System

Abstract

The system according to the embodiment is intended to perform a test in a digital format and to fairly and quickly score the test using generated AI.SOLUTION: A system includes a digital test execution part, a generation AI scoring part, an evaluation reference application part, a pass / fail determination part, and a cost reduction part. The digital test implementation unit implements a test in digital form. The generated AI scorer analyzes the responses received by the digital exam implementer. An evaluation criteria application unit applies evaluation criteria to the answer analyzed by the generated AI scoring unit. The pass / fail determination unit determines pass or fail based on the result evaluated by the evaluation criterion application unit. The cost reduction unit reduces the scoring cost by the generated AI scoring unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional techniques, there are problems with grader inconsistency and grading costs when grading handwritten essay tests, and there is room for improvement.

[0005] The system according to the embodiment aims to administer digital exams and grade them fairly and quickly using generative AI. [Means for solving the problem]

[0006] The system according to the embodiment includes a digital test implementation unit, a generative AI scoring unit, an evaluation criteria application unit, a pass / fail determination unit, and a cost reduction unit. The digital test implementation unit implements a digital test. The generative AI scoring unit analyzes answers received by the digital test implementation unit. The evaluation criteria application unit applies evaluation criteria to the answers analyzed by the generative AI scoring unit. The pass / fail determination unit determines pass / fail based on the results evaluated by the evaluation criteria application unit. The cost reduction unit reduces the scoring costs using the generative AI scoring unit. [Effects of the Invention]

[0007] The system according to the embodiment can administer digital exams and grade them fairly and quickly using generative AI. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A qualification exam scoring system according to an embodiment of the present invention uses generative AI to score qualification exams, ensuring fairness in the exam, enabling quick confirmation of pass / fail results, and reducing implementation costs. As a result, the qualification exam scoring system ensures fairness in the exam, enabling quick confirmation of pass / fail results, and reducing implementation costs.

[0029] A qualification exam scoring system according to an embodiment includes a digital exam implementation unit, a generative AI scoring unit, an evaluation criteria application unit, a pass / fail determination unit, and a cost reduction unit. The digital exam implementation unit accepts digital answers from examinees. For example, examinees can take the exam using a PC or tablet. The generative AI scoring unit analyzes the answers accepted by the digital exam implementation unit. For example, the generative AI analyzes the answers using a text generation AI (e.g., LLM). The evaluation criteria application unit applies evaluation criteria to the answers analyzed by the generative AI scoring unit. For example, the evaluation criteria application unit evaluates the content of the essay, logical consistency, grammatical accuracy, etc. The pass / fail determination unit determines pass / fail based on the results of evaluation by the evaluation criteria application unit. For example, the pass / fail determination unit sets a passing score and determines pass / fail based on that score. The cost reduction unit reduces scoring costs using the generative AI scoring unit. For example, the cost reduction unit reduces labor costs associated with grading. As a result, the qualification exam scoring system according to the embodiment maintains the fairness of the exam, allows quick confirmation of pass / fail results, and reduces implementation costs. For example, examinees are notified of their pass / fail results within minutes of completing the exam. Costs are reduced because there is no need to hire scorers.

[0030] The digital test administration unit can analyze the test taker's input speed and typing patterns to estimate the stress level during the test. For example, the digital test administration unit can analyze the test taker's keyboard input speed and typing patterns in real time to build a system that estimates stress levels. For example, if the test taker's input speed suddenly slows or if the number of typos increases, it can be determined that stress is increasing. This makes it possible to estimate the test taker's stress level in real time.

[0031] The Digital Testing Department will use a generation AI to analyze test takers' answers in real time during the test, and automatically correct any typos or grammatical errors. The Digital Testing Department will build a system where, for example, a generation AI will analyze test takers' answers in real time and automatically correct any typos or grammatical errors. For example, it will detect typos as they are being entered and automatically correct them. This will allow typos and grammatical errors in test takers' answers to be corrected in real time.

[0032] The digital test administration unit can provide a variety of input methods for digital tests, including voice input and handwriting input. The digital test administration unit, for example, builds a system that supports voice input for digital tests. For example, it allows test takers to use a microphone to input answers by voice. This provides a variety of input methods, improving convenience for test takers.

