system

Abstract

We provide the system. [Solution] A means of inputting educational objectives set by the teacher, Means for collecting student learning data, A method for extracting keywords from collected data and performing text analysis, A means of performing data evaluation using a generative model based on extracted keywords, A means of accumulating evaluation results and performing retraining, Means of providing evaluation results to teachers, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern educational settings, it is required to fairly evaluate students' thinking and expression abilities. However, conventional evaluation methods have the problem that it is difficult to objectively quantify these abilities. In particular, accurately evaluating the content written in notes or essays in a short time places a heavy burden on teachers. Therefore, a more efficient and fair evaluation method is needed.

Means for Solving the Problems

[0005] Note: There seems to be a small error in the original text where <000001³> should probably be . This has been corrected in the translation as much as possible while maintaining the original format.This invention provides a system for analyzing and evaluating student learning data based on educational objectives set by teachers. The system preprocesses collected data, performs keyword extraction and text analysis, and conducts qualitative evaluations using a generative model. The results are stored in a database, and evaluation accuracy is improved through continuous retraining. Furthermore, the evaluation results are provided to teachers, enabling feedback to be given to students as needed. This ensures fair and objective evaluation in educational settings.

[0006] A "teacher" is an educator whose role is to impart knowledge and skills to students.

[0007] "Educational goals" are specific targets for the knowledge and skills that should be achieved through particular learning activities.

[0008] The term "student" refers to a person who belongs to an educational institution and engages in learning activities.

[0009] "Learning data" refers to data that includes records such as notes and reports generated by students during the learning process.

[0010] A "keyword" is a word or phrase that has significant meaning within text data and is used as a criterion for analysis.

[0011] A "generative model" is an algorithm or statistical model that uses machine learning techniques to generate or analyze new data.

[0012] "Data evaluation" is the process of evaluating collected data based on established criteria.

[0013] "Retraining" is the process of updating an algorithm to improve the accuracy of a model using saved evaluation data.

[0014] "Feedback" is the act of providing students with information and advice based on their evaluation results to help them improve their learning. [Brief explanation of the drawing]

[0015] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] The educational evaluation system according to the present invention is designed particularly for the purpose of evaluating students' thinking and expression skills. The system begins with the teacher inputting the educational objectives for the lesson. This allows the teacher to clarify the focus of learning and prepare to evaluate students based on that focus.

[0037] The system collects learning data, such as notes and reports created by students, from their devices and sends it to a central server. The server analyzes the received data and processes the text based on pre-configured keywords.

[0038] Specifically, the server uses natural language processing techniques to cleanse the data and extract important information. Then, a generative model is used to evaluate the data's logical structure and vocabulary selection. The evaluation is based on keyword frequency, sentence logical coherence, and expressiveness.

[0039] The evaluation results are stored in a database, and the model is retrained over time. This improves the accuracy and reliability of the evaluation. Based on the accumulated data, the server can provide more refined results in subsequent evaluations. The evaluation results are provided to the user (teacher) via a terminal, and the teacher uses these results to provide specific feedback to the students.

[0040] For example, if the objective of a class is "understanding environmental issues," the teacher enters specific keywords (e.g., "climate change," "sustainability," etc.) into the system. The system analyzes how and how often these keywords are used in student reports and evaluates how well the logical development aligns with the objective. The evaluation results are communicated to the teacher, who can then use them to provide specific guidance.

[0041] This invention functions as a system that significantly improves the efficiency of individualized instruction in educational settings and fairly evaluates students' abilities.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user (teacher) configures the system to input the lesson objectives and corresponding keywords. This information forms the basis for the subsequent evaluation process.

[0045] Step 2:

[0046] The terminal collects learning data such as notes and reports written by students. The collected data is sent directly to the server.

[0047] Step 3:

[0048] The server begins preparing to analyze the received training data. First, it preprocesses the text data using natural language processing techniques and converts it into structured data.

[0049] Step 4:

[0050] The server extracts and analyzes important information from cleansed data based on pre-configured keywords. This includes keyword frequency analysis and contextual analysis.

[0051] Step 5:

[0052] The server evaluates the extracted information using a generative model. It generates scores for the logical structure of the text, vocabulary diversity, and suitability to the objectives.

[0053] Step 6:

[0054] The server stores the evaluation results in a database, allowing the model to be retrained over time. The evaluation results will be used to further improve the evaluation accuracy in future processes.

[0055] Step 7:

[0056] The terminal receives evaluation results from the server and displays them to the user (teacher). Based on these results, the teacher can provide feedback to students and improve the quality of education.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] In today's educational environment, there is a need to accurately assess the thinking and expression skills of each individual student. However, traditional educational assessment methods make it difficult to conduct efficient and objective evaluations. In particular, when providing individualized support for lessons and assignments, the burden on teachers increases, making it difficult to ensure fairness and reliability in evaluations. A system is needed to solve this problem and improve the quality of education.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes means for inputting educational objectives, means for collecting learning outcomes, and means for extracting specific terms from the collected information and performing information analysis. This makes it possible to efficiently analyze students' learning outcomes and provide objective evaluations.

[0062] "Educational goals" refer to the specific learning outcomes that should be achieved in lessons and learning activities.

[0063] "Learning outcomes" refer to records such as notes and reports that students create based on educational objectives.

[0064] "Means of collection" refers to methods and devices for electronically accumulating learning outcomes and utilizing them as data.

[0065] "Specific terms" refer to keywords that are related to educational goals and play an important role in assessment.

[0066] "Information analysis" refers to the process of processing collected learning outcomes and evaluating the frequency of specific terms and their logical structure.

[0067] A "generated analytical model" refers to a model used for information analysis that applies statistical or machine learning techniques to analyze data based on evaluation criteria.

[0068] "Evaluation results" refer to objective indicators and feedback regarding students' learning outcomes obtained through information analysis.

[0069] "Methods for performing retraining" refer to techniques for improving the analysis model based on past evaluation results and performing evaluations with even higher accuracy.

[0070] This invention is an educational assessment system for evaluating students' thinking and expression skills. Users input educational goals into the system using a terminal. This clarifies the focus of learning and sets evaluation criteria.

[0071] The terminal collects student-created notes, reports, and other learning outcomes in digital format and sends them to the server. To ensure data security, the data is encrypted before transmission.

[0072] The server analyzes the received learning results using natural language processing techniques. Specifically, it uses libraries such as Python's NLTK and Spacy to cleanse the data and extract important specific terms.

[0073] Furthermore, the server uses the generated analysis model to evaluate the logical structure and vocabulary selection of the data. This process employs methods such as BERT, which is based on the Transformer model, to analyze the frequency of use of specific terms and the coherence of sentences.

[0074] The evaluation results are stored in a database, and the server retrains itself to improve the accuracy of the evaluation. This increases the accuracy of the analysis model over time, allowing it to provide more refined results in subsequent evaluations.

[0075] The evaluation results are provided to the user (teacher) via the terminal. Based on these results, the teacher can provide specific feedback to the students. For example, if the learning objective for a class is "understanding environmental issues," the teacher can input specific terms such as "climate change" or "sustainability" into the system as prompts. The server analyzes the learning outcomes based on these prompts and provides evaluation results, allowing the teacher to give specific guidance such as "Let's further deepen the discussion on sustainability."

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

[0077] Step 1:

[0078] The user inputs educational goals using a terminal. The system then generates criteria based on these goals. The input is in string format, for example, a theme such as "Understanding Environmental Issues." The output is the educational goals stored in a database.

[0079] Step 2:

[0080] The terminal collects learning outcomes such as notes and reports created by students. These are input as text data. The terminal organizes the collected data into a structured format and sends it to the server as output.

[0081] Step 3:

[0082] The server receives data sent from the terminal. Natural language processing techniques are used to analyze the input text data, first using NLTK or Spacy to cleanse the text. This reduces noise and extracts specific terms. The output is the cleaned data.

[0083] Step 4:

[0084] The server evaluates the data by applying an analytical model generated based on the cleansed data. Here, a generative AI model such as BERT is used to analyze the frequency of specific terms and the logical structure of sentences. The input is cleansed data, and the output is the evaluation results.

[0085] Step 5:

[0086] The server saves the evaluation results to a database and uses them as data to retrain the model. This improves the accuracy of subsequent data evaluations. The input consists of the evaluation results and historical data, and the output is an updated evaluation model that has been retrained.

[0087] Step 6:

[0088] The server generates evaluation results and provides them to the user via the terminal. The evaluation results are provided as input and converted into a visually easy-to-understand format on the terminal. The output is an evaluation report that the user can review.

[0089] Step 7:

[0090] Users provide specific feedback to students based on evaluation reports displayed on their devices. The content of the feedback is customized according to the evaluation results. The output consists of specific instructional content that is directly communicated to the students.

[0091] (Application Example 1)

[0092] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] In today's educational settings, efficiently evaluating individual learners' thinking and expression skills and conducting real-time analysis of their comprehension is challenging. In particular, there is a need for immediate feedback on learners' understanding when they view educational content containing complex concepts. Without addressing this challenge, improving the quality of instruction and providing individualized support to learners will be difficult.

[0094] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0095] In this invention, the server includes means for inputting learning objectives set by the educator, means for collecting learner learning data, and means for extracting concepts from the collected data and performing character data analysis. This makes it possible to evaluate learning progress in real time and provide learners with quick and appropriate feedback.

[0096] "Educational objectives" refer to the standards of knowledge and skills that learners should achieve regarding specific tasks or units.

[0097] A "learner" refers to an individual or group that seeks to acquire knowledge or skills by using educational content.

[0098] "Educational data" refers to a collection of data that includes information obtained from notes and reports created by learners, as well as from learning management systems.

[0099] A "concept" refers to important information or keywords related to a specific educational objective.

[0100] "Text data analysis" refers to the process of analyzing text data, understanding its content, and classifying it.

[0101] A "generative model" is an artificial intelligence model that generates new information based on input data.

[0102] "Real-time" refers to processing with very short delays, almost simultaneously.

[0103] "Comprehension level" is an indicator that shows how deeply learners understand the educational objectives and content.

[0104] "Feedback" refers to the act of providing learners with areas for improvement and additional learning guidance based on evaluation results and learning progress.

[0105] In this invention, a server, terminals, and users each play their respective roles in implementing an educational evaluation system. The server first receives learning objectives set by the educator and registers keywords related to those learning objectives in a database. Then, it collects educational data such as notes and reports provided by learners from the terminals and transmits it to the central server. The server then processes the text data and performs character data analysis using natural language processing technology.

[0106] The server extracts concepts from the collected text data and then evaluates that data using a generative AI model. The evaluation is based on keyword frequency, the logical consistency of the text, and its expressiveness. The evaluation results are stored in a database, and the server improves the accuracy and reliability of the evaluation by retraining the model over time. More refined evaluation results will be provided in subsequent evaluations.

[0107] The user, i.e., the educator, receives the evaluation results via a terminal and provides specific feedback to the learner based on them. Specifically, the server can evaluate the learner's understanding of the audio or video content they are viewing in real time and notify the user of the indicators of their level of understanding.

[0108] As a concrete example of its use, suppose a learner is watching an online lecture on the topic of "sustainable urban design." In this scenario, the server extracts keywords from the lecture content in real time and evaluates how much they contribute to achieving the learning objectives. An example of a prompt to input into the generative AI model would be, "Please input the speech-recognized lecture text and summarize the knowledge about sustainability."

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

[0110] Step 1:

[0111] The server first receives educational objectives provided by educators as input data. Based on this, it identifies relevant keywords and registers them in the database. In this process, key concepts related to the educational objectives are listed as keywords, which form the basis for subsequent analysis.

[0112] Step 2:

[0113] The device collects educational data from learners. This educational data includes notes, reports, audio, or video. The collected data is converted into a digital format and sent to a server. This makes the structured data available for processing on the server.

[0114] Step 3:

[0115] The server performs textual analysis on the received educational data. Specifically, it cleanses the data using natural language processing techniques and extracts concepts based on registered keywords. The input is educational data, and the output is the extracted concepts and their frequency of use. Unnecessary parts are removed from the data, and parts useful for analysis are highlighted.

[0116] Step 4:

[0117] The server uses a generative AI model to evaluate the extracted concepts. This model assesses the logical consistency and expressiveness of the text and determines the learner's level of understanding. The input is conceptual data, and the output is an evaluation score. In this step, data calculations are performed based on the evaluation criteria, and the results are shown numerically.

