System

Abstract

An object of a system according to an embodiment is to evaluate a conversation ability in multiple languages at low cost.SOLUTION: A system according to an embodiment includes a conversation unit, an evaluation unit, a multilingual handling unit, and a low cost providing unit. The conversation unit allows the subject to have a conversation with the generated AI for the presented theme. The evaluation unit evaluates the speed of the conversation performed by the conversation unit and the appropriateness of the response. The multilingual support provides conversational performance testing in all languages supported by the production AI. The low cost provider provides the language ability test at a lower cost than the conventional language ability test.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem of making it difficult to assess conversational ability in multiple languages ​​at low cost.

[0005] The system according to the embodiment aims to assess conversational ability in multiple languages ​​at low cost. [Means for solving the problem]

[0006] The system according to the embodiment comprises a conversation unit, an evaluation unit, a multilingual support unit, and a low-cost provision unit. The conversation unit allows a subject to converse with the generation AI on a presented topic. The evaluation unit evaluates the speed of the conversation conducted by the conversation unit and the appropriateness of the responses. The multilingual support unit provides a conversational ability test in all languages ​​supported by the generation AI. The low-cost provision unit provides the test at a lower cost than conventional language ability tests. [Effects of the Invention]

[0007] The system according to the embodiment can assess conversational ability in multiple languages ​​at low cost. [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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[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 conversational ability testing system according to an embodiment of the present invention is a system in which a test subject converses with a generative AI on a given topic, the speed of the conversation and the appropriateness of the responses are evaluated using the generative AI's language model, and a score is calculated. This enables the conversational ability testing system to efficiently and inexpensively conduct personnel recruitment tests for jobs requiring conversational ability.

[0029] A conversational proficiency testing system according to an embodiment includes a conversation unit, an evaluation unit, a multilingual support unit, and a low-cost provision unit. The conversation unit allows a subject to converse with a generation AI on a presented topic. For example, the generation AI understands what the subject says and generates an appropriate response. The conversation unit can also provide appropriate feedback to the generation AI in response to the subject's comments. The evaluation unit evaluates the speed of the conversation and the appropriateness of the responses provided by the conversation unit. For example, the evaluation unit evaluates whether the subject's comments are made at the appropriate time and whether the content is in line with the topic. The evaluation unit can also analyze the content of the subject's conversation and calculate a score. The multilingual support unit provides a conversational proficiency test in all languages ​​supported by the generation AI. For example, the multilingual support unit allows the generation AI to respond in an appropriate language, such as English, Japanese, or Chinese, depending on the language used by the subject. The low-cost provision unit provides a conversational proficiency test at a lower cost than conventional language proficiency tests. For example, the low-cost provision unit reduces examiner labor costs by using the generation AI. In addition, since the low-cost provision unit can conduct the test online, the preparation and operation costs of the test site can also be reduced. As a result, the conversational ability testing system according to the embodiment can conduct personnel recruitment tests for jobs that require conversational ability efficiently and at low cost.

[0030] The conversation unit can refer to the subject's past conversation history and generate questions that are individually customized. For example, the conversation unit stores the subject's past conversation history in a database and generates customized questions based on that information. For example, questions related to topics that the subject showed interest in in previous conversations are asked. The conversation unit also analyzes the subject's conversation history and finds specific patterns and trends. For example, questions are generated based on keywords frequently used by the subject. The conversation unit also generates questions that encourage deeper understanding based on the content of the subject's past conversations. For example, detailed questions are asked about topics that were touched upon in previous conversations. This makes it possible to generate questions that are individually customized for the subject.

[0031] The conversational unit can analyze the subject's non-verbal communication and adjust its responses based on that. For example, the conversational unit analyzes the subject's facial expressions using a camera and estimates their emotions in real time. For example, if the subject is confused, the generation AI will simplify the explanation. The conversational unit also detects the subject's gestures using a sensor and adjusts its responses based on that information. For example, if the subject nods, the generation AI will respond with agreement. The conversational unit also analyzes the subject's posture and movements to understand their non-verbal communication. For example, if the subject is relaxed, the generation AI will also respond in a relaxed tone. This allows the response to be adjusted based on the subject's non-verbal communication.

[0032] The conversation unit automatically changes the topic of the conversation, enabling the subject's diverse conversational abilities to be evaluated. For example, the generation AI automatically changes the topic of the conversation based on the subject's responses. For example, if the subject is good at technical topics, it will select a technology-related topic. The generation AI also suggests different topics as the conversation progresses. For example, it will provide new topics related to topics that the subject has shown interest in. The generation AI also sequentially presents multiple topics in the conversation unit to evaluate the subject's conversational abilities from multiple angles. For example, it will cover topics from different fields such as business, culture, and science. This allows the subject's diverse conversational abilities to be evaluated.

[0033] The conversation unit can evaluate the quality of responses to questions posed by the subject to the generation AI and measure two-way conversation ability. For example, the conversation unit analyzes the content of questions posed by the subject to the generation AI and evaluates the quality of the generation AI's response to those questions. For example, it evaluates based on the clarity of the question and the appropriateness of the response. The conversation unit also builds a system to evaluate whether the generation AI's response to the subject's question is appropriate. For example, it evaluates whether the response is specific to the question. The conversation unit also measures the subject's two-way conversation ability based on the quality of the generation AI's response to the subject's question. For example, it comprehensively evaluates the frequency of questions and the quality of responses. This makes it possible to measure the subject's two-way conversation ability.