[0033] The Digital Testing Department uses a generation AI to automatically summarize answers to test questions, making it easier for test takers to check the answers. The Digital Testing Department, for example, builds a system in which a generation AI automatically summarizes test takers' answers, making it easier for test takers to check the answers. For example, it can display a short summary of a long answer. This provides a summary function that makes it easier for test takers to check the answers.

[0034] When analyzing the examinee's answers, the generative AI scoring unit can introduce an algorithm that evaluates the originality and creativity of the answers. For example, the generative AI scoring unit develops an algorithm that analyzes the examinee's answers and evaluates the originality and creativity of the answers. For example, it scores the novelty and originality of the answers. This makes it possible to introduce an algorithm that evaluates the originality and creativity of the examinee's answers.

[0035] The generative AI scoring unit can refer to the background information and related knowledge of the answers and perform scoring based on a deeper understanding. For example, the generative AI scoring unit constructs a system in which the generative AI analyzes the content of the examinee's answers and performs scoring by referring to the background information and related knowledge. For example, it evaluates the theory and knowledge behind the answers. This allows scoring based on a deeper understanding by referring to the background information and related knowledge of the answers.

[0036] The generation AI scoring unit can automatically translate answers in different languages ​​and provide multilingual scoring. The generation AI scoring unit, for example, builds a system in which the generation AI automatically translates answers in different languages ​​and provides multilingual scoring. For example, it supports multiple languages ​​such as English and French. This allows answers in different languages ​​to be automatically translated and multilingual scoring to be provided.

[0037] The generative AI scoring unit can visualize the content of the answers and visually evaluate them using graphs and charts. For example, the generative AI scoring unit constructs a system in which the generative AI visualizes the content of the examinee's answers and visually evaluates them using graphs and charts. For example, the structure and logic of the answers can be displayed in graphs. This allows the content of the answers to be visualized and visually evaluated.

[0038] The evaluation criteria application unit can learn from past scoring data and perform scoring that takes into account the evolution and changes in the scoring criteria. For example, the evaluation criteria application unit constructs a system in which a generation AI learns from past scoring data and performs scoring that takes into account the evolution and changes in the scoring criteria. For example, it adjusts the current scoring criteria based on the past scoring criteria. This makes it possible to learn from past scoring data and perform scoring that takes into account the evolution and changes in the scoring criteria.

[0039] The evaluation criteria application unit can compare the scoring results with multiple evaluators and provide feedback to increase the degree of agreement between the evaluators. For example, the evaluation criteria application unit constructs a system in which the generation AI compares the scoring results with multiple evaluators and provides feedback to increase the degree of agreement between the evaluators. For example, the evaluation criteria application unit scores the degree of agreement between the evaluators and provides feedback. This makes it possible to compare the scoring results with multiple evaluators and provide feedback to increase the degree of agreement between the evaluators.

[0040] The evaluation criteria application unit can generate multiple scoring results using different evaluation criteria and select the fairest result. The evaluation criteria application unit, for example, constructs a system in which a generation AI generates multiple scoring results using different evaluation criteria and selects the fairest result. For example, the evaluation criteria application unit generates scoring results based on multiple evaluation criteria and selects the fairest result. This makes it possible to generate multiple scoring results using different evaluation criteria and select the fairest result.

[0041] The evaluation criteria application unit visualizes the scoring results in real time, making it easier for test takers to understand their own evaluations. For example, the evaluation criteria application unit constructs a system in which a generation AI visualizes the scoring results in real time, making it easier for test takers to understand their own evaluations. For example, the evaluation criteria application unit displays the scoring results in graphs and charts. This visualizes the scoring results in real time, making it easier for test takers to understand their own evaluations.

[0042] The pass / fail determination unit can make a pass / fail decision immediately after the end of the test and notify the test taker of the results in real time. For example, the pass / fail determination unit will build a system in which the generation AI makes a pass / fail decision immediately after the end of the test and notifies the test taker of the results in real time. For example, the pass / fail result will be notified within a few minutes after the end of the test. This makes it possible to make a pass / fail decision immediately after the end of the test and notify the test taker of the results in real time.

