system

Abstract

The system according to the embodiment aims to efficiently improve the quality of generated English sentences and words. [Solution] A system according to an embodiment includes a generation unit, a check unit, and a learning unit. The generation unit generates English sentences or words based on input from a learner. The check unit checks the English sentences or words generated by the generation unit. The learning unit learns the check results obtained by the check unit.

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 efficiently improve the quality of generated English sentences and words.

[0005] The system according to the embodiment aims to efficiently improve the quality of generated English sentences and words. [Means for solving the problem]

[0006] The system according to the embodiment includes a generation unit, a check unit, and a learning unit. The generation unit generates English sentences or words based on input from a learner. The check unit checks the English sentences or words generated by the generation unit. The learning unit learns the check results obtained by the check unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently improve the quality of generated English sentences and words. [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) An English learning system according to an embodiment of the present invention generates English sentences and words based on learner input, which are checked by a native speaker and then trained by a generation AI. In this system, learners use a generation AI to create English sentences and words, and a native speaker checks and provides feedback. Monetary rewards are provided for this checking, improving the quality of the learning content. Furthermore, the check results are used as correct answer labels for the generation AI's own training, reducing the time required for annotation. For example, in an English learning system, learners use a generation AI to create English sentences and words. The generation AI then generates appropriate English sentences and words based on the learner's input. For example, if a learner inputs, "I want to write an English sentence about travel," the generation AI generates an English sentence related to travel. The generated English sentences and words are then checked by a native speaker. The native speaker checks the accuracy of the grammar and expression of the generated English sentences and words and makes any necessary corrections. For example, if the generation AI generates "I am go to the park," the native speaker corrects it to "I am going to the park." Monetary rewards are provided for this checking. Native speakers can receive rewards for checking, which increases their motivation to check and improves the quality of learning content. Furthermore, the checking results are used as correct answer labels for training the generative AI itself. The generative AI learns the English sentences and words corrected by native speakers and improves its generation accuracy from the next time onwards. This reduces the time spent on annotation. This allows the English learning system to contribute to learners' improvement of their English skills and improve the learning accuracy of the generative AI. This allows the English learning system to contribute to learners' improvement of their English skills and improve the learning accuracy of the generative AI. For example, learners can efficiently improve their English skills while enjoying the benefits of both the generative AI and native checking. Furthermore, rewards encourage native speakers to check, improving the quality of learning content.Furthermore, the learning accuracy of the generative AI will improve and the time spent on annotation will decrease, improving overall efficiency.

[0029] The English language learning system according to the embodiment includes a generation unit, a check unit, and a learning unit. The generation unit generates English sentences and words based on input from a learner. For example, if a learner inputs, "I want to write an English sentence about travel," the generation unit generates an English sentence related to travel. The generation unit can also generate English sentences to be used in appropriate contexts based on the words input by the learner. For example, if a learner sets "business English" as a learning goal, the generation unit can generate business-related English sentences and words. The check unit checks the English sentences and words generated by the generation unit. For example, a native speaker may check the accuracy of the grammar and expression of the generated English sentences and words and make any necessary corrections. The check unit can also check the grammar, spelling, and meaning of the English sentences and words generated by the generation AI. For example, if the generation AI generates, "I am go to the park," the check unit corrects it to, "I am going to the park." The learning unit learns the check results obtained by the check unit. The learning unit, for example, learns English sentences and words corrected by native speakers, thereby improving the generation accuracy from the next time onwards. The learning unit also allows the generation AI to learn based on the check results, thereby reducing the time spent on annotation. For example, the learning unit allows the generation AI to learn English sentences and words corrected by native speakers, thereby improving the generation accuracy from the next time onwards. This allows the English learning system according to the embodiment to contribute to the improvement of learners' English skills and improve the learning accuracy of the generation AI.

[0030] The English learning system includes a reward unit that provides a monetary reward for checking work. The reward unit provides a monetary reward for checking work. For example, the reward unit allows native speakers to receive a reward for performing the checking work. The reward unit can also set the amount of the reward and the payment method to increase motivation for the checking work. For example, the reward unit can adjust the amount of the reward depending on the difficulty of the checking work. This increases motivation for the checking work and improves the quality of the learning content. Some or all of the above-described processing in the reward unit may be performed using, for example, AI, or may be performed without using AI. For example, the reward unit can input the difficulty of the checking work into AI and have the AI ​​calculate the amount of the reward.

[0031] The generation unit can analyze the learner's past learning history and select an appropriate generation method. For example, the generation unit generates English sentences that focus on grammar items that the learner previously struggled with. The generation unit can also generate words related to topics that the learner has previously shown interest in. The generation unit can also preferentially use generation methods that the learner has previously rated highly. This allows the optimal generation method to be selected based on the learner's past learning history. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's past learning data into the generation AI and have the generation AI select the optimal generation method.

[0032] During generation, the generation unit can perform filtering based on the learner's current learning goals and areas of interest. For example, if a learner has set "business English" as their learning goal, the generation unit can generate business-related English sentences and words. Furthermore, if a learner is interested in "travel English," the generation unit can also generate travel-related English sentences and words. Furthermore, if a learner's goal is "everyday conversation," the generation unit can also generate English sentences and words suitable for everyday conversation. This allows the generation of English sentences and words according to the learner's learning goals and areas of interest. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's learning goals and areas of interest into the generation AI and have the generation AI perform the filtering.

[0033] The generation unit can select an appropriate generation means according to the learner's input method during generation. For example, if the learner uses voice input, the generation AI can generate English sentences and words using voice recognition technology. Furthermore, if the learner uses text input, the generation unit can also generate English sentences and words using text analysis technology. Furthermore, if the learner uses image input, the generation AI can also generate related English sentences and words using image recognition technology. This allows the optimal generation means to be selected according to the learner's input method. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's input data into the generation AI and have the generation AI select the optimal generation means.

[0034] During generation, the generation unit can prioritize generating highly relevant English sentences and words by taking into account the learner's geographical location information. For example, if the learner is in Japan, the generation unit can generate English sentences and words related to Japan. Furthermore, if the learner is in the United States, the generation unit can also generate English sentences and words related to the United States. Furthermore, if the learner is traveling, the generation unit can also generate English sentences and words related to the travel destination. In this way, highly relevant English sentences and words can be generated based on the learner's geographical location information. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's geographical location information into the generation AI and cause the generation AI to generate highly relevant English sentences and words.

[0035] During generation, the generation unit can analyze the learner's social media activities and generate related English sentences and words. For example, the generation unit generates English sentences based on words frequently used by the learner on social media. The generation unit can also generate English sentences and words related to topics in which the learner is interested on social media. The generation unit can also analyze the content of the learner's social media posts and generate related English sentences and words. In this way, related English sentences and words can be generated based on the learner's social media activities. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's social media data into the generation AI and cause the generation AI to generate related English sentences and words.

[0036] The generation unit can customize the generation method by reflecting the learner's past feedback during generation. For example, the generation unit preferentially uses generation methods that the learner has previously rated highly. The generation unit can also avoid generation methods that the learner has previously rated poorly. The generation unit can also have the generation AI improve the generation method based on the learner's feedback. This allows the generation method to be customized based on the learner's past feedback. Some or all of the above-mentioned processing in the generation unit may be performed using AI, for example, or may be performed without using AI. For example, the generation unit can input the learner's feedback data into the generation AI and have the generation AI customize the generation method.

[0037] The checking unit can adjust the level of detail of the check based on the importance of English sentences and words during the check. For example, the checking unit performs a detailed check on important grammar items. The checking unit can also perform a simplified check on less important words and expressions. The checking unit can also perform a focused check on items related to the learner's learning goals. This allows checking to be performed with a level of detail according to the importance of English sentences and words. Some or all of the above-mentioned processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit can input importance data of English sentences and words into the generating AI and cause the generating AI to adjust the level of detail of the check.

[0038] The checking unit can apply different checking algorithms depending on the category of English sentences and words when checking. For example, the checking unit performs a check that emphasizes formal expressions for business English. The checking unit can also perform a check that emphasizes natural expressions for everyday conversation. The checking unit can also perform a check that emphasizes accuracy for technical terms. This allows the application of checking algorithms depending on the category of English sentences and words. Some or all of the above-mentioned processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit can input category data of English sentences and words into the generation AI and cause the generation AI to apply the checking algorithm.

