learning terminal means, an information processing means, an evaluation means, a feedback means, a storage and learning means, a sensor means, an anomaly detection means, and a warning means. Specific embodiments of the system are described below.

[1456] Educational terminal means

[1457] This is a device or software that teachers use to input lesson goals and evaluation criteria. For example, teachers use a tablet or PC to input evaluation criteria such as "understanding environmental issues," "personal opinions," and "suggested actions." This data is sent to a server through an interface.

[1458] Learning terminal means

[1459] This is the device or software that students use to enter their answers and assignments during class. For example, a student might type into their tablet, "I think we need to learn more about environmental issues. For example, I think we should recycle more." This data is sent to a server.

[1460] Information Processing Means

[1461] This system receives, stores, and analyzes data from the education terminal means and learning terminal means. For example, the server stores the input data in a database and passes the data to an evaluation model or anomaly detection model as needed.

[1462] Evaluation methods

[1463] The system runs on a server and analyzes students' responses based on the lesson's goals and assessment criteria. Specifically, it uses natural language processing technology to analyze the responses and assigns scores to "understanding environmental issues," "personal opinions," and "action suggestions."

[1464] Feedback Methods

[1465] The server is used to feed back the evaluation results to the education terminal means and the learning terminal means. For example, the evaluation results for the students' answers are sent from the server to the teacher's tablet and the student's tablet. This allows the teacher to provide appropriate feedback.

[1466] Accumulation and learning means

[1467] This system stores evaluation data over the long term and improves the accuracy of the evaluation model based on the accumulated data. For example, the server periodically learns from the data and updates the evaluation model, enabling more accurate evaluations.

[1468] Sensor Means

[1469] A device that acquires monitoring data. For example, it monitors the situation inside and outside the home using IP cameras and various sensors.

[1470] Anomaly detection means

[1471] This system analyzes and detects abnormal behavior and dangerous situations based on data acquired from sensors. For example, it can detect abnormalities such as when an elderly person collapses or a suspicious person enters a building.

[1472] warning means

[1473] This function alerts users to any abnormal behavior detected by the anomaly detection method. For example, it can immediately notify users of the abnormality by sending a push notification to their smartphone.

[1474] Specific examples

[1475] Scenario 1: A teacher is teaching a lesson about environmental issues.

[1476] Device use: Teachers input lesson goals and assessment criteria into tablets.

[1477] Evaluation process: Students enter their answers into a tablet, and the server analyzes the answers using natural language processing and generates a score.

[1478] Feedback: Evaluation results are fed back to teachers and students to guide further instruction.

[1479] Scenario 2: Monitoring the safety of elderly people.

[1480] Device use: IP cameras and sensors installed inside and outside the home.

[1481] Anomaly detection process: The server analyzes video data to detect falls by elderly people or intrusions by suspicious individuals.

[1482] Warning: When an abnormality is detected, a push notification such as "Fall detected!" or "Intruder detected!" will be sent to your smartphone.

[1483] Prompt Sentence Examples

[1484] "Create an algorithm that detects whether an elderly person is sitting or slumped in their living room."

[1485] "Explain how to train a model to detect if there is an intruder outside your home."

[1486] Thus, the present invention provides a system that is useful for both education and security purposes.

[1487] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1488] Step 1:

[1489] The teacher inputs the lesson goals and evaluation criteria into the educational terminal means. The input data includes "understanding of environmental issues," "personal opinions," "action proposals," etc. This input data is sent to the server.

[1490] Step 2:

[1491] During class, students input their answers and assignments into the learning terminal means. For example, a student might input an answer such as, "I think we need to learn more about environmental issues. For example, I think we should recycle more." This data is also sent to the server.

[1492] Step 3:

[1493] The server receives input data from the education terminal means and the learning terminal means, and stores the data in a database using the information processing means. This stored data is the basis for analysis.

[1494] Step 4:

[1495] The server uses the evaluation tools based on the received data and performs natural language processing based on the lesson goals and evaluation criteria entered. Specifically, it uses a generative AI model to analyze the answers and assign scores to "understanding environmental issues," "personal opinions," and "suggested actions."

[1496] Step 5:

[1497] The analysis results are sent back to the education terminal means and the learning terminal means via the feedback means. For example, the server sends the scores generated by the evaluation means to the terminals of the teacher and students and displays them on the screen.