[0034] The evaluation unit can evaluate the grammatical accuracy and vocabulary richness of the subject's speech. The evaluation unit, for example, analyzes the subject's speech and evaluates the grammatical accuracy. For example, the evaluation is based on the number of grammatical errors and sentence structure. The evaluation unit also builds a system to evaluate the vocabulary richness contained in the subject's speech. For example, the evaluation is based on the diversity of words used and the frequency of use of technical terms. The evaluation unit also comprehensively evaluates the grammatical accuracy and vocabulary richness of the subject's speech. For example, the evaluation unit calculates a score based on the number of grammatical errors and the diversity of vocabulary. This makes it possible to evaluate the grammatical accuracy and vocabulary richness of the subject's speech.

[0035] The evaluation unit can evaluate the consistency and logic of the subject's statements. The evaluation unit, for example, analyzes the subject's statements and evaluates their consistency. For example, it evaluates based on whether the statements are in line with the theme. The evaluation unit also builds a system to evaluate the logic of the subject's statements. For example, it evaluates based on whether the statements are logically consistent. The evaluation unit also comprehensively evaluates the consistency and logic of the subject's statements. For example, it calculates a score based on whether the statements are consistent and logically consistent. This makes it possible to evaluate the consistency and logic of the subject's statements.

[0036] The evaluation unit can compare the content of the subject's conversation with other subjects and perform a relative evaluation. The evaluation unit, for example, stores the content of the subject's conversation in a database and compares it with the content of the conversations of other subjects. For example, it compares and evaluates the quality of responses to the same topic. The evaluation unit also analyzes the content of the subject's conversation and builds a system for performing a relative evaluation with other subjects. For example, it compares and evaluates based on the appropriateness and speed of the responses. The evaluation unit also compares the content of the subject's conversation with other subjects and calculates a relative score. For example, it evaluates the subject's score by comparing it with the overall average score. This allows the content of the subject's conversation to be evaluated relatively in comparison with other subjects.

[0037] The evaluation unit can reevaluate the subject's conversation content under different scenarios and measure the adaptability for each scenario. The evaluation unit, for example, builds a system that reevaluates the subject's conversation content under different scenarios. For example, it compares responses under business scenarios and everyday conversation scenarios. The evaluation unit also evaluates the subject's conversation content under multiple scenarios and measures the adaptability for each scenario. For example, it calculates a score based on the quality of responses under different scenarios. The evaluation unit also reevaluates the subject's conversation content under different scenarios and comprehensively evaluates the adaptability. For example, it calculates an overall score by averaging the scores for each scenario. This makes it possible to reevaluate the subject's conversation content under different scenarios and measure the adaptability.

[0038] The multilingual support unit can evaluate the grammatical accuracy and vocabulary richness of the subject's multilingual utterances. The multilingual support unit, for example, analyzes the subject's multilingual utterances and builds a system to evaluate grammatical accuracy. For example, it detects grammatical errors in English, Japanese, Chinese, etc. The multilingual support unit also evaluates the vocabulary richness contained in the subject's multilingual utterances. For example, it evaluates based on the variety of words used and the frequency of use of technical terms. The multilingual support unit also comprehensively evaluates the grammatical accuracy and vocabulary richness of the subject's multilingual utterances. For example, it calculates a score based on the number of grammatical errors and the diversity of vocabulary. This makes it possible to evaluate the grammatical accuracy and vocabulary richness of the subject's multilingual utterances.

[0039] The multilingual support unit can evaluate the consistency and logic of the subject's multilingual statements. The multilingual support unit, for example, analyzes the subject's multilingual statements and builds a system to evaluate their consistency. For example, it evaluates whether the statements in English, Japanese, Chinese, etc. are in line with the theme. The multilingual support unit also evaluates the logic of the subject's multilingual statements. For example, it evaluates based on whether the statements are logically consistent. The multilingual support unit also comprehensively evaluates the consistency and logic of the subject's multilingual statements. For example, it calculates a score based on whether the statements are consistent and logically consistent. This makes it possible to evaluate the consistency and logic of the subject's multilingual statements.

[0040] The multilingual support unit can have subjects converse on the same topic in multiple languages ​​and compare and evaluate their conversational ability in each language. The multilingual support unit, for example, builds a system in which subjects converse on the same topic in multiple languages ​​and the content of the conversation is compared and evaluated. For example, responses on the same topic are evaluated in English, Japanese, and Chinese. The multilingual support unit also analyzes the content of the subjects' conversations in multiple languages ​​and compares their conversational ability in each language. For example, evaluations are made based on grammatical accuracy and vocabulary richness. The multilingual support unit also comprehensively evaluates the subjects' conversational ability when they converse on the same topic in multiple languages. For example, an overall score is calculated by averaging the scores in each language. This allows subjects to converse on the same topic in multiple languages ​​and compare and evaluate their conversational ability in each language.

[0041] The multilingual support unit can compare the content of the subject's multilingual conversation with other subjects and perform a relative evaluation. For example, the multilingual support unit stores the content of the subject's multilingual conversation in a database and compares it with the content of the conversations of other subjects. For example, it compares and evaluates the quality of responses to the same topic. The multilingual support unit also analyzes the content of the subject's multilingual conversation and builds a system for performing a relative evaluation with other subjects. For example, it compares and evaluates based on the appropriateness and speed of responses. The multilingual support unit also compares the content of the subject's multilingual conversation with other subjects and calculates a relative score. For example, it evaluates the subject's score by comparing it with the overall average score. This allows the content of the subject's multilingual conversation to be evaluated relatively to other subjects.