[0039] The checking unit can improve the accuracy of the check by referring to the learner's past check results when checking. For example, the checking unit may focus on checking items that the learner has previously answered incorrectly. The checking unit may also perform a simplified check for items that the learner has previously answered correctly. The checking unit may also optimize the checking algorithm based on the learner's past check results. This allows the accuracy of the check to be improved based on the learner's past check results. Some or all of the above-mentioned processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit may input the learner's past check data into the generation AI and cause the generation AI to improve the accuracy of the check.

[0040] When checking, the checking unit can determine the priority of checking based on the time of submission of the English sentences and words. For example, the checking unit prioritizes checking of recently submitted English sentences and words. The checking unit can also postpone checking of older submitted sentences and words. The checking unit can also dynamically adjust the priority of checking based on the time of submission. This allows checking to be performed in priority according to the time of submission of the English sentences and words. Some or all of the above-mentioned processing in the checking unit may be performed using AI, for example, or may be performed without using AI. For example, the checking unit can input submission time data into the generation AI and have the generation AI determine the priority of checking.

[0041] The checking unit can adjust the order of checking based on the relevance of English sentences and words when checking. For example, the checking unit prioritizes checking highly relevant English sentences and words. The checking unit can also postpone checking less relevant ones. The checking unit can also dynamically adjust the order of checking based on the relevance. This allows checking to be performed in an order based on the relevance of English sentences and words. Some or all of the above-mentioned processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit can input relevance data of English sentences and words into the generating AI and have the generating AI adjust the order of checking.

[0042] During the check, the checking unit can adjust the use of technical terminology in the check according to the learner's level of expertise. For example, if the learner is a beginner, the checking unit can avoid technical terminology and use simple expressions. Furthermore, if the learner is an intermediate learner, the checking unit can also use technical terminology moderately. Furthermore, if the learner is an advanced learner, the checking unit can provide detailed feedback using a lot of technical terminology. This allows the check to be performed with the use of technical terminology according to the learner's level of expertise. Some or all of the above-described processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit can input the learner's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terminology.

[0043] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on data previously learned by the learner. The learning unit can also analyze the learner's past learning data and improve the learning algorithm. The learning unit can also adjust the parameters of the learning algorithm by referring to the learner's past learning data. This allows the learning algorithm to be optimized based on the past learning data. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input past learning data into a generation AI and cause the generation AI to optimize the learning algorithm.

[0044] The learning unit can update the learning data during learning by reflecting the learner's feedback. The learning unit updates the learning data, for example, based on feedback provided by the learner. The learning unit can also improve the content of the learning data by reflecting the learner's feedback. The learning unit can also review the criteria for selecting learning data based on the learner's feedback. This allows the learning data to be updated based on the learner's feedback. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the learner's feedback data into a generation AI and have the generation AI update the learning data.

[0045] During learning, the learning unit can weight the learning data based on the time of submission of the English sentences and words. For example, the learning unit can weight recently submitted English sentences and words highly. The learning unit can also weight older submitted sentences and words less. The learning unit can also dynamically adjust the weighting of the learning data according to the time of submission. This allows the learning data to be handled with weighting according to the time of submission. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input submission time data into the generation AI and have the generation AI perform weighting of the learning data.

[0046] During learning, the learning unit can integrate information from different data sources to enrich the learning data. For example, the learning unit may acquire data from other learning apps used by the learner and integrate it into the learning data. The learning unit may also acquire information from online dictionaries and grammar guides and integrate it into the learning data. The learning unit may also acquire related information from the learner's social media activities and integrate it into the learning data. In this way, the learning data can be enriched by integrating information from different data sources. Some or all of the above-described processing in the learning unit may be performed using, or without, AI, for example. For example, the learning unit may input information from different data sources into a generation AI and have the generation AI integrate the information.

[0047] The reward unit can adjust the details of the reward based on the difficulty of the check task when providing the reward. For example, the reward unit can provide a high reward for a high-difficulty check task. The reward unit can also provide a low reward for a low-difficulty check task. The reward unit can also dynamically adjust the details of the reward according to the difficulty of the check task. This makes it possible to adjust the details of the reward according to the difficulty of the check task. Some or all of the above-mentioned processing in the reward unit may be performed using AI, for example, or may be performed without using AI. For example, the reward unit can input difficulty data of the check task to the generation AI and cause the generation AI to adjust the details of the reward.

[0048] When providing a reward, the reward unit can apply different reward algorithms depending on the category of the checking task. For example, the reward unit applies a specific reward algorithm to the checking task of business English. The reward unit can also apply a different reward algorithm to the checking task of everyday conversation. The reward unit can also apply a specific reward algorithm to the checking task of technical terminology. This makes it possible to apply a reward algorithm depending on the category of the checking task. Some or all of the above-mentioned processing in the reward unit may be performed using AI, for example, or may be performed without using AI. For example, the reward unit can input checking task category data into the generation AI and cause the generation AI to apply the reward algorithm.

[0049] When providing rewards, the reward unit can determine the priority of rewards based on the time of submission of the check work. For example, the reward unit can provide a higher reward for a recently submitted check work. The reward unit can also provide a lower reward for an older submitted check work. The reward unit can also dynamically adjust the priority of rewards depending on the time of submission. This allows rewards to be provided in a priority order depending on the time of submission. Some or all of the above-mentioned processing in the reward unit may be performed using AI, for example, or may be performed without using AI. For example, the reward unit can input submission time data into the generation AI and have the generation AI determine the priority of rewards.

[0050] When providing rewards, the reward unit can determine the priority of rewards based on the time of submission of the check work. For example, the reward unit can provide a higher reward for a recently submitted check work. The reward unit can also provide a lower reward for an older submitted check work. The reward unit can also dynamically adjust the priority of rewards depending on the time of submission. This allows rewards to be provided in a priority order depending on the time of submission. Some or all of the above-mentioned processing in the reward unit may be performed using AI, for example, or may be performed without using AI. For example, the reward unit can input submission time data into the generation AI and have the generation AI determine the priority of rewards.

[0051] The reward unit can adjust the order of rewards based on the relevance of the check tasks when providing rewards. For example, the reward unit can provide a higher reward for a highly relevant check task. The reward unit can also provide a lower reward for a less relevant check task. The reward unit can also dynamically adjust the order of rewards according to the relevance. This allows rewards to be provided in an order according to the relevance. Some or all of the above-described processing in the reward unit can be performed using AI, for example, or can be performed without using AI. For example, the reward unit can input relevance data of the check tasks to a generation AI and cause the generation AI to adjust the order of rewards.

[0052] When providing a reward, the reward unit can apply different reward algorithms depending on the category of the checking task. For example, the reward unit applies a specific reward algorithm to the checking task of business English. The reward unit can also apply a different reward algorithm to the checking task of everyday conversation. The reward unit can also apply a specific reward algorithm to the checking task of technical terminology. This makes it possible to apply a reward algorithm depending on the category of the checking task. Some or all of the above-mentioned processing in the reward unit may be performed using AI, for example, or may be performed without using AI. For example, the reward unit can input checking task category data into the generation AI and cause the generation AI to apply the reward algorithm.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] The generation unit generates English sentences and words based on the learner's input. For example, if a learner inputs, "I want to write an English sentence about travel," the generation AI generates an English sentence related to travel. The generation unit can also generate English sentences to be used in appropriate contexts based on the words input by the learner. For example, if a learner sets "business English" as their learning goal, the generation unit can generate business-related English sentences and words. The check unit checks the English sentences and words generated by the generation unit. For example, a native speaker may check the accuracy of the grammar and expression of the generated English sentences and words and make any necessary corrections. The check unit can also check the grammar, spelling, and meaning of the English sentences and words generated by the generation AI. For example, if the generation AI generates, "I am go to the park," the check unit corrects it to, "I am going to the park." The learning unit learns the check results obtained by the check unit. For example, the learning unit learns English sentences and words corrected by native speakers to improve the accuracy of future generation. In addition, the learning unit allows the generation AI to learn based on the check results, reducing the time it spends on annotation. For example, the learning unit allows the generation AI to learn English sentences and words corrected by native speakers, improving the generation accuracy from the next time onwards. As a result, the English learning system according to the embodiment can contribute to the improvement of learners' English skills and improve the learning accuracy of the generation AI.

