System

Abstract

To provide a system for supporting personalized foreign language learning on the basis of a user's learning history.SOLUTION: A system includes a collection section, an evaluation section, a generation section, and a learning support section. The collection section collects a user's learning history. The evaluation section analyzes data collected by the collection section and evaluates the pronunciation and conversation ability of the user. The generation section generates a conversation scenario corresponding to a specific weak point of the user on the basis of an evaluation result by the evaluation section. The learning support section conducts a dialogue with the user in the conversation scenario generated by the generation section.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques do not adequately provide personalized support that addresses the weaknesses of individual learners in foreign language learning, and there is room for improvement.

[0005] The system according to the embodiment aims to provide personalized foreign language learning support based on the user's learning history. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an evaluation unit, a generation unit, and a learning support unit. The collection unit collects a user's learning history. The evaluation unit analyzes the data collected by the collection unit and evaluates the user's pronunciation and conversation ability. The generation unit generates a conversation scenario that addresses a specific weakness of the user based on the evaluation result by the evaluation unit. The learning support unit engages in a dialogue with the user using the conversation scenario generated by the generation unit. Effect of the Invention

[0007] The system according to the embodiment can provide personalized foreign language learning support based on the user's learning history. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The foreign language learning support system according to the embodiment of the present invention is a system that supports foreign language learning using a generation AI. This system allows for powerful personalization not available in conventional teaching materials. Specifically, the system collects the user's learning history, analyzes the data, and evaluates the user's pronunciation and conversation ability. Based on the evaluation results, a conversation scenario according to the user's weaknesses is generated, and a dialogue is conducted with the user using the scenario. This allows the user to efficiently learn a foreign language while overcoming their weaknesses. For example, the user's learning history is collected. For example, data such as what words and phrases the user has learned in the past and what pronunciation practice they have performed is collected. This data is collected by a collection unit that may include AI processing. Next, the collected data is analyzed to evaluate the user's pronunciation and conversation ability. For example, the user's pronunciation is evaluated to an extent to which the user's pronunciation is accurate, the user's conversation fluency, etc. are evaluated. This evaluation is performed by an evaluation unit that may include AI processing or generation AI processing. Based on the evaluation results, a conversation scenario according to the user's weaknesses is generated. For example, if the user is not good at a particular pronunciation, a conversation scenario including that pronunciation is generated. This scenario is generated by a generation unit that includes generation AI processing. A dialogue is conducted with the user based on the generated conversation scenario. For example, the user actually has a conversation based on the generated scenario, and practices pronunciation and conversation in the conversation. This dialogue is conducted by a learning support unit including the processing of the generation AI. Furthermore, it is also possible to generate exercises based on the evaluation results and provide them to the user. For example, if the user is not good at a particular grammar, an exercise including that grammar is generated and provided to the user. This exercise is generated by a generation unit including the processing of the generation AI, and is provided by a learning support unit including the processing of the generation AI. It is also possible to generate a conversation scenario based on the user's future occupation and lifestyle. For example, if the user aims to be a doctor in the future, a conversation scenario in the medical field is generated. This scenario is generated by a generation unit including the processing of the generation AI. Furthermore, it is also possible to provide pronunciation practice that is individually optimized based on the characteristics of the user's voice. For example, pronunciation practice that matches the pitch and tone of the user's voice is provided.This pronunciation practice is provided by a learning support unit including the processing of a generation AI. Finally, it is also possible to generate a conversation scenario based on the behavior of the user's pet. For example, a conversation scenario is generated for the user to proceed with learning together with the pet. This scenario is generated by a generation unit including the processing of a generation AI. In this way, the foreign language learning support system can efficiently learn a foreign language by collecting and evaluating the user's learning history and conducting a dialogue using the generated conversation scenario.