[1498] Step 6:

[1499] The server processes data over the long term using a storage and learning method, storing the evaluation data over the long term and using this data to train the evaluation model, thereby continuously improving the system's evaluation accuracy.

[1500] Step 7:

[1501] To obtain the monitoring data, the sensor means obtains data from various sensors and IP cameras inside and outside the home, for example, a camera captures video of the living room.

[1502] Step 8:

[1503] The server receives the data sent from the sensor means and uses the anomaly detection means to analyze and detect abnormal behavior or dangerous situations, such as when an elderly person collapses or a suspicious person enters the building.

[1504] Step 9:

[1505] If an abnormality is detected, the server will immediately send alert information to the user's smartphone or device using an alerting method, such as a push notification saying "Fall detected!" or "Intruder detected!"

[1506] By taking these steps, it is possible to build a system that simultaneously improves the accuracy of evaluations in educational settings and strengthens security within the home.

[1507] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1508] The system of the present invention utilizes an evaluation generation AI and an emotion engine to qualitatively evaluate students' thinking ability and independent learning based on goals and evaluation criteria set by teachers during lessons. This system includes teacher terminal means, student terminal means, server means, evaluation means, feedback means, an emotion engine, and storage and learning means. Specific embodiments of the system are described below.

[1509] Teacher terminal means

[1510] The user (teacher) inputs the lesson goals and evaluation criteria using the teacher's terminal means. For example, the user sets evaluation items such as "understanding environmental issues," "personal opinions," and "action proposals." This data is sent to the server means via the interface.

[1511] Student terminal means

[1512] Students use the student terminal means to input answers to assignments during class. For example, if student A inputs "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle," this data is transmitted from the student terminal means to the server means.

[1513] Server Means

[1514] The server means receives data transmitted from the teacher terminal means and the student terminal means, and stores the received data in a database.

[1515] Evaluation methods

[1516] The server incorporates an evaluation system that uses natural language processing to analyze students' responses based on lesson objectives and evaluation criteria, and evaluates their level of achievement. Specifically, the system extracts from the responses parts that correspond to "understanding environmental issues," "personal opinions," and "action proposals," and assigns a score to each part.

[1517] Emotion Engine

[1518] The emotion engine analyzes students' responses and their behavior when entering answers to recognize their emotions. For example, through text analysis, it can identify emotions such as joy, anger, sadness, and happiness contained in the responses. The emotion data recognized by the emotion engine is provided to the evaluation tool and reflected in the achievement evaluation.

[1519] Feedback Methods

[1520] The evaluation results and emotion data generated by the evaluation means and emotion engine are sent back to the teacher terminal means and student terminal means via the feedback means. For example, the evaluation results and emotion evaluations for Student A's answer are displayed on the teacher terminal means and student terminal means. This feedback information is useful for the teacher when providing the next instruction.

[1521] Accumulation and learning means

[1522] Furthermore, the storage and learning means in the server means stores the evaluation data and emotion data over the long term and updates the evaluation model, thereby continuously improving the system's evaluation accuracy.

[1523] Specific examples

[1524] As a concrete example, consider the case where a teacher is giving a "lesson on environmental issues." The teacher inputs the lesson's goals and evaluation criteria (e.g., understanding of environmental issues, personal opinions, action suggestions) into the teacher's terminal means. During the lesson, students input their answers to assignments into the student's terminal means, and the data is sent to the server means. The server analyzes the answer data and scores the level of achievement for each item based on the evaluation criteria. Furthermore, an emotion engine analyzes the answers, recognizes emotions, and provides the results to the evaluation means. The evaluation results and emotion data are fed back to the teacher and students, and the evaluation data and emotion data are accumulated over the long term and used to train the evaluation model. This makes qualitative evaluation possible, allowing the thinking ability and independent learning of students to be accurately captured.

[1525] In this way, the present invention provides an effective means for assessing students' emotional aspects in addition to their thinking ability and independent learning, thereby realizing a more comprehensive educational evaluation.

[1526] The processing flow will be explained below.

[1527] Step 1:

[1528] The user (teacher) inputs the lesson goals and evaluation criteria into the teacher's terminal. For example, the user sets evaluation items such as "understanding environmental issues," "personal opinions," and "action proposals."