[0055] The reward unit provides monetary rewards for checking work. For example, the reward unit allows native speakers to receive rewards for performing the checking work. The reward unit can also set the amount of reward and payment method to increase motivation for the checking work. For example, the reward unit can adjust the amount of reward depending on the difficulty of the checking work. This increases motivation for the checking work and improves the quality of the learning content. Some or all of the above-described processing in the reward unit may be performed using, or without, AI. For example, the reward unit can input the difficulty of the checking work into AI and have the AI ​​calculate the amount of reward.

[0056] The generation unit can analyze the learner's past learning history and select an appropriate generation method. For example, the generation unit generates English sentences that focus on grammar items that the learner previously struggled with. The generation unit can also generate words related to topics that the learner has previously shown interest in. The generation unit can also preferentially use generation methods that the learner has previously rated highly. This allows the optimal generation method to be selected based on the learner's past learning history. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's past learning data into the generation AI and have the generation AI select the optimal generation method.

[0057] During generation, the generation unit can perform filtering based on the learner's current learning goals and areas of interest. For example, if a learner has set "business English" as their learning goal, the generation unit can generate business-related English sentences and words. Furthermore, if a learner is interested in "travel English," the generation unit can also generate travel-related English sentences and words. Furthermore, if a learner's goal is "everyday conversation," the generation unit can also generate English sentences and words suitable for everyday conversation. This allows the generation of English sentences and words according to the learner's learning goals and areas of interest. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's learning goals and areas of interest into the generation AI and have the generation AI perform the filtering.

[0058] The generation unit can select an appropriate generation means according to the learner's input method during generation. For example, if the learner uses voice input, the generation AI can generate English sentences and words using voice recognition technology. Furthermore, if the learner uses text input, the generation unit can also generate English sentences and words using text analysis technology. Furthermore, if the learner uses image input, the generation AI can also generate related English sentences and words using image recognition technology. This allows the optimal generation means to be selected according to the learner's input method. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's input data into the generation AI and have the generation AI select the optimal generation means.

[0059] During generation, the generation unit can prioritize generating highly relevant English sentences and words by taking into account the learner's geographical location information. For example, if the learner is in Japan, the generation unit can generate English sentences and words related to Japan. Furthermore, if the learner is in the United States, the generation unit can also generate English sentences and words related to the United States. Furthermore, if the learner is traveling, the generation unit can also generate English sentences and words related to the travel destination. In this way, highly relevant English sentences and words can be generated based on the learner's geographical location information. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's geographical location information into the generation AI and cause the generation AI to generate highly relevant English sentences and words.

[0060] During generation, the generation unit can analyze the learner's social media activities and generate related English sentences and words. For example, the generation unit generates English sentences based on words frequently used by the learner on social media. The generation unit can also generate English sentences and words related to topics in which the learner is interested on social media. The generation unit can also analyze the content of the learner's social media posts and generate related English sentences and words. In this way, related English sentences and words can be generated based on the learner's social media activities. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's social media data into the generation AI and cause the generation AI to generate related English sentences and words.

[0061] The generation unit can customize the generation method by reflecting the learner's past feedback during generation. For example, the generation unit preferentially uses generation methods that the learner has previously rated highly. The generation unit can also avoid generation methods that the learner has previously rated poorly. The generation unit can also have the generation AI improve the generation method based on the learner's feedback. This allows the generation method to be customized based on the learner's past feedback. Some or all of the above-mentioned processing in the generation unit may be performed using AI, for example, or may be performed without using AI. For example, the generation unit can input the learner's feedback data into the generation AI and have the generation AI customize the generation method.

[0062] The checking unit can adjust the level of detail of the check based on the importance of English sentences and words during the check. For example, the checking unit performs a detailed check on important grammar items. The checking unit can also perform a simplified check on less important words and expressions. The checking unit can also perform a focused check on items related to the learner's learning goals. This allows checking to be performed with a level of detail according to the importance of English sentences and words. Some or all of the above-mentioned processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit can input importance data of English sentences and words into the generating AI and cause the generating AI to adjust the level of detail of the check.

[0063] The checking unit can apply different checking algorithms depending on the category of English sentences and words when checking. For example, the checking unit performs a check that emphasizes formal expressions for business English. The checking unit can also perform a check that emphasizes natural expressions for everyday conversation. The checking unit can also perform a check that emphasizes accuracy for technical terms. This allows the application of checking algorithms depending on the category of English sentences and words. Some or all of the above-mentioned processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit can input category data of English sentences and words into the generation AI and cause the generation AI to apply the checking algorithm.

[0064] The checking unit can improve the accuracy of the check by referring to the learner's past check results when checking. For example, the checking unit may focus on checking items that the learner has previously answered incorrectly. The checking unit may also perform a simplified check for items that the learner has previously answered correctly. The checking unit may also optimize the checking algorithm based on the learner's past check results. This allows the accuracy of the check to be improved based on the learner's past check results. Some or all of the above-mentioned processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit may input the learner's past check data into the generation AI and cause the generation AI to improve the accuracy of the check.

[0065] When checking, the checking unit can determine the priority of checking based on the time of submission of the English sentences and words. For example, the checking unit prioritizes checking of recently submitted English sentences and words. The checking unit can also postpone checking of older submitted sentences and words. The checking unit can also dynamically adjust the priority of checking based on the time of submission. This allows checking to be performed in priority according to the time of submission of the English sentences and words. Some or all of the above-mentioned processing in the checking unit may be performed using AI, for example, or may be performed without using AI. For example, the checking unit can input submission time data into the generation AI and have the generation AI determine the priority of checking.

[0066] The checking unit can adjust the order of checking based on the relevance of English sentences and words when checking. For example, the checking unit prioritizes checking highly relevant English sentences and words. The checking unit can also postpone checking less relevant ones. The checking unit can also dynamically adjust the order of checking based on the relevance. This allows checking to be performed in an order based on the relevance of English sentences and words. Some or all of the above-mentioned processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit can input relevance data of English sentences and words into the generating AI and have the generating AI adjust the order of checking.

[0067] During the check, the checking unit can adjust the use of technical terminology in the check according to the learner's level of expertise. For example, if the learner is a beginner, the checking unit can avoid technical terminology and use simple expressions. Furthermore, if the learner is an intermediate learner, the checking unit can also use technical terminology moderately. Furthermore, if the learner is an advanced learner, the checking unit can provide detailed feedback using a lot of technical terminology. This allows the check to be performed with the use of technical terminology according to the learner's level of expertise. Some or all of the above-described processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit can input the learner's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terminology.

[0068] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on data previously learned by the learner. The learning unit can also analyze the learner's past learning data and improve the learning algorithm. The learning unit can also adjust the parameters of the learning algorithm by referring to the learner's past learning data. This allows the learning algorithm to be optimized based on the past learning data. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input past learning data into a generation AI and cause the generation AI to optimize the learning algorithm.

[0069] The learning unit can update the learning data during learning by reflecting the learner's feedback. The learning unit updates the learning data, for example, based on feedback provided by the learner. The learning unit can also improve the content of the learning data by reflecting the learner's feedback. The learning unit can also review the criteria for selecting learning data based on the learner's feedback. This allows the learning data to be updated based on the learner's feedback. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the learner's feedback data into a generation AI and have the generation AI update the learning data.

[0070] During learning, the learning unit can weight the learning data based on the time of submission of the English sentences and words. For example, the learning unit can weight recently submitted English sentences and words highly. The learning unit can also weight older submitted sentences and words less. The learning unit can also dynamically adjust the weighting of the learning data according to the time of submission. This allows the learning data to be handled with weighting according to the time of submission. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input submission time data into the generation AI and have the generation AI perform weighting of the learning data.

[0071] During learning, the learning unit can integrate information from different data sources to enrich the learning data. For example, the learning unit may acquire data from other learning apps used by the learner and integrate it into the learning data. The learning unit may also acquire information from online dictionaries and grammar guides and integrate it into the learning data. The learning unit may also acquire related information from the learner's social media activities and integrate it into the learning data. In this way, the learning data can be enriched by integrating information from different data sources. Some or all of the above-described processing in the learning unit may be performed using, or without, AI, for example. For example, the learning unit may input information from different data sources into a generation AI and have the generation AI integrate the information.