[0042] The low-cost providing unit can reduce costs by automatically recording the content of the subject's conversation and re-evaluating it later. The low-cost providing unit, for example, builds a system that automatically records the content of the subject's conversation and later re-evaluates it based on that data. For example, the content of the conversation is saved as text data. The low-cost providing unit also records the content of the conversation and later re-evaluates it based on that audio data. For example, the content of the conversation is converted into text using audio analysis technology. The low-cost providing unit also reduces costs by automatically recording the content of the subject's conversation and re-evaluating it based on that data. For example, the evaluation process is automated. This allows the content of the subject's conversation to be automatically recorded and later re-evaluated, thereby reducing costs.

[0043] The low-cost providing unit analyzes the content of the subject's conversation on the cloud, thereby reducing local processing costs. The low-cost providing unit, for example, analyzes the content of the subject's conversation on the cloud and builds a system that evaluates based on the data. For example, the analysis is performed using cloud computing. The low-cost providing unit also uploads the content of the conversation to the cloud and analyzes based on that data. For example, the evaluation is performed using an AI model on the cloud. The low-cost providing unit also analyzes the content of the subject's conversation on the cloud, thereby reducing local processing costs. For example, the analysis results on the cloud are transmitted locally. This allows the content of the subject's conversation to be analyzed on the cloud, thereby reducing local processing costs.

[0044] The low-cost provider allows test subjects to take the test online from home, thereby reducing the costs of test centers. For example, the low-cost provider builds a system that allows test subjects to take the test online from home. For example, it uses a webcam and microphone to have real-time conversations. The low-cost provider also introduces an online test system to reduce the costs of test centers. For example, it provides a dedicated online platform. The low-cost provider also allows test subjects to take the test online from home, thereby reducing the costs of preparing and operating test centers. For example, it introduces an online test proctoring system. This allows test subjects to take the test online from home, thereby reducing the costs of test centers.

[0045] The low-cost provision unit can reduce costs by automatically translating the content of subjects' conversations and centralizing evaluations in different languages. The low-cost provision unit, for example, builds a system that automatically translates the content of subjects' conversations and centralizes evaluations in different languages. For example, it uses translation AI to convert the content of conversations into multiple languages. The low-cost provision unit also automatically translates the content of conversations and performs evaluations based on that data. For example, it can support multiple languages ​​such as English, Japanese, and Chinese. The low-cost provision unit also reduces costs by automatically translating the content of subjects' conversations and centralizing evaluations in different languages. For example, it automates the evaluation process based on the translation results. This allows it to automatically translate the content of subjects' conversations and centralize evaluations in different languages, reducing costs.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] The conversation unit can analyze what the subject says and provide additional information related to the topic. For example, if the subject is talking about a particular technology, it can provide the latest research findings and news about that technology. The conversation unit can also generate related questions based on what the subject says to deepen the conversation. For example, if the subject is talking about a problem, it can provide solutions or other perspectives related to that problem. The conversation unit can also provide related materials and links based on what the subject says. For example, if the subject wants to learn more about a particular topic, it can provide references and website links related to that topic. This allows the conversation to be deeper and richer based on what the subject says.

[0048] The conversation unit can refer to the subject's past conversation history and provide individually customized feedback. For example, if the subject mentioned in a previous conversation that they would like to learn about a specific skill, the conversation unit can provide specific advice about that skill. The conversation unit can also analyze the subject's conversation history and track their progress. For example, it can check the progress toward goals the subject set in a previous conversation and provide feedback based on the level of achievement. The conversation unit can also suggest next steps based on the subject's past conversations. For example, if the subject wants to learn more about a specific topic, the conversation unit can suggest the next learning step related to that topic. This makes it possible to provide individually customized feedback to the subject.

[0049] The conversational part can analyze the subject's nonverbal communication and adjust the content of the conversation based on that. For example, if the subject shows a confused expression, the generation AI can simplify the explanation. If the subject shows interest, the generation AI can go into more detail about the topic. The conversational part can also analyze the subject's gestures and adjust its responses based on that. For example, if the subject nods, the generation AI will respond with agreement. The conversational part can also analyze the subject's posture and movements to understand nonverbal communication. For example, if the subject is relaxed, the generation AI will also respond in a relaxed tone. This allows the content of the conversation to be adjusted based on the subject's nonverbal communication.

[0050] The conversation unit automatically changes the topic of the conversation, enabling it to evaluate the diverse conversational abilities of the subject. For example, the generation AI automatically changes the topic of the conversation based on the subject's responses. For example, if the subject is good at technical topics, it will select a technology-related topic. The conversation unit also suggests different topics as the conversation progresses. For example, it will provide new topics related to topics that the subject has shown interest in. The conversation unit also sequentially presents multiple topics to evaluate the subject's conversational abilities from multiple angles. For example, it will cover topics from different fields such as business, culture, and science. This allows it to evaluate the diverse conversational abilities of the subject.

[0051] The conversation unit can evaluate the quality of responses to questions posed to the generating AI by the subject, and measure the subject's two-way conversation ability. For example, it analyzes the content of questions posed to the generating AI by the subject, and evaluates the quality of the generating AI's response to those questions. For example, it evaluates based on the clarity of the question and the appropriateness of the response. The conversation unit also builds a system to evaluate whether the generating AI's response to the subject's question is appropriate. For example, it evaluates whether the response is specific to the question. The conversation unit also measures the subject's two-way conversation ability based on the quality of the generating AI's response to the subject's question. For example, it comprehensively evaluates the frequency of questions and the quality of responses. This makes it possible to measure the subject's two-way conversation ability.