[1529] Step 2:

[1530] The terminal transmits the input lesson objectives and evaluation criteria to the server means, and the teacher terminal means converts the data into packets via the interface and transfers them to the server via the network.

[1531] Step 3:

[1532] The server receives the lesson objectives and evaluation criteria data and stores them in a database. The database management system within the server ensures data integrity while storing the data.

[1533] Step 4:

[1534] Students use student terminals to input answers to assignments during class. For example, Student A inputs a sentence such as, "I think we need to learn more about environmental issues. For example, I think we should try harder to recycle."

[1535] Step 5:

[1536] The terminal sends the students' answer data to the server means. The input text data is formatted, organized into packets, and sent to the server via the Internet.

[1537] Step 6:

[1538] The server stores the received student response data in a database, ready to be analyzed by the evaluation tool and emotion engine.

[1539] Step 7:

[1540] The server's emotion engine analyzes students' response data and recognizes emotions from the text content. For example, emotions such as joy, anger, sadness, and happiness are identified based on positive and negative expressions in the text.

[1541] Step 8:

[1542] The server's evaluation means incorporates the emotional data analyzed by the emotion engine into the evaluation, and also uses a natural language processing engine to analyze the response content based on the evaluation criteria. Specifically, it extracts and classifies the parts of the text that correspond to "understanding," "opinion," and "suggestion."

[1543] Step 9:

[1544] The assessment tool calculates a score for each item according to the lesson objectives and assessment criteria. For example, 10 points are assigned to "understanding environmental issues," 8 points to "personal opinions," and 9 points to "action suggestions," and these are adjusted based on emotional data.

[1545] Step 10:

[1546] The server compiles the evaluation results and emotion data and generates feedback data. The evaluation results are generated as JSON format data for each student.

[1547] Step 11:

[1548] The server transmits feedback data to the teacher terminal means and the student terminal means, and the transmitted data is displayed on the interface of each terminal.

[1549] Step 12:

[1550] The device displays the evaluation results and emotional data. The user (teacher) can check the evaluation results and emotional data and use them to plan the next lesson. Students can also check their own evaluations and reflect on their learning.

[1551] Step 13:

[1552] The server stores the evaluation data and emotion data in the storage and learning means. By accumulating data over the long term, the accuracy of the evaluation model will be improved in the future.

[1553] Step 14:

[1554] The server's storage and learning means trains the evaluation model. Using the accumulated data, machine learning algorithms are applied to improve evaluation accuracy.

[1555] Example 2

[1556] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1557] Conventional educational evaluation systems are limited to quantitative assessment of students' thinking ability and independent learning, making it difficult to comprehensively evaluate students' emotional aspects. Furthermore, there is insufficient long-term data accumulation and learning to continuously improve the accuracy of evaluation models. As a result, there is a lack of information that contributes to the reliability of evaluation results and the improvement of teachers' teaching strategies.

[1558] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1559] In this invention, the server includes a data receiving means, an evaluation means, an emotion analysis means, a feedback means, and an accumulation and learning means. This allows for analysis and evaluation of students' answers using natural language processing, and for identifying emotions to provide a comprehensive evaluation. Furthermore, by accumulating evaluation data and emotion data over the long term and continuously learning the evaluation model, the accuracy of the evaluation can be improved.

[1560] "Educator terminal means" means an electronic device used by an educator to input lesson objectives and assessment criteria.

[1561] "Student terminal means" refers to an electronic device used by a student to input answers to assignments during class.

[1562] The "data receiving means" is a device having the function of receiving data transmitted from the teacher terminal means and the student terminal means.

[1563] The "server means" is a central processing unit that includes a data receiving means and has the function of analyzing and storing received data.

[1564] An "assessment tool" is a device or program that performs natural language processing based on the lesson's objectives and evaluation criteria and has the function of evaluating the learner's achievement.

[1565] "Emotion analysis means" refers to a device or program that has the function of analyzing the content of a learner's answers and their behavior when entering answers, and identifying their emotions.

[1566] The "feedback means" is a device or program that has the function of returning the evaluation results and emotion data to the educator terminal means and the learner terminal means.

[1567] "Storage and learning means" refers to a device or program that has the function of storing evaluation data and emotion data over the long term and continuously learning the evaluation model.