[0043] The pass / fail determination unit can explain in detail the basis for the pass / fail determination, making it easier for test takers to understand the results. For example, the pass / fail determination unit constructs a system in which the generation AI explains in detail the basis for the pass / fail determination, making it easier for test takers to understand the results. For example, it explains in detail the reasons for the pass / fail determination. This allows the basis for the pass / fail determination to be explained in detail, making it easier for test takers to understand the results.

[0044] The pass / fail determination unit can notify the test taker of the pass / fail result in different formats. For example, the pass / fail determination unit builds a system in which the generation AI notifies the test taker of the pass / fail result in different formats. For example, the results can be notified by email, SMS, app notification, etc. This makes it possible to notify the test taker of the pass / fail result in different formats.

[0045] The pass / fail determination unit can visualize the pass / fail determination results and make them visually easier to understand using graphs and charts. The pass / fail determination unit, for example, constructs a system in which the generation AI visualizes the pass / fail determination results and makes them visually easier to understand using graphs and charts. For example, the pass / fail results are displayed in graphs and charts. This makes it possible to visualize the pass / fail determination results and make them visually easier to understand using graphs and charts.

[0046] The Cost Reduction Department can reduce costs by optimizing the scoring process and eliminating unnecessary processes. For example, the Cost Reduction Department develops an algorithm that uses generative AI to optimize the scoring process and eliminate unnecessary processes. For example, it can eliminate duplicate processes and achieve efficient scoring. This can reduce costs by optimizing the scoring process and eliminating unnecessary processes.

[0047] The cost reduction unit can efficiently manage the scoring data and reduce data storage costs. The cost reduction unit, for example, constructs a system in which the generative AI efficiently manages the scoring data and reduces data storage costs. For example, it compresses and optimizes the data. This makes it possible to efficiently manage the scoring data and reduce data storage costs.

[0048] The cost reduction unit executes the scoring process on a cloud basis, thereby reducing infrastructure costs. For example, the cost reduction unit builds a system in which the generative AI executes the scoring process on a cloud basis, thereby reducing infrastructure costs. For example, the scoring process is executed using a cloud server. This allows the scoring process to be executed on a cloud basis, thereby reducing infrastructure costs.

[0049] The cost reduction department can automatically archive the scoring results and make them available for future reference and analysis. The cost reduction department, for example, builds a system that enables the generative AI to automatically archive the scoring results and make them available for future reference and analysis. For example, the scoring results are stored in a database. This enables the scoring results to be automatically archived and made available for future reference and analysis.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The qualification exam scoring system can also be equipped with a learning support unit that analyzes the test taker's learning history and provides individualized study advice based on the test results. For example, it can analyze what questions the test taker struggled with in the past and provide specific study advice for the next test. It can also identify the test taker's strengths and weaknesses and propose an efficient study plan. This makes it easier for test takers to overcome their weaknesses and improves the test pass rate.

[0052] The Digital Test Administration Department not only uses generative AI to analyze test takers' answers in real time during the test, but also monitors the materials and websites that test takers refer to during the test to detect cheating. For example, a warning will be displayed if a test taker views a website containing specific keywords during the test. It can also detect cheating if a test taker communicates with other test takers during the test. This further enhances the fairness of the test.

[0053] The Digital Test Administration Department not only supports voice input and handwriting input for digital tests, but also provides accessibility features to accommodate test takers with visual or hearing impairments. For example, it can provide a screen reader for the visually impaired, and sign language interpretation and subtitle display functions for the hearing impaired. This will create an environment in which all test takers can take the test equally.

[0054] The Digital Test Administration Department not only uses AI to automatically summarize answers to test questions, but also provides a digital notebook function for test takers to take notes during the test. For example, test takers can record ideas and important points that come to mind during the test in a digital notebook. It can also automatically organize the contents of the digital notebook after the test is over and provide them as review material. This allows test takers to efficiently prepare for the test.

[0055] When analyzing test takers' answers, the generative AI scoring unit not only employs algorithms to evaluate the originality and creativity of the answers, but also provides feedback on the test takers' answers. For example, it can display specific evaluation points for the originality and creativity of the answers. It can also provide advice on how test takers can improve their answers. This allows test takers to reflect on their answers and identify areas for improvement for the next test.

