system

Abstract

The system according to this embodiment aims to automate essay examinations and interview evaluations, thereby enabling fair and efficient evaluation. [Solution] The system according to the embodiment comprises an analysis unit, an evaluation unit, a customization unit, and a detection unit. The analysis unit analyzes the written answers and performs scoring. The evaluation unit analyzes the audio data of the interview analyzed by the analysis unit and evaluates the examinee's thinking ability and communication ability. The customization unit customizes the AI ​​evaluation model according to the evaluation criteria of each educational institution evaluated by the evaluation unit. The detection unit detects cheating and inappropriate answers customized by the customization unit.

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, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that in discourse tests and interview evaluations, the evaluation burden on teachers is large and it is difficult to conduct fair and efficient evaluations.

[0005] The system according to the embodiment aims to automate discourse tests and interview evaluations and conduct fair and efficient evaluations.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, an evaluation unit, a customization unit, and a detection unit. The analysis unit analyzes the written answers and performs scoring. The evaluation unit analyzes the audio data of the interview analyzed by the analysis unit and evaluates the examinee's thinking ability and communication skills. The customization unit customizes the AI ​​evaluation model according to the evaluation criteria of each educational institution evaluated by the evaluation unit. The detection unit detects cheating and inappropriate answers customized by the customization unit. [Effects of the Invention]

[0007] The system according to this embodiment can automate essay examinations and interview evaluations, enabling fair and efficient evaluation. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10]This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 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.

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

[0019] The smart device 14 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.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

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

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

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

[0028] (Example of form 1) An AI agent system according to an embodiment of the present invention is a system that automates and supports essay examinations and interview evaluations in university and high school entrance examinations. This system can reduce the evaluation burden on teachers and promote fair and efficient entrance examination reform. This will enable a shift from entrance examinations that are heavily focused on knowledge to those that emphasize thinking and expression skills. For example, the AI ​​agent system performs automatic evaluation of essay answers. The AI ​​agent system analyzes the essay answers submitted by applicants and evaluates the logic, depth of content, and expressiveness of the writing. The AI ​​agent system uses natural language processing technology to analyze the structure and content of the writing in detail and perform scoring. Next, the AI ​​agent system provides support for interview evaluation. The AI ​​agent system analyzes the audio data of the interview and evaluates the applicant's thinking and communication skills. The AI ​​agent system uses speech recognition technology to analyze the content and manner of the applicant's statements and performs scoring based on evaluation criteria. Furthermore, the AI ​​agent system sets the evaluation criteria. The AI ​​agent system can customize the AI ​​evaluation model to match the evaluation criteria of each educational institution. This makes it possible to perform evaluations that meet the needs of each educational institution. In addition, the AI ​​agent system provides feedback on the results. The AI ​​agent system can provide test takers with evaluation results and areas for improvement. Only those who request it can receive feedback, allowing test takers to understand their weaknesses and improve for the next exam. Finally, the AI ​​agent system performs cheating detection. The AI ​​agent system detects cheating and inappropriate answers, ensuring fairness. In this way, the AI ​​agent system can reduce the burden on teachers and realize fair and efficient entrance examination reform by automating and supporting entrance examination evaluation using AI. Thus, the AI ​​agent system can reduce the burden on teachers and realize fair and efficient entrance examination reform by automating and supporting essay and interview evaluations in university and high school entrance examinations.

[0029] The AI ​​agent system according to this embodiment comprises an analysis unit, an evaluation unit, a customization unit, and a detection unit. The analysis unit analyzes the written response and performs scoring. The analysis unit performs scoring by, for example, using natural language processing technology to analyze the structure and content of the text in detail. The analysis unit can, for example, use morphological analysis to analyze the words in the text, grammatical analysis to analyze the structure of the text, and semantic analysis to analyze the content of the text. The evaluation unit analyzes the audio data of the interview and evaluates the applicant's thinking ability and communication ability. The evaluation unit performs scoring based on evaluation criteria by, for example, using speech recognition technology to analyze the content and manner of the applicant's statements. The evaluation unit can, for example, preprocess the audio data, convert the content of the statements into text using a speech recognition algorithm, and evaluate the logic and expressiveness of the content of the statements. The customization unit customizes the AI ​​evaluation model to match the evaluation criteria of each educational institution. The customization unit adjusts the evaluation model by, for example, having the AI ​​learn based on sample data provided by the educational institution. The customization unit can adjust the parameters of the evaluation model by, for example, analyzing the format and content of the sample data. The detection unit detects cheating and inappropriate answers. For example, the detection unit detects when the same answer is submitted by multiple applicants or when there are unnatural speech patterns during an interview. For example, the detection unit can calculate the degree of agreement between answers and detect abnormalities in speech patterns. As a result, the AI ​​agent system according to this embodiment can automate essay responses and interview evaluations and can be customized to match the evaluation criteria of each educational institution.

[0030] The analysis unit analyzes and scores essay responses. For example, it uses natural language processing techniques to analyze the structure and content of the text in detail and then scores it. Specifically, it can analyze words in a text using morphological analysis, analyze the structure of the text using grammatical analysis, and analyze the content of the text using semantic analysis. Morphological analysis divides the text into words and identifies the part of speech and meaning of each word. Grammatical analysis analyzes the structure of the text and identifies grammatical elements such as subject, predicate, and object. Semantic analysis understands the meaning of the entire text and makes an appropriate evaluation based on the context. This allows the analysis unit to analyze the content of essay responses in detail and perform accurate scoring. Furthermore, the analysis unit can learn from past data and continuously improve its evaluation criteria. For example, by using past essay responses and their evaluation results as training data and updating the evaluation model, it can achieve more accurate scoring. The analysis unit can also set flexible evaluation criteria to accommodate different educational institutions and examination formats. This allows the analysis unit to respond to various situations and efficiently and accurately evaluate essay responses.

[0031] The evaluation unit analyzes interview audio data to assess the applicant's thinking and communication skills. For example, it uses speech recognition technology to analyze the applicant's statements and speaking style, and scores them based on evaluation criteria. Specifically, it preprocesses the audio data, removing noise and adjusting volume, and then uses a speech recognition algorithm to convert the statements into text. Next, it analyzes the text data to evaluate the logic and expressiveness of the statements. For example, it scores based on criteria such as the consistency and logical structure of the statements and the richness of the vocabulary used. The evaluation unit can also evaluate fluency, clarity of pronunciation, and emotional expression. This allows the evaluation unit to comprehensively assess the applicant's thinking and communication skills. Furthermore, the evaluation unit can continuously improve its evaluation model by learning from past interview data. For example, by using past interview evaluation results as training data and updating the evaluation model, it can achieve more accurate evaluations. The evaluation unit can also set flexible evaluation criteria to accommodate different educational institutions and interview formats. This allows the evaluation unit to respond to various situations and conduct interview evaluations efficiently and accurately.

[0032] The customization department customizes the AI ​​evaluation model to match the evaluation criteria of each educational institution. For example, the customization department uses sample data provided by educational institutions to train the AI ​​and adjust the evaluation model. Specifically, it analyzes the format and content of the sample data and adjusts the parameters of the evaluation model. For instance, it can adjust the weighting and scoring methods of the evaluation model based on the evaluation items and criteria that a particular educational institution emphasizes. This allows the customization department to provide evaluation models tailored to the needs of each educational institution. Furthermore, the customization department can continuously improve the evaluation model based on feedback from educational institutions. For example, by collecting opinions and requests from educational institutions regarding the evaluation results and updating the evaluation model based on them, it can achieve more accurate evaluations. In addition, the customization department can set flexible evaluation criteria to accommodate different educational institutions and examination formats. This allows the customization department to respond to various situations and efficiently and accurately customize evaluations to match the evaluation criteria of each educational institution.

[0033] The detection unit detects cheating and inappropriate answers. For example, it detects cases where the same answer is submitted by multiple test-takers or unnatural speech patterns during interviews. Specifically, it calculates the degree of agreement between answers and detects abnormalities in speech patterns. For example, if the same answer is submitted by multiple test-takers, it calculates the degree of agreement and identifies answers with a high degree of agreement as fraudulent. It can also analyze speech patterns during interviews to detect unnatural pauses, repetitions, and abnormal pronunciation patterns. This allows the detection unit to quickly and accurately detect cheating and inappropriate answers. Furthermore, the detection unit can learn from past data and continuously improve its detection model. For example, by using data on past cheating behavior as training data and updating the detection model, it can achieve more accurate detection. In addition, the detection unit can set flexible detection criteria to accommodate different educational institutions and examination formats. This allows the detection unit to respond to various situations and efficiently and accurately detect cheating and inappropriate answers.