[0029] The foreign language learning support system according to the embodiment includes a collection unit, an evaluation unit, a generation unit, and a learning support unit. The collection unit collects the user's learning history. The user's learning history includes, for example, learning time, learning content, learning results, etc., but is not limited to such examples. The collection unit collects, for example, words and phrases that the user has previously learned, pronunciation practice data, etc. The collection unit may include AI processing. For example, the collection unit can analyze the user's learning history using AI and extract important data. The evaluation unit analyzes the data collected by the collection unit and evaluates the user's pronunciation and conversation ability. The evaluation is performed, for example, based on the accuracy of pronunciation, fluency, naturalness of conversation, etc., but is not limited to such examples. The evaluation unit may include AI processing or generation AI processing. For example, the evaluation unit can input the user's pronunciation data to the generation AI and evaluate the accuracy of pronunciation. The generation unit generates a conversation scenario according to the user's weaknesses based on the evaluation result by the evaluation unit. The generated conversation scenario includes, for example, daily conversation, business conversation, specific situations, etc., but is not limited to such examples. The generation unit includes processing of the generation AI. For example, the generation unit can input the user's evaluation result to the generation AI and generate a conversation scenario corresponding to the user's weak points. The learning support unit dialogues with the user using the conversation scenario generated by the generation unit. The learning support unit includes processing of the generation AI. For example, the learning support unit can input the generated conversation scenario to the generation AI and dialogue with the user. As a result, the foreign language learning support system according to the embodiment can efficiently learn a foreign language by collecting and evaluating the user's learning history and dialogue with the generated conversation scenario. For example, the collection unit can analyze the user's learning history using AI and extract important data. The evaluation unit can input the user's pronunciation data to the generation AI and evaluate the accuracy of the pronunciation. The generation unit can input the user's evaluation result to the generation AI and generate a conversation scenario corresponding to the user's weak points. The learning support unit can input the generated conversation scenario to the generation AI and dialogue with the user.This allows the foreign language learning support system to collect and evaluate the user's learning history, and engage in dialogue using the generated conversation scenario, thereby enabling efficient foreign language learning.

[0030] The collection unit collects the user's learning history. The user's learning history includes, for example, learning time, learning content, learning results, etc., but is not limited to such examples. The collection unit collects, for example, words and phrases that the user has learned in the past, pronunciation practice data, etc. Specifically, data that records the learning progress and achievement level is collected from the learning application or online platform used by the user. This includes detailed information such as how often the user learned which words and phrases, what errors were common during pronunciation practice, or what grammatical mistakes are frequent. The collection unit may include AI processing. For example, the collection unit can analyze the user's learning history using AI and extract important data. The AI ​​can analyze the user's learning pattern and evaluate the acquisition status of specific words and phrases. In addition, the pronunciation practice data can be analyzed to identify sounds and accents that the user is particularly weak at. This allows the collection unit to grasp the user's learning history in detail and provide data according to individual learning needs. Furthermore, the collection unit stores the user's learning history on a cloud server so that other system components can access it. This allows the collected data to serve as a foundation for use by the evaluation and generation components, strengthening collaboration throughout the system.

[0031] The evaluation unit analyzes the data collected by the collection unit and evaluates the user's pronunciation and conversation ability. The evaluation is performed based on, for example, the accuracy of pronunciation, fluency, naturalness of conversation, etc., but is not limited to such examples. Specifically, the evaluation unit analyzes the user's pronunciation data and evaluates the accuracy of pronunciation using voice recognition technology. For example, the words and phrases pronounced by the user are compared with standard pronunciation and the degree of match is scored. The evaluation of fluency also includes the user's speaking speed, rhythm, intonation, etc. Regarding the naturalness of the conversation, how naturally the user can continue the conversation and whether they can respond at the appropriate time are evaluated. The evaluation unit may include AI processing or generation AI processing. For example, the evaluation unit can input the user's pronunciation data into the generation AI and evaluate the accuracy of the pronunciation. The generation AI analyzes the user's pronunciation, identifies differences from standard pronunciation, and presents specific improvements. In addition, for the evaluation of conversation ability, the generation AI can have a mock conversation with the user and evaluate the appropriateness and naturalness of the user's response in the mock conversation. This allows the assessor to evaluate the user's pronunciation and speaking ability in detail and provide feedback tailored to individual learning needs. Furthermore, the assessor can track the user's progress based on past assessment data and evaluate the long-term learning effect.

[0032] The generation unit generates a conversation scenario according to the user's weaknesses based on the evaluation results by the evaluation unit. The conversation scenarios to be generated include, for example, daily conversations, business conversations, and specific situations, but are not limited to such examples. Specifically, the generation unit analyzes the user's evaluation results and generates a conversation scenario focusing on areas and situations in which the user is particularly weak. For example, if the user is not good at a specific phrase or expression in business conversation, a scenario including the phrase or expression is generated. The generation unit includes processing of the generation AI. For example, the generation unit can input the user's evaluation results to the generation AI and generate a conversation scenario corresponding to the user's weaknesses. The generation AI automatically generates an appropriate scenario based on the user's evaluation data, enabling the user to study efficiently. The generated scenario is customized according to the user's learning level and goals, and corresponds to individual learning needs. In addition, the generation unit stores the generated scenario in a cloud server and allows the learning support unit to access it. As a result, the generation unit can provide an effective learning scenario based on the user's evaluation results, maximizing the user's learning effect. Furthermore, the generator can continually improve the scenario based on user feedback to provide a more effective learning experience.