[0056] The generative AI scoring unit not only scores based on a deeper understanding of the answer by referring to the background information and related knowledge, but also provides reference materials for the test-taker's answer. For example, it can display links to academic papers and books related to the answer. It can also provide information on video lectures and online courses related to the answer. This allows test-takers to find reference materials to further refine their answers.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The digital testing department accepts the test taker's digital responses. For example, the test taker can take the test using a PC or tablet. Step 2: The Generative AI Marking Unit analyzes the answers received by the Digital Test Administration Unit. For example, the Generative AI may analyze the answers using a text-generating AI (e.g., LLM). Step 3: The evaluation criteria applicator applies evaluation criteria to the answers analyzed by the generative AI scorer. For example, the evaluation criteria applicator evaluates the content of the essay, logical consistency, grammatical accuracy, etc. Step 4: The pass / fail determination unit determines whether the application passes or fails based on the results of the evaluation performed by the evaluation criteria application unit. For example, the pass / fail determination unit sets a passing score and determines whether the application passes or fails based on that standard. Step 5: The cost reduction unit reduces the scoring costs using the generation AI scoring unit. For example, the cost reduction unit reduces the labor costs involved in scoring. As a result, the qualification exam scoring system according to the embodiment maintains the fairness of the exam, can quickly confirm pass / fail results, and reduces implementation costs.

[0059] (Example 2) A qualification exam scoring system according to an embodiment of the present invention uses generative AI to score qualification exams, ensuring fairness in the exam, enabling quick confirmation of pass / fail results, and reducing implementation costs. As a result, the qualification exam scoring system ensures fairness in the exam, enabling quick confirmation of pass / fail results, and reducing implementation costs.

[0060] A qualification exam scoring system according to an embodiment includes a digital exam implementation unit, a generative AI scoring unit, an evaluation criteria application unit, a pass / fail determination unit, and a cost reduction unit. The digital exam implementation unit accepts digital answers from examinees. For example, examinees can take the exam using a PC or tablet. The generative AI scoring unit analyzes the answers accepted by the digital exam implementation unit. For example, the generative AI analyzes the answers using a text generation AI (e.g., LLM). The evaluation criteria application unit applies evaluation criteria to the answers analyzed by the generative AI scoring unit. For example, the evaluation criteria application unit evaluates the content of the essay, logical consistency, grammatical accuracy, etc. The pass / fail determination unit determines pass / fail based on the results of evaluation by the evaluation criteria application unit. For example, the pass / fail determination unit sets a passing score and determines pass / fail based on that score. The cost reduction unit reduces scoring costs using the generative AI scoring unit. For example, the cost reduction unit reduces labor costs associated with grading. As a result, the qualification exam scoring system according to the embodiment maintains the fairness of the exam, allows quick confirmation of pass / fail results, and reduces implementation costs. For example, examinees are notified of their pass / fail results within minutes of completing the exam. Costs are reduced because there is no need to hire scorers.

[0061] The digital test administration unit can analyze the test taker's input speed and typing patterns to estimate the stress level during the test. For example, the digital test administration unit can analyze the test taker's keyboard input speed and typing patterns in real time to build a system that estimates stress levels. For example, if the test taker's input speed suddenly slows or if the number of typos increases, it can be determined that stress is increasing. This makes it possible to estimate the test taker's stress level in real time.

[0062] The Digital Testing Department will use a generation AI to analyze test takers' answers in real time during the test, and automatically correct any typos or grammatical errors. The Digital Testing Department will build a system where, for example, a generation AI will analyze test takers' answers in real time and automatically correct any typos or grammatical errors. For example, it will detect typos as they are being entered and automatically correct them. This will allow typos and grammatical errors in test takers' answers to be corrected in real time.

[0063] The digital test administration unit can use the emotion estimation function to monitor the emotional state of the test taker and provide relaxing music or messages to reduce stress and anxiety. For example, the digital test administration unit can use the emotion estimation function to monitor the emotional state of the test taker in real time and build a system to provide relaxing music to reduce stress and anxiety. For example, relaxing music can be played when stress increases. This makes it possible to provide relaxing music or messages to reduce the test taker's stress and anxiety.