[0034] The system includes a feedback unit that provides evaluation results and areas for improvement. The feedback unit provides evaluation results and areas for improvement. For example, the feedback unit can explain the evaluation results in detail to the test taker and point out areas for improvement. For example, the feedback unit can visually display the evaluation results in graphs or charts and specifically show areas for improvement. For example, the feedback unit can analyze the test taker's weaknesses and provide advice for improvement for the next exam. This allows the test taker to improve for the next exam by providing evaluation results and areas for improvement. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input the evaluation results into a generative AI and have the generative AI extract areas for improvement.

[0035] The analysis unit can use natural language processing techniques to analyze the structure and content of a text in detail and perform scoring. For example, the analysis unit can analyze the words in a text using morphological analysis. For example, the analysis unit can analyze the structure of a text using grammatical analysis. For example, the analysis unit can analyze the content of a text using semantic analysis. As a result, the accuracy of the analysis of argumentative responses is improved by using natural language processing techniques. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the structure and content of the text into a generative AI and have the generative AI perform the scoring.

[0036] The evaluation unit can use speech recognition technology to analyze the content and manner of speech of applicants and score them based on evaluation criteria. For example, the evaluation unit can preprocess the audio data and convert the content of speech into text using a speech recognition algorithm. For example, the evaluation unit can evaluate the logic and expressiveness of the content of speech. For example, the evaluation unit can analyze the emotions in the content of speech and reflect them in the evaluation. As a result, the accuracy of interview evaluation is improved by using speech recognition technology. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input the content and manner of speech into a generative AI and have the generative AI perform the scoring.

[0037] The customization unit allows the AI ​​to learn from sample data provided by educational institutions and adjust the evaluation model. For example, the customization unit can analyze the format and content of the sample data and adjust the parameters of the evaluation model. For example, the customization unit can improve the accuracy of the evaluation model using the sample data. For example, the customization unit can customize the evaluation model according to the needs of educational institutions. This makes it possible to customize the evaluation model to match the evaluation criteria of each educational institution. Some or all of the above-described processes in the customization unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the customization unit can input sample data into a generative AI and have the generative AI perform the adjustment of the evaluation model.

[0038] The detection unit can detect cases where the same answer is submitted by multiple candidates or where there are unnatural patterns of speech during an interview. For example, the detection unit can calculate the degree of agreement between answers to detect cases where the same answer is submitted by multiple candidates. For example, the detection unit can detect abnormalities in speech patterns to detect unnatural speech patterns. For example, the detection unit can analyze the content of answers and the timing of speech to detect cheating. This allows for the detection of cheating and inappropriate answers, ensuring fairness. Some or all of the above-described processes in the detection unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the detection unit can input answers and speech patterns into a generating AI and have the generating AI perform the detection of cheating.

[0039] The analysis unit can improve the accuracy of its evaluation by referring to the examinee's past answer history when analyzing essay responses. For example, the analysis unit can analyze the examinee's past answer history and reflect the degree of improvement in the evaluation. For example, the analysis unit can refer to the examinee's past answer patterns and highly value consistent answers. For example, the analysis unit can set evaluation criteria to reinforce specific weaknesses based on the examinee's past answer history. This improves the accuracy of the evaluation by referring to past answer history. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input past answer history into a generative AI and have the generative AI perform the evaluation accuracy improvement.

[0040] The analysis unit can apply different analysis algorithms to essay responses depending on the theme or topic of the response. For example, the analysis unit can apply an algorithm that emphasizes logical structure to responses on scientific themes. For example, the analysis unit can apply an algorithm that emphasizes expressiveness and creativity to responses on literary themes. For example, the analysis unit can apply an algorithm that emphasizes problem-solving ability and critical thinking to responses on social themes. This enables analysis tailored to the theme and topic. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the theme or topic of the response into a generative AI and have the generative AI apply an appropriate analysis algorithm.

[0041] The analysis unit can evaluate essay responses while considering the examinee's geographical and cultural background. For example, the analysis unit can consider the examinee's geographical background and reflect region-specific expressions and examples in the evaluation. For example, the analysis unit can consider the examinee's cultural background and reflect cultural perspectives in the evaluation. For example, the analysis unit can consider the examinee's linguistic background and reflect language use and expression methods in the evaluation. This makes it possible to perform evaluations that take geographical and cultural backgrounds into consideration. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the analysis unit can input the examinee's geographical and cultural background into a generative AI and have the generative AI perform adjustments to the evaluation.

[0042] The analysis unit can analyze the examinee's social media activity and supplement relevant information when analyzing essay responses. For example, the analysis unit can understand the examinee's interests and concerns from their social media activity and reflect this as background information in the evaluation of the response. For example, the analysis unit can reflect the examinee's knowledge and understanding of specific topics in the evaluation from their social media activity. For example, the analysis unit can reflect the examinee's communication skills and expressive abilities in the evaluation from their social media activity. In this way, relevant information can be supplemented by analyzing social media activity. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the examinee's social media activity into a generative AI and have the generative AI perform the supplementation of relevant information.

[0043] The evaluation unit can improve the accuracy of its evaluations by referring to the applicant's past interview history during the interview evaluation process. For example, the evaluation unit can analyze the applicant's past interview history and reflect their growth in the evaluation. For example, the evaluation unit can refer to the applicant's past speaking patterns and highly value consistent statements. For example, the evaluation unit can set evaluation criteria to reinforce specific weaknesses based on the applicant's past interview history. This improves the accuracy of the evaluation by referring to past interview history. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit can input past interview history into a generative AI and have the generative AI perform the task of improving the accuracy of the evaluation.

[0044] The evaluation unit can apply algorithms to analyze in detail the content and speaking patterns of the applicant during the interview evaluation. For example, the evaluation unit can analyze the content of the applicant's statements in detail and evaluate the logical structure and depth of content. For example, the evaluation unit can analyze the patterns of the applicant's speaking and evaluate communication skills and expressive abilities. For example, the evaluation unit can comprehensively analyze the content of the applicant's statements and speaking patterns and make an overall evaluation. This improves the accuracy of the evaluation by analyzing the content of statements and speaking patterns in detail. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input the content of statements and speaking patterns into a generative AI and have the generative AI perform a detailed analysis.

[0045] The evaluation unit can take into account the applicant's geographical and cultural background when conducting interview evaluations. For example, the evaluation unit can consider the applicant's geographical background and reflect regionally specific expressions and examples in the evaluation. For example, the evaluation unit can consider the applicant's cultural background and reflect cultural perspectives in the evaluation. For example, the evaluation unit can consider the applicant's linguistic background and reflect language use and expression methods in the evaluation. This makes it possible to conduct evaluations that take geographical and cultural backgrounds into account. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input the applicant's geographical and cultural background into a generative AI and have the generative AI perform adjustments to the evaluation.

[0046] The evaluation unit can analyze the applicant's social media activity during the interview evaluation and supplement relevant information. For example, the evaluation unit can understand the applicant's interests and concerns from their social media activity and reflect this in the evaluation as background information for their statements. For example, the evaluation unit can reflect the applicant's knowledge and understanding of specific topics from their social media activity in the evaluation. For example, the evaluation unit can reflect the applicant's communication skills and expressive abilities from their social media activity in the evaluation. In this way, relevant information can be supplemented by analyzing social media activity. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input the applicant's social media activity into a generative AI and have the generative AI perform the supplementation of relevant information.

[0047] The customization unit can improve the accuracy of the model by referring to the educational institution's past evaluation data during customization. For example, the customization unit can analyze the educational institution's past evaluation data to improve the accuracy of the evaluation model. For example, the customization unit can refer to the educational institution's past evaluation patterns to perform consistent evaluations. For example, the customization unit can set evaluation criteria to reinforce specific weaknesses from the educational institution's past evaluation data. This improves the accuracy of the model by referring to past evaluation data. Some or all of the above processing in the customization unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the customization unit can input past evaluation data into a generative AI and have the generative AI perform the model accuracy improvement.