[0033] The learning support unit interacts with the user using the conversation scenario generated by the generation unit. The learning support unit includes processing of the generation AI. Specifically, the learning support unit can input the generated conversation scenario to the generation AI and interact with the user. The generation AI provides appropriate feedback to the user's response, allowing the user to practice natural conversation. For example, if the user makes an error in pronunciation or expression, the generation AI suggests corrections on the spot and shows the correct pronunciation or expression. The learning support unit can also monitor the user's progress in real time and adjust the scenario as necessary. This allows the user to always continue practicing in an optimal learning environment. Furthermore, the learning support unit can also propose individual learning plans based on the user's learning history. For example, if the user is lagging behind in a particular area, the learning support unit can propose a learning plan that focuses on that area to support efficient learning. The learning support unit can also collect user feedback and use it to improve the entire system. This allows the learning support unit to provide effective learning support to the user and significantly improve the efficiency of foreign language learning. Furthermore, the learning support unit also has a function of providing rewards and a sense of accomplishment according to the user's learning progress in order to maintain the user's motivation. This allows users to continue learning in an enjoyable way and achieve long-term learning results.

[0034] The generation unit generates exercises based on the evaluation result by the evaluation unit, and the learning support unit can provide the exercises to the user. The generation unit generates exercises such as listening questions, speaking questions, and grammar questions based on the evaluation result of the user. The generation unit includes processing of the generation AI. For example, the generation unit can input the evaluation result of the user to the generation AI and generate exercises corresponding to the weak points of the user. The learning support unit provides the generated exercises to the user. The learning support unit includes processing of the generation AI. For example, the learning support unit can input the generated exercises to the generation AI and provide them to the user. As a result, the weak points of the user can be effectively overcome by generating exercises based on the evaluation result and providing them to the user. For example, the generation unit can input the evaluation result of the user to the generation AI and generate exercises corresponding to the weak points of the user. The learning support unit can input the generated exercises to the generation AI and provide them to the user. As a result, the foreign language learning support system can effectively overcome the weak points of the user by generating exercises based on the evaluation result of the user and providing them to the user.

[0035] The generation unit can generate a conversation scenario based on the user's future occupation or lifestyle. For example, if the user aims to be a doctor in the future, the generation unit generates a conversation scenario in a medical field. The generation unit includes a generation AI process. For example, the generation unit can generate a related conversation scenario based on the user's future occupation or lifestyle. This enables practical learning by generating a conversation scenario based on the user's future occupation or lifestyle. For example, the generation unit can generate a related conversation scenario based on the user's future occupation or lifestyle. This enables practical learning by the foreign language learning support system generating a conversation scenario based on the user's future occupation or lifestyle.

[0036] The learning support unit can provide the user with individually adjusted pronunciation practice based on the characteristics of the user's voice. The learning support unit provides, for example, pronunciation practice that matches the pitch and tone of the user's voice. The learning support unit includes processing of the generation AI. For example, the learning support unit can input the characteristics of the user's voice into the generation AI and provide individually adjusted pronunciation practice. This allows for more effective pronunciation practice by providing pronunciation practice based on the characteristics of the user's voice. For example, the learning support unit can input the characteristics of the user's voice into the generation AI and provide individually adjusted pronunciation practice. This allows the foreign language learning support system to provide more effective pronunciation practice by providing pronunciation practice based on the characteristics of the user's voice.

[0037] The generation unit can generate a conversation scenario that corresponds to a specific weakness of the user based on the behavior of the user's pet and is used to advance learning together with the pet. The generation unit generates, for example, a conversation scenario for the user to advance learning together with the pet. The generation unit includes a generation AI process. For example, the generation unit can generate a related conversation scenario based on the behavior of the user's pet. This allows the user to advance learning in a fun way by generating a conversation scenario based on the behavior of the user's pet. For example, the generation unit can generate a related conversation scenario based on the behavior of the user's pet. This allows the foreign language learning support system to advance learning in a fun way by generating a conversation scenario based on the behavior of the user's pet.