[0064] The digital test administration unit can provide a variety of input methods for digital tests, including voice input and handwriting input. The digital test administration unit, for example, builds a system that supports voice input for digital tests. For example, it allows test takers to use a microphone to input answers by voice. This provides a variety of input methods, improving convenience for test takers.

[0065] The Digital Testing Department uses a generation AI to automatically summarize answers to test questions, making it easier for test takers to check the answers. The Digital Testing Department, for example, builds a system in which a generation AI automatically summarizes test takers' answers, making it easier for test takers to check the answers. For example, it can display a short summary of a long answer. This provides a summary function that makes it easier for test takers to check the answers.

[0066] The digital test administration unit can use the emotion estimation function to provide interactive feedback to reinforce the positive emotions felt by the test taker during the test. For example, the digital test administration unit uses the emotion estimation function to build a system that provides interactive feedback to reinforce the positive emotions felt by the test taker during the test. For example, the digital test administration unit displays compliments when positive emotions increase. This makes it possible to provide interactive feedback to reinforce the positive emotions felt by the test taker.

[0067] When analyzing the examinee's answers, the generative AI scoring unit can introduce an algorithm that evaluates the originality and creativity of the answers. For example, the generative AI scoring unit develops an algorithm that analyzes the examinee's answers and evaluates the originality and creativity of the answers. For example, it scores the novelty and originality of the answers. This makes it possible to introduce an algorithm that evaluates the originality and creativity of the examinee's answers.

[0068] The generative AI scoring unit can refer to the background information and related knowledge of the answers and perform scoring based on a deeper understanding. For example, the generative AI scoring unit constructs a system in which the generative AI analyzes the content of the examinee's answers and performs scoring by referring to the background information and related knowledge. For example, it evaluates the theory and knowledge behind the answers. This allows scoring based on a deeper understanding by referring to the background information and related knowledge of the answers.

[0069] The generative AI scoring unit uses the emotion estimation function to analyze the emotions expressed in the test taker's answers and can reflect emotional expressions in the evaluation. The generative AI scoring unit, for example, uses the emotion estimation function to analyze the emotions expressed in the test taker's answers and build a system that reflects emotional expressions in the evaluation. For example, it evaluates the passion and emotion expressed in the answers. This allows the emotion expressed in the test taker's answers to be analyzed and emotional expressions to be reflected in the evaluation.

[0070] The generation AI scoring unit can automatically translate answers in different languages ​​and provide multilingual scoring. The generation AI scoring unit, for example, builds a system in which the generation AI automatically translates answers in different languages ​​and provides multilingual scoring. For example, it supports multiple languages ​​such as English and French. This allows answers in different languages ​​to be automatically translated and multilingual scoring to be provided.

[0071] The generative AI scoring unit can visualize the content of the answers and visually evaluate them using graphs and charts. For example, the generative AI scoring unit constructs a system in which the generative AI visualizes the content of the examinee's answers and visually evaluates them using graphs and charts. For example, the structure and logic of the answers can be displayed in graphs. This allows the content of the answers to be visualized and visually evaluated.

[0072] The evaluation criteria application unit can learn from past scoring data and perform scoring that takes into account the evolution and changes in the scoring criteria. For example, the evaluation criteria application unit constructs a system in which a generation AI learns from past scoring data and performs scoring that takes into account the evolution and changes in the scoring criteria. For example, it adjusts the current scoring criteria based on the past scoring criteria. This makes it possible to learn from past scoring data and perform scoring that takes into account the evolution and changes in the scoring criteria.

[0073] The evaluation criteria application unit can compare the scoring results with multiple evaluators and provide feedback to increase the degree of agreement between the evaluators. For example, the evaluation criteria application unit constructs a system in which the generation AI compares the scoring results with multiple evaluators and provides feedback to increase the degree of agreement between the evaluators. For example, the evaluation criteria application unit scores the degree of agreement between the evaluators and provides feedback. This makes it possible to compare the scoring results with multiple evaluators and provide feedback to increase the degree of agreement between the evaluators.

[0074] The evaluation criteria application unit can use the emotion estimation function to consider the emotional state of the examinee and perform emotionally fair scoring. The evaluation criteria application unit, for example, uses the emotion estimation function to develop an algorithm that considers the emotional state of the examinee and performs emotionally fair scoring. For example, the evaluation criteria application unit scores the emotional state of the examinee and reflects it in the score. This allows the emotional state of the examinee to be considered and emotionally fair scoring to be performed.