[0052] The evaluation unit can evaluate the grammatical accuracy and vocabulary richness of the subject's speech. For example, it analyzes the subject's speech and evaluates grammatical accuracy. For example, it evaluates based on the number of grammatical errors and sentence structure. The evaluation unit also builds a system to evaluate the vocabulary richness contained in the subject's speech. For example, it evaluates based on the variety of words used and the frequency of use of technical terms. The evaluation unit also comprehensively evaluates the grammatical accuracy and vocabulary richness of the subject's speech. For example, it calculates a score based on the number of grammatical errors and the diversity of vocabulary. This makes it possible to evaluate the grammatical accuracy and vocabulary richness of the subject's speech.

[0053] The evaluation unit can evaluate the consistency and logic of the subject's statements. For example, it analyzes the subject's statements and evaluates their consistency. For example, it evaluates based on whether the statements are in line with the theme. The evaluation unit also builds a system to evaluate the logic of the subject's statements. For example, it evaluates based on whether the statements are logically consistent. The evaluation unit also comprehensively evaluates the consistency and logic of the subject's statements. For example, it calculates a score based on whether the statements are consistent and logically consistent. This makes it possible to evaluate the consistency and logic of the subject's statements.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The conversation unit engages in a conversation with the generation AI about a topic presented by the subject. For example, the generation AI understands what the subject says and generates an appropriate response. The conversation unit can also enable the generation AI to provide appropriate feedback to the subject's comments. Step 2: The evaluation unit evaluates the speed of the conversation conducted by the conversation unit and the appropriateness of the responses. For example, the evaluation unit evaluates whether the subject's remarks are made at the appropriate time and whether the content is in line with the topic. The evaluation unit can also use the generation AI to analyze the content of the subject's conversation and calculate a score. Step 3: The multilingual support unit provides the conversational ability test in all languages ​​supported by the generation AI. For example, the multilingual support unit allows the generation AI to respond in the appropriate language depending on the language used by the subject, such as English, Japanese, or Chinese. Step 4: Low-cost providers offer conversation proficiency tests at lower costs than traditional language proficiency tests. For example, low-cost providers reduce examiner labor costs by using generative AI. Low-cost providers can also reduce test center preparation and operation costs by enabling tests to be conducted online.

[0056] (Example 2) A conversational ability testing system according to an embodiment of the present invention is a system in which a test subject converses with a generative AI on a given topic, the speed of the conversation and the appropriateness of the responses are evaluated using the generative AI's language model, and a score is calculated. This enables the conversational ability testing system to efficiently and inexpensively conduct personnel recruitment tests for jobs requiring conversational ability.

[0057] A conversational proficiency testing system according to an embodiment includes a conversation unit, an evaluation unit, a multilingual support unit, and a low-cost provision unit. The conversation unit allows a subject to converse with a generation AI on a presented topic. For example, the generation AI understands what the subject says and generates an appropriate response. The conversation unit can also provide appropriate feedback to the generation AI in response to the subject's comments. The evaluation unit evaluates the speed of the conversation and the appropriateness of the responses provided by the conversation unit. For example, the evaluation unit evaluates whether the subject's comments are made at the appropriate time and whether the content is in line with the topic. The evaluation unit can also analyze the content of the subject's conversation and calculate a score. The multilingual support unit provides a conversational proficiency test in all languages ​​supported by the generation AI. For example, the multilingual support unit allows the generation AI to respond in an appropriate language, such as English, Japanese, or Chinese, depending on the language used by the subject. The low-cost provision unit provides a conversational proficiency test at a lower cost than conventional language proficiency tests. For example, the low-cost provision unit reduces examiner labor costs by using the generation AI. In addition, since the low-cost provision unit can conduct the test online, the preparation and operation costs of the test site can also be reduced. As a result, the conversational ability testing system according to the embodiment can conduct personnel recruitment tests for jobs that require conversational ability efficiently and at low cost.

[0058] The conversational unit can estimate the subject's emotions in real time and generate responses that correspond to those emotions. The conversational unit, for example, analyzes the subject's tone of voice and facial expressions to estimate emotions in real time. For example, if the subject is nervous, the generation AI will respond in a way that relaxes them. The conversational unit also refers to the subject's past conversation history to track changes in emotions. For example, it may revisit a topic that elicited a positive response in a previous conversation. The conversational unit also analyzes the subject's non-verbal communication (e.g., facial expressions and gestures) and adjusts responses based on that. For example, if the subject smiles, the generation AI will also respond positively. This enables natural conversations that correspond to the subject's emotions.

[0059] The conversation unit can refer to the subject's past conversation history and generate questions that are individually customized. For example, the conversation unit stores the subject's past conversation history in a database and generates customized questions based on that information. For example, questions related to topics that the subject showed interest in in previous conversations are asked. The conversation unit also analyzes the subject's conversation history and finds specific patterns and trends. For example, questions are generated based on keywords frequently used by the subject. The conversation unit also generates questions that encourage deeper understanding based on the content of the subject's past conversations. For example, detailed questions are asked about topics that were touched upon in previous conversations. This makes it possible to generate questions that are individually customized for the subject.

[0060] The conversational unit can analyze the subject's non-verbal communication and adjust its responses based on that. For example, the conversational unit analyzes the subject's facial expressions using a camera and estimates their emotions in real time. For example, if the subject is confused, the generation AI will simplify the explanation. The conversational unit also detects the subject's gestures using a sensor and adjusts its responses based on that information. For example, if the subject nods, the generation AI will respond with agreement. The conversational unit also analyzes the subject's posture and movements to understand their non-verbal communication. For example, if the subject is relaxed, the generation AI will also respond in a relaxed tone. This allows the response to be adjusted based on the subject's non-verbal communication.