[0072] The reward unit can adjust the details of the reward based on the difficulty of the check task when providing the reward. For example, the reward unit can provide a high reward for a high-difficulty check task. The reward unit can also provide a low reward for a low-difficulty check task. The reward unit can also dynamically adjust the details of the reward according to the difficulty of the check task. This makes it possible to adjust the details of the reward according to the difficulty of the check task. Some or all of the above-mentioned processing in the reward unit may be performed using AI, for example, or may be performed without using AI. For example, the reward unit can input difficulty data of the check task to the generation AI and cause the generation AI to adjust the details of the reward.

[0073] When providing a reward, the reward unit can apply different reward algorithms depending on the category of the checking task. For example, the reward unit applies a specific reward algorithm to the checking task of business English. The reward unit can also apply a different reward algorithm to the checking task of everyday conversation. The reward unit can also apply a specific reward algorithm to the checking task of technical terminology. This makes it possible to apply a reward algorithm depending on the category of the checking task. Some or all of the above-mentioned processing in the reward unit may be performed using AI, for example, or may be performed without using AI. For example, the reward unit can input checking task category data into the generation AI and cause the generation AI to apply the reward algorithm.

[0074] When providing rewards, the reward unit can determine the priority of rewards based on the time of submission of the check work. For example, the reward unit can provide a higher reward for a recently submitted check work. The reward unit can also provide a lower reward for an older submitted check work. The reward unit can also dynamically adjust the priority of rewards depending on the time of submission. This allows rewards to be provided in a priority order depending on the time of submission. Some or all of the above-mentioned processing in the reward unit may be performed using AI, for example, or may be performed without using AI. For example, the reward unit can input submission time data into the generation AI and have the generation AI determine the priority of rewards.

[0075] The processing flow of the first embodiment will be briefly explained below.

[0076] Step 1: The generation unit generates English sentences and words based on the learner's input. For example, if a learner inputs, "I want to write English sentences about travel," the generation AI will generate English sentences related to travel. It can also generate English sentences to be used in appropriate contexts based on the words input by the learner. Furthermore, if a learner sets "business English" as their learning goal, it can generate business-related English sentences and words. Step 2: The checking unit checks the English sentences and words generated by the generation unit. For example, a native speaker checks the accuracy of the grammar and expressions of the generated English sentences and words, and makes any necessary corrections. The checking unit can also check the grammar, spelling, and meaning of the English sentences and words generated by the generation AI. For example, if the generation AI generates "I am go to the park," it will correct it to "I am going to the park." Step 3: The learning unit learns from the checking results obtained by the checking unit. For example, it learns from English sentences and words corrected by native speakers, improving the accuracy of future generation. In addition, the generation AI learns based on the checking results, reducing the time spent on annotation. This improves the learning accuracy of the generation AI and contributes to improving learners' English skills.

[0077] (Example 2) An English learning system according to an embodiment of the present invention generates English sentences and words based on learner input, which are checked by a native speaker and then trained by a generation AI. In this system, learners use a generation AI to create English sentences and words, and a native speaker checks and provides feedback. Monetary rewards are provided for this checking, improving the quality of the learning content. Furthermore, the check results are used as correct answer labels for the generation AI's own training, reducing the time required for annotation. For example, in an English learning system, learners use a generation AI to create English sentences and words. The generation AI then generates appropriate English sentences and words based on the learner's input. For example, if a learner inputs, "I want to write an English sentence about travel," the generation AI generates an English sentence related to travel. The generated English sentences and words are then checked by a native speaker. The native speaker checks the accuracy of the grammar and expression of the generated English sentences and words and makes any necessary corrections. For example, if the generation AI generates "I am go to the park," the native speaker corrects it to "I am going to the park." Monetary rewards are provided for this checking. Native speakers can receive rewards for checking, which increases their motivation to check and improves the quality of learning content. Furthermore, the checking results are used as correct answer labels for training the generative AI itself. The generative AI learns the English sentences and words corrected by native speakers and improves its generation accuracy from the next time onwards. This reduces the time spent on annotation. This allows the English learning system to contribute to learners' improvement of their English skills and improve the learning accuracy of the generative AI. This allows the English learning system to contribute to learners' improvement of their English skills and improve the learning accuracy of the generative AI. For example, learners can efficiently improve their English skills while enjoying the benefits of both the generative AI and native checking. Furthermore, rewards encourage native speakers to check, improving the quality of learning content.Furthermore, the learning accuracy of the generative AI will improve and the time spent on annotation will decrease, improving overall efficiency.

[0078] The English language learning system according to the embodiment includes a generation unit, a check unit, and a learning unit. The generation unit generates English sentences and words based on input from a learner. For example, if a learner inputs, "I want to write an English sentence about travel," the generation unit generates an English sentence related to travel. The generation unit can also generate English sentences to be used in appropriate contexts based on the words input by the learner. For example, if a learner sets "business English" as a learning goal, the generation unit can generate business-related English sentences and words. The check unit checks the English sentences and words generated by the generation unit. For example, a native speaker may check the accuracy of the grammar and expression of the generated English sentences and words and make any necessary corrections. The check unit can also check the grammar, spelling, and meaning of the English sentences and words generated by the generation AI. For example, if the generation AI generates, "I am go to the park," the check unit corrects it to, "I am going to the park." The learning unit learns the check results obtained by the check unit. The learning unit, for example, learns English sentences and words corrected by native speakers, thereby improving the generation accuracy from the next time onwards. The learning unit also allows the generation AI to learn based on the check results, thereby reducing the time spent on annotation. For example, the learning unit allows the generation AI to learn English sentences and words corrected by native speakers, thereby improving the generation accuracy from the next time onwards. This allows the English learning system according to the embodiment to contribute to the improvement of learners' English skills and improve the learning accuracy of the generation AI.

[0079] The English learning system includes a reward unit that provides a monetary reward for checking work. The reward unit provides a monetary reward for checking work. For example, the reward unit allows native speakers to receive a reward for performing the checking work. The reward unit can also set the amount of the reward and the payment method to increase motivation for the checking work. For example, the reward unit can adjust the amount of the reward depending on the difficulty of the checking work. This increases motivation for the checking work and improves the quality of the learning content. Some or all of the above-described processing in the reward unit may be performed using, for example, AI, or may be performed without using AI. For example, the reward unit can input the difficulty of the checking work into AI and have the AI ​​calculate the amount of the reward.

[0080] The generation unit can estimate the learner's emotions and adjust the tone of the generated English sentences and words based on the estimated learner's emotions. For example, if the learner is relaxed, the generation AI can generate English sentences and words with a casual tone. If the learner is nervous, the generation AI can generate English sentences and words with a formal and calm tone. If the learner is excited, the generation AI can generate English sentences and words with an energetic and positive tone. This allows the generation of English sentences and words with a tone that matches the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the learner's emotional data into the generation AI and cause the generation AI to adjust the tone of the English sentences and words to be generated.

[0081] The generation unit can analyze the learner's past learning history and select an appropriate generation method. For example, the generation unit generates English sentences that focus on grammar items that the learner previously struggled with. The generation unit can also generate words related to topics that the learner has previously shown interest in. The generation unit can also preferentially use generation methods that the learner has previously rated highly. This allows the optimal generation method to be selected based on the learner's past learning history. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's past learning data into the generation AI and have the generation AI select the optimal generation method.

[0082] During generation, the generation unit can perform filtering based on the learner's current learning goals and areas of interest. For example, if a learner has set "business English" as their learning goal, the generation unit can generate business-related English sentences and words. Furthermore, if a learner is interested in "travel English," the generation unit can also generate travel-related English sentences and words. Furthermore, if a learner's goal is "everyday conversation," the generation unit can also generate English sentences and words suitable for everyday conversation. This allows the generation of English sentences and words according to the learner's learning goals and areas of interest. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's learning goals and areas of interest into the generation AI and have the generation AI perform the filtering.

[0083] The generation unit can select an appropriate generation means according to the learner's input method during generation. For example, if the learner uses voice input, the generation AI can generate English sentences and words using voice recognition technology. Furthermore, if the learner uses text input, the generation unit can also generate English sentences and words using text analysis technology. Furthermore, if the learner uses image input, the generation AI can also generate related English sentences and words using image recognition technology. This allows the optimal generation means to be selected according to the learner's input method. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's input data into the generation AI and have the generation AI select the optimal generation means.