[0075] The evaluation criteria application unit can generate multiple scoring results using different evaluation criteria and select the fairest result. The evaluation criteria application unit, for example, constructs a system in which a generation AI generates multiple scoring results using different evaluation criteria and selects the fairest result. For example, the evaluation criteria application unit generates scoring results based on multiple evaluation criteria and selects the fairest result. This makes it possible to generate multiple scoring results using different evaluation criteria and select the fairest result.

[0076] The evaluation criteria application unit visualizes the scoring results in real time, making it easier for test takers to understand their own evaluations. For example, the evaluation criteria application unit constructs a system in which a generation AI visualizes the scoring results in real time, making it easier for test takers to understand their own evaluations. For example, the evaluation criteria application unit displays the scoring results in graphs and charts. This visualizes the scoring results in real time, making it easier for test takers to understand their own evaluations.

[0077] The evaluation criteria application unit uses the emotion estimation function to analyze the emotions felt by the examinee regarding the scoring results and can provide emotionally convincing feedback. The evaluation criteria application unit, for example, uses the emotion estimation function to analyze the emotions felt by the examinee regarding the scoring results and builds a system that provides emotionally convincing feedback. For example, the evaluation criteria application unit scores the examinee's emotional state and reflects it in the feedback. This makes it possible to analyze the emotions felt by the examinee regarding the scoring results and provide emotionally convincing feedback.

[0078] The pass / fail determination unit can make a pass / fail decision immediately after the end of the test and notify the test taker of the results in real time. For example, the pass / fail determination unit will build a system in which the generation AI makes a pass / fail decision immediately after the end of the test and notifies the test taker of the results in real time. For example, the pass / fail result will be notified within a few minutes after the end of the test. This makes it possible to make a pass / fail decision immediately after the end of the test and notify the test taker of the results in real time.

[0079] The pass / fail determination unit can explain in detail the basis for the pass / fail determination, making it easier for test takers to understand the results. For example, the pass / fail determination unit constructs a system in which the generation AI explains in detail the basis for the pass / fail determination, making it easier for test takers to understand the results. For example, it explains in detail the reasons for the pass / fail determination. This allows the basis for the pass / fail determination to be explained in detail, making it easier for test takers to understand the results.

[0080] The pass / fail determination unit can use the emotion estimation function to analyze the examinee's emotional reaction to the pass / fail result and provide positive feedback. The pass / fail determination unit, for example, uses the emotion estimation function to analyze the examinee's emotional reaction to the pass / fail result and builds a system to provide positive feedback. For example, the emotional reaction to the pass / fail result is scored and reflected in the feedback. This makes it possible to analyze the examinee's emotional reaction to the pass / fail result and provide positive feedback.

[0081] The pass / fail determination unit can notify the test taker of the pass / fail result in different formats. For example, the pass / fail determination unit builds a system in which the generation AI notifies the test taker of the pass / fail result in different formats. For example, the results can be notified by email, SMS, app notification, etc. This makes it possible to notify the test taker of the pass / fail result in different formats.

[0082] The pass / fail determination unit can visualize the pass / fail determination results and make them visually easier to understand using graphs and charts. The pass / fail determination unit, for example, constructs a system in which the generation AI visualizes the pass / fail determination results and makes them visually easier to understand using graphs and charts. For example, the pass / fail results are displayed in graphs and charts. This makes it possible to visualize the pass / fail determination results and make them visually easier to understand using graphs and charts.

[0083] The pass / fail determination unit can use the emotion estimation function to monitor the examinee's emotions regarding the pass / fail result and provide support to reduce negative emotions. The pass / fail determination unit, for example, uses the emotion estimation function to build a system that monitors the examinee's emotions regarding the pass / fail result and provides support to reduce negative emotions. For example, an encouraging message is displayed when negative emotions increase. This makes it possible to monitor the examinee's emotions regarding the pass / fail result and provide support to reduce negative emotions.