[1568] The system of the present invention includes educator terminal means, learner terminal means, server means, evaluation means, emotion analysis means, feedback means, and accumulation and learning means. This system utilizes generative AI and natural language processing technology to evaluate learners' thinking ability and independent learning, and analyze their emotions.

[1569] System configuration

[1570] Educator terminal means

[1571] The user (educator) uses an educator's terminal to input lesson goals and evaluation criteria. This terminal is a personal computer or tablet equipped with a standard web browser, and the user inputs the goals and evaluation criteria through a dedicated interface. For example, the user inputs data such as: "Understanding environmental issues," "Own opinion," and "Proposed actions." The input data is sent to the server via an HTTP request.

[1572] Learner terminal means

[1573] Learners use learner terminals to input answers to assignments during class. These terminals are also personal computers or tablets equipped with a web browser. For example, if Learner A inputs, "I think we need to learn more about environmental issues. For example, I think we should recycle more," this data is sent to the server.

[1574] Server Means

[1575] The server means receives the data sent from the teacher's terminal and the student's terminal and stores it in a database. This server uses database software such as MySQL or PostgreSQL. Based on the received and stored data, the server performs data analysis using the evaluation means.

[1576] Evaluation methods

[1577] The evaluation method within the server analyzes the data using a generative AI model and a natural language processing library (e.g., NLTK or spaCy). Specifically, it extracts the parts of the response that correspond to "understanding environmental issues," "personal opinions," and "action proposals," and assigns a score to each. For example, it assigns a score to each evaluation item for Learner A's response and evaluates the level of achievement.

[1578] Emotion analysis means

[1579] The server uses a sentiment analysis method to analyze the learner's responses and input behavior to identify emotions. This analysis utilizes text analysis tools (e.g., Affectiva and IBM Watson Natural Language Understanding). For example, from the phrase "I need to learn more," it identifies emotions such as "motivation" and "responsibility."

[1580] Feedback Methods

[1581] The results generated by the evaluation means and emotion analysis means are sent back to the teacher's terminal and the student's terminal via the feedback means. For example, the evaluation result for Student A's answer is scored and displayed on the screen. The identified emotion is also displayed.

[1582] Accumulation and learning means

[1583] Evaluation data and emotion data are stored over the long term using a storage and learning method. Based on the stored data, a machine learning algorithm continuously trains the evaluation model. This process is performed periodically as a batch process, contributing to improving the performance of the entire system.

[1584] Specific examples

[1585] For example, if a teacher is giving a lesson on environmental issues, he or she would follow these steps:

[1586] 1. The educator uses the educator terminal to enter the evaluation criteria.

[1587] Examples: "Understanding environmental issues," "Your own opinion," "Proposals for action."

[1588] 2. During class, students enter their answers to the assignments through their student devices.

[1589] Example: Learner A types, "I think I need to learn more about environmental issues. For example, I think we should recycle more."

[1590] 3. The server receives the data and stores it in a database.

[1591] 4. The evaluation instrument analyzes the data and assigns a score to each evaluation item.

[1592] 5. A sentiment analyzer analyzes the responses and identifies the sentiment.

[1593] For example, identify "motivation" and "responsibility."

[1594] 6. The results of the evaluation and sentiment analysis measures are fed back to the teacher's terminal and the student's terminal.

[1595] Prompt Sentence Examples

[1596] Here's an example prompt to input to the generative AI model:

[1597] Example prompt 1: "Analyze Student A's answer, 'I think we need to learn more about environmental issues. For example, I think we should recycle more.'" and evaluate it in terms of 'Understanding of environmental issues,' 'Own opinion,' and 'Suggested actions.'

[1598] Example prompt 2: "Identify the emotion in this passage and rate it as 'happy,' 'anger,' 'sad,' or 'surprise.'"

[1599] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1600] Step 1:

[1601] The user (educator) uses an educator terminal to input lesson goals and evaluation criteria.

[1602] Specific actions: Evaluation items such as "understanding of environmental issues," "own opinion," and "suggested actions" are entered into a dedicated interface displayed in the web browser on the educator's device.

[1603] Input: Course objectives and assessment criteria

[1604] Output: Assessment item data sent to the server

[1605] Step 2:

[1606] The server receives the evaluation item data sent from the teacher's terminal and stores it in a database.