[0084] The generation unit can estimate the learner's emotions and adjust the difficulty of the English sentences and words to be generated based on the estimated learner's emotions. For example, if the learner is relaxed, the generation AI can generate high-difficulty English sentences and words. Furthermore, if the learner is nervous, the generation AI can generate low-difficulty English sentences and words. Furthermore, if the learner is excited, the generation AI can generate medium-difficulty English sentences and words. This allows for the generation of English sentences and words of a level of difficulty that corresponds to the learner's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the learner's emotional data into the generation AI and cause the generation AI to adjust the difficulty of the English sentences and words to be generated.

[0085] During generation, the generation unit can prioritize generating highly relevant English sentences and words by taking into account the learner's geographical location information. For example, if the learner is in Japan, the generation unit can generate English sentences and words related to Japan. Furthermore, if the learner is in the United States, the generation unit can also generate English sentences and words related to the United States. Furthermore, if the learner is traveling, the generation unit can also generate English sentences and words related to the travel destination. In this way, highly relevant English sentences and words can be generated based on the learner's geographical location information. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's geographical location information into the generation AI and cause the generation AI to generate highly relevant English sentences and words.

[0086] During generation, the generation unit can analyze the learner's social media activities and generate related English sentences and words. For example, the generation unit generates English sentences based on words frequently used by the learner on social media. The generation unit can also generate English sentences and words related to topics in which the learner is interested on social media. The generation unit can also analyze the content of the learner's social media posts and generate related English sentences and words. In this way, related English sentences and words can be generated based on the learner's social media activities. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's social media data into the generation AI and cause the generation AI to generate related English sentences and words.

[0087] The generation unit can customize the generation method by reflecting the learner's past feedback during generation. For example, the generation unit preferentially uses generation methods that the learner has previously rated highly. The generation unit can also avoid generation methods that the learner has previously rated poorly. The generation unit can also have the generation AI improve the generation method based on the learner's feedback. This allows the generation method to be customized based on the learner's past feedback. Some or all of the above-mentioned processing in the generation unit may be performed using AI, for example, or may be performed without using AI. For example, the generation unit can input the learner's feedback data into the generation AI and have the generation AI customize the generation method.

[0088] The checking unit can estimate the learner's emotions and adjust the way the check is expressed based on the estimated learner's emotions. For example, if the learner is relaxed, the checking unit can provide detailed feedback. If the learner is nervous, the checking unit can also provide concise and to-the-point feedback. If the learner is excited, the checking unit can also provide feedback that makes use of positive expressions. This allows the check to be performed in an expression that corresponds to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the checking unit can be performed using, for example, an AI, or without an AI. For example, the checking unit can input the learner's emotion data into the generation AI and have the generation AI adjust the way the check is expressed.

[0089] The checking unit can adjust the level of detail of the check based on the importance of English sentences and words during the check. For example, the checking unit performs a detailed check on important grammar items. The checking unit can also perform a simplified check on less important words and expressions. The checking unit can also perform a focused check on items related to the learner's learning goals. This allows checking to be performed with a level of detail according to the importance of English sentences and words. Some or all of the above-mentioned processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit can input importance data of English sentences and words into the generating AI and cause the generating AI to adjust the level of detail of the check.

[0090] The checking unit can apply different checking algorithms depending on the category of English sentences and words when checking. For example, the checking unit performs a check that emphasizes formal expressions for business English. The checking unit can also perform a check that emphasizes natural expressions for everyday conversation. The checking unit can also perform a check that emphasizes accuracy for technical terms. This allows the application of checking algorithms depending on the category of English sentences and words. Some or all of the above-mentioned processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit can input category data of English sentences and words into the generation AI and cause the generation AI to apply the checking algorithm.

[0091] The checking unit can improve the accuracy of the check by referring to the learner's past check results when checking. For example, the checking unit may focus on checking items that the learner has previously answered incorrectly. The checking unit may also perform a simplified check for items that the learner has previously answered correctly. The checking unit may also optimize the checking algorithm based on the learner's past check results. This allows the accuracy of the check to be improved based on the learner's past check results. Some or all of the above-mentioned processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit may input the learner's past check data into the generation AI and cause the generation AI to improve the accuracy of the check.

[0092] The checking unit can estimate the learner's emotions and adjust the length of the check based on the estimated learner's emotions. For example, if the learner is relaxed, the checking unit can provide a detailed check. If the learner is nervous, the checking unit can also provide a brief check. If the learner is excited, the checking unit can also provide a check that includes a lot of positive feedback. This allows the check to be performed at a length that corresponds to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the checking unit can be performed using, for example, AI, or without AI. For example, the checking unit can input the learner's emotion data into the generation AI and have the generation AI adjust the length of the check.

[0093] When checking, the checking unit can determine the priority of checking based on the time of submission of the English sentences and words. For example, the checking unit prioritizes checking of recently submitted English sentences and words. The checking unit can also postpone checking of older submitted sentences and words. The checking unit can also dynamically adjust the priority of checking based on the time of submission. This allows checking to be performed in priority according to the time of submission of the English sentences and words. Some or all of the above-mentioned processing in the checking unit may be performed using AI, for example, or may be performed without using AI. For example, the checking unit can input submission time data into the generation AI and have the generation AI determine the priority of checking.

[0094] The checking unit can adjust the order of checking based on the relevance of English sentences and words when checking. For example, the checking unit prioritizes checking highly relevant English sentences and words. The checking unit can also postpone checking less relevant ones. The checking unit can also dynamically adjust the order of checking based on the relevance. This allows checking to be performed in an order based on the relevance of English sentences and words. Some or all of the above-mentioned processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit can input relevance data of English sentences and words into the generating AI and have the generating AI adjust the order of checking.

[0095] During the check, the checking unit can adjust the use of technical terminology in the check according to the learner's level of expertise. For example, if the learner is a beginner, the checking unit can avoid technical terminology and use simple expressions. Furthermore, if the learner is an intermediate learner, the checking unit can also use technical terminology moderately. Furthermore, if the learner is an advanced learner, the checking unit can provide detailed feedback using a lot of technical terminology. This allows the check to be performed with the use of technical terminology according to the learner's level of expertise. Some or all of the above-described processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit can input the learner's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terminology.

[0096] The learning unit can estimate the learner's emotions and select learning data based on the estimated learner's emotions. For example, if the learner is relaxed, the learning unit selects learning data with a high level of difficulty. Furthermore, if the learner is nervous, the learning unit can select learning data with a low level of difficulty. Furthermore, if the learner is excited, the learning unit can select learning data with content that will interest the learner. This allows for the selection of learning data according to the learner's emotions. The emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the learner's emotional data into the generation AI and have the generation AI select the learning data.

[0097] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on data previously learned by the learner. The learning unit can also analyze the learner's past learning data and improve the learning algorithm. The learning unit can also adjust the parameters of the learning algorithm by referring to the learner's past learning data. This allows the learning algorithm to be optimized based on the past learning data. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input past learning data into a generation AI and cause the generation AI to optimize the learning algorithm.

[0098] The learning unit can update the learning data during learning by reflecting the learner's feedback. The learning unit updates the learning data, for example, based on feedback provided by the learner. The learning unit can also improve the content of the learning data by reflecting the learner's feedback. The learning unit can also review the criteria for selecting learning data based on the learner's feedback. This allows the learning data to be updated based on the learner's feedback. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the learner's feedback data into a generation AI and have the generation AI update the learning data.

[0099] The learning unit can estimate the learner's emotions and adjust the frequency of learning based on the estimated learner's emotions. For example, the learning unit can increase the frequency of learning when the learner is relaxed. The learning unit can also decrease the frequency of learning when the learner is nervous. The learning unit can also moderately adjust the frequency of learning when the learner is excited. This allows the learner to study at a frequency that corresponds to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the learning unit can be performed using, for example, an AI, or without an AI. For example, the learning unit can input the learner's emotional data into the generation AI and have the generation AI adjust the frequency of learning.

[0100] During learning, the learning unit can weight the learning data based on the time of submission of the English sentences and words. For example, the learning unit can weight recently submitted English sentences and words highly. The learning unit can also weight older submitted sentences and words less. The learning unit can also dynamically adjust the weighting of the learning data according to the time of submission. This allows the learning data to be handled with weighting according to the time of submission. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input submission time data into the generation AI and have the generation AI perform weighting of the learning data.