[0061] The conversation unit automatically changes the topic of the conversation, enabling the subject's diverse conversational abilities to be evaluated. For example, the generation AI automatically changes the topic of the conversation based on the subject's responses. For example, if the subject is good at technical topics, it will select a technology-related topic. The generation AI also suggests different topics as the conversation progresses. For example, it will provide new topics related to topics that the subject has shown interest in. The generation AI also sequentially presents multiple topics in the conversation unit to evaluate the subject's conversational abilities from multiple angles. For example, it will cover topics from different fields such as business, culture, and science. This allows the subject's diverse conversational abilities to be evaluated.

[0062] The conversation unit can evaluate the quality of responses to questions posed by the subject to the generation AI and measure two-way conversation ability. For example, the conversation unit analyzes the content of questions posed by the subject to the generation AI and evaluates the quality of the generation AI's response to those questions. For example, it evaluates based on the clarity of the question and the appropriateness of the response. The conversation unit also builds a system to evaluate whether the generation AI's response to the subject's question is appropriate. For example, it evaluates whether the response is specific to the question. The conversation unit also measures the subject's two-way conversation ability based on the quality of the generation AI's response to the subject's question. For example, it comprehensively evaluates the frequency of questions and the quality of responses. This makes it possible to measure the subject's two-way conversation ability.

[0063] The conversation unit uses an emotion estimation function to automatically select the topic that the subject is most interested in and can progress the conversation based on that topic. For example, the conversation unit analyzes the subject's emotional responses in real time and automatically selects the topic that the subject is most interested in. For example, it prioritizes selecting topics to which the subject has a positive response. The conversation unit also uses the emotion estimation function to identify topics that interest the subject and progress the conversation based on those topics. For example, it develops the conversation around topics that make the subject smile. The conversation unit also builds a system in which the generation AI selects the optimal topic based on the subject's emotional data and progresses the conversation. For example, it prioritizes selecting topics with high emotion scores. This allows the conversation to progress based on the topic that the subject is most interested in.

[0064] The evaluation unit can estimate the subject's emotions and evaluate the appropriateness of responses based on those emotions. For example, the evaluation unit estimates the subject's emotions in real time and evaluates the appropriateness of the generation AI's response based on those emotions. For example, if the subject is nervous, it evaluates whether a response that relaxes the subject is appropriate. The evaluation unit also builds a system that evaluates the quality of responses based on the subject's emotions based on the emotion estimation data. For example, it evaluates whether a response that elicits positive emotions is appropriate. The evaluation unit also tracks changes in the subject's emotions and evaluates the appropriateness of responses based on those changes. For example, if the emotion changes to positive, it evaluates that the response was appropriate. This makes it possible to evaluate the appropriateness of responses based on the subject's emotions.

[0065] The evaluation unit can evaluate the grammatical accuracy and vocabulary richness of the subject's speech. The evaluation unit, for example, analyzes the subject's speech and evaluates the grammatical accuracy. For example, the evaluation is based on the number of grammatical errors and sentence structure. The evaluation unit also builds a system to evaluate the vocabulary richness contained in the subject's speech. For example, the evaluation is based on the diversity of words used and the frequency of use of technical terms. The evaluation unit also comprehensively evaluates the grammatical accuracy and vocabulary richness of the subject's speech. For example, the evaluation unit calculates a score based on the number of grammatical errors and the diversity of vocabulary. This makes it possible to evaluate the grammatical accuracy and vocabulary richness of the subject's speech.

[0066] The evaluation unit can evaluate the consistency and logic of the subject's statements. The evaluation unit, for example, analyzes the subject's statements and evaluates their consistency. For example, it evaluates based on whether the statements are in line with the theme. The evaluation unit also builds a system to evaluate the logic of the subject's statements. For example, it evaluates based on whether the statements are logically consistent. The evaluation unit also comprehensively evaluates the consistency and logic of the subject's statements. For example, it calculates a score based on whether the statements are consistent and logically consistent. This makes it possible to evaluate the consistency and logic of the subject's statements.

[0067] The evaluation unit can compare the content of the subject's conversation with other subjects and perform a relative evaluation. The evaluation unit, for example, stores the content of the subject's conversation in a database and compares it with the content of the conversations of other subjects. For example, it compares and evaluates the quality of responses to the same topic. The evaluation unit also analyzes the content of the subject's conversation and builds a system for performing a relative evaluation with other subjects. For example, it compares and evaluates based on the appropriateness and speed of the responses. The evaluation unit also compares the content of the subject's conversation with other subjects and calculates a relative score. For example, it evaluates the subject's score by comparing it with the overall average score. This allows the content of the subject's conversation to be evaluated relatively in comparison with other subjects.

[0068] The evaluation unit can reevaluate the subject's conversation content under different scenarios and measure the adaptability for each scenario. The evaluation unit, for example, builds a system that reevaluates the subject's conversation content under different scenarios. For example, it compares responses under business scenarios and everyday conversation scenarios. The evaluation unit also evaluates the subject's conversation content under multiple scenarios and measures the adaptability for each scenario. For example, it calculates a score based on the quality of responses under different scenarios. The evaluation unit also reevaluates the subject's conversation content under different scenarios and comprehensively evaluates the adaptability. For example, it calculates an overall score by averaging the scores for each scenario. This makes it possible to reevaluate the subject's conversation content under different scenarios and measure the adaptability.

[0069] The evaluation unit can use the emotion estimation function to track changes in the subject's emotions and evaluate the stability of the emotions. The evaluation unit, for example, builds a system that estimates the subject's emotions in real time and tracks those changes. For example, it records an emotion score from the start to the end of a conversation. The evaluation unit also evaluates the stability of the subject's emotions based on the emotion estimation data. For example, it evaluates the stability based on the range of fluctuation in the emotion score. The evaluation unit also tracks the subject's emotional changes and comprehensively evaluates the emotional stability based on that data. For example, it calculates a score based on the average value and range of fluctuation of the emotion score. This makes it possible to track changes in the subject's emotions and evaluate the emotional stability.