[0118] Step 5:

[0119] The server stores the evaluation results in a database and retrains the model. This improves the accuracy of the evaluation model, leading to better evaluations in the next session. The input is the evaluation score, and the output is the updated evaluation model. The accumulated information is used to enable the model to handle new data.

[0120] Step 6:

[0121] The server provides the evaluation results to the user. The user receives this information via their terminal and provides feedback to the learner. The input is the evaluation result, and the output is the feedback content. This process allows educators to set appropriate teaching strategies.

[0122] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0123] This invention is a system that enables more comprehensive learning assessment by adding an emotion recognition function to the evaluation of students' thinking and expression skills in educational settings. This system aims to improve the quality of education by considering students' emotional responses in addition to conventional evaluation processes.

[0124] First, the user (teacher) inputs the lesson's educational objectives and keywords they want to evaluate into the system. This clarifies the learning indicators and sets evaluation criteria.

[0125] Next, the terminal collects notes and reports written by students. This data reflects the results of their learning activities and is sent to the server.

[0126] Upon receiving transmitted data, the server first preprocesses the data using natural language processing to extract necessary information. Then, it uses an evaluation model based on pre-configured keywords to assess the logical structure and vocabulary diversity.

[0127] In addition, the emotion engine recognizes students' emotions from text and related comments within the data and generates an emotion score. The emotion score evaluates students' motivation and stress levels, and complements their understanding of educational objectives.

[0128] These analysis results are aggregated by the server and stored in a database as evaluation results. The evaluation results are then provided to the user (teacher) via a terminal, allowing the teacher to use this information to provide feedback on the student's learning process.

[0129] For example, if a teacher sets the goal of "writing a paper on environmental issues without feeling stressed," the system analyzes how the teacher's keywords (e.g., "environment," "sustainability") are used in the student's notes and reports, while simultaneously evaluating the emotions expressed in the writing. The emotion score generated by the emotion engine then allows the system to recognize the student's level of stress, enabling the teacher to provide more individualized guidance and support.

[0130] Thus, this system enables multidimensional assessment in real time, making it a powerful tool for educators to gain a deeper understanding of and support for learning.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The user (teacher) sets up the system by entering the lesson's educational objectives and the keywords they want to evaluate. This clarifies the criteria for learning assessment.

[0134] Step 2:

[0135] The terminal collects notes and reports written by students and prepares them to be sent to the server. The collected data includes text information and, in some cases, metadata such as comments.

[0136] Step 3:

[0137] The server preprocesses the received data. Specifically, it uses natural language processing techniques to clean up the text data and performs syntactic analysis to extract important keywords and phrases.

[0138] Step 4:

[0139] The server uses a sentiment engine to recognize emotions within the text. This includes identifying the emotions expressed by the entire text and emotions associated with specific keywords. It generates a sentiment score, evaluating the degree to which positive or negative emotions are expressed.

[0140] Step 5:

[0141] The server uses a generative model to evaluate the relevance of pre-processed data to educational objectives. This is done by considering the logical structure of the text, vocabulary diversity, and the degree of relevance to the set objectives.

[0142] Step 6:

[0143] The server integrates the sentiment score and the evaluation results from the generative model to perform a comprehensive learning assessment. The results are stored in a database.

[0144] Step 7:

[0145] The terminal receives evaluation results from the server and displays them to the user (teacher). Based on this, the teacher can provide feedback on the student's learning process and adjust instruction as needed.

[0146] (Example 2)

[0147] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0148] Conventional educational assessment systems only evaluate learners' logical abilities and knowledge levels, failing to consider emotional aspects. This makes it difficult to understand learners' motivation and stress levels in detail, hindering individualized educational guidance. This invention aims to solve the problem of achieving comprehensive learning assessment that also considers learners' emotional states, thereby enabling more flexible and effective educational guidance.

[0149] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0150] In this invention, the server includes means for inputting educational objectives, means for collecting learning data, and means for identifying emotions within the learning data and generating an emotion score using an emotion recognition engine. This enables detailed feedback that takes into account not only the learner's knowledge but also their emotional state.

[0151] "Educational goals" are indicators of the knowledge and skills that educators expect learners to achieve.

[0152] "Learning data" refers to written and other forms of information generated by students through classes and other learning activities.

[0153] "Keywords" are words or phrases that are particularly important for evaluation and searching, and they play a role in highlighting specific themes or content in the analysis of texts and data.

[0154] A "generative model" is an algorithm that generates new information based on pre-trained data and evaluates its content.

[0155] An "emotion recognition engine" is a technology used to analyze and identify emotions from text and audio data, and is a system used to generate an emotion score.

[0156] "Evaluation results" refer to judgments about learners' performance derived from generative models and emotion recognition based on educational objectives and keywords.

[0157] "Means of storing in a database" refers to a system that efficiently stores evaluation results and other important information, making it available for retrieval as needed.

[0158] "Feedback" refers to the points and areas for improvement that educators provide to learners, and is information used to appropriately adjust the direction of learning.

[0159] To build a comprehensive evaluation system for educational settings, users (teachers) first input educational objectives and keywords necessary for evaluation into the system. This step clarifies the learning guidelines. The keywords to be used are important terms related to the lesson's theme. For example, in a lesson on environmental issues, keywords would include "environment" and "sustainability."

[0160] Next, the terminal collects notes and reports created by students. This data is stored digitally and transmitted to a server via the network. During this process, the collected data is encrypted and kept secure, ensuring security.

[0161] The server performs natural language processing on the received data. Using tools such as spaCy, the data is tokenized, tagged with parts of speech, and stop words are removed to prepare it for analysis. This pre-processed data is then fed into a generative model, where its logical structure and vocabulary diversity are evaluated based on keywords.

[0162] Furthermore, analysis for emotion recognition is also performed. The server uses an emotion recognition engine, leveraging technologies such as IBM Watson® Natural Language Understanding, to extract emotions from the text and generate an emotion score. This result reflects the motivation and stress that students felt while writing.

[0163] The analyzed evaluation results are stored in a database and used for re-evaluation and improvement as needed. The evaluation results are then presented to the user (teacher) via a terminal, allowing the teacher to provide feedback to students based on that information. This enables adjustments to specific teaching content and enhances learning effectiveness.

[0164] As a concrete example, in relation to the teacher's set goal of "writing an environmental paper without feeling stressed," the system checks the use of the teacher's set keywords, "environment" and "sustainability." A prompt example might be, "Analyze the following text and generate a sentiment score. The keywords are 'environment' and 'sustainability'." This allows for a detailed understanding of how the student's work aligns with the goal. In this way, multifaceted evaluation is achieved, enabling deeper learning support.

[0165] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0166] Step 1:

[0167] The user (teacher) enters educational objectives and keywords. This generates input data for the system to set evaluation criteria. The entered information is sent to the server and stored in the database as a guide for evaluation.

[0168] Step 2:

[0169] The terminal collects students' learning output, such as notes and reports. This data is either scanned on the terminal or uploaded as digital data. The terminal then sends the collected data to a server. The output from this server is the raw data necessary for evaluation.

[0170] Step 3:

[0171] The server preprocesses the received data. Here, natural language processing tools are used to tokenize the data, tag it with parts of speech, and remove stop words. The input is raw data from students, and the output is processed text data suitable for analysis.

[0172] Step 4:

[0173] The server uses a generative AI model to evaluate preprocessed data. Specifically, it analyzes the logical structure and vocabulary diversity of the text based on keywords that have already been input. The input to this process is processed data, and the output is the evaluation result.

[0174] Step 5:

[0175] The server uses an emotion recognition engine to identify emotions from the same processed data and generate emotion scores. The input is student text data, and the output is a score representing the emotional state.

[0176] Step 6:

[0177] The server stores the analyzed evaluation results and sentiment scores in a database. This is a step that aggregates data from the entire evaluation process, with the input being evaluation data and sentiment scores, and the output being the stored database entries.

[0178] Step 7:

[0179] The server provides evaluation results to the user (teacher) via the terminal. The teacher can then refer to this data and provide feedback to the students. The input to this process is the evaluation results stored in the database, and the output is the presented evaluation information.

[0180] (Application Example 2)

[0181] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0182] Traditional customer service practices face challenges in evaluating staff customer service skills and the quality of their interactions with customers, as these evaluations are subjective and difficult to implement using standardized, objective criteria. Furthermore, analyzing staff emotional responses during customer interactions is difficult, resulting in a lack of concrete feedback for improving customer service. This can potentially delay improvements in staff capabilities and overall service quality.

[0183] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0184] In this invention, the server includes means for setting goals, means for collecting learning-related information, means for acquiring voice information in real time and performing text conversion, and means for analyzing the converted text information and performing emotion recognition. This makes it possible to evaluate staff's customer service skills using objective and standardized criteria and to provide specific feedback to individual staff members.

[0185] A "goal" is a specific objective or indicator to be achieved that is set as a criterion for evaluation.

[0186] "Means" refer to the methods or mechanisms used to achieve a specific objective.

[0187] "Learning-related information" refers to data and records related to the activities and results being evaluated.

[0188] "Acquiring audio information in real time and performing text conversion" refers to the process of instantly converting audio data into text information.

[0189] "Analyzing textual information and performing sentiment recognition" refers to the process of identifying emotional tendencies from textual data and scoring them as evaluation metrics.

[0190] A "server" is a computer system used for data processing and analysis, and for storing and managing the results.

[0191] A "standardized standard" is a unified evaluation index that can be applied to a variety of situations.

[0192] "Staff" refers to employees whose role is to provide a service.

[0193] "Objective" means being based on facts and not influenced by personal feelings or opinions.

[0194] "Feedback" refers to improvement suggestions and advice provided based on evaluation results.

[0195] The system that realizes this invention is intended for the evaluation and feedback of staff performance in customer service. The main components are a server, smart glasses, and a management terminal.

[0196] The server plays a central role in data processing and aggregating evaluation results. Smart glasses are effectively utilized to acquire audio information in real time, and this acquired audio information is converted into text. Devices such as Google® Glass® or Vuzix Blade can be used for this purpose.

[0197] Smart glasses are devices worn by staff during daily customer service duties, instantly converting collected audio information into text data. This converted text data is then sent to a server for detailed analysis using natural language processing tools. For example, SpaCy and Google Cloud Natural Language API are used to analyze the information and provide a detailed evaluation of staff speech and customer interactions.

[0198] Next, an emotion recognition engine on the server analyzes the text information and evaluates the staff's emotional state. Using tools such as IBM Watson Tone Analyzer, it generates an emotion score, which is used to measure the staff's stress and motivation levels.

[0199] The evaluation results are provided to the management terminal and are accessible to the store manager, who is the user. The manager can use this feedback to provide specific guidance for improvement to individual staff members.

[0200] For example, in a scenario where a staff member is asked to "briefly describe the features of this product," the prompt would be: "Briefly describe the features of the product you recommend to the customer, and consider how to attract the customer's interest. For example, use specific language such as, 'This laptop is high-performance and currently on sale.'" This would then be evaluated and feedback would be provided.

[0201] In this way, the system contributes to improving the quality of customer service and developing staff.

[0202] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0203] Step 1:

[0204] The system collects audio information from the user while they are wearing smart glasses and interacting with customers. This audio information becomes the input data for the system.

[0205] Step 2:

[0206] The device converts collected audio information into text information in real time. This process utilizes speech recognition technology to convert audio data into text data. The output is text information.

[0207] Step 3:

[0208] The server receives text data and performs detailed analysis using natural language processing tools. Specifically, it uses SpaCy to analyze the structure of the text and extract relevant keywords. The input to this process is text data, and the output is the analyzed data.

[0209] Step 4:

[0210] The server uses an emotion recognition engine based on analyzed data to evaluate the emotions contained in the text data. IBM Watson Tone Analyzer is used to generate emotion scores, quantifying the emotional state of the staff. The input is the analyzed data, and the output is the emotion evaluation result.

[0211] Step 5:

[0212] The server integrates the sentiment evaluation results and text analysis results to generate integrated evaluation data. This data represents an overall evaluation of the staff's customer service abilities.