[0038] The collection unit can analyze the user's past learning history and select an appropriate collection method. For example, the collection unit prioritizes and collects learning methods that the user frequently used in the past. The collection unit may include AI processing. For example, the collection unit can analyze the user's past learning history using AI and select an optimal collection method. In addition, the collection unit can identify an effective learning method from the user's past learning history and collect the method with priority. For example, the collection unit can analyze the user's past learning history using AI and identify an effective learning method. Furthermore, the collection unit can analyze the user's past learning history and select the most efficient collection timing. For example, the collection unit can analyze the user's past learning history using AI and select the optimal collection timing. As a result, the optimal collection method can be selected by analyzing the user's past learning history. For example, the collection unit can analyze the user's past learning history using AI and select the optimal collection method. As a result, the foreign language learning support system can select the optimal collection method by analyzing the user's past learning history.

[0039] The collection unit can filter the learning history based on the user's current learning progress and field of interest when collecting the learning history. For example, the collection unit preferentially collects data related to a topic that the user is currently learning. The collection unit may include AI processing. For example, the collection unit can filter and collect related data based on the user's current learning progress and field of interest. In addition, the collection unit can filter and collect related learning history based on the user's field of interest. For example, the collection unit can identify the user's field of interest using AI and collect related data. Furthermore, the collection unit can collect only necessary data according to the user's learning progress. For example, the collection unit can evaluate the user's learning progress using AI and collect necessary data. As a result, more relevant data can be collected by filtering data based on the user's current learning progress and field of interest. For example, the collection unit can filter and collect related data based on the user's current learning progress and field of interest. As a result, the foreign language learning support system can collect more relevant data by filtering data based on the user's current learning progress and field of interest.

[0040] When collecting the learning history, the collection unit can preferentially collect a history with high relevance in consideration of the geographical location information of the user. For example, when the user is in a specific area, the collection unit preferentially collects a learning history related to the area. The collection unit may include AI processing. For example, the collection unit can analyze the geographical location information of the user using AI to collect highly relevant data. In addition, the collection unit can collect data on related cultures and languages ​​based on the geographical location information of the user. For example, the collection unit can analyze the geographical location information of the user using AI to collect related data. Furthermore, when the user is traveling, the collection unit can preferentially collect a learning history related to the travel destination. For example, the collection unit can analyze the geographical location information of the user using AI to collect related data. As a result, more effective learning is possible by collecting highly relevant data based on the geographical location information of the user. For example, the collection unit can analyze the geographical location information of the user using AI to collect highly relevant data. As a result, the foreign language learning support system can collect highly relevant data based on the geographical location information of the user, thereby enabling more effective learning.

[0041] The collection unit can analyze the user's social media activities and collect related histories when collecting the learning history. The collection unit, for example, collects learning contents shared by the user on social media. The collection unit may include AI processing. For example, the collection unit can analyze the user's social media activities using AI and collect related data. In addition, the collection unit can identify topics of interest from the user's social media activities and collect related data. For example, the collection unit can analyze the user's social media activities using AI and identify topics of interest. In addition, the collection unit can analyze the posted content of an account followed by the user and collect related learning history. For example, the collection unit can analyze the user's social media activities using AI and collect related data. As a result, more effective learning is possible by collecting related data based on the user's social media activities. For example, the collection unit can analyze the user's social media activities using AI and collect related data. As a result, the foreign language learning support system can collect related data based on the user's social media activities and collect related data.

[0042] The evaluation unit can improve the accuracy of the evaluation by referring to the user's past learning data at the time of evaluation. The evaluation unit, for example, refers to the user's past pronunciation data and performs a current pronunciation evaluation. The evaluation unit may include AI processing or generation AI processing. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the user's past learning data using AI or generation AI. In addition, the evaluation unit can evaluate the conversation ability by referring to the user's past conversation data. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the user's past conversation data using AI or generation AI. Furthermore, the evaluation unit can perform a comprehensive evaluation by referring to the user's past learning history. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the user's past learning history using AI or generation AI. As a result, the accuracy of the evaluation is improved by referring to the user's past learning data. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the user's past learning data using AI or generation AI. As a result, the foreign language learning support system improves the accuracy of the evaluation by referring to the user's past learning data.

[0043] The evaluation unit can apply different evaluation algorithms depending on the learning style of the user at the time of evaluation. For example, when the user is a visual learner, the evaluation unit applies a visual evaluation algorithm. The evaluation unit may include AI processing or generation AI processing. For example, the evaluation unit can apply different evaluation algorithms using AI or generation AI depending on the learning style of the user. Also, when the user is an auditory learner, the evaluation unit can apply an auditory evaluation algorithm. For example, the evaluation unit can apply different evaluation algorithms using AI or generation AI depending on the learning style of the user. Furthermore, when the user is an experiential learner, the evaluation unit can apply an experiential evaluation algorithm. For example, the evaluation unit can apply different evaluation algorithms using AI or generation AI depending on the learning style of the user. As a result, more appropriate evaluation is possible by applying an evaluation algorithm according to the learning style of the user. For example, the evaluation unit can apply different evaluation algorithms using AI or generation AI depending on the learning style of the user. As a result, the foreign language learning support system can apply a more appropriate evaluation by applying an evaluation algorithm according to the learning style of the user.