[0048] The customization unit can apply different customization algorithms during the customization process according to the specific needs of the educational institution. For example, if the educational institution emphasizes a particular skill, the customization unit can apply a customization algorithm that focuses on that skill. For example, if the educational institution has a particular evaluation standard, the customization unit can apply a customization algorithm that matches that standard. For example, if the educational institution employs a particular evaluation method, the customization unit can apply a customization algorithm that matches that method. This enables customization to meet specific needs. Some or all of the above-described processes in the customization unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the customization unit can input the educational institution's needs into a generative AI and have the generative AI apply an appropriate customization algorithm.

[0049] The customization unit can adjust the model during customization, taking into account the geographical and cultural background of the educational institution. For example, the customization unit can consider the geographical background of the educational institution and set region-specific evaluation criteria. For example, the customization unit can consider the cultural background of the educational institution and reflect a cultural perspective in the evaluation. For example, the customization unit can consider the linguistic background of the educational institution and reflect language use and expression methods in the evaluation. This makes it possible to adjust the model to take geographical and cultural backgrounds into account. Some or all of the above processing in the customization unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the customization unit can input the geographical and cultural background of the educational institution into a generative AI and have the generative AI perform the model adjustments.

[0050] The customization unit can analyze the social media activities of educational institutions and supplement relevant information during the customization process. For example, the customization unit can identify interests in specific topics from the social media activities of educational institutions and reflect this in evaluation criteria. For example, the customization unit can reflect the emphasis placed on specific skills in evaluations based on the social media activities of educational institutions. For example, if an educational institution employs a specific evaluation method, the customization unit can set evaluation criteria that align with that method based on the social media activities of educational institutions. This allows for the supplementation of relevant information by analyzing social media activities. Some or all of the above-described processes in the customization unit may be performed using, for example, generative AI, or without generative AI. For example, the customization unit can input the social media activities of educational institutions into a generative AI and have the generative AI perform the supplementation of relevant information.

[0051] The detection unit can improve the accuracy of detection by referring to the test taker's past behavioral history when detecting fraud. For example, the detection unit can analyze the test taker's past behavioral history and detect abnormal behavior. For example, the detection unit can refer to the test taker's past behavioral patterns and highly value inconsistent behavior. For example, the detection unit can set detection criteria to reinforce specific fraudulent activities based on the test taker's past behavioral history. This improves the accuracy of detection by referring to past behavioral history. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input past behavioral history into a generative AI and have the generative AI perform the detection accuracy improvement.

[0052] The detection unit can apply algorithms that analyze response patterns and interview utterance patterns in detail when fraud is detected. For example, the detection unit can analyze the applicant's response patterns in detail and detect abnormal responses. For example, the detection unit can analyze the applicant's interview utterance patterns and detect unnatural utterances. For example, the detection unit can comprehensively analyze the applicant's response patterns and interview utterance patterns to perform comprehensive fraud detection. This improves the accuracy of detection by analyzing response patterns and utterance patterns in detail. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input response patterns and utterance patterns into a generative AI and have the generative AI perform a detailed analysis.

[0053] The detection unit can perform fraud detection while considering the test-taker's geographical and cultural background. For example, the detection unit can consider the test-taker's geographical background to detect region-specific fraudulent activities. For example, the detection unit can consider the test-taker's cultural background to reflect a cultural perspective in the evaluation. For example, the detection unit can consider the test-taker's linguistic background to reflect language use and expression methods in the evaluation. This makes it possible to detect fraud while considering geographical and cultural background. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input the test-taker's geographical and cultural background into a generative AI and have the generative AI perform adjustments to the detection.

[0054] The detection unit can analyze the examinee's social media activity and supplement relevant information when fraud is detected. For example, the detection unit can detect abnormal behavior from the examinee's social media activity. For example, the detection unit can detect specific fraudulent activities from the examinee's social media activity. For example, the detection unit can reflect the examinee's communication and expressive abilities in the evaluation based on their social media activity. In this way, relevant information can be supplemented by analyzing social media activity. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input the examinee's social media activity into a generative AI and have the generative AI perform the supplementation of relevant information.

[0055] The feedback unit can provide optimal feedback by referring to the examinee's past evaluation results during the feedback process. For example, the feedback unit can analyze the examinee's past evaluation results and reflect their level of growth in the evaluation. For example, the feedback unit can refer to the examinee's past evaluation patterns and provide consistent feedback. For example, the feedback unit can provide feedback to reinforce specific weaknesses based on the examinee's past evaluation results. In this way, optimal feedback is provided by referring to past evaluation results. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input past evaluation results into a generative AI and have the generative AI perform the task of providing optimal feedback.

[0056] The feedback unit can provide optimal feedback by considering the examinee's geographical and cultural background. For example, the feedback unit can consider the examinee's geographical background and provide region-specific feedback. For example, the feedback unit can consider the examinee's cultural background and reflect a cultural perspective in the evaluation. For example, the feedback unit can consider the examinee's linguistic background and reflect language use and expression in the evaluation. This ensures that feedback is provided that takes geographical and cultural backgrounds into account. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input the examinee's geographical and cultural background into a generative AI and have the generative AI provide optimal feedback.

[0057] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0058] The analysis unit can evaluate examinees' essay responses while considering the style and tone of the answers. For example, if an examinee uses a formal style, the analysis unit can apply evaluation criteria appropriate to that style. Similarly, if an examinee uses a casual style, the analysis unit can apply evaluation criteria appropriate to that style. Furthermore, the analysis unit can determine whether the tone of the examinee's answer is positive or negative and provide an evaluation accordingly. This enables flexible evaluation that takes into account the examinee's style and tone.

[0059] The evaluation unit can analyze the nonverbal communication elements of applicants during interviews. For example, it can analyze applicants' facial expressions and gestures and reflect this in the evaluation of their communication skills. It can also analyze applicants' eye contact and posture and reflect their confidence and sincerity during the interview. Furthermore, it can analyze the applicants' voice tone and rhythm and reflect the emotional nuances of their statements in the evaluation. This enables a comprehensive evaluation that takes nonverbal communication elements into consideration.

[0060] The customization function can adjust the evaluation model based on the specific educational policies and philosophies of an educational institution. For example, if an educational institution emphasizes creativity, the customization function can set evaluation criteria that highly value creative answers. If an educational institution emphasizes logical thinking, the customization function can set evaluation criteria that highly value answers with a logical structure. Furthermore, if an educational institution emphasizes communication skills, the customization function can set evaluation criteria that reflect the clarity and consistency of speech in the evaluation. This makes it possible to adjust the evaluation model to suit the educational policies and philosophies of an educational institution.

[0061] The detection unit monitors the examinee's behavior patterns in real time and can detect signs of cheating early. For example, the detection unit can analyze the examinee's eye movements to detect the possibility of cheating. It can also analyze the examinee's hand movements to detect unnatural movements. Furthermore, the detection unit can analyze changes in the examinee's posture to detect signs of tension or anxiety. This enables early detection of cheating through real-time behavioral monitoring.

[0062] The feedback system can provide feedback tailored to the test-taker's learning style. For example, it can provide visual feedback using graphs and charts for visual learners, audio feedback for auditory learners, and practical advice and exercises for experiential learners. This ensures that the optimal feedback is provided according to the test-taker's learning style.

[0063] The following briefly describes the processing flow for example form 1.

[0064] Step 1: The analysis unit analyzes and scores the essay responses. The analysis unit uses natural language processing techniques to analyze the structure and content of the text in detail and then scores it. For example, it uses morphological analysis to analyze the words in the text, grammatical analysis to analyze the structure of the text, and semantic analysis to analyze the content of the text. Step 2: The evaluation department analyzes the interview audio data to assess the applicant's thinking and communication skills. The evaluation department uses speech recognition technology to analyze the applicant's statements and speaking style, and scores them based on evaluation criteria. For example, it preprocesses the audio data, uses a speech recognition algorithm to convert the statements into text, and evaluates the logic and expressiveness of the statements. Step 3: The customization team customizes the AI ​​evaluation model to match the evaluation criteria of each educational institution. The customization team uses sample data provided by the educational institution to train the AI ​​and adjust the evaluation model. For example, they analyze the format and content of the sample data and adjust the parameters of the evaluation model. Step 4: The detection unit detects cheating and inappropriate answers. The detection unit detects cases where the same answer is submitted by multiple candidates, or unnatural patterns of speech during the interview. For example, it calculates the degree of similarity of answers and detects abnormalities in speech patterns.