[0213] Step 6:

[0214] The terminal sends integrated evaluation data to the management terminal, which receives this information. The administrator uses the integrated evaluation data to provide specific feedback to staff. The output is specific guidance content for staff.

[0215] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0216] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0217] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0218] [Second Embodiment]

[0219] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0220] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0221] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0222] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0223] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0224] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0225] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0226] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0227] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0228] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0229] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0230] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0231] The educational evaluation system according to the present invention is designed particularly for the purpose of evaluating students' thinking and expression skills. The system begins with the teacher inputting the educational objectives for the lesson. This allows the teacher to clarify the focus of learning and prepare to evaluate students based on that focus.

[0232] The system collects learning data, such as notes and reports created by students, from their devices and sends it to a central server. The server analyzes the received data and processes the text based on pre-configured keywords.

[0233] Specifically, the server uses natural language processing techniques to cleanse the data and extract important information. Then, a generative model is used to evaluate the data's logical structure and vocabulary selection. The evaluation is based on keyword frequency, sentence logical coherence, and expressiveness.

[0234] The evaluation results are stored in a database, and the model is retrained over time. This improves the accuracy and reliability of the evaluation. Based on the accumulated data, the server can provide more refined results in subsequent evaluations. The evaluation results are provided to the user (teacher) via a terminal, and the teacher uses these results to provide specific feedback to the students.

[0235] For example, if the objective of a class is "understanding environmental issues," the teacher enters specific keywords (e.g., "climate change," "sustainability," etc.) into the system. The system analyzes how and how often these keywords are used in student reports and evaluates how well the logical development aligns with the objective. The evaluation results are communicated to the teacher, who can then use them to provide specific guidance.

[0236] This invention functions as a system that significantly improves the efficiency of individualized instruction in educational settings and fairly evaluates students' abilities.

[0237] The following describes the processing flow.

[0238] Step 1:

[0239] The user (teacher) configures the system to input the lesson objectives and corresponding keywords. This information forms the basis for the subsequent evaluation process.

[0240] Step 2:

[0241] The terminal collects learning data such as notes and reports written by students. The collected data is sent directly to the server.

[0242] Step 3:

[0243] The server begins preparing to analyze the received training data. First, it preprocesses the text data using natural language processing techniques and converts it into structured data.

[0244] Step 4:

[0245] The server extracts and analyzes important information from cleansed data based on pre-configured keywords. This includes keyword frequency analysis and contextual analysis.

[0246] Step 5:

[0247] The server evaluates the extracted information using a generative model. It generates scores for the logical structure of the text, vocabulary diversity, and suitability to the objectives.

[0248] Step 6:

[0249] The server stores the evaluation results in a database, allowing the model to be retrained over time. The evaluation results will be used to further improve the evaluation accuracy in future processes.

[0250] Step 7:

[0251] The terminal receives evaluation results from the server and displays them to the user (teacher). Based on these results, the teacher can provide feedback to students and improve the quality of education.

[0252] (Example 1)

[0253] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0254] In today's educational environment, there is a need to accurately assess the thinking and expression skills of each individual student. However, traditional educational assessment methods make it difficult to conduct efficient and objective evaluations. In particular, when providing individualized support for lessons and assignments, the burden on teachers increases, making it difficult to ensure fairness and reliability in evaluations. A system is needed to solve this problem and improve the quality of education.

[0255] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0256] In this invention, the server includes means for inputting educational objectives, means for collecting learning outcomes, and means for extracting specific terms from the collected information and performing information analysis. This makes it possible to efficiently analyze students' learning outcomes and provide objective evaluations.

[0257] "Educational goals" refer to the specific learning outcomes that should be achieved in lessons and learning activities.

[0258] "Learning outcomes" refer to records such as notes and reports that students create based on educational objectives.

[0259] "Means of collection" refers to methods and devices for electronically accumulating learning outcomes and utilizing them as data.

[0260] "Specific terms" refer to keywords that are related to educational goals and play an important role in assessment.

[0261] "Information analysis" refers to the process of processing collected learning outcomes and evaluating the frequency of specific terms and their logical structure.

[0262] A "generated analytical model" refers to a model used for information analysis that applies statistical or machine learning techniques to analyze data based on evaluation criteria.

[0263] "Evaluation results" refer to objective indicators and feedback regarding students' learning outcomes obtained through information analysis.

[0264] "Methods for performing retraining" refer to techniques for improving the analysis model based on past evaluation results and performing evaluations with even higher accuracy.

[0265] This invention is an educational assessment system for evaluating students' thinking and expression skills. Users input educational goals into the system using a terminal. This clarifies the focus of learning and sets evaluation criteria.

[0266] The terminal collects student-created notes, reports, and other learning outcomes in digital format and sends them to the server. To ensure data security, the data is encrypted before transmission.

[0267] The server analyzes the received learning results using natural language processing techniques. Specifically, it uses libraries such as Python's NLTK and Spacy to cleanse the data and extract important specific terms.

[0268] Furthermore, the server uses the generated analysis model to evaluate the logical structure and vocabulary selection of the data. This process employs methods such as BERT, which is based on the Transformer model, to analyze the frequency of use of specific terms and the coherence of sentences.

[0269] The evaluation results are stored in a database, and the server retrains itself to improve the accuracy of the evaluation. This increases the accuracy of the analysis model over time, allowing it to provide more refined results in subsequent evaluations.

[0270] The evaluation results are provided to the user (teacher) via the terminal. Based on these results, the teacher can provide specific feedback to the students. For example, if the learning objective for a class is "understanding environmental issues," the teacher can input specific terms such as "climate change" or "sustainability" into the system as prompts. The server analyzes the learning outcomes based on these prompts and provides evaluation results, allowing the teacher to give specific guidance such as "Let's further deepen the discussion on sustainability."

[0271] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0272] Step 1:

[0273] The user inputs educational goals using a terminal. The system then generates criteria based on these goals. The input is in string format, for example, a theme such as "Understanding Environmental Issues." The output is the educational goals stored in a database.

[0274] Step 2:

[0275] The terminal collects learning outcomes such as notes and reports created by students. These are input as text data. The terminal organizes the collected data into a structured format and sends it to the server as output.

[0276] Step 3:

[0277] The server receives data sent from the terminal. Natural language processing techniques are used to analyze the input text data, first using NLTK or Spacy to cleanse the text. This reduces noise and extracts specific terms. The output is the cleaned data.

[0278] Step 4:

[0279] The server applies an analysis model generated based on the cleansed data to evaluate the data. Here, a generative AI model such as BERT is used to analyze the frequency of specific terms and the logical structure of sentences. The input is the cleansed data, and the output is the evaluation result.

[0280] Step 5:

[0281] The server saves the evaluation result in the database and utilizes it as data for model re-training. This improves the accuracy of the next data evaluation. The input includes the evaluation result and past data, and the output is an evaluation model updated through re-training.

[0282] Step 6:

[0283] The server provides the evaluation result generated to the user via the terminal. The evaluation result is prepared as the input and is converted into a visually understandable format on the terminal. The output is an evaluation report that the user can view.

[0284] Step 7:

[0285] The user provides specific feedback to the students based on the evaluation report on the terminal. The content of the feedback is customized according to the evaluation result. The output is the specific guidance content directly conveyed to the students.

[0286] (Application Example 1)

[0287] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0288] In today's educational settings, efficiently evaluating individual learners' thinking and expression skills and conducting real-time analysis of their comprehension is challenging. In particular, there is a need for immediate feedback on learners' understanding when they view educational content containing complex concepts. Without addressing this challenge, improving the quality of instruction and providing individualized support to learners will be difficult.

[0289] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0290] In this invention, the server includes means for inputting learning objectives set by the educator, means for collecting learner learning data, and means for extracting concepts from the collected data and performing character data analysis. This makes it possible to evaluate learning progress in real time and provide learners with quick and appropriate feedback.

[0291] "Educational objectives" refer to the standards of knowledge and skills that learners should achieve regarding specific tasks or units.

[0292] A "learner" refers to an individual or group that seeks to acquire knowledge or skills by using educational content.

[0293] "Educational data" refers to a collection of data that includes information obtained from notes and reports created by learners, as well as from learning management systems.

[0294] A "concept" refers to important information or keywords related to a specific educational objective.

[0295] "Text data analysis" refers to the process of analyzing text data, understanding its content, and classifying it.

[0296] A "generative model" is an artificial intelligence model that generates new information based on input data.

[0297] "Real-time" refers to processing with very short delays, almost simultaneously.

[0298] "Comprehension level" is an indicator that shows how deeply learners understand the educational objectives and content.

[0299] "Feedback" refers to the act of providing learners with areas for improvement and additional learning guidance based on evaluation results and learning progress.

[0300] In this invention, a server, terminals, and users each play their respective roles in implementing an educational evaluation system. The server first receives learning objectives set by the educator and registers keywords related to those learning objectives in a database. Then, it collects educational data such as notes and reports provided by learners from the terminals and transmits it to the central server. The server then processes the text data and performs character data analysis using natural language processing technology.

[0301] The server extracts concepts from the collected text data and then evaluates that data using a generative AI model. The evaluation is based on keyword frequency, the logical consistency of the text, and its expressiveness. The evaluation results are stored in a database, and the server improves the accuracy and reliability of the evaluation by retraining the model over time. More refined evaluation results will be provided in subsequent evaluations.

[0302] The user, i.e., the educator, receives the evaluation results via a terminal and provides specific feedback to the learner based on them. Specifically, the server can evaluate the learner's understanding of the audio or video content they are viewing in real time and notify the user of the indicators of their level of understanding.

[0303] As a specific example of use, assume that a learner is watching an online lecture on the theme of "sustainable urban design". At this time, the server extracts keywords in real time from the lecture content and evaluates how much it contributes to achieving the learning goals. An example of a prompt sentence to be input into the generative AI model is "Input the text of the lecture recognized by voice and summarize the knowledge related to sustainability."

[0304] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0305] Step 1:

[0306] The server first receives the educational goals provided by the educator as input data. Based on this, relevant keywords are identified and registered in the database. In this process, the main concepts related to the educational goals are listed as keywords, which serve as the basis for subsequent analysis.

[0307] Step 2:

[0308] The terminal collects educational data from the learner. This educational data includes notes, reports, voice or video. The collected data is converted into a digital format and sent to the server. As a result, structured data becomes available for processing on the server.

[0309] Step 3:

[0310] The server performs character data analysis on the received educational data. Specifically, natural language processing technology is used to cleanse the data and extract concepts based on the registered keywords. The input is the educational data, and the output is the extracted concepts and their frequencies of use. Unnecessary parts are removed from the data, and useful parts for analysis are emphasized.

[0311] Step 4:

[0312] The server uses a generative AI model to evaluate the extracted concepts. This model assesses the logical consistency and expressiveness of the text and determines the learner's level of understanding. The input is conceptual data, and the output is an evaluation score. In this step, data calculations are performed based on the evaluation criteria, and the results are shown numerically.

[0313] Step 5:

[0314] The server stores the evaluation results in a database and retrains the model. This improves the accuracy of the evaluation model, leading to better evaluations in the next session. The input is the evaluation score, and the output is the updated evaluation model. The accumulated information is used to enable the model to handle new data.

[0315] Step 6:

[0316] The server provides the evaluation results to the user. The user receives this information via their terminal and provides feedback to the learner. The input is the evaluation result, and the output is the feedback content. This process allows educators to set appropriate teaching strategies.

[0317] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0318] This invention is a system that enables more comprehensive learning assessment by adding an emotion recognition function to the evaluation of students' thinking and expression skills in educational settings. This system aims to improve the quality of education by considering students' emotional responses in addition to conventional evaluation processes.

[0319] First, the user (teacher) inputs the lesson's educational objectives and keywords they want to evaluate into the system. This clarifies the learning indicators and sets evaluation criteria.

[0320] Next, the terminal collects notes and reports written by students. This data reflects the results of their learning activities and is sent to the server.

[0321] Upon receiving transmitted data, the server first preprocesses the data using natural language processing to extract necessary information. Then, it uses an evaluation model based on pre-configured keywords to assess the logical structure and vocabulary diversity.

[0322] In addition, the emotion engine recognizes students' emotions from text and related comments within the data and generates an emotion score. The emotion score evaluates students' motivation and stress levels, and complements their understanding of educational objectives.