[0101] During learning, the learning unit can integrate information from different data sources to enrich the learning data. For example, the learning unit may acquire data from other learning apps used by the learner and integrate it into the learning data. The learning unit may also acquire information from online dictionaries and grammar guides and integrate it into the learning data. The learning unit may also acquire related information from the learner's social media activities and integrate it into the learning data. In this way, the learning data can be enriched by integrating information from different data sources. Some or all of the above-described processing in the learning unit may be performed using, or without, AI, for example. For example, the learning unit may input information from different data sources into a generation AI and have the generation AI integrate the information.

[0102] The reward unit can estimate the learner's emotions and adjust the type and amount of reward based on the estimated learner's emotions. For example, the reward unit can increase the amount of reward when the learner is relaxed. The reward unit can also diversify the types of reward when the learner is nervous. The reward unit can also balance the amount and type of reward when the learner is excited. This allows the type and amount of reward to be adjusted according to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the reward unit can be performed using, for example, an AI, or without an AI. For example, the reward unit can input the learner's emotion data into the generation AI and have the generation AI adjust the type and amount of reward.

[0103] The reward unit can adjust the details of the reward based on the difficulty of the check task when providing the reward. For example, the reward unit can provide a high reward for a high-difficulty check task. The reward unit can also provide a low reward for a low-difficulty check task. The reward unit can also dynamically adjust the details of the reward according to the difficulty of the check task. This makes it possible to adjust the details of the reward according to the difficulty of the check task. Some or all of the above-mentioned processing in the reward unit may be performed using AI, for example, or may be performed without using AI. For example, the reward unit can input difficulty data of the check task to the generation AI and cause the generation AI to adjust the details of the reward.

[0104] When providing a reward, the reward unit can apply different reward algorithms depending on the category of the checking task. For example, the reward unit applies a specific reward algorithm to the checking task of business English. The reward unit can also apply a different reward algorithm to the checking task of everyday conversation. The reward unit can also apply a specific reward algorithm to the checking task of technical terminology. This makes it possible to apply a reward algorithm depending on the category of the checking task. Some or all of the above-mentioned processing in the reward unit may be performed using AI, for example, or may be performed without using AI. For example, the reward unit can input checking task category data into the generation AI and cause the generation AI to apply the reward algorithm.

[0105] When providing rewards, the reward unit can determine the priority of rewards based on the time of submission of the check work. For example, the reward unit can provide a higher reward for a recently submitted check work. The reward unit can also provide a lower reward for an older submitted check work. The reward unit can also dynamically adjust the priority of rewards depending on the time of submission. This allows rewards to be provided in a priority order depending on the time of submission. Some or all of the above-mentioned processing in the reward unit may be performed using AI, for example, or may be performed without using AI. For example, the reward unit can input submission time data into the generation AI and have the generation AI determine the priority of rewards.

[0106] The reward unit can estimate the learner's emotions and adjust the timing of reward provision based on the estimated learner's emotions. For example, if the learner is relaxed, the reward unit can provide the reward immediately. If the learner is nervous, the reward unit can also provide the reward gradually. If the learner is excited, the reward unit can also provide the reward randomly. This allows rewards to be provided at timings that correspond to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the reward unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the reward unit can input the learner's emotion data into the generation AI and cause the generation AI to adjust the timing of reward provision.

[0107] When providing rewards, the reward unit can determine the priority of rewards based on the time of submission of the check work. For example, the reward unit can provide a higher reward for a recently submitted check work. The reward unit can also provide a lower reward for an older submitted check work. The reward unit can also dynamically adjust the priority of rewards depending on the time of submission. This allows rewards to be provided in a priority order depending on the time of submission. Some or all of the above-mentioned processing in the reward unit may be performed using AI, for example, or may be performed without using AI. For example, the reward unit can input submission time data into the generation AI and have the generation AI determine the priority of rewards.

[0108] The reward unit can adjust the order of rewards based on the relevance of the check tasks when providing rewards. For example, the reward unit can provide a higher reward for a highly relevant check task. The reward unit can also provide a lower reward for a less relevant check task. The reward unit can also dynamically adjust the order of rewards according to the relevance. This allows rewards to be provided in an order according to the relevance. Some or all of the above-described processing in the reward unit can be performed using AI, for example, or can be performed without using AI. For example, the reward unit can input relevance data of the check tasks to a generation AI and cause the generation AI to adjust the order of rewards.

[0109] When providing a reward, the reward unit can apply different reward algorithms depending on the category of the checking task. For example, the reward unit applies a specific reward algorithm to the checking task of business English. The reward unit can also apply a different reward algorithm to the checking task of everyday conversation. The reward unit can also apply a specific reward algorithm to the checking task of technical terminology. This makes it possible to apply a reward algorithm depending on the category of the checking task. Some or all of the above-mentioned processing in the reward unit may be performed using AI, for example, or may be performed without using AI. For example, the reward unit can input checking task category data into the generation AI and cause the generation AI to apply the reward algorithm. === Hard Collateral 1-1 === Each of the multiple elements, including the generation unit, check unit, learning unit, and reward unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the generation unit is realized by the control unit 46A of the smart device 14 and generates English sentences and words based on the learner's input. The check unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and checks the accuracy of the grammar and expression of the generated English sentences and words and makes any necessary corrections. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and learns from the checking results to improve the accuracy of the generation AI. The reward unit is realized, for example, by the control unit 46A of the smart device 14 and sets and provides monetary rewards for the checking work. === Hard Collateral 1-2 === Each of the multiple elements, including the generation unit, check unit, learning unit, and reward unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the generation unit is realized by the control unit 46A of the smart glasses 214 and generates English sentences and words based on the learner's input. The check unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and checks the accuracy of the grammar and expression of the generated English sentences and words and makes any necessary corrections. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and learns from the checking results to improve the accuracy of the generation AI. The reward unit is realized, for example, by the control unit 46A of the smart glasses 214 and sets and provides monetary rewards for the checking work. === Hard Collateral 1-3 === Each of the multiple elements, including the generation unit, check unit, learning unit, and reward unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the generation unit is realized by the control unit 46A of the headset-type terminal 314 and generates English sentences and words based on the learner's input. The check unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and checks the accuracy of the grammar and expression of the generated English sentences and words and makes any necessary corrections. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and learns from the checking results to improve the accuracy of the generation AI. The reward unit is realized, for example, by the control unit 46A of the headset-type terminal 314 and sets and provides monetary rewards for the checking work. === Hard Collateral 1-4 === Each of the multiple elements, including the generation unit, check unit, learning unit, and reward unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the generation unit is realized by the control unit 46A of the robot 414 and generates English sentences and words based on the learner's input. The check unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and checks the accuracy of the grammar and expression of the generated English sentences and words and makes any necessary corrections. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and learns from the checking results to improve the accuracy of the generation AI. The reward unit is realized, for example, by the control unit 46A of the robot 414 and sets and provides monetary rewards for the checking work.

[0110] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0111] The generation unit generates English sentences and words based on the learner's input. For example, if a learner inputs, "I want to write an English sentence about travel," the generation AI generates an English sentence related to travel. The generation unit can also generate English sentences to be used in appropriate contexts based on the words input by the learner. For example, if a learner sets "business English" as their learning goal, the generation unit can generate business-related English sentences and words. The check unit checks the English sentences and words generated by the generation unit. For example, a native speaker may check the accuracy of the grammar and expression of the generated English sentences and words and make any necessary corrections. The check unit can also check the grammar, spelling, and meaning of the English sentences and words generated by the generation AI. For example, if the generation AI generates, "I am go to the park," the check unit corrects it to, "I am going to the park." The learning unit learns the check results obtained by the check unit. For example, the learning unit learns English sentences and words corrected by native speakers to improve the accuracy of future generation. In addition, the learning unit allows the generation AI to learn based on the check results, reducing the time it spends on annotation. For example, the learning unit allows the generation AI to learn English sentences and words corrected by native speakers, improving the generation accuracy from the next time onwards. As a result, the English learning system according to the embodiment can contribute to the improvement of learners' English skills and improve the learning accuracy of the generation AI.