[0065] (Example of form 2) An AI agent system according to an embodiment of the present invention is a system that automates and supports essay examinations and interview evaluations in university and high school entrance examinations. This system can reduce the evaluation burden on teachers and promote fair and efficient entrance examination reform. This will enable a shift from entrance examinations that are heavily focused on knowledge to those that emphasize thinking and expression skills. For example, the AI ​​agent system performs automatic evaluation of essay answers. The AI ​​agent system analyzes the essay answers submitted by applicants and evaluates the logic, depth of content, and expressiveness of the writing. The AI ​​agent system uses natural language processing technology to analyze the structure and content of the writing in detail and perform scoring. Next, the AI ​​agent system provides support for interview evaluation. The AI ​​agent system analyzes the audio data of the interview and evaluates the applicant's thinking and communication skills. The AI ​​agent system uses speech recognition technology to analyze the content and manner of the applicant's statements and performs scoring based on evaluation criteria. Furthermore, the AI ​​agent system sets the evaluation criteria. The AI ​​agent system can customize the AI ​​evaluation model to match the evaluation criteria of each educational institution. This makes it possible to perform evaluations that meet the needs of each educational institution. In addition, the AI ​​agent system provides feedback on the results. The AI ​​agent system can provide test takers with evaluation results and areas for improvement. Only those who request it can receive feedback, allowing test takers to understand their weaknesses and improve for the next exam. Finally, the AI ​​agent system performs cheating detection. The AI ​​agent system detects cheating and inappropriate answers, ensuring fairness. In this way, the AI ​​agent system can reduce the burden on teachers and realize fair and efficient entrance examination reform by automating and supporting entrance examination evaluation using AI. Thus, the AI ​​agent system can reduce the burden on teachers and realize fair and efficient entrance examination reform by automating and supporting essay and interview evaluations in university and high school entrance examinations.

[0066] The AI ​​agent system according to this embodiment comprises an analysis unit, an evaluation unit, a customization unit, and a detection unit. The analysis unit analyzes the written response and performs scoring. The analysis unit performs scoring by, for example, using natural language processing technology to analyze the structure and content of the text in detail. The analysis unit can, for example, use morphological analysis to analyze the words in the text, grammatical analysis to analyze the structure of the text, and semantic analysis to analyze the content of the text. The evaluation unit analyzes the audio data of the interview and evaluates the applicant's thinking ability and communication ability. The evaluation unit performs scoring based on evaluation criteria by, for example, using speech recognition technology to analyze the content and manner of the applicant's statements. The evaluation unit can, for example, preprocess the audio data, convert the content of the statements into text using a speech recognition algorithm, and evaluate the logic and expressiveness of the content of the statements. The customization unit customizes the AI ​​evaluation model to match the evaluation criteria of each educational institution. The customization unit adjusts the evaluation model by, for example, having the AI ​​learn based on sample data provided by the educational institution. The customization unit can adjust the parameters of the evaluation model by, for example, analyzing the format and content of the sample data. The detection unit detects cheating and inappropriate answers. For example, the detection unit detects when the same answer is submitted by multiple applicants or when there are unnatural speech patterns during an interview. For example, the detection unit can calculate the degree of agreement between answers and detect abnormalities in speech patterns. As a result, the AI ​​agent system according to this embodiment can automate essay responses and interview evaluations and can be customized to match the evaluation criteria of each educational institution.

[0067] The analysis unit analyzes and scores essay responses. For example, it uses natural language processing techniques to analyze the structure and content of the text in detail and then scores it. Specifically, it can analyze words in a text using morphological analysis, analyze the structure of the text using grammatical analysis, and analyze the content of the text using semantic analysis. Morphological analysis divides the text into words and identifies the part of speech and meaning of each word. Grammatical analysis analyzes the structure of the text and identifies grammatical elements such as subject, predicate, and object. Semantic analysis understands the meaning of the entire text and makes an appropriate evaluation based on the context. This allows the analysis unit to analyze the content of essay responses in detail and perform accurate scoring. Furthermore, the analysis unit can learn from past data and continuously improve its evaluation criteria. For example, by using past essay responses and their evaluation results as training data and updating the evaluation model, it can achieve more accurate scoring. The analysis unit can also set flexible evaluation criteria to accommodate different educational institutions and examination formats. This allows the analysis unit to respond to various situations and efficiently and accurately evaluate essay responses.

[0068] The evaluation unit analyzes interview audio data to assess the applicant's thinking and communication skills. For example, it uses speech recognition technology to analyze the applicant's statements and speaking style, and scores them based on evaluation criteria. Specifically, it preprocesses the audio data, removing noise and adjusting volume, and then uses a speech recognition algorithm to convert the statements into text. Next, it analyzes the text data to evaluate the logic and expressiveness of the statements. For example, it scores based on criteria such as the consistency and logical structure of the statements and the richness of the vocabulary used. The evaluation unit can also evaluate fluency, clarity of pronunciation, and emotional expression. This allows the evaluation unit to comprehensively assess the applicant's thinking and communication skills. Furthermore, the evaluation unit can continuously improve its evaluation model by learning from past interview data. For example, by using past interview evaluation results as training data and updating the evaluation model, it can achieve more accurate evaluations. The evaluation unit can also set flexible evaluation criteria to accommodate different educational institutions and interview formats. This allows the evaluation unit to respond to various situations and conduct interview evaluations efficiently and accurately.

[0069] The customization department customizes the AI ​​evaluation model to match the evaluation criteria of each educational institution. For example, the customization department uses sample data provided by educational institutions to train the AI ​​and adjust the evaluation model. Specifically, it analyzes the format and content of the sample data and adjusts the parameters of the evaluation model. For instance, it can adjust the weighting and scoring methods of the evaluation model based on the evaluation items and criteria that a particular educational institution emphasizes. This allows the customization department to provide evaluation models tailored to the needs of each educational institution. Furthermore, the customization department can continuously improve the evaluation model based on feedback from educational institutions. For example, by collecting opinions and requests from educational institutions regarding the evaluation results and updating the evaluation model based on them, it can achieve more accurate evaluations. In addition, the customization department can set flexible evaluation criteria to accommodate different educational institutions and examination formats. This allows the customization department to respond to various situations and efficiently and accurately customize evaluations to match the evaluation criteria of each educational institution.

[0070] The detection unit detects cheating and inappropriate answers. For example, it detects cases where the same answer is submitted by multiple test-takers or unnatural speech patterns during interviews. Specifically, it calculates the degree of agreement between answers and detects abnormalities in speech patterns. For example, if the same answer is submitted by multiple test-takers, it calculates the degree of agreement and identifies answers with a high degree of agreement as fraudulent. It can also analyze speech patterns during interviews to detect unnatural pauses, repetitions, and abnormal pronunciation patterns. This allows the detection unit to quickly and accurately detect cheating and inappropriate answers. Furthermore, the detection unit can learn from past data and continuously improve its detection model. For example, by using data on past cheating behavior as training data and updating the detection model, it can achieve more accurate detection. In addition, the detection unit can set flexible detection criteria to accommodate different educational institutions and examination formats. This allows the detection unit to respond to various situations and efficiently and accurately detect cheating and inappropriate answers.

[0071] The system includes a feedback unit that provides evaluation results and areas for improvement. The feedback unit provides evaluation results and areas for improvement. For example, the feedback unit can explain the evaluation results in detail to the test taker and point out areas for improvement. For example, the feedback unit can visually display the evaluation results in graphs or charts and specifically show areas for improvement. For example, the feedback unit can analyze the test taker's weaknesses and provide advice for improvement for the next exam. This allows the test taker to improve for the next exam by providing evaluation results and areas for improvement. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input the evaluation results into a generative AI and have the generative AI extract areas for improvement.

[0072] The analysis unit can use natural language processing techniques to analyze the structure and content of a text in detail and perform scoring. For example, the analysis unit can analyze the words in a text using morphological analysis. For example, the analysis unit can analyze the structure of a text using grammatical analysis. For example, the analysis unit can analyze the content of a text using semantic analysis. As a result, the accuracy of the analysis of argumentative responses is improved by using natural language processing techniques. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the structure and content of the text into a generative AI and have the generative AI perform the scoring.