[0323] These analysis results are aggregated by the server and stored in a database as evaluation results. The evaluation results are then provided to the user (teacher) via a terminal, allowing the teacher to use this information to provide feedback on the student's learning process.

[0324] For example, if a teacher sets the goal of "writing a paper on environmental issues without feeling stressed," the system analyzes how the teacher's keywords (e.g., "environment," "sustainability") are used in the student's notes and reports, while simultaneously evaluating the emotions expressed in the writing. The emotion score generated by the emotion engine then allows the system to recognize the student's level of stress, enabling the teacher to provide more individualized guidance and support.

[0325] Thus, this system enables multidimensional assessment in real time, making it a powerful tool for educators to gain a deeper understanding of and support for learning.

[0326] The following describes the processing flow.

[0327] Step 1:

[0328] The user (teacher) sets up the system by entering the lesson's educational objectives and the keywords they want to evaluate. This clarifies the criteria for learning assessment.

[0329] Step 2:

[0330] The terminal collects notes and reports written by students and prepares them to be sent to the server. The collected data includes text information and, in some cases, metadata such as comments.

[0331] Step 3:

[0332] The server preprocesses the received data. Specifically, it uses natural language processing techniques to clean up the text data and performs syntactic analysis to extract important keywords and phrases.

[0333] Step 4:

[0334] The server uses a sentiment engine to recognize emotions within the text. This includes identifying the emotions expressed by the entire text and emotions associated with specific keywords. It generates a sentiment score, evaluating the degree to which positive or negative emotions are expressed.

[0335] Step 5:

[0336] The server uses a generative model to evaluate the relevance of pre-processed data to educational objectives. This is done by considering the logical structure of the text, vocabulary diversity, and the degree of relevance to the set objectives.

[0337] Step 6:

[0338] The server integrates the sentiment score and the evaluation results from the generative model to perform a comprehensive learning assessment. The results are stored in a database.

[0339] Step 7:

[0340] The terminal receives evaluation results from the server and displays them to the user (teacher). Based on this, the teacher can provide feedback on the student's learning process and adjust instruction as needed.

[0341] (Example 2)

[0342] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0343] Conventional educational assessment systems only evaluate learners' logical abilities and knowledge levels, failing to consider emotional aspects. This makes it difficult to understand learners' motivation and stress levels in detail, hindering individualized educational guidance. This invention aims to solve the problem of achieving comprehensive learning assessment that also considers learners' emotional states, thereby enabling more flexible and effective educational guidance.

[0344] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0345] In this invention, the server includes means for inputting educational objectives, means for collecting learning data, and means for identifying emotions within the learning data and generating an emotion score using an emotion recognition engine. This enables detailed feedback that takes into account not only the learner's knowledge but also their emotional state.

[0346] "Educational goals" are indicators of the knowledge and skills that educators expect learners to achieve.

[0347] "Learning data" refers to written and other forms of information generated by students through classes and other learning activities.

[0348] "Keywords" are words or phrases that are particularly important for evaluation and searching, and they play a role in highlighting specific themes or content in the analysis of texts and data.

[0349] A "generative model" is an algorithm that generates new information based on pre-trained data and evaluates its content.

[0350] An "emotion recognition engine" is a technology used to analyze and identify emotions from text and audio data, and is a system used to generate an emotion score.

[0351] "Evaluation results" refer to judgments about learners' performance derived from generative models and emotion recognition based on educational objectives and keywords.

[0352] "Means of storing in a database" refers to a system that efficiently stores evaluation results and other important information, making it available for retrieval as needed.

[0353] "Feedback" refers to the points and areas for improvement that educators provide to learners, and is information used to appropriately adjust the direction of learning.

[0354] To build a comprehensive evaluation system for educational settings, users (teachers) first input educational objectives and keywords necessary for evaluation into the system. This step clarifies the learning guidelines. The keywords to be used are important terms related to the lesson's theme. For example, in a lesson on environmental issues, keywords would include "environment" and "sustainability."

[0355] Next, the terminal collects notes and reports created by students. This data is stored digitally and transmitted to a server via the network. During this process, the collected data is encrypted and kept secure, ensuring security.

[0356] The server performs natural language processing on the received data. Using tools such as spaCy, the data is tokenized, tagged with parts of speech, and stop words are removed to prepare it for analysis. This pre-processed data is then fed into a generative model, where its logical structure and vocabulary diversity are evaluated based on keywords.

[0357] Furthermore, analysis for emotion recognition is also performed. The server uses an emotion recognition engine, leveraging technologies such as IBM Watson Natural Language Understanding, to extract emotions from the text and generate an emotion score. This result reflects the motivation and stress that students felt while writing the text.

[0358] The analyzed evaluation results are stored in a database and used for re-evaluation and improvement as needed. The evaluation results are then presented to the user (teacher) via a terminal, allowing the teacher to provide feedback to students based on that information. This enables adjustments to specific teaching content and enhances learning effectiveness.

[0359] As a concrete example, in relation to the teacher's set goal of "writing an environmental paper without feeling stressed," the system checks the use of the teacher's set keywords, "environment" and "sustainability." A prompt example might be, "Analyze the following text and generate a sentiment score. The keywords are 'environment' and 'sustainability'." This allows for a detailed understanding of how the student's work aligns with the goal. In this way, multifaceted evaluation is achieved, enabling deeper learning support.

[0360] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0361] Step 1:

[0362] The user (teacher) enters educational objectives and keywords. This generates input data for the system to set evaluation criteria. The entered information is sent to the server and stored in the database as a guide for evaluation.

[0363] Step 2:

[0364] The terminal collects students' learning output, such as notes and reports. This data is either scanned on the terminal or uploaded as digital data. The terminal then sends the collected data to a server. The output from this server is the raw data necessary for evaluation.

[0365] Step 3:

[0366] The server preprocesses the received data. Here, natural language processing tools are used to tokenize the data, tag it with parts of speech, and remove stop words. The input is raw data from students, and the output is processed text data suitable for analysis.

[0367] Step 4:

[0368] The server uses a generative AI model to evaluate preprocessed data. Specifically, it analyzes the logical structure and vocabulary diversity of the text based on keywords that have already been input. The input to this process is processed data, and the output is the evaluation result.

[0369] Step 5:

[0370] The server uses an emotion recognition engine to identify emotions from the same processed data and generate emotion scores. The input is student text data, and the output is a score representing the emotional state.

[0371] Step 6:

[0372] The server stores the analyzed evaluation results and sentiment scores in a database. This is a step that aggregates data from the entire evaluation process, with the input being evaluation data and sentiment scores, and the output being the stored database entries.

[0373] Step 7:

[0374] The server provides evaluation results to the user (teacher) via the terminal. The teacher can then refer to this data and provide feedback to the students. The input to this process is the evaluation results stored in the database, and the output is the presented evaluation information.

[0375] (Application Example 2)

[0376] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0377] Traditional customer service practices face challenges in evaluating staff customer service skills and the quality of their interactions with customers, as these evaluations are subjective and difficult to implement using standardized, objective criteria. Furthermore, analyzing staff emotional responses during customer interactions is difficult, resulting in a lack of concrete feedback for improving customer service. This can potentially delay improvements in staff capabilities and overall service quality.

[0378] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0379] In this invention, the server includes means for setting goals, means for collecting learning-related information, means for acquiring voice information in real time and performing text conversion, and means for analyzing the converted text information and performing emotion recognition. This makes it possible to evaluate staff's customer service skills using objective and standardized criteria and to provide specific feedback to individual staff members.

[0380] A "goal" is a specific objective or indicator to be achieved that is set as a criterion for evaluation.

[0381] "Means" refer to the methods or mechanisms used to achieve a specific objective.

[0382] "Learning-related information" refers to data and records related to the activities and results being evaluated.

[0383] "Acquiring audio information in real time and performing text conversion" refers to the process of instantly converting audio data into text information.

[0384] "Analyzing textual information and performing sentiment recognition" refers to the process of identifying emotional tendencies from textual data and scoring them as evaluation metrics.

[0385] A "server" is a computer system used for data processing and analysis, and for storing and managing the results.

[0386] A "standardized standard" is a unified evaluation index that can be applied to a variety of situations.

[0387] "Staff" refers to employees whose role is to provide a service.

[0388] "Objective" means being based on facts and not influenced by personal feelings or opinions.

[0389] "Feedback" refers to improvement suggestions and advice provided based on evaluation results.

[0390] The system that realizes this invention is intended for the evaluation and feedback of staff performance in customer service. The main components are a server, smart glasses, and a management terminal.

[0391] The server plays a central role in data processing and aggregating evaluation results. Smart glasses are effectively utilized to acquire audio information in real time, and this acquired audio information is converted into text. Devices such as Google Glass or Vuzix Blade can be used for this purpose.

[0392] Smart glasses are devices worn by staff during daily customer service duties, instantly converting collected audio information into text data. This converted text data is then sent to a server for detailed analysis using natural language processing tools. For example, SpaCy and Google Cloud Natural Language API are used to analyze the information and provide a detailed evaluation of staff speech and customer interactions.

[0393] Next, an emotion recognition engine on the server analyzes the text information and evaluates the staff's emotional state. Using tools such as IBM Watson Tone Analyzer, it generates an emotion score, which is used to measure the staff's stress and motivation levels.

[0394] The evaluation results are provided to the management terminal and are accessible to the store manager, who is the user. The manager can use this feedback to provide specific guidance for improvement to individual staff members.

[0395] For example, in a scenario where a staff member is asked to "briefly describe the features of this product," the prompt would be: "Briefly describe the features of the product you recommend to the customer, and consider how to attract the customer's interest. For example, use specific language such as, 'This laptop is high-performance and currently on sale.'" This would then be evaluated and feedback would be provided.

[0396] In this way, the system contributes to improving the quality of customer service and developing staff.

[0397] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0398] Step 1:

[0399] The system collects audio information from the user while they are wearing smart glasses and interacting with customers. This audio information becomes the input data for the system.

[0400] Step 2:

[0401] The device converts collected audio information into text information in real time. This process utilizes speech recognition technology to convert audio data into text data. The output is text information.

[0402] Step 3:

[0403] The server receives text data and performs detailed analysis using natural language processing tools. Specifically, it uses SpaCy to analyze the structure of the text and extract relevant keywords. The input to this process is text data, and the output is the analyzed data.

[0404] Step 4:

[0405] The server uses an emotion recognition engine based on analyzed data to evaluate the emotions contained in the text data. IBM Watson Tone Analyzer is used to generate emotion scores, quantifying the emotional state of the staff. The input is the analyzed data, and the output is the emotion evaluation result.

[0406] Step 5:

[0407] The server integrates the sentiment evaluation results and text analysis results to generate integrated evaluation data. This data represents an overall evaluation of the staff's customer service abilities.

[0408] Step 6:

[0409] The terminal sends integrated evaluation data to the management terminal, which receives this information. The administrator uses the integrated evaluation data to provide specific feedback to staff. The output is specific guidance content for staff.

[0410] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0411] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0412] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0413] [Third Embodiment]

[0414] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0415] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0416] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0417] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0418] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0419] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0420] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0421] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0422] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0423] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0424] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0425] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0426] The educational evaluation system according to the present invention is designed particularly for the purpose of evaluating students' thinking and expression skills. The system begins with the teacher inputting the educational objectives for the lesson. This allows the teacher to clarify the focus of learning and prepare to evaluate students based on that focus.

[0427] The system collects learning data, such as notes and reports created by students, from their devices and sends it to a central server. The server analyzes the received data and processes the text based on pre-configured keywords.

[0428] Specifically, the server uses natural language processing techniques to cleanse the data and extract important information. Then, a generative model is used to evaluate the data's logical structure and vocabulary selection. The evaluation is based on keyword frequency, sentence logical coherence, and expressiveness.

[0429] The evaluation results are stored in a database, and the model is retrained over time. This improves the accuracy and reliability of the evaluation. Based on the accumulated data, the server can provide more refined results in subsequent evaluations. The evaluation results are provided to the user (teacher) via a terminal, and the teacher uses these results to provide specific feedback to the students.

[0430] For example, if the objective of a class is "understanding environmental issues," the teacher enters specific keywords (e.g., "climate change," "sustainability," etc.) into the system. The system analyzes how and how often these keywords are used in student reports and evaluates how well the logical development aligns with the objective. The evaluation results are communicated to the teacher, who can then use them to provide specific guidance.