[0070] The multilingual support unit can estimate the subject's emotions in multiple languages ​​and generate multilingual responses according to the emotions. The multilingual support unit, for example, builds a system that estimates the subject's emotions in multiple languages ​​in real time and generates responses according to those emotions. For example, emotions are analyzed in English, Japanese, Chinese, etc. The multilingual support unit also uses a multilingual emotion estimation function to generate appropriate responses according to the subject's emotions. For example, if the subject is nervous in English, a response that relaxes the subject is provided. The multilingual support unit also analyzes the subject's emotions in multiple languages ​​and generates multilingual responses based on that data. For example, if the subject responds positively in Japanese, a positive response is provided. This makes it possible to generate multilingual responses according to the subject's emotions.

[0071] The multilingual support unit can evaluate the grammatical accuracy and vocabulary richness of the subject's multilingual utterances. The multilingual support unit, for example, analyzes the subject's multilingual utterances and builds a system to evaluate grammatical accuracy. For example, it detects grammatical errors in English, Japanese, Chinese, etc. The multilingual support unit also evaluates the vocabulary richness contained in the subject's multilingual utterances. For example, it evaluates based on the variety of words used and the frequency of use of technical terms. The multilingual support unit also comprehensively evaluates the grammatical accuracy and vocabulary richness of the subject's multilingual utterances. For example, it calculates a score based on the number of grammatical errors and the diversity of vocabulary. This makes it possible to evaluate the grammatical accuracy and vocabulary richness of the subject's multilingual utterances.

[0072] The multilingual support unit can evaluate the consistency and logic of the subject's multilingual statements. The multilingual support unit, for example, analyzes the subject's multilingual statements and builds a system to evaluate their consistency. For example, it evaluates whether the statements in English, Japanese, Chinese, etc. are in line with the theme. The multilingual support unit also evaluates the logic of the subject's multilingual statements. For example, it evaluates based on whether the statements are logically consistent. The multilingual support unit also comprehensively evaluates the consistency and logic of the subject's multilingual statements. For example, it calculates a score based on whether the statements are consistent and logically consistent. This makes it possible to evaluate the consistency and logic of the subject's multilingual statements.

[0073] The multilingual support unit can have subjects converse on the same topic in multiple languages ​​and compare and evaluate their conversational ability in each language. The multilingual support unit, for example, builds a system in which subjects converse on the same topic in multiple languages ​​and the content of the conversation is compared and evaluated. For example, responses on the same topic are evaluated in English, Japanese, and Chinese. The multilingual support unit also analyzes the content of the subjects' conversations in multiple languages ​​and compares their conversational ability in each language. For example, evaluations are made based on grammatical accuracy and vocabulary richness. The multilingual support unit also comprehensively evaluates the subjects' conversational ability when they converse on the same topic in multiple languages. For example, an overall score is calculated by averaging the scores in each language. This allows subjects to converse on the same topic in multiple languages ​​and compare and evaluate their conversational ability in each language.

[0074] The multilingual support unit can compare the content of the subject's multilingual conversation with other subjects and perform a relative evaluation. For example, the multilingual support unit stores the content of the subject's multilingual conversation in a database and compares it with the content of the conversations of other subjects. For example, it compares and evaluates the quality of responses to the same topic. The multilingual support unit also analyzes the content of the subject's multilingual conversation and builds a system for performing a relative evaluation with other subjects. For example, it compares and evaluates based on the appropriateness and speed of responses. The multilingual support unit also compares the content of the subject's multilingual conversation with other subjects and calculates a relative score. For example, it evaluates the subject's score by comparing it with the overall average score. This allows the content of the subject's multilingual conversation to be evaluated relatively to other subjects.

[0075] The multilingual support unit can use the emotion estimation function to track changes in the subject's emotions in multiple languages ​​and evaluate the stability of the emotions. The multilingual support unit, for example, builds a system that estimates the subject's emotions in multiple languages ​​in real time and tracks those changes. For example, it records emotion scores in English, Japanese, and Chinese. The multilingual support unit also evaluates the stability of the subject's emotions in multiple languages ​​based on the emotion estimation data. For example, it evaluates the stability based on the range of fluctuation in the emotion scores. The multilingual support unit also tracks changes in the subject's emotions in multiple languages ​​and comprehensively evaluates the stability of the emotions based on that data. For example, it calculates a score based on the average value and range of fluctuation of the emotion scores. This makes it possible to track changes in the subject's emotions in multiple languages ​​and evaluate the stability of the emotions.

[0076] The low-cost providing unit can estimate the subject's emotions and generate low-cost responses based on the emotions. The low-cost providing unit, for example, builds a system that estimates the subject's emotions in real time and generates low-cost responses based on the emotions. For example, it selects an appropriate response based on the emotion score. The low-cost providing unit also generates low-cost responses according to the subject's emotions based on the emotion estimation data. For example, it provides a response that elicits positive emotions. The low-cost providing unit also analyzes the subject's emotions and generates low-cost responses based on that data. For example, if the emotion score is high, it can use a simple response. This makes it possible to generate low-cost responses based on the subject's emotions.

[0077] The low-cost providing unit can reduce costs by automatically recording the content of the subject's conversation and re-evaluating it later. The low-cost providing unit, for example, builds a system that automatically records the content of the subject's conversation and later re-evaluates it based on that data. For example, the content of the conversation is saved as text data. The low-cost providing unit also records the content of the conversation and later re-evaluates it based on that audio data. For example, the content of the conversation is converted into text using audio analysis technology. The low-cost providing unit also reduces costs by automatically recording the content of the subject's conversation and re-evaluating it based on that data. For example, the evaluation process is automated. This allows the content of the subject's conversation to be automatically recorded and later re-evaluated, thereby reducing costs.