[0112] The reward unit provides monetary rewards for checking work. For example, the reward unit allows native speakers to receive rewards for performing the checking work. The reward unit can also set the amount of reward and payment method to increase motivation for the checking work. For example, the reward unit can adjust the amount of reward depending on the difficulty of the checking work. This increases motivation for the checking work and improves the quality of the learning content. Some or all of the above-described processing in the reward unit may be performed using, or without, AI. For example, the reward unit can input the difficulty of the checking work into AI and have the AI ​​calculate the amount of reward.

[0113] The generation unit can estimate the learner's emotions and adjust the tone of the generated English sentences and words based on the estimated learner's emotions. For example, if the learner is relaxed, the generation AI can generate English sentences and words with a casual tone. If the learner is nervous, the generation AI can generate English sentences and words with a formal and calm tone. If the learner is excited, the generation AI can generate English sentences and words with an energetic and positive tone. This allows the generation of English sentences and words with a tone that matches the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the learner's emotional data into the generation AI and cause the generation AI to adjust the tone of the English sentences and words to be generated.

[0114] The generation unit can analyze the learner's past learning history and select an appropriate generation method. For example, the generation unit generates English sentences that focus on grammar items that the learner previously struggled with. The generation unit can also generate words related to topics that the learner has previously shown interest in. The generation unit can also preferentially use generation methods that the learner has previously rated highly. This allows the optimal generation method to be selected based on the learner's past learning history. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's past learning data into the generation AI and have the generation AI select the optimal generation method.

[0115] During generation, the generation unit can perform filtering based on the learner's current learning goals and areas of interest. For example, if a learner has set "business English" as their learning goal, the generation unit can generate business-related English sentences and words. Furthermore, if a learner is interested in "travel English," the generation unit can also generate travel-related English sentences and words. Furthermore, if a learner's goal is "everyday conversation," the generation unit can also generate English sentences and words suitable for everyday conversation. This allows the generation of English sentences and words according to the learner's learning goals and areas of interest. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's learning goals and areas of interest into the generation AI and have the generation AI perform the filtering.

[0116] The generation unit can select an appropriate generation means according to the learner's input method during generation. For example, if the learner uses voice input, the generation AI can generate English sentences and words using voice recognition technology. Furthermore, if the learner uses text input, the generation unit can also generate English sentences and words using text analysis technology. Furthermore, if the learner uses image input, the generation AI can also generate related English sentences and words using image recognition technology. This allows the optimal generation means to be selected according to the learner's input method. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's input data into the generation AI and have the generation AI select the optimal generation means.

[0117] The generation unit can estimate the learner's emotions and adjust the difficulty of the English sentences and words to be generated based on the estimated learner's emotions. For example, if the learner is relaxed, the generation AI can generate high-difficulty English sentences and words. Furthermore, if the learner is nervous, the generation AI can generate low-difficulty English sentences and words. Furthermore, if the learner is excited, the generation AI can generate medium-difficulty English sentences and words. This allows for the generation of English sentences and words of a level of difficulty that corresponds to the learner's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the learner's emotional data into the generation AI and cause the generation AI to adjust the difficulty of the English sentences and words to be generated.

[0118] During generation, the generation unit can prioritize generating highly relevant English sentences and words by taking into account the learner's geographical location information. For example, if the learner is in Japan, the generation unit can generate English sentences and words related to Japan. Furthermore, if the learner is in the United States, the generation unit can also generate English sentences and words related to the United States. Furthermore, if the learner is traveling, the generation unit can also generate English sentences and words related to the travel destination. In this way, highly relevant English sentences and words can be generated based on the learner's geographical location information. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's geographical location information into the generation AI and cause the generation AI to generate highly relevant English sentences and words.

[0119] During generation, the generation unit can analyze the learner's social media activities and generate related English sentences and words. For example, the generation unit generates English sentences based on words frequently used by the learner on social media. The generation unit can also generate English sentences and words related to topics in which the learner is interested on social media. The generation unit can also analyze the content of the learner's social media posts and generate related English sentences and words. In this way, related English sentences and words can be generated based on the learner's social media activities. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the learner's social media data into the generation AI and cause the generation AI to generate related English sentences and words.

[0120] The generation unit can customize the generation method by reflecting the learner's past feedback during generation. For example, the generation unit preferentially uses generation methods that the learner has previously rated highly. The generation unit can also avoid generation methods that the learner has previously rated poorly. The generation unit can also have the generation AI improve the generation method based on the learner's feedback. This allows the generation method to be customized based on the learner's past feedback. Some or all of the above-mentioned processing in the generation unit may be performed using AI, for example, or may be performed without using AI. For example, the generation unit can input the learner's feedback data into the generation AI and have the generation AI customize the generation method.

[0121] The checking unit can estimate the learner's emotions and adjust the way the check is expressed based on the estimated learner's emotions. For example, if the learner is relaxed, the checking unit can provide detailed feedback. If the learner is nervous, the checking unit can also provide concise and to-the-point feedback. If the learner is excited, the checking unit can also provide feedback that makes use of positive expressions. This allows the check to be performed in an expression that corresponds to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the checking unit can be performed using, for example, an AI, or without an AI. For example, the checking unit can input the learner's emotion data into the generation AI and have the generation AI adjust the way the check is expressed.

[0122] The checking unit can adjust the level of detail of the check based on the importance of English sentences and words during the check. For example, the checking unit performs a detailed check on important grammar items. The checking unit can also perform a simplified check on less important words and expressions. The checking unit can also perform a focused check on items related to the learner's learning goals. This allows checking to be performed with a level of detail according to the importance of English sentences and words. Some or all of the above-mentioned processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit can input importance data of English sentences and words into the generating AI and cause the generating AI to adjust the level of detail of the check.

[0123] The checking unit can apply different checking algorithms depending on the category of English sentences and words when checking. For example, the checking unit performs a check that emphasizes formal expressions for business English. The checking unit can also perform a check that emphasizes natural expressions for everyday conversation. The checking unit can also perform a check that emphasizes accuracy for technical terms. This allows the application of checking algorithms depending on the category of English sentences and words. Some or all of the above-mentioned processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit can input category data of English sentences and words into the generation AI and cause the generation AI to apply the checking algorithm.

[0124] The checking unit can improve the accuracy of the check by referring to the learner's past check results when checking. For example, the checking unit may focus on checking items that the learner has previously answered incorrectly. The checking unit may also perform a simplified check for items that the learner has previously answered correctly. The checking unit may also optimize the checking algorithm based on the learner's past check results. This allows the accuracy of the check to be improved based on the learner's past check results. Some or all of the above-mentioned processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit may input the learner's past check data into the generation AI and cause the generation AI to improve the accuracy of the check.

[0125] The checking unit can estimate the learner's emotions and adjust the length of the check based on the estimated learner's emotions. For example, if the learner is relaxed, the checking unit can provide a detailed check. If the learner is nervous, the checking unit can also provide a brief check. If the learner is excited, the checking unit can also provide a check that includes a lot of positive feedback. This allows the check to be performed at a length that corresponds to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the checking unit can be performed using, for example, AI, or without AI. For example, the checking unit can input the learner's emotion data into the generation AI and have the generation AI adjust the length of the check.

[0126] When checking, the checking unit can determine the priority of checking based on the time of submission of the English sentences and words. For example, the checking unit prioritizes checking of recently submitted English sentences and words. The checking unit can also postpone checking of older submitted sentences and words. The checking unit can also dynamically adjust the priority of checking based on the time of submission. This allows checking to be performed in priority according to the time of submission of the English sentences and words. Some or all of the above-mentioned processing in the checking unit may be performed using AI, for example, or may be performed without using AI. For example, the checking unit can input submission time data into the generation AI and have the generation AI determine the priority of checking.

[0127] The checking unit can adjust the order of checking based on the relevance of English sentences and words when checking. For example, the checking unit prioritizes checking highly relevant English sentences and words. The checking unit can also postpone checking less relevant ones. The checking unit can also dynamically adjust the order of checking based on the relevance. This allows checking to be performed in an order based on the relevance of English sentences and words. Some or all of the above-mentioned processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit can input relevance data of English sentences and words into the generating AI and have the generating AI adjust the order of checking.

[0128] During the check, the checking unit can adjust the use of technical terminology in the check according to the learner's level of expertise. For example, if the learner is a beginner, the checking unit can avoid technical terminology and use simple expressions. Furthermore, if the learner is an intermediate learner, the checking unit can also use technical terminology moderately. Furthermore, if the learner is an advanced learner, the checking unit can provide detailed feedback using a lot of technical terminology. This allows the check to be performed with the use of technical terminology according to the learner's level of expertise. Some or all of the above-described processing in the checking unit may be performed using, for example, AI, or may be performed without using AI. For example, the checking unit can input the learner's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terminology.