[0073] The evaluation unit can use speech recognition technology to analyze the content and manner of speech of applicants and score them based on evaluation criteria. For example, the evaluation unit can preprocess the audio data and convert the content of speech into text using a speech recognition algorithm. For example, the evaluation unit can evaluate the logic and expressiveness of the content of speech. For example, the evaluation unit can analyze the emotions in the content of speech and reflect them in the evaluation. As a result, the accuracy of interview evaluation is improved by using speech recognition technology. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input the content and manner of speech into a generative AI and have the generative AI perform the scoring.

[0074] The customization unit allows the AI ​​to learn from sample data provided by educational institutions and adjust the evaluation model. For example, the customization unit can analyze the format and content of the sample data and adjust the parameters of the evaluation model. For example, the customization unit can improve the accuracy of the evaluation model using the sample data. For example, the customization unit can customize the evaluation model according to the needs of educational institutions. This makes it possible to customize the evaluation model to match the evaluation criteria of each educational institution. Some or all of the above-described processes in the customization unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the customization unit can input sample data into a generative AI and have the generative AI perform the adjustment of the evaluation model.

[0075] The detection unit can detect cases where the same answer is submitted by multiple candidates or where there are unnatural patterns of speech during an interview. For example, the detection unit can calculate the degree of agreement between answers to detect cases where the same answer is submitted by multiple candidates. For example, the detection unit can detect abnormalities in speech patterns to detect unnatural speech patterns. For example, the detection unit can analyze the content of answers and the timing of speech to detect cheating. This allows for the detection of cheating and inappropriate answers, ensuring fairness. Some or all of the above-described processes in the detection unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the detection unit can input answers and speech patterns into a generating AI and have the generating AI perform the detection of cheating.

[0076] The analysis unit can estimate the examinee's emotions and adjust the evaluation criteria for the essay response based on the estimated emotions. For example, if the examinee is nervous, the analysis unit can relax the evaluation criteria and emphasize responses given in a relaxed state. For example, if the examinee is confident, the analysis unit can tighten the evaluation criteria and demand a higher level of response. For example, if the examinee is anxious, the analysis unit can adjust the evaluation criteria and emphasize accuracy of content over speed of response. This allows for more appropriate evaluation by adjusting the evaluation criteria according to the examinee's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using a generative AI, or not. For example, the analysis unit can input the examinee's emotion data into a generative AI and have the generative AI perform the adjustment of the evaluation criteria.

[0077] The analysis unit can improve the accuracy of its evaluation by referring to the examinee's past answer history when analyzing essay responses. For example, the analysis unit can analyze the examinee's past answer history and reflect the degree of improvement in the evaluation. For example, the analysis unit can refer to the examinee's past answer patterns and highly value consistent answers. For example, the analysis unit can set evaluation criteria to reinforce specific weaknesses based on the examinee's past answer history. This improves the accuracy of the evaluation by referring to past answer history. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input past answer history into a generative AI and have the generative AI perform the evaluation accuracy improvement.

[0078] The analysis unit can apply different analysis algorithms to essay responses depending on the theme or topic of the response. For example, the analysis unit can apply an algorithm that emphasizes logical structure to responses on scientific themes. For example, the analysis unit can apply an algorithm that emphasizes expressiveness and creativity to responses on literary themes. For example, the analysis unit can apply an algorithm that emphasizes problem-solving ability and critical thinking to responses on social themes. This enables analysis tailored to the theme and topic. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the theme or topic of the response into a generative AI and have the generative AI apply an appropriate analysis algorithm.

[0079] The analysis unit can estimate the examinee's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the examinee is nervous, the analysis unit can provide a simple and highly visible display method. For example, if the examinee is relaxed, the analysis unit can provide a display method that includes detailed information. For example, if the examinee is anxious, the analysis unit can provide a display method that gets straight to the point. This makes it possible to display analysis results according to the examinee's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using a generative AI, or not using a generative AI. For example, the analysis unit can input the examinee's emotion data into a generative AI and have the generative AI adjust the display method.

[0080] The analysis unit can evaluate essay responses while considering the examinee's geographical and cultural background. For example, the analysis unit can consider the examinee's geographical background and reflect region-specific expressions and examples in the evaluation. For example, the analysis unit can consider the examinee's cultural background and reflect cultural perspectives in the evaluation. For example, the analysis unit can consider the examinee's linguistic background and reflect language use and expression methods in the evaluation. This makes it possible to perform evaluations that take geographical and cultural backgrounds into consideration. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the analysis unit can input the examinee's geographical and cultural background into a generative AI and have the generative AI perform adjustments to the evaluation.

[0081] The analysis unit can analyze the examinee's social media activity and supplement relevant information when analyzing essay responses. For example, the analysis unit can understand the examinee's interests and concerns from their social media activity and reflect this as background information in the evaluation of the response. For example, the analysis unit can reflect the examinee's knowledge and understanding of specific topics in the evaluation from their social media activity. For example, the analysis unit can reflect the examinee's communication skills and expressive abilities in the evaluation from their social media activity. In this way, relevant information can be supplemented by analyzing social media activity. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the examinee's social media activity into a generative AI and have the generative AI perform the supplementation of relevant information.

[0082] The evaluation unit can estimate the applicant's emotions and adjust the interview evaluation criteria based on the estimated emotions. For example, if the applicant is nervous, the evaluation unit can relax the evaluation criteria and emphasize relaxed speech. For example, if the applicant is confident, the evaluation unit can tighten the evaluation criteria and demand a higher level of speech. For example, if the applicant is anxious, the evaluation unit can adjust the evaluation criteria and emphasize accuracy of content over speed of speech. By adjusting the interview evaluation criteria according to the applicant's emotions, a more appropriate evaluation becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit can input the applicant's emotion data into a generative AI and have the generative AI adjust the evaluation criteria.

[0083] The evaluation unit can improve the accuracy of its evaluations by referring to the applicant's past interview history during the interview evaluation process. For example, the evaluation unit can analyze the applicant's past interview history and reflect their growth in the evaluation. For example, the evaluation unit can refer to the applicant's past speaking patterns and highly value consistent statements. For example, the evaluation unit can set evaluation criteria to reinforce specific weaknesses based on the applicant's past interview history. This improves the accuracy of the evaluation by referring to past interview history. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit can input past interview history into a generative AI and have the generative AI perform the task of improving the accuracy of the evaluation.

[0084] The evaluation unit can apply algorithms to analyze in detail the content and speaking patterns of the applicant during the interview evaluation. For example, the evaluation unit can analyze the content of the applicant's statements in detail and evaluate the logical structure and depth of content. For example, the evaluation unit can analyze the patterns of the applicant's speaking and evaluate communication skills and expressive abilities. For example, the evaluation unit can comprehensively analyze the content of the applicant's statements and speaking patterns and make an overall evaluation. This improves the accuracy of the evaluation by analyzing the content of statements and speaking patterns in detail. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input the content of statements and speaking patterns into a generative AI and have the generative AI perform a detailed analysis.

[0085] The evaluation unit can estimate the examinee's emotions and adjust the display method of the evaluation results based on the estimated emotions. For example, if the examinee is nervous, the evaluation unit can provide a simple and highly visible display method. For example, if the examinee is relaxed, the evaluation unit can provide a display method that includes detailed information. For example, if the examinee is anxious, the evaluation unit can provide a display method that gets straight to the point. This makes it possible to display evaluation results according to the examinee's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the evaluation unit may be performed using a generative AI, or not using a generative AI. For example, the evaluation unit can input the examinee's emotion data into a generative AI and have the generative AI adjust the display method.

[0086] The evaluation unit can take into account the applicant's geographical and cultural background when conducting interview evaluations. For example, the evaluation unit can consider the applicant's geographical background and reflect regionally specific expressions and examples in the evaluation. For example, the evaluation unit can consider the applicant's cultural background and reflect cultural perspectives in the evaluation. For example, the evaluation unit can consider the applicant's linguistic background and reflect language use and expression methods in the evaluation. This makes it possible to conduct evaluations that take geographical and cultural backgrounds into account. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input the applicant's geographical and cultural background into a generative AI and have the generative AI perform adjustments to the evaluation.