[0431] This invention functions as a system that significantly improves the efficiency of individualized instruction in educational settings and fairly evaluates students' abilities.

[0432] The following describes the processing flow.

[0433] Step 1:

[0434] The user (teacher) configures the system to input the lesson objectives and corresponding keywords. This information forms the basis for the subsequent evaluation process.

[0435] Step 2:

[0436] The terminal collects learning data such as notes and reports written by students. The collected data is sent directly to the server.

[0437] Step 3:

[0438] The server begins preparing to analyze the received training data. First, it preprocesses the text data using natural language processing techniques and converts it into structured data.

[0439] Step 4:

[0440] The server extracts and analyzes important information from cleansed data based on pre-configured keywords. This includes keyword frequency analysis and contextual analysis.

[0441] Step 5:

[0442] The server evaluates the extracted information using a generative model. It generates scores for the logical structure of the text, vocabulary diversity, and suitability to the objectives.

[0443] Step 6:

[0444] The server stores the evaluation results in a database, allowing the model to be retrained over time. The evaluation results will be used to further improve the evaluation accuracy in future processes.

[0445] Step 7:

[0446] The terminal receives evaluation results from the server and displays them to the user (teacher). Based on these results, the teacher can provide feedback to students and improve the quality of education.

[0447] (Example 1)

[0448] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0449] In today's educational environment, there is a need to accurately assess the thinking and expression skills of each individual student. However, traditional educational assessment methods make it difficult to conduct efficient and objective evaluations. In particular, when providing individualized support for lessons and assignments, the burden on teachers increases, making it difficult to ensure fairness and reliability in evaluations. A system is needed to solve this problem and improve the quality of education.

[0450] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0451] In this invention, the server includes means for inputting educational objectives, means for collecting learning outcomes, and means for extracting specific terms from the collected information and performing information analysis. This makes it possible to efficiently analyze students' learning outcomes and provide objective evaluations.

[0452] "Educational goals" refer to the specific learning outcomes that should be achieved in lessons and learning activities.

[0453] "Learning outcomes" refer to records such as notes and reports that students create based on educational objectives.

[0454] "Means of collection" refers to methods and devices for electronically accumulating learning outcomes and utilizing them as data.

[0455] "Specific terms" refer to keywords that are related to educational goals and play an important role in assessment.

[0456] "Information analysis" refers to the process of processing collected learning outcomes and evaluating the frequency of specific terms and their logical structure.

[0457] A "generated analytical model" refers to a model used for information analysis that applies statistical or machine learning techniques to analyze data based on evaluation criteria.

[0458] "Evaluation results" refer to objective indicators and feedback regarding students' learning outcomes obtained through information analysis.

[0459] "Methods for performing retraining" refer to techniques for improving the analysis model based on past evaluation results and performing evaluations with even higher accuracy.

[0460] This invention is an educational assessment system for evaluating students' thinking and expression skills. Users input educational goals into the system using a terminal. This clarifies the focus of learning and sets evaluation criteria.

[0461] The terminal collects student-created notes, reports, and other learning outcomes in digital format and sends them to the server. To ensure data security, the data is encrypted before transmission.

[0462] The server analyzes the received learning results using natural language processing techniques. Specifically, it uses libraries such as Python's NLTK and Spacy to cleanse the data and extract important specific terms.

[0463] Furthermore, the server uses the generated analysis model to evaluate the logical structure and vocabulary selection of the data. This process employs methods such as BERT, which is based on the Transformer model, to analyze the frequency of use of specific terms and the coherence of sentences.

[0464] The evaluation results are stored in a database, and the server retrains itself to improve the accuracy of the evaluation. This increases the accuracy of the analysis model over time, allowing it to provide more refined results in subsequent evaluations.

[0465] The evaluation results are provided to the user (teacher) via the terminal. Based on these results, the teacher can provide specific feedback to the students. For example, if the learning objective for a class is "understanding environmental issues," the teacher can input specific terms such as "climate change" or "sustainability" into the system as prompts. The server analyzes the learning outcomes based on these prompts and provides evaluation results, allowing the teacher to give specific guidance such as "Let's further deepen the discussion on sustainability."

[0466] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0467] Step 1:

[0468] The user inputs educational goals using a terminal. The system then generates criteria based on these goals. The input is in string format, for example, a theme such as "Understanding Environmental Issues." The output is the educational goals stored in a database.

[0469] Step 2:

[0470] The terminal collects learning outcomes such as notes and reports created by students. These are input as text data. The terminal organizes the collected data into a structured format and sends it to the server as output.

[0471] Step 3:

[0472] The server receives data sent from the terminal. Natural language processing techniques are used to analyze the input text data, first using NLTK or Spacy to cleanse the text. This reduces noise and extracts specific terms. The output is the cleaned data.

[0473] Step 4:

[0474] The server evaluates the data by applying an analytical model generated based on the cleansed data. Here, a generative AI model such as BERT is used to analyze the frequency of specific terms and the logical structure of sentences. The input is cleansed data, and the output is the evaluation results.

[0475] Step 5:

[0476] The server saves the evaluation results to a database and uses them as data to retrain the model. This improves the accuracy of subsequent data evaluations. The input consists of the evaluation results and historical data, and the output is an updated evaluation model that has been retrained.

[0477] Step 6:

[0478] The server generates evaluation results and provides them to the user via the terminal. The evaluation results are provided as input and converted into a visually easy-to-understand format on the terminal. The output is an evaluation report that the user can review.

[0479] Step 7:

[0480] Users provide specific feedback to students based on evaluation reports displayed on their devices. The content of the feedback is customized according to the evaluation results. The output consists of specific instructional content that is directly communicated to the students.

[0481] (Application Example 1)

[0482] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0483] In today's educational settings, efficiently evaluating individual learners' thinking and expression skills and conducting real-time analysis of their comprehension is challenging. In particular, there is a need for immediate feedback on learners' understanding when they view educational content containing complex concepts. Without addressing this challenge, improving the quality of instruction and providing individualized support to learners will be difficult.

[0484] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0485] In this invention, the server includes means for inputting learning objectives set by the educator, means for collecting learner learning data, and means for extracting concepts from the collected data and performing character data analysis. This makes it possible to evaluate learning progress in real time and provide learners with quick and appropriate feedback.

[0486] "Educational objectives" refer to the standards of knowledge and skills that learners should achieve regarding specific tasks or units.

[0487] A "learner" refers to an individual or group that seeks to acquire knowledge or skills by using educational content.

[0488] "Educational data" refers to a collection of data that includes information obtained from notes and reports created by learners, as well as from learning management systems.

[0489] A "concept" refers to important information or keywords related to a specific educational objective.

[0490] "Text data analysis" refers to the process of analyzing text data, understanding its content, and classifying it.

[0491] A "generative model" is an artificial intelligence model that generates new information based on input data.

[0492] "Real-time" refers to processing with very short delays, almost simultaneously.

[0493] "Comprehension level" is an indicator that shows how deeply learners understand the educational objectives and content.

[0494] "Feedback" refers to the act of providing learners with areas for improvement and additional learning guidance based on evaluation results and learning progress.

[0495] In this invention, a server, terminals, and users each play their respective roles in implementing an educational evaluation system. The server first receives learning objectives set by the educator and registers keywords related to those learning objectives in a database. Then, it collects educational data such as notes and reports provided by learners from the terminals and transmits it to the central server. The server then processes the text data and performs character data analysis using natural language processing technology.

[0496] The server extracts concepts from the collected text data and then evaluates that data using a generative AI model. The evaluation is based on keyword frequency, the logical consistency of the text, and its expressiveness. The evaluation results are stored in a database, and the server improves the accuracy and reliability of the evaluation by retraining the model over time. More refined evaluation results will be provided in subsequent evaluations.

[0497] The user, i.e., the educator, receives the evaluation results via a terminal and provides specific feedback to the learner based on them. Specifically, the server can evaluate the learner's understanding of the audio or video content they are viewing in real time and notify the user of the indicators of their level of understanding.

[0498] As a concrete example of its use, suppose a learner is watching an online lecture on the topic of "sustainable urban design." In this scenario, the server extracts keywords from the lecture content in real time and evaluates how much they contribute to achieving the learning objectives. An example of a prompt to input into the generative AI model would be, "Please input the speech-recognized lecture text and summarize the knowledge about sustainability."

[0499] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0500] Step 1:

[0501] The server first receives educational objectives provided by educators as input data. Based on this, it identifies relevant keywords and registers them in the database. In this process, key concepts related to the educational objectives are listed as keywords, which form the basis for subsequent analysis.

[0502] Step 2:

[0503] The device collects educational data from learners. This educational data includes notes, reports, audio, or video. The collected data is converted into a digital format and sent to a server. This makes the structured data available for processing on the server.

[0504] Step 3:

[0505] The server performs textual analysis on the received educational data. Specifically, it cleanses the data using natural language processing techniques and extracts concepts based on registered keywords. The input is educational data, and the output is the extracted concepts and their frequency of use. Unnecessary parts are removed from the data, and parts useful for analysis are highlighted.

[0506] Step 4:

[0507] The server uses a generative AI model to evaluate the extracted concepts. This model assesses the logical consistency and expressiveness of the text and determines the learner's level of understanding. The input is conceptual data, and the output is an evaluation score. In this step, data calculations are performed based on the evaluation criteria, and the results are shown numerically.

[0508] Step 5:

[0509] The server stores the evaluation results in a database and retrains the model. This improves the accuracy of the evaluation model, leading to better evaluations in the next session. The input is the evaluation score, and the output is the updated evaluation model. The accumulated information is used to enable the model to handle new data.

[0510] Step 6:

[0511] The server provides the evaluation results to the user. The user receives this information via their terminal and provides feedback to the learner. The input is the evaluation result, and the output is the feedback content. This process allows educators to set appropriate teaching strategies.

[0512] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0513] This invention is a system that enables more comprehensive learning assessment by adding an emotion recognition function to the evaluation of students' thinking and expression skills in educational settings. This system aims to improve the quality of education by considering students' emotional responses in addition to conventional evaluation processes.

[0514] First, the user (teacher) inputs the lesson's educational objectives and keywords they want to evaluate into the system. This clarifies the learning indicators and sets evaluation criteria.

[0515] Next, the terminal collects notes and reports written by students. This data reflects the results of their learning activities and is sent to the server.

[0516] Upon receiving transmitted data, the server first preprocesses the data using natural language processing to extract necessary information. Then, it uses an evaluation model based on pre-configured keywords to assess the logical structure and vocabulary diversity.

[0517] In addition, the emotion engine recognizes students' emotions from text and related comments within the data and generates an emotion score. The emotion score evaluates students' motivation and stress levels, and complements their understanding of educational objectives.

[0518] These analysis results are aggregated by the server and stored in a database as evaluation results. The evaluation results are then provided to the user (teacher) via a terminal, allowing the teacher to use this information to provide feedback on the student's learning process.

[0519] For example, if a teacher sets the goal of "writing a paper on environmental issues without feeling stressed," the system analyzes how the teacher's keywords (e.g., "environment," "sustainability") are used in the student's notes and reports, while simultaneously evaluating the emotions expressed in the writing. The emotion score generated by the emotion engine then allows the system to recognize the student's level of stress, enabling the teacher to provide more individualized guidance and support.

[0520] Thus, this system enables multidimensional assessment in real time, making it a powerful tool for educators to gain a deeper understanding of and support for learning.

[0521] The following describes the processing flow.

[0522] Step 1:

[0523] The user (teacher) sets up the system by entering the lesson's educational objectives and the keywords they want to evaluate. This clarifies the criteria for learning assessment.

[0524] Step 2:

[0525] The terminal collects notes and reports written by students and prepares them to be sent to the server. The collected data includes text information and, in some cases, metadata such as comments.

[0526] Step 3:

[0527] The server preprocesses the received data. Specifically, it uses natural language processing techniques to clean up the text data and performs syntactic analysis to extract important keywords and phrases.

[0528] Step 4:

[0529] The server uses a sentiment engine to recognize emotions within the text. This includes identifying the emotions expressed by the entire text and emotions associated with specific keywords. It generates a sentiment score, evaluating the degree to which positive or negative emotions are expressed.