[1607] Specific operation: The server receives the data sent through the HTTP request and uses database software (e.g., MySQL, PostgreSQL) to issue an INSERT statement to the database to store the data.

[1608] Input: Evaluation item data

[1609] Output: Evaluation item data stored in a database

[1610] Step 3:

[1611] The learner uses the learner's terminal to input answers to the assignment.

[1612] Specific actions: Learner A enters "I think we need to learn more about environmental issues. For example, I think we should recycle more" into the input form on the learner's device and clicks the send button.

[1613] Input: Learner's response data

[1614] Output: Learner's response data sent to the server

[1615] Step 4:

[1616] The server receives the response data sent from the learner's terminal and stores it in a database.

[1617] Specific operation: The server receives the data sent through the HTTP request, issues an INSERT statement to the database, and saves it. At the same time, it logs that the receiving process has been completed.

[1618] Input: Learner's response data

[1619] Output: Learner response data stored in a database

[1620] Step 5:

[1621] The server uses the evaluation means to analyze and evaluate the stored data.

[1622] Specific operation: The server analyzes the saved response data using generative AI models and natural language processing libraries (NLTK, spaCy, etc.). It generates prompt sentences and assigns scores to each evaluation item. Example: "Student A's response, 'I think we need to learn more about environmental issues. For example, I think we should recycle more,' is analyzed and evaluated in terms of 'Understanding environmental issues,' 'Own opinion,' and 'Suggested actions.'"

[1623] Input: Learner's response data

[1624] Output: Evaluation result score data

[1625] Step 6:

[1626] The server uses emotion analysis means to analyze the content of the learner's answers and identify their emotions.

[1627] Specific behavior: Use text analysis tools (such as Affectiva or IBM Watson Natural Language Understanding) to identify emotions such as joy, anger, sadness, and happiness contained in the response data using emotion analysis methods. Example: "Identify the emotion contained in this sentence and rate it as 'joy,' 'anger,' 'sadness,' or 'surprise.'"

[1628] Input: Learner's response data

[1629] Output: Sentiment analysis result data

[1630] Step 7:

[1631] The server feeds back the evaluation results and emotion data to the teacher's terminal and the student's terminal.

[1632] Specific operation: Evaluation results and sentiment analysis results are sent in real time using feedback tools and displayed on the screens of the teacher's and learner's devices. Real-time notifications are sent using WebSocket.

[1633] Input: Evaluation results and sentiment analysis results

[1634] Output: Feedback information displayed on teacher and student devices

[1635] Step 8:

[1636] The server stores the rating data and emotion data for a long period of time and updates the rating model.

[1637] Specific operation: Using the accumulation and learning method, the evaluation data and emotion data are stored in a database, and the evaluation model is updated periodically by applying a machine learning algorithm. This is executed periodically as a batch process using a scheduler.

[1638] Input: Evaluation results and sentiment analysis results

[1639] Output: Updated valuation model

[1640] This allows the system to comprehensively evaluate students' thinking abilities and independent learning, and supports teachers' teaching strategies.

[1641] (Application example 2)

[1642] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1643] Traditional education systems lack effective means for qualitatively evaluating students' thinking skills and independent learning. Furthermore, in the field of customer service, there are few systems for real-time emotion recognition and providing appropriate feedback, making it difficult to improve customer satisfaction. These issues are barriers to comprehensive evaluation and improvement of satisfaction in education and customer service.

[1644] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a teacher terminal means for inputting lesson goals and evaluation criteria; a student terminal means for inputting answers by students; a server means for receiving data from the teacher terminal means and the student terminal means; an evaluation means for performing natural language processing based on the lesson goals and evaluation criteria input to the server means and evaluating the level of achievement; a feedback means for feeding back the evaluation results to the teacher terminal means and the student terminal means; a storage and learning means for accumulating evaluation data over the long term and learning an evaluation model; an evaluation means for analyzing customer input text in real time and identifying customer emotions; and a feedback means for providing appropriate feedback based on the identified emotions. This makes it possible to qualitatively evaluate students' thinking abilities and independent learning while recognizing customer emotions in real time and providing appropriate feedback.

[1645] The "teacher terminal means" is a device for inputting lesson goals and evaluation criteria.