[0078] The low-cost providing unit analyzes the content of the subject's conversation on the cloud, thereby reducing local processing costs. The low-cost providing unit, for example, analyzes the content of the subject's conversation on the cloud and builds a system that evaluates based on the data. For example, the analysis is performed using cloud computing. The low-cost providing unit also uploads the content of the conversation to the cloud and analyzes based on that data. For example, the evaluation is performed using an AI model on the cloud. The low-cost providing unit also analyzes the content of the subject's conversation on the cloud, thereby reducing local processing costs. For example, the analysis results on the cloud are transmitted locally. This allows the content of the subject's conversation to be analyzed on the cloud, thereby reducing local processing costs.

[0079] The low-cost provider allows test subjects to take the test online from home, thereby reducing the costs of test centers. For example, the low-cost provider builds a system that allows test subjects to take the test online from home. For example, it uses a webcam and microphone to have real-time conversations. The low-cost provider also introduces an online test system to reduce the costs of test centers. For example, it provides a dedicated online platform. The low-cost provider also allows test subjects to take the test online from home, thereby reducing the costs of preparing and operating test centers. For example, it introduces an online test proctoring system. This allows test subjects to take the test online from home, thereby reducing the costs of test centers.

[0080] The low-cost provision unit can reduce costs by automatically translating the content of subjects' conversations and centralizing evaluations in different languages. The low-cost provision unit, for example, builds a system that automatically translates the content of subjects' conversations and centralizes evaluations in different languages. For example, it uses translation AI to convert the content of conversations into multiple languages. The low-cost provision unit also automatically translates the content of conversations and performs evaluations based on that data. For example, it can support multiple languages ​​such as English, Japanese, and Chinese. The low-cost provision unit also reduces costs by automatically translating the content of subjects' conversations and centralizing evaluations in different languages. For example, it automates the evaluation process based on the translation results. This allows it to automatically translate the content of subjects' conversations and centralize evaluations in different languages, reducing costs.

[0081] The low-cost providing unit can use the emotion estimation function to provide low-cost feedback according to the emotion of the subject. The low-cost providing unit, for example, uses the emotion estimation function to build a system that provides low-cost feedback according to the emotion of the subject. For example, it generates simple feedback based on the emotion score. The low-cost providing unit also estimates the emotion of the subject in real time and provides low-cost feedback based on that data. For example, it provides feedback that elicits positive emotions. The low-cost providing unit also provides low-cost feedback according to the emotion of the subject based on the emotion estimation data. For example, if the emotion score is high, simple feedback will suffice. This makes it possible to provide low-cost feedback according to the emotion of the subject.

[0082] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0083] The conversation unit can analyze what the subject says and provide additional information related to the topic. For example, if the subject is talking about a particular technology, it can provide the latest research findings and news about that technology. The conversation unit can also generate related questions based on what the subject says to deepen the conversation. For example, if the subject is talking about a problem, it can provide solutions or other perspectives related to that problem. The conversation unit can also provide related materials and links based on what the subject says. For example, if the subject wants to learn more about a particular topic, it can provide references and website links related to that topic. This allows the conversation to be deeper and richer based on what the subject says.

[0084] The conversational part can estimate the subject's emotions and adjust the tone of the conversation based on the estimated emotions. For example, if the subject is nervous, the generation AI can respond in a calm, relaxing tone. If the subject is excited, the generation AI can respond in an energetic tone. Furthermore, the conversational part can adjust the pace of the conversation according to the subject's emotions. For example, if the subject is impatient, the generation AI will speak at a slower pace. The conversational part can also provide appropriate feedback based on the subject's emotions. For example, if the subject is depressed, the generation AI will offer words of encouragement. This enables natural conversation that corresponds to the subject's emotions.

[0085] The conversation unit can refer to the subject's past conversation history and provide individually customized feedback. For example, if the subject mentioned in a previous conversation that they would like to learn about a specific skill, the conversation unit can provide specific advice about that skill. The conversation unit can also analyze the subject's conversation history and track their progress. For example, it can check the progress toward goals the subject set in a previous conversation and provide feedback based on the level of achievement. The conversation unit can also suggest next steps based on the subject's past conversations. For example, if the subject wants to learn more about a specific topic, the conversation unit can suggest the next learning step related to that topic. This makes it possible to provide individually customized feedback to the subject.

[0086] The conversational part can analyze the subject's nonverbal communication and adjust the content of the conversation based on that. For example, if the subject shows a confused expression, the generation AI can simplify the explanation. If the subject shows interest, the generation AI can go into more detail about the topic. The conversational part can also analyze the subject's gestures and adjust its responses based on that. For example, if the subject nods, the generation AI will respond with agreement. The conversational part can also analyze the subject's posture and movements to understand nonverbal communication. For example, if the subject is relaxed, the generation AI will also respond in a relaxed tone. This allows the content of the conversation to be adjusted based on the subject's nonverbal communication.

[0087] The conversation unit automatically changes the topic of the conversation, enabling it to evaluate the diverse conversational abilities of the subject. For example, the generation AI automatically changes the topic of the conversation based on the subject's responses. For example, if the subject is good at technical topics, it will select a technology-related topic. The conversation unit also suggests different topics as the conversation progresses. For example, it will provide new topics related to topics that the subject has shown interest in. The conversation unit also sequentially presents multiple topics to evaluate the subject's conversational abilities from multiple angles. For example, it will cover topics from different fields such as business, culture, and science. This allows it to evaluate the diverse conversational abilities of the subject.