[0044] At the time of evaluation, the evaluation unit can determine the priority of evaluation based on the time of submission of the user's learning history. For example, the evaluation unit prioritizes evaluation of the learning history recently submitted by the user. The evaluation unit may include processing of AI or processing of generation AI. For example, the evaluation unit can determine the priority of evaluation using AI or generation AI based on the time of submission of the user's learning history. In addition, the evaluation unit can prioritize evaluation of the learning history submitted by the user within a specific period. For example, the evaluation unit can determine the priority of evaluation using AI or generation AI based on the time of submission of the user's learning history. Furthermore, the evaluation unit can prioritize evaluation of the learning history that the user has not submitted for a long period of time. For example, the evaluation unit can determine the priority of evaluation using AI or generation AI based on the time of submission of the user's learning history. As a result, more effective evaluation is possible by determining the priority of evaluation based on the time of submission of the user's learning history. For example, the evaluation unit can determine the priority of evaluation using AI or generation AI based on the time of submission of the user's learning history. This enables the foreign language learning support system to determine the priority of evaluation based on the time of submission of the user's learning history, thereby enabling more effective evaluation.

[0045] The evaluation unit can improve the accuracy of the evaluation by referring to the user's related literature at the time of evaluation. The evaluation unit adjusts the evaluation criteria based on the literature referred to by the user, for example. The evaluation unit may include AI processing or generation AI processing. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the literature related to the user's learning content. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the literature related to the user's learning content. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the literature related to the user's learning content. Furthermore, the evaluation unit can improve the accuracy of the evaluation based on the literature referred to by the user in the past. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the user's related literature using AI or generation AI. As a result, the accuracy of the evaluation is improved by referring to the user's related literature. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the user's related literature using AI or generation AI. As a result, the foreign language learning support system improves the accuracy of the evaluation by referring to the user's related literature.

[0046] The generation unit can generate an appropriate scenario by referring to the user's past learning data when generating a conversation scenario. The generation unit generates a conversation scenario including, for example, words and phrases that the user has learned in the past. The generation unit includes processing of the generation AI. For example, the generation unit can input the user's past learning data to the generation AI and generate an optimal conversation scenario. Furthermore, the generation unit can generate a conversation scenario including a pronunciation that the user is not good at from the user's past learning data. For example, the generation unit can input the user's past learning data to the generation AI and generate an optimal conversation scenario. Furthermore, the generation unit can generate the most effective conversation scenario by referring to the user's past learning history. For example, the generation unit can input the user's past learning data to the generation AI and generate an optimal conversation scenario. As a result, the optimal conversation scenario is generated by referring to the user's past learning data. For example, the generation unit can input the user's past learning data to the generation AI and generate an optimal conversation scenario. As a result, the foreign language learning support system generates an optimal conversation scenario by referring to the user's past learning data.

[0047] The generation unit can apply different scenario generation algorithms according to the user's learning style when generating a conversation scenario. For example, when the user is a visual learner, the generation unit generates a conversation scenario that includes many visual elements. The generation unit includes processing of the generation AI. For example, the generation unit can input different scenario generation algorithms to the generation AI according to the user's learning style and apply them. Furthermore, when the user is an auditory learner, the generation unit can generate a conversation scenario that includes many auditory elements. For example, the generation unit can input different scenario generation algorithms to the generation AI according to the user's learning style and apply them. Furthermore, when the user is an experiential learner, the generation unit can generate a conversation scenario that includes many experiential elements. For example, the generation unit can input different scenario generation algorithms to the generation AI according to the user's learning style and apply them. As a result, a more effective conversation scenario is generated by applying a scenario generation algorithm according to the user's learning style. For example, the generation unit can input different scenario generation algorithms to the generation AI according to the user's learning style and apply them. This allows the foreign language learning support system to generate more effective conversation scenarios by applying a scenario generation algorithm that suits the user's learning style.