[0087] The evaluation unit can analyze the applicant's social media activity during the interview evaluation and supplement relevant information. For example, the evaluation unit can understand the applicant's interests and concerns from their social media activity and reflect this in the evaluation as background information for their statements. For example, the evaluation unit can reflect the applicant's knowledge and understanding of specific topics from their social media activity in the evaluation. For example, the evaluation unit can reflect the applicant's communication skills and expressive abilities from their social media activity in the evaluation. In this way, relevant information can be supplemented by analyzing social media activity. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input the applicant's social media activity into a generative AI and have the generative AI perform the supplementation of relevant information.

[0088] The customization unit can estimate the sentiment of educational institutions and adjust the evaluation model based on the estimated sentiment of the educational institutions. For example, if an educational institution requests rigorous evaluation, the customization unit can set strict evaluation criteria. For example, if an educational institution requests flexible evaluation, the customization unit can relax the evaluation criteria. For example, if an educational institution emphasizes a particular skill, the customization unit can set evaluation criteria that focus on that skill. This makes it possible to adjust the evaluation model according to the sentiment of the educational institutions. Sentiment estimation is achieved using a sentiment estimation function, for example, using a sentiment engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the customization unit may be performed using a generative AI, or not using a generative AI. For example, the customization unit can input the sentiment data of educational institutions into a generative AI and have the generative AI perform the adjustment of the evaluation model.

[0089] The customization unit can improve the accuracy of the model by referring to the educational institution's past evaluation data during customization. For example, the customization unit can analyze the educational institution's past evaluation data to improve the accuracy of the evaluation model. For example, the customization unit can refer to the educational institution's past evaluation patterns to perform consistent evaluations. For example, the customization unit can set evaluation criteria to reinforce specific weaknesses from the educational institution's past evaluation data. This improves the accuracy of the model by referring to past evaluation data. Some or all of the above processing in the customization unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the customization unit can input past evaluation data into a generative AI and have the generative AI perform the model accuracy improvement.

[0090] The customization unit can apply different customization algorithms during the customization process according to the specific needs of the educational institution. For example, if the educational institution emphasizes a particular skill, the customization unit can apply a customization algorithm that focuses on that skill. For example, if the educational institution has a particular evaluation standard, the customization unit can apply a customization algorithm that matches that standard. For example, if the educational institution employs a particular evaluation method, the customization unit can apply a customization algorithm that matches that method. This enables customization to meet specific needs. Some or all of the above-described processes in the customization unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the customization unit can input the educational institution's needs into a generative AI and have the generative AI apply an appropriate customization algorithm.

[0091] The customization unit can estimate the sentiment of educational institutions and adjust the display method of the customization results based on the estimated sentiment of the educational institution. For example, if an educational institution is seeking rigorous evaluation, the customization unit can provide a simple and highly visible display method. For example, if an educational institution is seeking flexible evaluation, the customization unit can provide a display method that includes detailed information. For example, if an educational institution values ​​a particular skill, the customization unit can provide a display method that emphasizes that skill. This makes it possible to display customization results that are tailored to the sentiment of the educational institution. Sentiment estimation is achieved using a sentiment estimation function, for example, using a sentiment engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the customization unit may be performed using a generative AI, or not. For example, the customization unit can input the sentiment data of educational institutions into a generative AI and have the generative AI perform the adjustment of the display method.

[0092] The customization unit can adjust the model during customization, taking into account the geographical and cultural background of the educational institution. For example, the customization unit can consider the geographical background of the educational institution and set region-specific evaluation criteria. For example, the customization unit can consider the cultural background of the educational institution and reflect a cultural perspective in the evaluation. For example, the customization unit can consider the linguistic background of the educational institution and reflect language use and expression methods in the evaluation. This makes it possible to adjust the model to take geographical and cultural backgrounds into account. Some or all of the above processing in the customization unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the customization unit can input the geographical and cultural background of the educational institution into a generative AI and have the generative AI perform the model adjustments.

[0093] The customization unit can analyze the social media activities of educational institutions and supplement relevant information during the customization process. For example, the customization unit can identify interests in specific topics from the social media activities of educational institutions and reflect this in evaluation criteria. For example, the customization unit can reflect the emphasis placed on specific skills in evaluations based on the social media activities of educational institutions. For example, if an educational institution employs a specific evaluation method, the customization unit can set evaluation criteria that align with that method based on the social media activities of educational institutions. This allows for the supplementation of relevant information by analyzing social media activities. Some or all of the above-described processes in the customization unit may be performed using, for example, generative AI, or without generative AI. For example, the customization unit can input the social media activities of educational institutions into a generative AI and have the generative AI perform the supplementation of relevant information.

[0094] The detection unit can estimate the test-taker's emotions and adjust the cheating detection criteria based on the estimated emotions. For example, if the test-taker is nervous, the detection unit can relax the cheating detection criteria and prioritize natural behavior. For example, if the test-taker is confident, the detection unit can tighten the cheating detection criteria and detect abnormal behavior. For example, if the test-taker is anxious, the detection unit can adjust the cheating detection criteria and prioritize accuracy of content over speed of action. By adjusting the cheating detection criteria according to the test-taker's emotions, more appropriate cheating detection becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the detection unit may be performed using a generative AI, or not. For example, the detection unit can input the test-taker's emotion data into a generative AI and have the generative AI adjust the cheating detection criteria.

[0095] The detection unit can improve the accuracy of detection by referring to the test taker's past behavioral history when detecting fraud. For example, the detection unit can analyze the test taker's past behavioral history and detect abnormal behavior. For example, the detection unit can refer to the test taker's past behavioral patterns and highly value inconsistent behavior. For example, the detection unit can set detection criteria to reinforce specific fraudulent activities based on the test taker's past behavioral history. This improves the accuracy of detection by referring to past behavioral history. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input past behavioral history into a generative AI and have the generative AI perform the detection accuracy improvement.

[0096] The detection unit can apply algorithms that analyze response patterns and interview utterance patterns in detail when fraud is detected. For example, the detection unit can analyze the applicant's response patterns in detail and detect abnormal responses. For example, the detection unit can analyze the applicant's interview utterance patterns and detect unnatural utterances. For example, the detection unit can comprehensively analyze the applicant's response patterns and interview utterance patterns to perform comprehensive fraud detection. This improves the accuracy of detection by analyzing response patterns and utterance patterns in detail. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input response patterns and utterance patterns into a generative AI and have the generative AI perform a detailed analysis.

[0097] The detection unit can estimate the examinee's emotions and adjust the display method of the detection results based on the estimated emotions. For example, if the examinee is nervous, the detection unit can provide a simple and highly visible display method. For example, if the examinee is relaxed, the detection unit can provide a display method that includes detailed information. For example, if the examinee is anxious, the detection unit can provide a display method that gets straight to the point. This makes it possible to display detection results according to the examinee's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the detection unit may be performed using a generative AI, or not using a generative AI. For example, the detection unit can input the examinee's emotion data into a generative AI and have the generative AI adjust the display method.

[0098] The detection unit can perform fraud detection while considering the test-taker's geographical and cultural background. For example, the detection unit can consider the test-taker's geographical background to detect region-specific fraudulent activities. For example, the detection unit can consider the test-taker's cultural background to reflect a cultural perspective in the evaluation. For example, the detection unit can consider the test-taker's linguistic background to reflect language use and expression methods in the evaluation. This makes it possible to detect fraud while considering geographical and cultural background. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input the test-taker's geographical and cultural background into a generative AI and have the generative AI perform adjustments to the detection.

[0099] The detection unit can analyze the examinee's social media activity and supplement relevant information when fraud is detected. For example, the detection unit can detect abnormal behavior from the examinee's social media activity. For example, the detection unit can detect specific fraudulent activities from the examinee's social media activity. For example, the detection unit can reflect the examinee's communication and expressive abilities in the evaluation based on their social media activity. In this way, relevant information can be supplemented by analyzing social media activity. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input the examinee's social media activity into a generative AI and have the generative AI perform the supplementation of relevant information.

[0100] The feedback unit can estimate the examinee's emotions and adjust the content of the feedback based on the estimated emotions. For example, if the examinee is nervous, the feedback unit can provide simple and easy-to-understand feedback. For example, if the examinee is relaxed, the feedback unit can provide feedback that includes detailed information. For example, if the examinee is anxious, the feedback unit can provide concise feedback. This ensures that the feedback content is tailored to the examinee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the feedback unit can input the examinee's emotion data into a generative AI and have the generative AI adjust the content of the feedback.