[0084] The Cost Reduction Department can reduce costs by optimizing the scoring process and eliminating unnecessary processes. For example, the Cost Reduction Department develops an algorithm that uses generative AI to optimize the scoring process and eliminate unnecessary processes. For example, it can eliminate duplicate processes and achieve efficient scoring. This can reduce costs by optimizing the scoring process and eliminating unnecessary processes.

[0085] The cost reduction unit can efficiently manage the scoring data and reduce data storage costs. The cost reduction unit, for example, constructs a system in which the generative AI efficiently manages the scoring data and reduces data storage costs. For example, it compresses and optimizes the data. This makes it possible to efficiently manage the scoring data and reduce data storage costs.

[0086] The cost reduction unit can use the emotion estimation function to monitor the emotional state of the grader and provide support for reducing stress. The cost reduction unit, for example, uses the emotion estimation function to build a system that monitors the emotional state of the grader and provides support for reducing stress. For example, advice on how to relax when stress increases is displayed. This makes it possible to monitor the emotional state of the grader and provide support for reducing stress.

[0087] The cost reduction unit executes the scoring process on a cloud basis, thereby reducing infrastructure costs. For example, the cost reduction unit builds a system in which the generative AI executes the scoring process on a cloud basis, thereby reducing infrastructure costs. For example, the scoring process is executed using a cloud server. This allows the scoring process to be executed on a cloud basis, thereby reducing infrastructure costs.

[0088] The cost reduction department can automatically archive the scoring results and make them available for future reference and analysis. The cost reduction department, for example, builds a system that enables the generative AI to automatically archive the scoring results and make them available for future reference and analysis. For example, the scoring results are stored in a database. This enables the scoring results to be automatically archived and made available for future reference and analysis.

[0089] The cost reduction unit can use the emotion estimation function to monitor the emotional states of all parties involved in the scoring process and provide support for maintaining a positive environment. The cost reduction unit, for example, uses the emotion estimation function to build a system that monitors the emotional states of all parties involved in the scoring process and provides support for maintaining a positive environment. For example, the cost reduction unit scores the emotional states and displays advice for maintaining a positive environment. This makes it possible to monitor the emotional states of all parties involved in the scoring process and provide support for maintaining a positive environment.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The qualification exam scoring system can also be equipped with a learning support unit that analyzes the test taker's learning history and provides individualized study advice based on the test results. For example, it can analyze what questions the test taker struggled with in the past and provide specific study advice for the next test. It can also identify the test taker's strengths and weaknesses and propose an efficient study plan. This makes it easier for test takers to overcome their weaknesses and improves the test pass rate.

[0092] The Digital Test Administration Department not only analyzes the test taker's input speed and typing patterns, but also monitors their posture and facial expressions with a camera to estimate their level of concentration and fatigue during the test. For example, if their posture is poor or they look tired, it will display a message encouraging them to take a break. It can also provide advice on how to improve concentration if their concentration level is declining. This allows test takers to take the test in the best possible condition.

[0093] The Digital Test Administration Department not only uses generative AI to analyze test takers' answers in real time during the test, but also monitors the materials and websites that test takers refer to during the test to detect cheating. For example, a warning will be displayed if a test taker views a website containing specific keywords during the test. It can also detect cheating if a test taker communicates with other test takers during the test. This further enhances the fairness of the test.

[0094] The Digital Test Administration Department can not only use emotion estimation to monitor the emotional state of test takers, but also introduce gamification elements to increase test taker motivation. For example, badges and points can be awarded for achieving a certain level of progress during the test. Test takers can also be ranked according to their performance after the test is over, with rewards offered to top performers. This can increase test taker motivation and encourage them to take the test more actively.

[0095] The Digital Test Administration Department not only supports voice input and handwriting input for digital tests, but also provides accessibility features to accommodate test takers with visual or hearing impairments. For example, it can provide a screen reader for the visually impaired, and sign language interpretation and subtitle display functions for the hearing impaired. This will create an environment in which all test takers can take the test equally.

[0096] The Digital Test Administration Department not only uses AI to automatically summarize answers to test questions, but also provides a digital notebook function for test takers to take notes during the test. For example, test takers can record ideas and important points that come to mind during the test in a digital notebook. It can also automatically organize the contents of the digital notebook after the test is over and provide them as review material. This allows test takers to efficiently prepare for the test.