[0048] The generation unit can generate an appropriate scenario in consideration of the geographical location information of the user when generating a conversation scenario. For example, when the user is in a specific region, the generation unit generates a conversation scenario related to the culture and language of that region. The generation unit includes processing of the generation AI. For example, the generation unit can input the geographical location information of the user to the generation AI and generate an optimal conversation scenario. In addition, the generation unit can generate a conversation scenario including a related topic based on the geographical location information of the user. For example, the generation unit can input the geographical location information of the user to the generation AI and generate an optimal conversation scenario. Furthermore, when the user is traveling, the generation unit can generate a conversation scenario related to the travel destination. For example, the generation unit can input the geographical location information of the user to the generation AI and generate an optimal conversation scenario. As a result, more effective learning is possible by generating an optimal conversation scenario based on the geographical location information of the user. For example, the generation unit can input the geographical location information of the user to the generation AI and generate an optimal conversation scenario. As a result, the foreign language learning support system can generate an optimal conversation scenario based on the geographical location information of the user, thereby enabling more effective learning.

[0049] The generation unit can generate a related scenario by analyzing the social media activity of the user when generating a conversation scenario. The generation unit generates, for example, a conversation scenario related to a topic shared by the user on social media. The generation unit includes processing of the generation AI. For example, the generation unit can input the social media activity of the user to the generation AI and generate a related conversation scenario. In addition, the generation unit can identify a topic of interest from the social media activity of the user and generate a related scenario. For example, the generation unit can input the social media activity of the user to the generation AI and generate a related conversation scenario. Furthermore, the generation unit can analyze the posted content of an account followed by the user and generate a related conversation scenario. For example, the generation unit can input the social media activity of the user to the generation AI and generate a related conversation scenario. As a result, more effective learning is possible by generating a related conversation scenario based on the social media activity of the user. For example, the generation unit can input the social media activity of the user to the generation AI and generate a related conversation scenario. As a result, the foreign language learning support system can generate a related conversation scenario based on the social media activity of the user, thereby enabling more effective learning.

[0050] The learning support unit can select the optimal support method by referring to the user's past learning data when providing learning support. For example, the learning support unit preferentially provides the user with a learning method that was effective in the past. The learning support unit includes processing of the generation AI. For example, the learning support unit can input the user's past learning data into the generation AI and select the optimal support method. In addition, the learning support unit can identify the optimal support method from the user's past learning data and provide the method. For example, the learning support unit can input the user's past learning data into the generation AI and select the optimal support method. Furthermore, the learning support unit can select the most effective support method by referring to the user's past learning history. For example, the learning support unit can input the user's past learning data into the generation AI and select the optimal support method. As a result, the optimal support method can be selected by referring to the user's past learning data. For example, the learning support unit can input the user's past learning data into the generation AI and select the optimal support method. As a result, the foreign language learning support system can select the optimal support method by referring to the user's past learning data.

[0051] The learning support unit can apply different support algorithms according to the learning style of the user during learning support. For example, when the user is a visual learner, the learning support unit applies a visual support algorithm. The learning support unit includes processing of the generation AI. For example, the learning support unit can input different support algorithms to the generation AI according to the learning style of the user and apply them. In addition, when the user is an auditory learner, the learning support unit can apply an auditory support algorithm. For example, the learning support unit can input different support algorithms to the generation AI according to the learning style of the user and apply them. In addition, when the user is an experiential learner, the learning support unit can apply an experiential support algorithm. For example, the learning support unit can input different support algorithms to the generation AI according to the learning style of the user and apply them. As a result, more effective learning support is possible by applying a support algorithm according to the learning style of the user. For example, the learning support unit can input different support algorithms to the generation AI according to the learning style of the user and apply them. As a result, the foreign language learning support system can provide more effective learning support by applying a support algorithm according to the learning style of the user.

[0052] The learning support unit can select an appropriate support method in consideration of the geographical location information of the user when providing learning support. For example, when the user is in a specific area, the learning support unit provides a learning support method related to the area. The learning support unit includes processing of the generation AI. For example, the learning support unit can input the geographical location information of the user to the generation AI and select an optimal support method. In addition, the learning support unit can provide a support method of a related culture or language based on the geographical location information of the user. For example, the learning support unit can input the geographical location information of the user to the generation AI and select an optimal support method. Furthermore, when the user is traveling, the learning support unit can provide a learning support method related to the travel destination. For example, the learning support unit can input the geographical location information of the user to the generation AI and select an optimal support method. As a result, more effective learning support is possible by selecting the optimal support method based on the geographical location information of the user. For example, the learning support unit can input the geographical location information of the user to the generation AI and select an optimal support method. As a result, the foreign language learning support system can provide more effective learning support by selecting the optimal support method based on the geographical location information of the user.