[0101] The feedback unit can provide optimal feedback by referring to the examinee's past evaluation results during the feedback process. For example, the feedback unit can analyze the examinee's past evaluation results and reflect their level of growth in the evaluation. For example, the feedback unit can refer to the examinee's past evaluation patterns and provide consistent feedback. For example, the feedback unit can provide feedback to reinforce specific weaknesses based on the examinee's past evaluation results. In this way, optimal feedback is provided by referring to past evaluation results. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input past evaluation results into a generative AI and have the generative AI perform the task of providing optimal feedback.

[0102] The feedback unit can estimate the examinee's emotions and adjust the way the feedback is displayed based on the estimated emotions. For example, if the examinee is nervous, the feedback unit can provide a simple and highly visible display method. For example, if the examinee is relaxed, the feedback unit can provide a display method that includes detailed information. For example, if the examinee is anxious, the feedback unit can provide a display method that gets straight to the point. This makes it possible to display feedback that is appropriate to the examinee's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using a generative AI, or not using a generative AI. For example, the feedback unit can input the examinee's emotion data into a generative AI and have the generative AI adjust the display method.

[0103] The feedback unit can provide optimal feedback by considering the examinee's geographical and cultural background. For example, the feedback unit can consider the examinee's geographical background and provide region-specific feedback. For example, the feedback unit can consider the examinee's cultural background and reflect a cultural perspective in the evaluation. For example, the feedback unit can consider the examinee's linguistic background and reflect language use and expression in the evaluation. This ensures that feedback is provided that takes geographical and cultural backgrounds into account. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input the examinee's geographical and cultural background into a generative AI and have the generative AI provide optimal feedback.

[0104] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0105] The analysis unit can evaluate examinees' essay responses while considering the style and tone of the answers. For example, if an examinee uses a formal style, the analysis unit can apply evaluation criteria appropriate to that style. Similarly, if an examinee uses a casual style, the analysis unit can apply evaluation criteria appropriate to that style. Furthermore, the analysis unit can determine whether the tone of the examinee's answer is positive or negative and provide an evaluation accordingly. This enables flexible evaluation that takes into account the examinee's style and tone.

[0106] The evaluation unit can analyze the nonverbal communication elements of applicants during interviews. For example, it can analyze applicants' facial expressions and gestures and reflect this in the evaluation of their communication skills. It can also analyze applicants' eye contact and posture and reflect their confidence and sincerity during the interview. Furthermore, it can analyze the applicants' voice tone and rhythm and reflect the emotional nuances of their statements in the evaluation. This enables a comprehensive evaluation that takes nonverbal communication elements into consideration.

[0107] The customization function can adjust the evaluation model based on the specific educational policies and philosophies of an educational institution. For example, if an educational institution emphasizes creativity, the customization function can set evaluation criteria that highly value creative answers. If an educational institution emphasizes logical thinking, the customization function can set evaluation criteria that highly value answers with a logical structure. Furthermore, if an educational institution emphasizes communication skills, the customization function can set evaluation criteria that reflect the clarity and consistency of speech in the evaluation. This makes it possible to adjust the evaluation model to suit the educational policies and philosophies of an educational institution.

[0108] The detection unit monitors the examinee's behavior patterns in real time and can detect signs of cheating early. For example, the detection unit can analyze the examinee's eye movements to detect the possibility of cheating. It can also analyze the examinee's hand movements to detect unnatural movements. Furthermore, the detection unit can analyze changes in the examinee's posture to detect signs of tension or anxiety. This enables early detection of cheating through real-time behavioral monitoring.

[0109] The feedback system can provide feedback tailored to the test-taker's learning style. For example, it can provide visual feedback using graphs and charts for visual learners, audio feedback for auditory learners, and practical advice and exercises for experiential learners. This ensures that the optimal feedback is provided according to the test-taker's learning style.

[0110] The analysis unit can estimate the examinee's emotions and adjust the evaluation criteria for essay responses based on those estimated emotions. For example, if the examinee is nervous, the evaluation criteria can be relaxed, emphasizing responses given in a relaxed state. Conversely, if the examinee is confident, the evaluation criteria can be made stricter, demanding a higher level of response. Furthermore, if the examinee is anxious, the evaluation criteria can be adjusted to prioritize accuracy of content over speed of response. By adjusting the evaluation criteria according to the examinee's emotions, a more appropriate evaluation becomes possible.

[0111] The evaluation department can estimate the applicant's emotions and adjust the interview evaluation criteria based on those estimates. For example, if the applicant is nervous, the evaluation criteria can be relaxed, and emphasis can be placed on relaxed speech. Conversely, if the applicant is confident, the evaluation criteria can be made stricter, requiring a higher level of speech. Furthermore, if the applicant is anxious, the evaluation criteria can be adjusted to prioritize accuracy of content over speed of speech. By adjusting the interview evaluation criteria according to the applicant's emotions, a more appropriate evaluation becomes possible.

[0112] The feedback unit can estimate the test-taker's emotions and adjust the content of the feedback based on those emotions. For example, if the test-taker is nervous, it can provide simple and easy-to-understand feedback. If the test-taker is relaxed, it can provide feedback that includes more detailed information. Furthermore, if the test-taker is anxious, it can provide concise and to-the-point feedback. This ensures that the feedback content is tailored to the test-taker's emotions.

[0113] The detection unit can estimate the test-taker's emotions and adjust the cheating detection criteria based on those emotions. For example, if the test-taker is nervous, the cheating detection criteria can be relaxed and emphasis can be placed on natural behavior. Conversely, if the test-taker is confident, the cheating detection criteria can be tightened to detect abnormal behavior. Furthermore, if the test-taker is anxious, the cheating detection criteria can be adjusted to prioritize accuracy of content over speed of action. By adjusting the cheating detection criteria according to the test-taker's emotions, more appropriate cheating detection becomes possible.

[0114] The customization section can estimate the sentiments of educational institutions and adjust the evaluation model based on those sentiments. For example, if an institution requests rigorous evaluation, the evaluation criteria can be set strictly. Conversely, if an institution requests flexible evaluation, the evaluation criteria can be relaxed. Furthermore, if an institution emphasizes specific skills, evaluation criteria can be set to focus on those skills. This makes it possible to adjust the evaluation model in accordance with the sentiments of educational institutions.

[0115] The following briefly describes the processing flow for example form 2.

[0116] Step 1: The analysis unit analyzes and scores the essay responses. The analysis unit uses natural language processing techniques to analyze the structure and content of the text in detail and then scores it. For example, it uses morphological analysis to analyze the words in the text, grammatical analysis to analyze the structure of the text, and semantic analysis to analyze the content of the text. Step 2: The evaluation department analyzes the interview audio data to assess the applicant's thinking and communication skills. The evaluation department uses speech recognition technology to analyze the applicant's statements and speaking style, and scores them based on evaluation criteria. For example, it preprocesses the audio data, uses a speech recognition algorithm to convert the statements into text, and evaluates the logic and expressiveness of the statements. Step 3: The customization team customizes the AI ​​evaluation model to match the evaluation criteria of each educational institution. The customization team uses sample data provided by the educational institution to train the AI ​​and adjust the evaluation model. For example, they analyze the format and content of the sample data and adjust the parameters of the evaluation model. Step 4: The detection unit detects cheating and inappropriate answers. The detection unit detects cases where the same answer is submitted by multiple candidates, or unnatural patterns of speech during the interview. For example, it calculates the degree of similarity of answers and detects abnormalities in speech patterns.

[0117] 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.

[0118] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0119] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0120] Each of the multiple elements described above, including the analysis unit, evaluation unit, customization unit, detection unit, and feedback unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the smart device 14, which analyzes the written answers and performs scoring. The evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the audio data of the interview and evaluates the examinee's thinking ability and communication skills. The customization unit is implemented by the specific processing unit 290 of the data processing unit 12, which customizes the AI ​​evaluation model to match the evaluation criteria of each educational institution. The detection unit is implemented by the control unit 46A of the smart device 14, which detects cheating and inappropriate answers. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12, which provides evaluation results and areas for improvement. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0121] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0122] 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.