[0530] Step 5:

[0531] The server uses a generative model to evaluate the relevance of pre-processed data to educational objectives. This is done by considering the logical structure of the text, vocabulary diversity, and the degree of relevance to the set objectives.

[0532] Step 6:

[0533] The server integrates the sentiment score and the evaluation results from the generative model to perform a comprehensive learning assessment. The results are stored in a database.

[0534] Step 7:

[0535] The terminal receives evaluation results from the server and displays them to the user (teacher). Based on this, the teacher can provide feedback on the student's learning process and adjust instruction as needed.

[0536] (Example 2)

[0537] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0538] Conventional educational assessment systems only evaluate learners' logical abilities and knowledge levels, failing to consider emotional aspects. This makes it difficult to understand learners' motivation and stress levels in detail, hindering individualized educational guidance. This invention aims to solve the problem of achieving comprehensive learning assessment that also considers learners' emotional states, thereby enabling more flexible and effective educational guidance.

[0539] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0540] In this invention, the server includes means for inputting educational objectives, means for collecting learning data, and means for identifying emotions within the learning data and generating an emotion score using an emotion recognition engine. This enables detailed feedback that takes into account not only the learner's knowledge but also their emotional state.

[0541] "Educational goals" are indicators of the knowledge and skills that educators expect learners to achieve.

[0542] "Learning data" refers to written and other forms of information generated by students through classes and other learning activities.

[0543] "Keywords" are words or phrases that are particularly important for evaluation and searching, and they play a role in highlighting specific themes or content in the analysis of texts and data.

[0544] A "generative model" is an algorithm that generates new information based on pre-trained data and evaluates its content.

[0545] An "emotion recognition engine" is a technology used to analyze and identify emotions from text and audio data, and is a system used to generate an emotion score.

[0546] "Evaluation results" refer to judgments about learners' performance derived from generative models and emotion recognition based on educational objectives and keywords.

[0547] "Means of storing in a database" refers to a system that efficiently stores evaluation results and other important information, making it available for retrieval as needed.

[0548] "Feedback" refers to the points and areas for improvement that educators provide to learners, and is information used to appropriately adjust the direction of learning.

[0549] To build a comprehensive evaluation system for educational settings, users (teachers) first input educational objectives and keywords necessary for evaluation into the system. This step clarifies the learning guidelines. The keywords to be used are important terms related to the lesson's theme. For example, in a lesson on environmental issues, keywords would include "environment" and "sustainability."

[0550] Next, the terminal collects notes and reports created by students. This data is stored digitally and transmitted to a server via the network. During this process, the collected data is encrypted and kept secure, ensuring security.

[0551] The server performs natural language processing on the received data. Using tools such as spaCy, the data is tokenized, tagged with parts of speech, and stop words are removed to prepare it for analysis. This pre-processed data is then fed into a generative model, where its logical structure and vocabulary diversity are evaluated based on keywords.

[0552] Furthermore, analysis for emotion recognition is also performed. The server uses an emotion recognition engine, leveraging technologies such as IBM Watson Natural Language Understanding, to extract emotions from the text and generate an emotion score. This result reflects the motivation and stress that students felt while writing the text.

[0553] The analyzed evaluation results are stored in a database and used for re-evaluation and improvement as needed. The evaluation results are then presented to the user (teacher) via a terminal, allowing the teacher to provide feedback to students based on that information. This enables adjustments to specific teaching content and enhances learning effectiveness.

[0554] As a concrete example, in relation to the teacher's set goal of "writing an environmental paper without feeling stressed," the system checks the use of the teacher's set keywords, "environment" and "sustainability." A prompt example might be, "Analyze the following text and generate a sentiment score. The keywords are 'environment' and 'sustainability'." This allows for a detailed understanding of how the student's work aligns with the goal. In this way, multifaceted evaluation is achieved, enabling deeper learning support.

[0555] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0556] Step 1:

[0557] The user (teacher) enters educational objectives and keywords. This generates input data for the system to set evaluation criteria. The entered information is sent to the server and stored in the database as a guide for evaluation.

[0558] Step 2:

[0559] The terminal collects students' learning output, such as notes and reports. This data is either scanned on the terminal or uploaded as digital data. The terminal then sends the collected data to a server. The output from this server is the raw data necessary for evaluation.

[0560] Step 3:

[0561] The server preprocesses the received data. Here, natural language processing tools are used to tokenize the data, tag it with parts of speech, and remove stop words. The input is raw data from students, and the output is processed text data suitable for analysis.

[0562] Step 4:

[0563] The server uses a generative AI model to evaluate preprocessed data. Specifically, it analyzes the logical structure and vocabulary diversity of the text based on keywords that have already been input. The input to this process is processed data, and the output is the evaluation result.

[0564] Step 5:

[0565] The server uses an emotion recognition engine to identify emotions from the same processed data and generate emotion scores. The input is student text data, and the output is a score representing the emotional state.

[0566] Step 6:

[0567] The server stores the analyzed evaluation results and sentiment scores in a database. This is a step that aggregates data from the entire evaluation process, with the input being evaluation data and sentiment scores, and the output being the stored database entries.

[0568] Step 7:

[0569] The server provides evaluation results to the user (teacher) via the terminal. The teacher can then refer to this data and provide feedback to the students. The input to this process is the evaluation results stored in the database, and the output is the presented evaluation information.

[0570] (Application Example 2)

[0571] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0572] Traditional customer service practices face challenges in evaluating staff customer service skills and the quality of their interactions with customers, as these evaluations are subjective and difficult to implement using standardized, objective criteria. Furthermore, analyzing staff emotional responses during customer interactions is difficult, resulting in a lack of concrete feedback for improving customer service. This can potentially delay improvements in staff capabilities and overall service quality.

[0573] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0574] In this invention, the server includes means for setting goals, means for collecting learning-related information, means for acquiring voice information in real time and performing text conversion, and means for analyzing the converted text information and performing emotion recognition. This makes it possible to evaluate staff's customer service skills using objective and standardized criteria and to provide specific feedback to individual staff members.

[0575] A "goal" is a specific objective or indicator to be achieved that is set as a criterion for evaluation.

[0576] "Means" refer to the methods or mechanisms used to achieve a specific objective.

[0577] "Learning-related information" refers to data and records related to the activities and results being evaluated.

[0578] "Acquiring audio information in real time and performing text conversion" refers to the process of instantly converting audio data into text information.

[0579] "Analyzing textual information and performing sentiment recognition" refers to the process of identifying emotional tendencies from textual data and scoring them as evaluation metrics.

[0580] A "server" is a computer system used for data processing and analysis, and for storing and managing the results.

[0581] A "standardized standard" is a unified evaluation index that can be applied to a variety of situations.

[0582] "Staff" refers to employees whose role is to provide a service.

[0583] "Objective" means being based on facts and not influenced by personal feelings or opinions.

[0584] "Feedback" refers to improvement suggestions and advice provided based on evaluation results.

[0585] The system that realizes this invention is intended for the evaluation and feedback of staff performance in customer service. The main components are a server, smart glasses, and a management terminal.

[0586] The server plays a central role in data processing and aggregating evaluation results. Smart glasses are effectively utilized to acquire audio information in real time, and this acquired audio information is converted into text. Devices such as Google Glass or Vuzix Blade can be used for this purpose.

[0587] Smart glasses are devices worn by staff during daily customer service duties, instantly converting collected audio information into text data. This converted text data is then sent to a server for detailed analysis using natural language processing tools. For example, SpaCy and Google Cloud Natural Language API are used to analyze the information and provide a detailed evaluation of staff speech and customer interactions.

[0588] Next, an emotion recognition engine on the server analyzes the text information and evaluates the staff's emotional state. Using tools such as IBM Watson Tone Analyzer, it generates an emotion score, which is used to measure the staff's stress and motivation levels.

[0589] The evaluation results are provided to the management terminal and are accessible to the store manager, who is the user. The manager can use this feedback to provide specific guidance for improvement to individual staff members.

[0590] For example, in a scenario where a staff member is asked to "briefly describe the features of this product," the prompt would be: "Briefly describe the features of the product you recommend to the customer, and consider how to attract the customer's interest. For example, use specific language such as, 'This laptop is high-performance and currently on sale.'" This would then be evaluated and feedback would be provided.

[0591] In this way, the system contributes to improving the quality of customer service and developing staff.

[0592] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0593] Step 1:

[0594] The system collects audio information from the user while they are wearing smart glasses and interacting with customers. This audio information becomes the input data for the system.

[0595] Step 2:

[0596] The device converts collected audio information into text information in real time. This process utilizes speech recognition technology to convert audio data into text data. The output is text information.

[0597] Step 3:

[0598] The server receives text data and performs detailed analysis using natural language processing tools. Specifically, it uses SpaCy to analyze the structure of the text and extract relevant keywords. The input to this process is text data, and the output is the analyzed data.

[0599] Step 4:

[0600] The server uses an emotion recognition engine based on analyzed data to evaluate the emotions contained in the text data. IBM Watson Tone Analyzer is used to generate emotion scores, quantifying the emotional state of the staff. The input is the analyzed data, and the output is the emotion evaluation result.

[0601] Step 5:

[0602] The server integrates the sentiment evaluation results and text analysis results to generate integrated evaluation data. This data represents an overall evaluation of the staff's customer service abilities.

[0603] Step 6:

[0604] The terminal sends integrated evaluation data to the management terminal, which receives this information. The administrator uses the integrated evaluation data to provide specific feedback to staff. The output is specific guidance content for staff.

[0605] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0606] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0607] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0608] [Fourth Embodiment]

[0609] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0610] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0611] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0612] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0613] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0614] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0615] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0616] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0617] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0618] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0619] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0620] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0621] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0622] The educational evaluation system according to the present invention is designed particularly for the purpose of evaluating students' thinking and expression skills. The system begins with the teacher inputting the educational objectives for the lesson. This allows the teacher to clarify the focus of learning and prepare to evaluate students based on that focus.

[0623] The system collects learning data, such as notes and reports created by students, from their devices and sends it to a central server. The server analyzes the received data and processes the text based on pre-configured keywords.

[0624] Specifically, the server uses natural language processing techniques to cleanse the data and extract important information. Then, a generative model is used to evaluate the data's logical structure and vocabulary selection. The evaluation is based on keyword frequency, sentence logical coherence, and expressiveness.

[0625] The evaluation results are stored in a database, and the model is retrained over time. This improves the accuracy and reliability of the evaluation. Based on the accumulated data, the server can provide more refined results in subsequent evaluations. The evaluation results are provided to the user (teacher) via a terminal, and the teacher uses these results to provide specific feedback to the students.

[0626] For example, if the objective of a class is "understanding environmental issues," the teacher enters specific keywords (e.g., "climate change," "sustainability," etc.) into the system. The system analyzes how and how often these keywords are used in student reports and evaluates how well the logical development aligns with the objective. The evaluation results are communicated to the teacher, who can then use them to provide specific guidance.

[0627] This invention functions as a system that significantly improves the efficiency of individualized instruction in educational settings and fairly evaluates students' abilities.

[0628] The following describes the processing flow.

[0629] Step 1:

[0630] The user (teacher) configures the system to input the lesson objectives and corresponding keywords. This information forms the basis for the subsequent evaluation process.

[0631] Step 2:

[0632] The terminal collects learning data such as notes and reports written by students. The collected data is sent directly to the server.

[0633] Step 3:

[0634] The server begins preparing to analyze the received training data. First, it preprocesses the text data using natural language processing techniques and converts it into structured data.

[0635] Step 4:

[0636] The server extracts and analyzes important information from cleansed data based on pre-configured keywords. This includes keyword frequency analysis and contextual analysis.

[0637] Step 5:

[0638] The server evaluates the extracted information using a generative model. It generates scores for the logical structure of the text, vocabulary diversity, and suitability to the objectives.

[0639] Step 6:

[0640] The server stores the evaluation results in a database, allowing the model to be retrained over time. The evaluation results will be used to further improve the evaluation accuracy in future processes.

[0641] Step 7:

[0642] The terminal receives evaluation results from the server and displays them to the user (teacher). Based on these results, the teacher can provide feedback to students and improve the quality of education.