[0053] The learning support unit can provide a related support method by analyzing the user's social media activity during learning support. The learning support unit provides a support method based on, for example, learning content shared by the user on social media. The learning support unit includes processing of the generation AI. For example, the learning support unit can input the user's social media activity to the generation AI and provide a related support method. In addition, the learning support unit can provide a support method related to a topic of interest from the user's social media activity. For example, the learning support unit can input the user's social media activity to the generation AI and provide a related support method. In addition, the learning support unit can analyze the posted content of an account followed by the user and provide a related learning support method. For example, the learning support unit can input the user's social media activity to the generation AI and provide a related support method. As a result, more effective learning support can be provided by providing a related support method based on the user's social media activity. For example, the learning support unit can input the user's social media activity to the generation AI and provide a related support method. As a result, the foreign language learning support system can provide a more effective learning support by providing a related support method based on the user's social media activity.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] When collecting the user's learning history, the collection unit can collect data taking into consideration the user's learning environment. For example, if the user is learning in a quiet environment, it can prioritize collection of pronunciation practice data. Also, if the user is learning while on the move, it can prioritize collection of listening data. Furthermore, if the user is learning in a group, it can prioritize collection of conversation data. This makes it possible to collect data according to the user's learning environment, thereby realizing more effective learning support.

[0056] The generator can generate exercises optimized for the user's learning style based on the user's learning history. For example, exercises including many images and diagrams can be generated for visual learners. Also, exercises including many audio can be generated for auditory learners. Furthermore, exercises including practical scenarios can be generated for experiential learners. This provides exercises according to the user's learning style, improving the learning effect.

[0057] The generation unit can generate a conversation scenario that attracts the user's interest based on the user's future occupation and lifestyle. For example, if the user hopes to work in the travel industry in the future, a conversation scenario related to travel can be generated. Also, if the user hopes to enjoy cooking as a future hobby, a conversation scenario related to cooking can be generated. Furthermore, if the user hopes to be involved in sports as a future goal, a conversation scenario related to sports can be generated. In this way, a conversation scenario according to the user's interests and goals is provided, improving motivation to learn.

[0058] The learning support unit can provide the user with optimal pronunciation practice based on the characteristics of the user's voice. For example, it can provide pronunciation practice that matches the pitch and tone of the user's voice. It can also provide pronunciation practice that matches the strength and weakness of the user's voice. It can also provide pronunciation practice that matches the rhythm of the user's voice. This provides pronunciation practice that matches the characteristics of the user's voice, improving the accuracy of pronunciation.

[0059] The generation unit can generate a conversation scenario that the user and the pet can enjoy together, based on the behavior of the user's pet. For example, when the user is walking with the pet, a conversation scenario that matches the situation can be generated. Also, when the user is playing with the pet, a conversation scenario that matches the situation can be generated. Furthermore, when the user is taking care of the pet, a conversation scenario that matches the situation can be generated. This provides a conversation scenario that the user and the pet can enjoy together, making learning more fun.

[0060] The process flow of the first embodiment will be briefly described below.

[0061] Step 1: The collection unit collects the user's learning history. The user's learning history includes study time, study content, study results, words and phrases learned in the past, pronunciation practice data, etc. The collection unit can analyze this data using AI and extract important data. Step 2: The evaluation unit analyzes the data collected by the collection unit and evaluates the user's pronunciation and speaking ability. The evaluation is based on pronunciation accuracy, fluency, naturalness of the conversation, etc. The evaluation unit includes AI processing or generation AI processing, and can input the user's pronunciation data into the generation AI to evaluate the pronunciation accuracy. Step 3: The generation unit generates a conversation scenario according to the user's weaknesses based on the evaluation results by the evaluation unit. The generated conversation scenarios include daily conversations, business conversations, specific situations, etc. The generation unit includes processing of the generation AI, and can generate a conversation scenario by inputting the user's evaluation results to the generation AI. Step 4: The learning support unit has a dialogue with the user using the conversation scenario generated by the generation unit. The learning support unit includes processing of the generation AI, and can input the generated conversation scenario to the generation AI to have a dialogue with the user.