[0088] The conversation unit can evaluate the quality of responses to questions posed to the generating AI by the subject, and measure the subject's two-way conversation ability. For example, it analyzes the content of questions posed to the generating AI by the subject, and evaluates the quality of the generating AI's response to those questions. For example, it evaluates based on the clarity of the question and the appropriateness of the response. The conversation unit also builds a system to evaluate whether the generating AI's response to the subject's question is appropriate. For example, it evaluates whether the response is specific to the question. The conversation unit also measures the subject's two-way conversation ability based on the quality of the generating AI's response to the subject's question. For example, it comprehensively evaluates the frequency of questions and the quality of responses. This makes it possible to measure the subject's two-way conversation ability.

[0089] The conversation unit uses the emotion estimation function to automatically select the topic that the subject is most interested in and can progress the conversation based on that topic. For example, it can analyze the subject's emotional responses in real time and automatically select the topic that the subject is most interested in. For example, it can prioritize selecting topics to which the subject has a positive response. The conversation unit also uses the emotion estimation function to identify topics that interest the subject and progress the conversation based on those topics. For example, it can develop a conversation centered around topics that make the subject smile. The conversation unit also builds a system in which the generation AI selects the optimal topic based on the subject's emotional data and progresses the conversation. For example, it can prioritize selecting topics with a high emotion score. This allows the conversation to progress based on the topic that the subject is most interested in.

[0090] The evaluation unit can estimate the subject's emotions and evaluate the appropriateness of responses based on those emotions. For example, it can estimate the subject's emotions in real time and evaluate the appropriateness of the generation AI's response based on those emotions. For example, if the subject is nervous, it can evaluate whether a response that relaxes them is appropriate. The evaluation unit also builds a system that evaluates the quality of responses based on the subject's emotions based on the emotion estimation data. For example, it evaluates whether a response that elicits positive emotions is appropriate. The evaluation unit also tracks changes in the subject's emotions and evaluates the appropriateness of responses based on those changes. For example, if emotions change to positive, it evaluates the response as appropriate. This makes it possible to evaluate the appropriateness of responses based on the subject's emotions.

[0091] The evaluation unit can evaluate the grammatical accuracy and vocabulary richness of the subject's speech. For example, it analyzes the subject's speech and evaluates grammatical accuracy. For example, it evaluates based on the number of grammatical errors and sentence structure. The evaluation unit also builds a system to evaluate the vocabulary richness contained in the subject's speech. For example, it evaluates based on the variety of words used and the frequency of use of technical terms. The evaluation unit also comprehensively evaluates the grammatical accuracy and vocabulary richness of the subject's speech. For example, it calculates a score based on the number of grammatical errors and the diversity of vocabulary. This makes it possible to evaluate the grammatical accuracy and vocabulary richness of the subject's speech.

[0092] The evaluation unit can evaluate the consistency and logic of the subject's statements. For example, it analyzes the subject's statements and evaluates their consistency. For example, it evaluates based on whether the statements are in line with the theme. The evaluation unit also builds a system to evaluate the logic of the subject's statements. For example, it evaluates based on whether the statements are logically consistent. The evaluation unit also comprehensively evaluates the consistency and logic of the subject's statements. For example, it calculates a score based on whether the statements are consistent and logically consistent. This makes it possible to evaluate the consistency and logic of the subject's statements.

[0093] The processing flow of the second embodiment will be briefly explained below.

[0094] Step 1: The conversation unit engages in a conversation with the generation AI about a topic presented by the subject. For example, the generation AI understands what the subject says and generates an appropriate response. The conversation unit can also enable the generation AI to provide appropriate feedback to the subject's comments. Step 2: The evaluation unit evaluates the speed of the conversation conducted by the conversation unit and the appropriateness of the responses. For example, the evaluation unit evaluates whether the subject's remarks are made at the appropriate time and whether the content is in line with the topic. The evaluation unit can also use the generation AI to analyze the content of the subject's conversation and calculate a score. Step 3: The multilingual support unit provides the conversational ability test in all languages ​​supported by the generation AI. For example, the multilingual support unit allows the generation AI to respond in the appropriate language depending on the language used by the subject, such as English, Japanese, or Chinese. Step 4: Low-cost providers offer conversation proficiency tests at lower costs than traditional language proficiency tests. For example, low-cost providers reduce examiner labor costs by using generative AI. Low-cost providers can also reduce test center preparation and operation costs by enabling tests to be conducted online.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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).

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0108] 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. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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).

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0123] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0129] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0139] In the robot 414, 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. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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.

[0149] 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."

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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]

[0162] 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 conversational ability testing system using a generation AI, A conversation section in which the subject converses with the AI ​​generator on the topic presented to them; an evaluation unit that evaluates the speed of the conversation and the appropriateness of the responses made by the conversation unit; a multilingual support unit that provides a conversational ability test in all languages ​​supported by the generation AI; and a low-cost provision unit that provides the test at a lower cost than conventional language proficiency tests. A system characterized by:

2. The conversation unit is Estimate the subject's emotions in real time and generate a response according to the emotions.

2. The system of claim 1.

3. The conversation unit is Refer to the subject's past conversation history and generate individually customized questions 2. The system of claim 1.

4. The conversation unit is Analyzing the subject's nonverbal communication and adjusting responses accordingly.

2. The system of claim 1.

5. The conversation unit is Automatically change the topic of conversation to evaluate the subject's diverse conversational abilities.

2. The system of claim 1.

Images