[0643] (Example 1)

[0644] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0645] In today's educational environment, there is a need to accurately assess the thinking and expression skills of each individual student. However, traditional educational assessment methods make it difficult to conduct efficient and objective evaluations. In particular, when providing individualized support for lessons and assignments, the burden on teachers increases, making it difficult to ensure fairness and reliability in evaluations. A system is needed to solve this problem and improve the quality of education.

[0646] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0647] In this invention, the server includes means for inputting educational objectives, means for collecting learning outcomes, and means for extracting specific terms from the collected information and performing information analysis. This makes it possible to efficiently analyze students' learning outcomes and provide objective evaluations.

[0648] "Educational goals" refer to the specific learning outcomes that should be achieved in lessons and learning activities.

[0649] "Learning outcomes" refer to records such as notes and reports that students create based on educational objectives.

[0650] "Means of collection" refers to methods and devices for electronically accumulating learning outcomes and utilizing them as data.

[0651] "Specific terms" refer to keywords that are related to educational goals and play an important role in assessment.

[0652] "Information analysis" refers to the process of processing collected learning outcomes and evaluating the frequency of specific terms and their logical structure.

[0653] A "generated analytical model" refers to a model used for information analysis that applies statistical or machine learning techniques to analyze data based on evaluation criteria.

[0654] "Evaluation results" refer to objective indicators and feedback regarding students' learning outcomes obtained through information analysis.

[0655] "Methods for performing retraining" refer to techniques for improving the analysis model based on past evaluation results and performing evaluations with even higher accuracy.

[0656] This invention is an educational assessment system for evaluating students' thinking and expression skills. Users input educational goals into the system using a terminal. This clarifies the focus of learning and sets evaluation criteria.

[0657] The terminal collects student-created notes, reports, and other learning outcomes in digital format and sends them to the server. To ensure data security, the data is encrypted before transmission.

[0658] The server analyzes the received learning results using natural language processing techniques. Specifically, it uses libraries such as Python's NLTK and Spacy to cleanse the data and extract important specific terms.

[0659] Furthermore, the server uses the generated analysis model to evaluate the logical structure and vocabulary selection of the data. This process employs methods such as BERT, which is based on the Transformer model, to analyze the frequency of use of specific terms and the coherence of sentences.

[0660] The evaluation results are stored in a database, and the server retrains itself to improve the accuracy of the evaluation. This increases the accuracy of the analysis model over time, allowing it to provide more refined results in subsequent evaluations.

[0661] The evaluation results are provided to the user (teacher) via the terminal. Based on these results, the teacher can provide specific feedback to the students. For example, if the learning objective for a class is "understanding environmental issues," the teacher can input specific terms such as "climate change" or "sustainability" into the system as prompts. The server analyzes the learning outcomes based on these prompts and provides evaluation results, allowing the teacher to give specific guidance such as "Let's further deepen the discussion on sustainability."

[0662] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0663] Step 1:

[0664] The user inputs educational goals using a terminal. The system then generates criteria based on these goals. The input is in string format, for example, a theme such as "Understanding Environmental Issues." The output is the educational goals stored in a database.

[0665] Step 2:

[0666] The terminal collects learning outcomes such as notes and reports created by students. These are input as text data. The terminal organizes the collected data into a structured format and sends it to the server as output.

[0667] Step 3:

[0668] The server receives data sent from the terminal. Natural language processing techniques are used to analyze the input text data, first using NLTK or Spacy to cleanse the text. This reduces noise and extracts specific terms. The output is the cleaned data.

[0669] Step 4:

[0670] The server evaluates the data by applying an analytical model generated based on the cleansed data. Here, a generative AI model such as BERT is used to analyze the frequency of specific terms and the logical structure of sentences. The input is cleansed data, and the output is the evaluation results.

[0671] Step 5:

[0672] The server saves the evaluation results to a database and uses them as data to retrain the model. This improves the accuracy of subsequent data evaluations. The input consists of the evaluation results and historical data, and the output is an updated evaluation model that has been retrained.

[0673] Step 6:

[0674] The server generates evaluation results and provides them to the user via the terminal. The evaluation results are provided as input and converted into a visually easy-to-understand format on the terminal. The output is an evaluation report that the user can review.

[0675] Step 7:

[0676] Users provide specific feedback to students based on evaluation reports displayed on their devices. The content of the feedback is customized according to the evaluation results. The output consists of specific instructional content that is directly communicated to the students.

[0677] (Application Example 1)

[0678] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0679] In today's educational settings, efficiently evaluating individual learners' thinking and expression skills and conducting real-time analysis of their comprehension is challenging. In particular, there is a need for immediate feedback on learners' understanding when they view educational content containing complex concepts. Without addressing this challenge, improving the quality of instruction and providing individualized support to learners will be difficult.

[0680] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0681] In this invention, the server includes means for inputting learning objectives set by the educator, means for collecting learner learning data, and means for extracting concepts from the collected data and performing character data analysis. This makes it possible to evaluate learning progress in real time and provide learners with quick and appropriate feedback.

[0682] "Educational objectives" refer to the standards of knowledge and skills that learners should achieve regarding specific tasks or units.

[0683] A "learner" refers to an individual or group that seeks to acquire knowledge or skills by using educational content.

[0684] "Educational data" refers to a collection of data that includes information obtained from notes and reports created by learners, as well as from learning management systems.

[0685] A "concept" refers to important information or keywords related to a specific educational objective.

[0686] "Text data analysis" refers to the process of analyzing text data, understanding its content, and classifying it.

[0687] A "generative model" is an artificial intelligence model that generates new information based on input data.

[0688] "Real-time" refers to processing with very short delays, almost simultaneously.

[0689] "Comprehension level" is an indicator that shows how deeply learners understand the educational objectives and content.

[0690] "Feedback" refers to the act of providing learners with areas for improvement and additional learning guidance based on evaluation results and learning progress.

[0691] In this invention, a server, terminals, and users each play their respective roles in implementing an educational evaluation system. The server first receives learning objectives set by the educator and registers keywords related to those learning objectives in a database. Then, it collects educational data such as notes and reports provided by learners from the terminals and transmits it to the central server. The server then processes the text data and performs character data analysis using natural language processing technology.

[0692] The server extracts concepts from the collected text data and then evaluates that data using a generative AI model. The evaluation is based on keyword frequency, the logical consistency of the text, and its expressiveness. The evaluation results are stored in a database, and the server improves the accuracy and reliability of the evaluation by retraining the model over time. More refined evaluation results will be provided in subsequent evaluations.

[0693] The user, i.e., the educator, receives the evaluation results via a terminal and provides specific feedback to the learner based on them. Specifically, the server can evaluate the learner's understanding of the audio or video content they are viewing in real time and notify the user of the indicators of their level of understanding.

[0694] As a concrete example of its use, suppose a learner is watching an online lecture on the topic of "sustainable urban design." In this scenario, the server extracts keywords from the lecture content in real time and evaluates how much they contribute to achieving the learning objectives. An example of a prompt to input into the generative AI model would be, "Please input the speech-recognized lecture text and summarize the knowledge about sustainability."

[0695] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0696] Step 1:

[0697] The server first receives educational objectives provided by educators as input data. Based on this, it identifies relevant keywords and registers them in the database. In this process, key concepts related to the educational objectives are listed as keywords, which form the basis for subsequent analysis.

[0698] Step 2:

[0699] The device collects educational data from learners. This educational data includes notes, reports, audio, or video. The collected data is converted into a digital format and sent to a server. This makes the structured data available for processing on the server.

[0700] Step 3:

[0701] The server performs textual analysis on the received educational data. Specifically, it cleanses the data using natural language processing techniques and extracts concepts based on registered keywords. The input is educational data, and the output is the extracted concepts and their frequency of use. Unnecessary parts are removed from the data, and parts useful for analysis are highlighted.

[0702] Step 4:

[0703] The server uses a generative AI model to evaluate the extracted concepts. This model assesses the logical consistency and expressiveness of the text and determines the learner's level of understanding. The input is conceptual data, and the output is an evaluation score. In this step, data calculations are performed based on the evaluation criteria, and the results are shown numerically.

[0704] Step 5:

[0705] The server stores the evaluation results in a database and retrains the model. This improves the accuracy of the evaluation model, leading to better evaluations in the next session. The input is the evaluation score, and the output is the updated evaluation model. The accumulated information is used to enable the model to handle new data.

[0706] Step 6:

[0707] The server provides the evaluation results to the user. The user receives this information via their terminal and provides feedback to the learner. The input is the evaluation result, and the output is the feedback content. This process allows educators to set appropriate teaching strategies.

[0708] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0709] This invention is a system that enables more comprehensive learning assessment by adding an emotion recognition function to the evaluation of students' thinking and expression skills in educational settings. This system aims to improve the quality of education by considering students' emotional responses in addition to conventional evaluation processes.

[0710] First, the user (teacher) inputs the lesson's educational objectives and keywords they want to evaluate into the system. This clarifies the learning indicators and sets evaluation criteria.

[0711] Next, the terminal collects notes and reports written by students. This data reflects the results of their learning activities and is sent to the server.

[0712] Upon receiving transmitted data, the server first preprocesses the data using natural language processing to extract necessary information. Then, it uses an evaluation model based on pre-configured keywords to assess the logical structure and vocabulary diversity.

[0713] In addition, the emotion engine recognizes students' emotions from text and related comments within the data and generates an emotion score. The emotion score evaluates students' motivation and stress levels, and complements their understanding of educational objectives.

[0714] These analysis results are aggregated by the server and stored in a database as evaluation results. The evaluation results are then provided to the user (teacher) via a terminal, allowing the teacher to use this information to provide feedback on the student's learning process.

[0715] For example, if a teacher sets the goal of "writing a paper on environmental issues without feeling stressed," the system analyzes how the teacher's keywords (e.g., "environment," "sustainability") are used in the student's notes and reports, while simultaneously evaluating the emotions expressed in the writing. The emotion score generated by the emotion engine then allows the system to recognize the student's level of stress, enabling the teacher to provide more individualized guidance and support.

[0716] Thus, this system enables multidimensional assessment in real time, making it a powerful tool for educators to gain a deeper understanding of and support for learning.

[0717] The following describes the processing flow.

[0718] Step 1:

[0719] The user (teacher) sets up the system by entering the lesson's educational objectives and the keywords they want to evaluate. This clarifies the criteria for learning assessment.

[0720] Step 2:

[0721] The terminal collects notes and reports written by students and prepares them to be sent to the server. The collected data includes text information and, in some cases, metadata such as comments.

[0722] Step 3:

[0723] The server preprocesses the received data. Specifically, it uses natural language processing techniques to clean up the text data and performs syntactic analysis to extract important keywords and phrases.

[0724] Step 4:

[0725] The server uses a sentiment engine to recognize emotions within the text. This includes identifying the emotions expressed by the entire text and emotions associated with specific keywords. It generates a sentiment score, evaluating the degree to which positive or negative emotions are expressed.

[0726] Step 5:

[0727] The server uses a generative model to evaluate the relevance of pre-processed data to educational objectives. This is done by considering the logical structure of the text, vocabulary diversity, and the degree of relevance to the set objectives.

[0728] Step 6:

[0729] The server integrates the sentiment score and the evaluation results from the generative model to perform a comprehensive learning assessment. The results are stored in a database.

[0730] Step 7:

[0731] The terminal receives evaluation results from the server and displays them to the user (teacher). Based on this, the teacher can provide feedback on the student's learning process and adjust instruction as needed.

[0732] (Example 2)

[0733] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0734] Conventional educational assessment systems only evaluate learners' logical abilities and knowledge levels, failing to consider emotional aspects. This makes it difficult to understand learners' motivation and stress levels in detail, hindering individualized educational guidance. This invention aims to solve the problem of achieving comprehensive learning assessment that also considers learners' emotional states, thereby enabling more flexible and effective educational guidance.

[0735] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0736] In this invention, the server includes means for inputting educational objectives, means for collecting learning data, and means for identifying emotions within the learning data and generating an emotion score using an emotion recognition engine. This enables detailed feedback that takes into account not only the learner's knowledge but also their emotional state.

[0737] "Educational goals" are indicators of the knowledge and skills that educators expect learners to achieve.

[0738] "Learning data" refers to written and other forms of information generated by students through classes and other learning activities.

[0739] "Keywords" are words or phrases that are particularly important for evaluation and searching, and they play a role in highlighting specific themes or content in the analysis of texts and data.