[1646] "Student terminal means" refers to a device that allows students to input answers to assignments during class.

[1647] The "server means" is a central system that receives and processes data sent from the teacher terminal means and the student terminal means.

[1648] The "evaluation means" is a device that has the function of performing natural language processing based on the lesson goals and evaluation criteria input in the server means, and evaluating the degree of achievement.

[1649] The "feedback means" is a mechanism for returning the evaluation results to the teacher terminal means and the student terminal means.

[1650] The "accumulation and learning means" is a mechanism for storing evaluation data over the long term and updating the evaluation model.

[1651] "Customer input text" is text data provided by a customer when using a service.

[1652] "Real-time analysis" is the process of processing data as soon as it is entered.

[1653] The "emotion identification evaluation means" is a device that has the function of recognizing and evaluating emotions from input text.

[1654] "Appropriate feedback" refers to advice and information returned to the user based on the evaluation results and emotional data.

[1655] The present invention is a system that can be effectively used in educational settings and virtual stores. Specific embodiments will be described below.

[1656] 1. System configuration:

[1657] This system includes a teacher terminal means, a student terminal means, a server means, an evaluation means, a feedback means, a storage and learning means, and an evaluation means for emotion recognition. The detailed configuration of each element is as follows:

[1658] 2. Teacher terminal means:

[1659] The teacher terminal means is a device that allows teachers to input lesson goals and evaluation criteria. Specifically, the teacher uses a tablet or PC to input goals and criteria through an interface.

[1660] 3. Student Devices:

[1661] The student terminal means is a device that students use to input answers during class. Students use tablets or PCs to input answers to assignments.

[1662] 4. Server means:

[1663] The server means is a central system that receives data sent from the teacher terminal means and the student terminal means, and performs natural language processing based on the input lesson goals and evaluation criteria.

[1664] 5. Evaluation method:

[1665] The evaluation means is a device that has the function of analyzing the answers of students in the server means and evaluating their achievement. Specifically, it uses a natural language processing model to extract parts of the answers that correspond to the evaluation items and assign a score to each item.

[1666] 6. Feedback methods:

[1667] The feedback means is a mechanism for returning the evaluation results to the teacher terminal means and the student terminal means, allowing students to check their own evaluation results and use them as a guide for their next learning.

[1668] 7. Storage and learning methods:

[1669] The accumulation and learning method is a mechanism for storing evaluation data over the long term and updating the evaluation model, which allows the accuracy of the evaluation model to be continuously improved.

[1670] 8. Customer Emotion Recognition:

[1671] When dealing with customers in a virtual store, the system analyzes the text entered by the customer in real time and has an evaluation method to identify emotions. Specifically, it uses smart glasses to capture the customer's text input, then recognizes their emotions through an emotion engine and provides feedback.

[1672] Hardware and software used:

[1673] Hardware: smart glasses (e.g., Google Glass), servers (for data processing and storage)

[1674] Software: Transformer model library (Hugging Face), emotion engine

[1675] The server analyzes the input text data of the customer in real time and identifies the emotion using the evaluation means, after which appropriate feedback is provided through the feedback means.

[1676] Examples:

[1677] If a customer says in-store, "I think this product is great, but it's too expensive," the emotion engine will analyze this and conclude, "That's a positive sentiment, but there's also dissatisfaction with the price." Staff can then immediately recommend specific discounts to improve customer satisfaction.

[1678] Example prompt sentence:

[1679] "Customer utterances are fed into the following sentiment analysis model to determine real-time sentiment as feedback. Example: 'I love the new features, but the price is too high.'"

[1680] This allows the system to provide more comprehensive and effective evaluation and feedback in both training and customer interactions.

[1681] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1682] Step 1:

[1683] The teacher uses the teacher's terminal means to input lesson goals and evaluation criteria. The input data is sent from the teacher's terminal means to the server means. Specifically, the teacher inputs evaluation items and criteria (e.g., understanding of environmental issues, personal opinions, action proposals).

[1684] Input: Text data of evaluation items and criteria

[1685] Output: Data sent from the teacher's computer to the server

[1686] Step 2:

[1687] Students use the student terminal means to input answers to assignments during class, and the answer data is transmitted from the student terminal means to the server means.