[0097] The digital test administration unit not only uses emotion estimation to reinforce the positive emotions experienced by test takers during the test, but also provides feedback to enhance test takers' self-efficacy. For example, specific words of praise can be displayed for questions that test takers answer correctly. Constructive advice can also be provided for questions that test takers get wrong, helping test takers feel more confident.

[0098] When analyzing test takers' answers, the generative AI scoring unit not only employs algorithms to evaluate the originality and creativity of the answers, but also provides feedback on the test takers' answers. For example, it can display specific evaluation points for the originality and creativity of the answers. It can also provide advice on how test takers can improve their answers. This allows test takers to reflect on their answers and identify areas for improvement for the next test.

[0099] The generative AI scoring unit not only scores based on a deeper understanding of the answer by referring to the background information and related knowledge, but also provides reference materials for the test-taker's answer. For example, it can display links to academic papers and books related to the answer. It can also provide information on video lectures and online courses related to the answer. This allows test-takers to find reference materials to further refine their answers.

[0100] The generative AI scoring unit not only uses emotion estimation to analyze the emotions expressed in test takers' answers, but also provides personalized feedback based on the test takers' emotions. For example, it can evaluate the passion and emotion expressed in the answers and display encouraging messages accordingly. It can also provide advice on how to relax if the test taker is in an emotionally difficult situation. This allows test takers to take the test with emotional support.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The digital testing department accepts the test taker's digital responses. For example, the test taker can take the test using a PC or tablet. Step 2: The Generative AI Marking Unit analyzes the answers received by the Digital Test Administration Unit. For example, the Generative AI may analyze the answers using a text-generating AI (e.g., LLM). Step 3: The evaluation criteria applicator applies evaluation criteria to the answers analyzed by the generative AI scorer. For example, the evaluation criteria applicator evaluates the content of the essay, logical consistency, grammatical accuracy, etc. Step 4: The pass / fail determination unit determines whether the application passes or fails based on the results of the evaluation performed by the evaluation criteria application unit. For example, the pass / fail determination unit sets a passing score and determines whether the application passes or fails based on that standard. Step 5: The cost reduction unit reduces the scoring costs using the generation AI scoring unit. For example, the cost reduction unit reduces the labor costs involved in scoring. As a result, the qualification exam scoring system according to the embodiment maintains the fairness of the exam, can quickly confirm pass / fail results, and reduces implementation costs.

[0103] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0113] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0114] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0116] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0128] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0131] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0132] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0138] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0139] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0142] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0143] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0144] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0147] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0153] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0154] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0155] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0156] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0157] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0158] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0159] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0160] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0161] 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.

[0162] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0163] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0164] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0165] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0166] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0167] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0168] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0169] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0170] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a digital testing department that conducts digital tests; a generating AI scoring unit that analyzes the answers received by the digital test administration unit; an evaluation criteria application unit that applies evaluation criteria to the answers analyzed by the generation AI scoring unit; a pass / fail determination unit that determines pass / fail based on the result of evaluation by the evaluation criterion application unit; The cost reduction unit reduces the scoring cost by the generation AI scoring unit. A system characterized by:

2. The digital test execution unit During the test, the AI ​​analyzes the examinee's answers in real time and automatically corrects spelling or grammatical errors.

2. The system of claim 1.

3. The generation AI scoring unit: When analyzing the test taker's answers, an algorithm is introduced to evaluate the originality or creativity of the answers.

2. The system of claim 1.

4. The evaluation criterion application unit Add a feature to learn from past grading data and perform grading that takes into account the evolution or changes in grading standards.

2. The system of claim 1.

5. The pass / fail determination unit Provide a function to determine pass / fail immediately after the test is completed and notify test takers of the results in real time 2. The system of claim 1.

6. The cost reduction unit Monitor graders' emotional state and provide support to reduce stress 2. The system of claim 1.

7. The digital test execution unit Monitor the test-taker's emotional state and provide relaxing music or messages to reduce stress or anxiety 2. The system of claim 1.

8. The generation AI scoring unit: Analyze the emotions expressed in the test taker's answers and reflect their emotional expressions in the evaluation.

2. The system of claim 1.

Images