[0123] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0124] 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.

[0125] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0126] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0127] 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.

[0128] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0129] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0130] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0131] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0132] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0133] 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.

[0134] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0135] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0136] Each of the multiple elements described above, including the analysis unit, evaluation unit, customization unit, detection unit, and feedback unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the smart glasses 214, which analyzes the written answers and performs scoring. The evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the audio data of the interview and evaluates the examinee's thinking ability and communication skills. The customization unit is implemented by the specific processing unit 290 of the data processing unit 12, which customizes the AI ​​evaluation model to match the evaluation criteria of each educational institution. The detection unit is implemented by the control unit 46A of the smart glasses 214, which detects cheating and inappropriate answers. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12, which provides evaluation results and areas for improvement. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0137] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0138] 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.

[0139] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0140] 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.

[0141] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0142] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0143] 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.

[0144] 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.

[0145] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0146] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0147] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0148] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0149] 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.

[0150] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0151] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0152] Each of the multiple elements described above, including the analysis unit, evaluation unit, customization unit, detection unit, and feedback unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the headset terminal 314, which analyzes the written answers and performs scoring. The evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the interview audio data and evaluates the examinee's thinking ability and communication skills. The customization unit is implemented by the specific processing unit 290 of the data processing unit 12, which customizes the AI ​​evaluation model to match the evaluation criteria of each educational institution. The detection unit is implemented by the control unit 46A of the headset terminal 314, which detects cheating and inappropriate answers. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12, which provides evaluation results and areas for improvement. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0153] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0154] 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.

[0155] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0156] 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.

[0157] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0158] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0159] 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.

[0160] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0161] 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.

[0162] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0163] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0164] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0165] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0166] 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.

[0167] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0168] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0169] Each of the multiple elements described above, including the analysis unit, evaluation unit, customization unit, detection unit, and feedback unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the robot 414, which analyzes the written answers and performs scoring. The evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the audio data of the interview and evaluates the examinee's thinking ability and communication skills. The customization unit is implemented by the specific processing unit 290 of the data processing unit 12, which customizes the AI ​​evaluation model to match the evaluation criteria of each educational institution. The detection unit is implemented by the control unit 46A of the robot 414, which detects cheating and inappropriate answers. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12, which provides evaluation results and areas for improvement. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0170] 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.

[0171] Figure 9 shows the 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.

[0172] 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.

[0173] 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.

[0174] 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, and motorcycles, 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 based, for example, 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.

[0175] 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."

[0176] 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.

[0177] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0186] 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 other things 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.

[0187] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0188] (Note 1) The analysis unit analyzes the essay responses and performs scoring, An evaluation unit analyzes the audio data of the interview analyzed by the aforementioned analysis unit and evaluates the applicant's thinking ability and communication skills. A customization unit customizes the AI ​​evaluation model to match the evaluation criteria for each educational institution evaluated by the aforementioned evaluation unit, The system includes a detection unit that detects cheating or inappropriate answers customized by the aforementioned customization unit. A system characterized by the following features. (Note 2) It includes a feedback section that provides evaluation results and suggestions for improvement. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, Using natural language processing techniques, the structure and content of a text are analyzed in detail and scored. The system described in Appendix 1, characterized by the features described herein. (Note 4) The evaluation unit, Using speech recognition technology, the content and manner of the test-taker's speech are analyzed, and a score is assigned based on evaluation criteria. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned customization unit is The AI ​​learns and adjusts its evaluation model based on sample data provided by educational institutions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The detection unit, The system detects instances where the same answer is submitted by multiple applicants, or where there are unnatural patterns in the interview responses. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, The system estimates the emotions of the test-takers and adjusts the evaluation criteria for their essay responses based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, When analyzing essay responses, we improve the accuracy of evaluation by referring to the examinee's past response history. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, When analyzing essay responses, different analysis algorithms are applied depending on the theme and topic of the response. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, The system estimates the emotions of test-takers and adjusts the display method of the analysis results based on the estimated emotions of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, When analyzing essay responses, the geographical and cultural backgrounds of the test-takers will be taken into consideration during the evaluation process. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, When analyzing essay responses, we analyze the examinee's social media activity and supplement it with relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The evaluation unit, The system estimates the applicant's emotions and adjusts the interview evaluation criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The evaluation unit, During interview evaluations, referencing the applicant's past interview history improves the accuracy of the evaluation. The system described in Appendix 1, characterized by the features described herein. (Note 15) The evaluation unit, During the interview evaluation, an algorithm is applied that analyzes in detail the content of the applicant's statements and their speaking patterns. The system described in Appendix 1, characterized by the features described herein. (Note 16) The evaluation unit, The system estimates the emotions of test-takers and adjusts how the evaluation results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The evaluation unit, During the interview evaluation, the applicant's geographical and cultural background will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 18) The evaluation unit, During the interview evaluation, analyze the applicant's social media activity and supplement it with relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned customization unit is The sentiment of educational institutions is estimated, and the evaluation model is adjusted based on the estimated sentiment of educational institutions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned customization unit is During customization, the accuracy of the model is improved by referencing past evaluation data from educational institutions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned customization unit is During customization, different customization algorithms are applied according to the specific needs of the educational institution. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned customization unit is It estimates the sentiment of educational institutions and adjusts how customized results are displayed based on the estimated sentiment of the educational institutions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned customization unit is During customization, the model is adjusted to take into account the geographical and cultural background of the educational institution. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned customization unit is During customization, analyze the social media activity of educational institutions and supplement with relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 25) The detection unit, The system estimates the emotions of test-takers and adjusts the criteria for detecting cheating based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The detection unit, When detecting fraud, the accuracy of the detection is improved by referring to the test taker's past behavioral history. The system described in Appendix 1, characterized by the features described herein. (Note 27) The detection unit, When fraud is detected, an algorithm is applied that analyzes in detail the patterns of responses and interview statements. The system described in Appendix 1, characterized by the features described herein. (Note 28) The detection unit, The system estimates the test-taker's emotions and adjusts how the detection results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The detection unit, When detecting fraud, the geographical and cultural background of the test take into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 30) The detection unit, When fraud is detected, the system analyzes the test taker's social media activity and supplements it with relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned feedback unit is The system estimates the test-taker's emotions and adjusts the content of the feedback based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned feedback unit is When providing feedback, refer to the applicant's past evaluation results to provide the most appropriate feedback. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned feedback unit is The system estimates the test-taker's emotions and adjusts how feedback is displayed based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned feedback unit is When providing feedback, we take into account the applicant's geographical and cultural background to provide the most appropriate feedback. The system described in Appendix 2, characterized by the features described herein. [Explanation of symbols]

[0189] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The analysis unit analyzes the essay responses and performs scoring, An evaluation unit analyzes the audio data of the interview analyzed by the aforementioned analysis unit and evaluates the applicant's thinking ability and communication skills. A customization unit customizes the AI ​​evaluation model to match the evaluation criteria for each educational institution evaluated by the aforementioned evaluation unit, The system includes a detection unit that detects cheating or inappropriate answers customized by the aforementioned customization unit. A system characterized by the following features.

2. It includes a feedback section that provides evaluation results and suggestions for improvement. The system according to feature 1.

3. The aforementioned analysis unit, Using natural language processing techniques, the structure and content of a text are analyzed in detail and scored. The system according to feature 1.

4. The evaluation unit, Using speech recognition technology, the content and manner of the test-taker's speech are analyzed, and a score is assigned based on evaluation criteria. The system according to feature 1.

5. The aforementioned customization unit is The AI ​​learns and adjusts its evaluation model based on sample data provided by educational institutions. The system according to feature 1.

6. The detection unit, The system detects instances where the same answer is submitted by multiple applicants, or where there are unnatural patterns in the interview responses. The system according to feature 1.

7. The aforementioned analysis unit, The system estimates the emotions of the test-takers and adjusts the evaluation criteria for their essay responses based on those estimated emotions. The system according to feature 1.

8. The aforementioned analysis unit, When analyzing essay responses, we improve the accuracy of evaluation by referring to the examinee's past response history. The system according to feature 1.

9. The aforementioned analysis unit, When analyzing essay responses, different analysis algorithms are applied depending on the theme and topic of the response. The system according to feature 1.

Images