[1688] Input: Text data of student responses

[1689] Output: Data sent from student devices to the server

[1690] Step 3:

[1691] The server means stores the data received from the teacher terminal means and the student terminal means, and stores lesson goals, evaluation criteria, and student response data in a database.

[1692] Input: Data submitted by teachers and students

[1693] Output: Data stored in the database

[1694] Step 4:

[1695] The server uses the evaluation means to perform natural language processing based on the input data and evaluates the level of achievement based on the lesson goals and evaluation criteria. Specifically, it extracts parts of the answer sentence that correspond to the evaluation items and assigns a score to each.

[1696] Input: lesson goals and evaluation criteria, student response data

[1697] Output: Scored evaluation data

[1698] Step 5:

[1699] The server uses an emotion engine to analyze the content of students' responses and recognize their emotions. It identifies emotions such as joy, anger, sadness, and happiness from the text data and generates emotion data.

[1700] Input: Text data of student responses

[1701] Output: Emotion data

[1702] Step 6:

[1703] The server sends the evaluation results and emotion data back to the teacher terminal means and the student terminal means via the feedback means, and the teacher and students can check the evaluation results and emotion evaluations on their terminals.

[1704] Input: scored evaluation data, sentiment data

[1705] Output: Feedback information to teacher and student devices

[1706] Step 7:

[1707] The server uses an accumulation and learning method to store evaluation data and emotion data over the long term and update the evaluation model.

[1708] Input: Rating data and emotion data

[1709] Output: Updated valuation model

[1710] Step 8:

[1711] Smart glasses are used to capture customer input text, which is then sent to the server in real time.

[1712] Input: Customer text data

[1713] Output: Customer data sent to server

[1714] Step 9:

[1715] The server analyzes the customer's input text in real time and identifies emotions using evaluation means. Emotions are recognized through an emotion engine.

[1716] Input: Customer text data

[1717] Output: Identified emotion data

[1718] Step 10:

[1719] The server uses a feedback means to provide appropriate feedback based on the identified emotion, and presents information to customer care staff.

[1720] Input: Identified emotion data

[1721] Output: Feedback information for customer service staff

[1722] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1723] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1724] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1725] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1726] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1727] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1728] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1729] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1730] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1731] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1732] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1733] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1734] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1735] 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.

[1736] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1737] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1738] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1739] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1740] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1741] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1742] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1743] The following is further disclosed regarding the above embodiment.

[1744] (Claim 1)

[1745] a teacher terminal means for inputting lesson goals and evaluation criteria;

[1746] a student terminal means for students to input answers;

[1747] a server means for receiving data from the teacher terminal means and the student terminal means;

[1748] evaluation means for performing natural language processing based on the lesson goals and evaluation criteria input in the server means and evaluating the degree of achievement;

[1749] a feedback means for feeding back the evaluation results to the teacher terminal means and the student terminal means;

[1750] A means of accumulating evaluation data over the long term and learning the evaluation model;

[1751] A system including:

[1752] (Claim 2)

[1753] 10. The system of claim 1, further comprising user interface means for inputting lesson goals and evaluation criteria.

[1754] (Claim 3)

[1755] 2. The system according to claim 1, wherein the evaluation means analyzes the answers of the students and evaluates them by assigning a score to each item.

[1756] "Example 1"

[1757] (Claim 1)

[1758] a teacher terminal means for inputting lesson goals and evaluation criteria;

[1759] a student terminal means for students to input answers;

[1760] a server means for receiving data from the teacher terminal means and the student terminal means and storing the data in a database;

[1761] evaluation means for performing natural language processing based on the lesson goals and evaluation criteria input in the server means and evaluating the degree of achievement;

[1762] a feedback means for feeding back the evaluation results to the teacher terminal means and the student terminal means;

[1763] A means of accumulating evaluation data over the long term and learning the evaluation model;

[1764] A technical means for analyzing student responses using natural language processing and assigning scores against specific evaluation criteria;

[1765] a display means for displaying the generated evaluation results on the teacher terminal and the student terminal;

[1766] A system including:

[1767] (Claim 2)

[1768] 10. The system of claim 1, further comprising user interface means for inputting lesson goals and evaluation criteria.