[0740] A "generative model" is an algorithm that generates new information based on pre-trained data and evaluates its content.

[0741] An "emotion recognition engine" is a technology used to analyze and identify emotions from text and audio data, and is a system used to generate an emotion score.

[0742] "Evaluation results" refer to judgments about learners' performance derived from generative models and emotion recognition based on educational objectives and keywords.

[0743] "Means of storing in a database" refers to a system that efficiently stores evaluation results and other important information, making it available for retrieval as needed.

[0744] "Feedback" refers to the points and areas for improvement that educators provide to learners, and is information used to appropriately adjust the direction of learning.

[0745] To build a comprehensive evaluation system for educational settings, users (teachers) first input educational objectives and keywords necessary for evaluation into the system. This step clarifies the learning guidelines. The keywords to be used are important terms related to the lesson's theme. For example, in a lesson on environmental issues, keywords would include "environment" and "sustainability."

[0746] Next, the terminal collects notes and reports created by students. This data is stored digitally and transmitted to a server via the network. During this process, the collected data is encrypted and kept secure, ensuring security.

[0747] The server performs natural language processing on the received data. Using tools such as spaCy, the data is tokenized, tagged with parts of speech, and stop words are removed to prepare it for analysis. This pre-processed data is then fed into a generative model, where its logical structure and vocabulary diversity are evaluated based on keywords.

[0748] Furthermore, analysis for emotion recognition is also performed. The server uses an emotion recognition engine, leveraging technologies such as IBM Watson Natural Language Understanding, to extract emotions from the text and generate an emotion score. This result reflects the motivation and stress that students felt while writing the text.

[0749] The analyzed evaluation results are stored in a database and used for re-evaluation and improvement as needed. The evaluation results are then presented to the user (teacher) via a terminal, allowing the teacher to provide feedback to students based on that information. This enables adjustments to specific teaching content and enhances learning effectiveness.

[0750] As a concrete example, in relation to the teacher's set goal of "writing an environmental paper without feeling stressed," the system checks the use of the teacher's set keywords, "environment" and "sustainability." A prompt example might be, "Analyze the following text and generate a sentiment score. The keywords are 'environment' and 'sustainability'." This allows for a detailed understanding of how the student's work aligns with the goal. In this way, multifaceted evaluation is achieved, enabling deeper learning support.

[0751] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0752] Step 1:

[0753] The user (teacher) enters educational objectives and keywords. This generates input data for the system to set evaluation criteria. The entered information is sent to the server and stored in the database as a guide for evaluation.

[0754] Step 2:

[0755] The terminal collects students' learning output, such as notes and reports. This data is either scanned on the terminal or uploaded as digital data. The terminal then sends the collected data to a server. The output from this server is the raw data necessary for evaluation.

[0756] Step 3:

[0757] The server preprocesses the received data. Here, natural language processing tools are used to tokenize the data, tag it with parts of speech, and remove stop words. The input is raw data from students, and the output is processed text data suitable for analysis.

[0758] Step 4:

[0759] The server uses a generative AI model to evaluate preprocessed data. Specifically, it analyzes the logical structure and vocabulary diversity of the text based on keywords that have already been input. The input to this process is processed data, and the output is the evaluation result.

[0760] Step 5:

[0761] The server uses an emotion recognition engine to identify emotions from the same processed data and generate emotion scores. The input is student text data, and the output is a score representing the emotional state.

[0762] Step 6:

[0763] The server stores the analyzed evaluation results and sentiment scores in a database. This is a step that aggregates data from the entire evaluation process, with the input being evaluation data and sentiment scores, and the output being the stored database entries.

[0764] Step 7:

[0765] The server provides evaluation results to the user (teacher) via the terminal. The teacher can then refer to this data and provide feedback to the students. The input to this process is the evaluation results stored in the database, and the output is the presented evaluation information.

[0766] (Application Example 2)

[0767] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0768] Traditional customer service practices face challenges in evaluating staff customer service skills and the quality of their interactions with customers, as these evaluations are subjective and difficult to implement using standardized, objective criteria. Furthermore, analyzing staff emotional responses during customer interactions is difficult, resulting in a lack of concrete feedback for improving customer service. This can potentially delay improvements in staff capabilities and overall service quality.

[0769] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0770] In this invention, the server includes means for setting goals, means for collecting learning-related information, means for acquiring voice information in real time and performing text conversion, and means for analyzing the converted text information and performing emotion recognition. This makes it possible to evaluate staff's customer service skills using objective and standardized criteria and to provide specific feedback to individual staff members.

[0771] A "goal" is a specific objective or indicator to be achieved that is set as a criterion for evaluation.

[0772] "Means" refer to the methods or mechanisms used to achieve a specific objective.

[0773] "Learning-related information" refers to data and records related to the activities and results being evaluated.

[0774] "Acquiring audio information in real time and performing text conversion" refers to the process of instantly converting audio data into text information.

[0775] "Analyzing textual information and performing sentiment recognition" refers to the process of identifying emotional tendencies from textual data and scoring them as evaluation metrics.

[0776] A "server" is a computer system used for data processing and analysis, and for storing and managing the results.

[0777] A "standardized standard" is a unified evaluation index that can be applied to a variety of situations.

[0778] "Staff" refers to employees whose role is to provide a service.

[0779] "Objective" means being based on facts and not influenced by personal feelings or opinions.

[0780] "Feedback" refers to improvement suggestions and advice provided based on evaluation results.

[0781] The system that realizes this invention is intended for the evaluation and feedback of staff performance in customer service. The main components are a server, smart glasses, and a management terminal.

[0782] The server plays a central role in data processing and aggregating evaluation results. Smart glasses are effectively utilized to acquire audio information in real time, and this acquired audio information is converted into text. Devices such as Google Glass or Vuzix Blade can be used for this purpose.

[0783] Smart glasses are devices worn by staff during daily customer service duties, instantly converting collected audio information into text data. This converted text data is then sent to a server for detailed analysis using natural language processing tools. For example, SpaCy and Google Cloud Natural Language API are used to analyze the information and provide a detailed evaluation of staff speech and customer interactions.

[0784] Next, an emotion recognition engine on the server analyzes the text information and evaluates the staff's emotional state. Using tools such as IBM Watson Tone Analyzer, it generates an emotion score, which is used to measure the staff's stress and motivation levels.

[0785] The evaluation results are provided to the management terminal and are accessible to the store manager, who is the user. The manager can use this feedback to provide specific guidance for improvement to individual staff members.

[0786] For example, in a scenario where a staff member is asked to "briefly describe the features of this product," the prompt would be: "Briefly describe the features of the product you recommend to the customer, and consider how to attract the customer's interest. For example, use specific language such as, 'This laptop is high-performance and currently on sale.'" This would then be evaluated and feedback would be provided.

[0787] In this way, the system contributes to improving the quality of customer service and developing staff.

[0788] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0789] Step 1:

[0790] The system collects audio information from the user while they are wearing smart glasses and interacting with customers. This audio information becomes the input data for the system.

[0791] Step 2:

[0792] The device converts collected audio information into text information in real time. This process utilizes speech recognition technology to convert audio data into text data. The output is text information.

[0793] Step 3:

[0794] The server receives text data and performs detailed analysis using natural language processing tools. Specifically, it uses SpaCy to analyze the structure of the text and extract relevant keywords. The input to this process is text data, and the output is the analyzed data.

[0795] Step 4:

[0796] The server uses an emotion recognition engine based on analyzed data to evaluate the emotions contained in the text data. IBM Watson Tone Analyzer is used to generate emotion scores, quantifying the emotional state of the staff. The input is the analyzed data, and the output is the emotion evaluation result.

[0797] Step 5:

[0798] The server integrates the sentiment evaluation results and text analysis results to generate integrated evaluation data. This data represents an overall evaluation of the staff's customer service abilities.

[0799] Step 6:

[0800] The terminal sends integrated evaluation data to the management terminal, which receives this information. The administrator uses the integrated evaluation data to provide specific feedback to staff. The output is specific guidance content for staff.

[0801] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0802] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0803] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0804] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0805] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0806] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0807] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0808] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0809] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0810] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0811] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0812] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0813] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0814] 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.

[0815] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0816] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0817] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0818] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0819] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0820] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0821] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0822] The following is further disclosed regarding the embodiments described above.

[0823] (Claim 1)

[0824] A means of inputting educational objectives set by the teacher,

[0825] Means for collecting student learning data,

[0826] A method for extracting keywords from collected data and performing text analysis,

[0827] A means of performing data evaluation using a generative model based on extracted keywords,

[0828] A means of accumulating evaluation results and performing retraining,

[0829] Means of providing evaluation results to teachers,

[0830] A system that includes this.

[0831] (Claim 2)

[0832] The system according to claim 1, further comprising means for preprocessing the text of the collected data.

[0833] (Claim 3)

[0834] The system according to claim 1, further comprising means for a teacher to provide feedback to a student based on evaluation results.

[0835] "Example 1"

[0836] (Claim 1)

[0837] A means of inputting educational goals,

[0838] Means for collecting learning outcomes,

[0839] A means of extracting specific terms from collected information and performing information analysis,

[0840] A means of performing information evaluation using an analytical model generated based on extracted terms,

[0841] A means of accumulating evaluation results and performing retraining,

[0842] Means of providing the evaluation results to the educators,

[0843] A system that includes this.

[0844] (Claim 2)

[0845] The system according to claim 1, comprising means for performing pretreatment.

[0846] (Claim 3)

[0847] The system according to claim 1, further comprising means for an instructor to provide learners with information based on the results of an evaluation.

[0848] "Application Example 1"

[0849] (Claim 1)

[0850] A means of inputting learning objectives set by educators,

[0851] Means for collecting learner education data,

[0852] A means of extracting concepts from collected data and performing textual data analysis,

[0853] A means of performing data evaluation using a generative model based on extracted concepts,

[0854] A means of accumulating evaluation results and performing retraining,

[0855] Means for providing evaluation results to educators,

[0856] A means of evaluating comprehension from audio or video content in real time,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, further comprising means for preprocessing the character data of the collected data.

[0860] (Claim 3)

[0861] The system according to claim 1, comprising means for an educator to provide feedback to a learner based on evaluation results.

[0862] "Example 2 of combining an emotion engine"

[0863] (Claim 1)

[0864] A means of inputting educational objectives,

[0865] Means of collecting training data,

[0866] A means of extracting keywords from collected information and performing information analysis,

[0867] A means of performing information evaluation using a generative model based on extracted keywords,

[0868] A means for identifying emotions in training data and generating an emotion score using an emotion recognition engine,

[0869] A means of saving the analyzed evaluation results to a database,

[0870] Means of providing evaluation results to educators,

[0871] A system that includes this.

[0872] (Claim 2)

[0873] The system according to claim 1, comprising means for preprocessing information from collected data.

[0874] (Claim 3)

[0875] The system according to claim 1, comprising means for an educator to provide feedback to a learner based on evaluation results and emotional scores.

[0876] "Application example 2 when combining with an emotional engine"

[0877] (Claim 1)

[0878] The means of setting goals,

[0879] Means of collecting learning-related information,

[0880] A means of extracting relevant terms from collected information and performing information analysis,

[0881] A means of performing information evaluation using a generative model based on extracted related terms,

[0882] A means of saving analysis information and performing retraining,

[0883] Means for providing analytical information,

[0884] A means of acquiring audio information in real time and performing text conversion,

[0885] A means of analyzing converted text information and performing emotion recognition,

[0886] A means of providing analysis results to administrators to improve their capabilities,

[0887] A system that includes this.

[0888] (Claim 2)

[0889] The system according to claim 1, further comprising means for preprocessing the character data of the collected information.

[0890] (Claim 3)

[0891] The system according to claim 1, further comprising means for an administrator to provide individual users with feedback based on analysis results. [Explanation of Symbols]

[0892] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of inputting educational objectives set by the teacher, Means for collecting student learning data, A method for extracting keywords from collected data and performing text analysis, A means of performing data evaluation using a generative model based on extracted keywords, A means of accumulating evaluation results and performing retraining, Means of providing evaluation results to teachers, A system that includes this.

2. The system according to claim 1, further comprising means for preprocessing the text of the collected data.

3. The system according to claim 1, further comprising means for a teacher to provide feedback to a student based on evaluation results.

Images