[0129] The learning unit can estimate the learner's emotions and select learning data based on the estimated learner's emotions. For example, if the learner is relaxed, the learning unit selects learning data with a high level of difficulty. Furthermore, if the learner is nervous, the learning unit can select learning data with a low level of difficulty. Furthermore, if the learner is excited, the learning unit can select learning data with content that will interest the learner. This allows for the selection of learning data according to the learner's emotions. The emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the learner's emotional data into the generation AI and have the generation AI select the learning data.

[0130] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on data previously learned by the learner. The learning unit can also analyze the learner's past learning data and improve the learning algorithm. The learning unit can also adjust the parameters of the learning algorithm by referring to the learner's past learning data. This allows the learning algorithm to be optimized based on the past learning data. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input past learning data into a generation AI and cause the generation AI to optimize the learning algorithm.

[0131] The learning unit can update the learning data during learning by reflecting the learner's feedback. The learning unit updates the learning data, for example, based on feedback provided by the learner. The learning unit can also improve the content of the learning data by reflecting the learner's feedback. The learning unit can also review the criteria for selecting learning data based on the learner's feedback. This allows the learning data to be updated based on the learner's feedback. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the learner's feedback data into a generation AI and have the generation AI update the learning data.

[0132] The learning unit can estimate the learner's emotions and adjust the frequency of learning based on the estimated learner's emotions. For example, the learning unit can increase the frequency of learning when the learner is relaxed. The learning unit can also decrease the frequency of learning when the learner is nervous. The learning unit can also moderately adjust the frequency of learning when the learner is excited. This allows the learner to study at a frequency that corresponds to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the learning unit can be performed using, for example, an AI, or without an AI. For example, the learning unit can input the learner's emotional data into the generation AI and have the generation AI adjust the frequency of learning.

[0133] During learning, the learning unit can weight the learning data based on the time of submission of the English sentences and words. For example, the learning unit can weight recently submitted English sentences and words highly. The learning unit can also weight older submitted sentences and words less. The learning unit can also dynamically adjust the weighting of the learning data according to the time of submission. This allows the learning data to be handled with weighting according to the time of submission. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input submission time data into the generation AI and have the generation AI perform weighting of the learning data.

[0134] During learning, the learning unit can integrate information from different data sources to enrich the learning data. For example, the learning unit may acquire data from other learning apps used by the learner and integrate it into the learning data. The learning unit may also acquire information from online dictionaries and grammar guides and integrate it into the learning data. The learning unit may also acquire related information from the learner's social media activities and integrate it into the learning data. In this way, the learning data can be enriched by integrating information from different data sources. Some or all of the above-described processing in the learning unit may be performed using, or without, AI, for example. For example, the learning unit may input information from different data sources into a generation AI and have the generation AI integrate the information.

[0135] The reward unit can estimate the learner's emotions and adjust the type and amount of reward based on the estimated learner's emotions. For example, the reward unit can increase the amount of reward when the learner is relaxed. The reward unit can also diversify the types of reward when the learner is nervous. The reward unit can also balance the amount and type of reward when the learner is excited. This allows the type and amount of reward to be adjusted according to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the reward unit can be performed using, for example, an AI, or without an AI. For example, the reward unit can input the learner's emotion data into the generation AI and have the generation AI adjust the type and amount of reward.

[0136] The reward unit can adjust the details of the reward based on the difficulty of the check task when providing the reward. For example, the reward unit can provide a high reward for a high-difficulty check task. The reward unit can also provide a low reward for a low-difficulty check task. The reward unit can also dynamically adjust the details of the reward according to the difficulty of the check task. This makes it possible to adjust the details of the reward according to the difficulty of the check task. Some or all of the above-mentioned processing in the reward unit may be performed using AI, for example, or may be performed without using AI. For example, the reward unit can input difficulty data of the check task to the generation AI and cause the generation AI to adjust the details of the reward.

[0137] When providing a reward, the reward unit can apply different reward algorithms depending on the category of the checking task. For example, the reward unit applies a specific reward algorithm to the checking task of business English. The reward unit can also apply a different reward algorithm to the checking task of everyday conversation. The reward unit can also apply a specific reward algorithm to the checking task of technical terminology. This makes it possible to apply a reward algorithm depending on the category of the checking task. Some or all of the above-mentioned processing in the reward unit may be performed using AI, for example, or may be performed without using AI. For example, the reward unit can input checking task category data into the generation AI and cause the generation AI to apply the reward algorithm.

[0138] When providing rewards, the reward unit can determine the priority of rewards based on the time of submission of the check work. For example, the reward unit can provide a higher reward for a recently submitted check work. The reward unit can also provide a lower reward for an older submitted check work. The reward unit can also dynamically adjust the priority of rewards depending on the time of submission. This allows rewards to be provided in a priority order depending on the time of submission. Some or all of the above-mentioned processing in the reward unit may be performed using AI, for example, or may be performed without using AI. For example, the reward unit can input submission time data into the generation AI and have the generation AI determine the priority of rewards.

[0139] The reward unit can estimate the learner's emotions and adjust the timing of reward provision based on the estimated learner's emotions. For example, if the learner is relaxed, the reward unit can provide the reward immediately. If the learner is nervous, the reward unit can also provide the reward gradually. If the learner is excited, the reward unit can also provide the reward randomly. This allows rewards to be provided at timings that correspond to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the reward unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the reward unit can input the learner's emotion data into the generation AI and cause the generation AI to adjust the timing of reward provision.

[0140] The processing flow of the second embodiment will be briefly explained below.

[0141] Step 1: The generation unit generates English sentences and words based on the learner's input. For example, if a learner inputs, "I want to write English sentences about travel," the generation AI will generate English sentences related to travel. It can also generate English sentences to be used in appropriate contexts based on the words input by the learner. Furthermore, if a learner sets "business English" as their learning goal, it can generate business-related English sentences and words. Step 2: The checking unit checks the English sentences and words generated by the generation unit. For example, a native speaker checks the accuracy of the grammar and expressions of the generated English sentences and words, and makes any necessary corrections. The checking unit can also check the grammar, spelling, and meaning of the English sentences and words generated by the generation AI. For example, if the generation AI generates "I am go to the park," it will correct it to "I am going to the park." Step 3: The learning unit learns from the checking results obtained by the checking unit. For example, it learns from English sentences and words corrected by native speakers, improving the accuracy of future generation. In addition, the generation AI learns based on the checking results, reducing the time spent on annotation. This improves the learning accuracy of the generation AI and contributes to improving learners' English skills.

[0142] 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.

[0143] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> 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.

[0144] 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.

[0145] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0146] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0147] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0162] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0163] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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).

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 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 identification processing unit 290 using these models.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0178] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0179] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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).

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also 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 perform the same process as the identification processing unit 290 using these models.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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).

[0199] 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.

[0200] 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."

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] [Explanation of symbols]

[0214] 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 generation unit that generates English sentences or words based on learner input; a checking unit that checks the English sentences or words generated by the generating unit; a learning unit that learns the check results obtained by the checking unit; Equipped with A system characterized by:

2. Equipping the Reward Department with monetary rewards for checking work 2. The system of claim 1.

3. The generation unit Estimate the learner's emotions and adjust the tone of the generated English sentences and words based on the estimated learner's emotions.

2. The system of claim 1.

4. The generation unit Analyze the learner's past learning history and select the appropriate generation method 2. The system of claim 1.

5. The generation unit At generation time, filtering based on the learner's current learning goals and interests 2. The system of claim 1.

6. The generation unit Select an appropriate generation method depending on the learner's input method during generation.

2. The system of claim 1.

7. The generation unit Estimate the learner's emotions and adjust the difficulty of the generated English sentences and words based on the estimated learner's emotions.

2. The system of claim 1.

8. The generation unit When generating sentences, the system takes into account the learner's geographic location information and prioritizes generating highly relevant English sentences and words.

2. The system of claim 1.

9. The generation unit During generation, the system analyzes the learner's social media activity and generates related English sentences and words.

2. The system of claim 1.

Images