[1769] (Claim 3)

[1770] 2. The system according to claim 1, wherein the evaluation means analyzes the answers of the students and evaluates them by assigning a score to each item.

[1771] "Application Example 1"

[1772] (Claim 1)

[1773] an educational terminal means for inputting lesson goals and evaluation criteria;

[1774] a learning terminal means for students to input answers;

[1775] an information processing means for receiving data from the education terminal means and the learning terminal means;

[1776] evaluation means for performing analysis processing based on the lesson goals and evaluation criteria inputted in the information processing means and evaluating the degree of achievement;

[1777] a feedback means for feeding back the evaluation results to the education terminal means and the learning terminal means;

[1778] A means of accumulating evaluation data over the long term and learning the evaluation model;

[1779] sensor means for acquiring monitoring data;

[1780] an abnormality detection means for detecting abnormal behavior based on the monitoring data;

[1781] a warning means for issuing a warning in response to abnormal behavior detected by the abnormality detection means;

[1782] A system including:

[1783] (Claim 2)

[1784] 10. The system of claim 1, further comprising user interface means for inputting lesson goals and evaluation criteria.

[1785] (Claim 3)

[1786] 2. The system according to claim 1, wherein the evaluation means analyzes the answers of the students and evaluates them by assigning a score to each item.

[1787] (Claim 4)

[1788] 2. The system according to claim 1, wherein when said abnormality detection means detects abnormal behavior of an elderly person or an intruder based on the monitoring data, said alarm means immediately issues an alarm.

[1789] "Example 2: Combining Emotion Engines"

[1790] (Claim 1)

[1791] an educator terminal means for inputting lesson goals and evaluation criteria;

[1792] a learner terminal means for the learner to input answers;

[1793] a server means including a data receiving means for receiving data from the teacher terminal means and the learner terminal means;

[1794] evaluation means for performing natural language processing based on the lesson goals and evaluation criteria input in the server means and evaluating the degree of achievement;

[1795] An emotion analysis means for analyzing the content of the answer and the behavior at the time of input and identifying the emotion;

[1796] a feedback means for feeding back the evaluation result and emotion data to the educator terminal means and the learner terminal means;

[1797] an accumulation and learning means for accumulating evaluation data and emotion data over the long term and learning an evaluation model;

[1798] A system including:

[1799] (Claim 2)

[1800] 10. The system of claim 1, further comprising user interface means for inputting lesson goals and evaluation criteria.

[1801] (Claim 3)

[1802] 2. The system according to claim 1, wherein the evaluation means analyzes the learner's answers and evaluates them by assigning a score to each item.

[1803] "Application example 2 when combining emotion engines"

[1804] (Claim 1)

[1805] a teacher terminal means for inputting lesson goals and evaluation criteria;

[1806] a student terminal means for students to input answers;

[1807] a server means for receiving data from the teacher terminal means and the student terminal means;

[1808] evaluation means for performing natural language processing based on the lesson goals and evaluation criteria input in the server means and evaluating the degree of achievement;

[1809] a feedback means for feeding back the evaluation results to the teacher terminal means and the student terminal means;

[1810] A means of accumulating evaluation data over the long term and learning the evaluation model;

[1811] an evaluation means for analyzing the customer's input text in real time and identifying the customer's sentiment;

[1812] feedback means for providing appropriate feedback based on the identified emotion;

[1813] A system including:

[1814] (Claim 2)

[1815] 10. The system of claim 1 further comprising a user interface means.

[1816] (Claim 3)

[1817] 2. The system according to claim 1, wherein the evaluation means performs evaluation by analyzing the input text of the customer and scoring the emotion. [Explanation of symbols]

[1818] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a teacher terminal means for inputting lesson goals and evaluation criteria; a student terminal means for students to input answers; a server means for receiving data from the teacher terminal means and the student terminal means; evaluation means for performing natural language processing based on the lesson goals and evaluation criteria input in the server means and evaluating the degree of achievement; a feedback means for feeding back the evaluation results to the teacher terminal means and the student terminal means; A means for accumulating evaluation data over the long term and learning the evaluation model; A system including:

2. 10. The system of claim 1, further comprising user interface means for inputting lesson goals and evaluation criteria.

3. 2. The system according to claim 1, wherein the evaluation means analyzes the answers of the students and evaluates them by assigning a score to each item.

Images