[0062] (Example 2) The foreign language learning support system according to the embodiment of the present invention is a system that supports foreign language learning using a generation AI. This system allows for powerful personalization not available in conventional teaching materials. Specifically, the system collects the user's learning history, analyzes the data, and evaluates the user's pronunciation and conversation ability. Based on the evaluation results, a conversation scenario according to the user's weaknesses is generated, and a dialogue is conducted with the user using the scenario. This allows the user to efficiently learn a foreign language while overcoming their weaknesses. For example, the user's learning history is collected. For example, data such as what words and phrases the user has learned in the past and what pronunciation practice they have performed is collected. This data is collected by a collection unit that may include AI processing. Next, the collected data is analyzed to evaluate the user's pronunciation and conversation ability. For example, the user's pronunciation is evaluated to an extent to which the user's pronunciation is accurate, the user's conversation fluency, etc. are evaluated. This evaluation is performed by an evaluation unit that may include AI processing or generation AI processing. Based on the evaluation results, a conversation scenario according to the user's weaknesses is generated. For example, if the user is not good at a particular pronunciation, a conversation scenario including that pronunciation is generated. This scenario is generated by a generation unit that includes generation AI processing. A dialogue is conducted with the user based on the generated conversation scenario. For example, the user actually has a conversation based on the generated scenario, and practices pronunciation and conversation in the conversation. This dialogue is conducted by a learning support unit including the processing of the generation AI. Furthermore, it is also possible to generate exercises based on the evaluation results and provide them to the user. For example, if the user is not good at a particular grammar, an exercise including that grammar is generated and provided to the user. This exercise is generated by a generation unit including the processing of the generation AI, and is provided by a learning support unit including the processing of the generation AI. It is also possible to generate a conversation scenario based on the user's future occupation and lifestyle. For example, if the user aims to be a doctor in the future, a conversation scenario in the medical field is generated. This scenario is generated by a generation unit including the processing of the generation AI. Furthermore, it is also possible to provide pronunciation practice that is individually optimized based on the characteristics of the user's voice. For example, pronunciation practice that matches the pitch and tone of the user's voice is provided.This pronunciation practice is provided by a learning support unit including the processing of a generation AI. Finally, it is also possible to generate a conversation scenario based on the behavior of the user's pet. For example, a conversation scenario is generated for the user to proceed with learning together with the pet. This scenario is generated by a generation unit including the processing of a generation AI. In this way, the foreign language learning support system can efficiently learn a foreign language by collecting and evaluating the user's learning history and conducting a dialogue using the generated conversation scenario.

[0063] The foreign language learning support system according to the embodiment includes a collection unit, an evaluation unit, a generation unit, and a learning support unit. The collection unit collects the user's learning history. The user's learning history includes, for example, learning time, learning content, learning results, etc., but is not limited to such examples. The collection unit collects, for example, words and phrases that the user has previously learned, pronunciation practice data, etc. The collection unit may include AI processing. For example, the collection unit can analyze the user's learning history using AI and extract important data. The evaluation unit analyzes the data collected by the collection unit and evaluates the user's pronunciation and conversation ability. The evaluation is performed, for example, based on the accuracy of pronunciation, fluency, naturalness of conversation, etc., but is not limited to such examples. The evaluation unit may include AI processing or generation AI processing. For example, the evaluation unit can input the user's pronunciation data to the generation AI and evaluate the accuracy of pronunciation. The generation unit generates a conversation scenario according to the user's weaknesses based on the evaluation result by the evaluation unit. The generated conversation scenario includes, for example, daily conversation, business conversation, specific situations, etc., but is not limited to such examples. The generation unit includes processing of the generation AI. For example, the generation unit can input the user's evaluation result to the generation AI and generate a conversation scenario corresponding to the user's weak points. The learning support unit dialogues with the user using the conversation scenario generated by the generation unit. The learning support unit includes processing of the generation AI. For example, the learning support unit can input the generated conversation scenario to the generation AI and dialogue with the user. As a result, the foreign language learning support system according to the embodiment can efficiently learn a foreign language by collecting and evaluating the user's learning history and dialogue with the generated conversation scenario. For example, the collection unit can analyze the user's learning history using AI and extract important data. The evaluation unit can input the user's pronunciation data to the generation AI and evaluate the accuracy of the pronunciation. The generation unit can input the user's evaluation result to the generation AI and generate a conversation scenario corresponding to the user's weak points. The learning support unit can input the generated conversation scenario to the generation AI and dialogue with the user.This allows the foreign language learning support system to collect and evaluate the user's learning history, and engage in dialogue using the generated conversation scenario, thereby enabling efficient foreign language learning.

[0064] The collection unit collects the user's learning history. The user's learning history includes, for example, learning time, learning content, learning results, etc., but is not limited to such examples. The collection unit collects, for example, words and phrases that the user has learned in the past, pronunciation practice data, etc. Specifically, data that records the learning progress and achievement level is collected from the learning application or online platform used by the user. This includes detailed information such as how often the user learned which words and phrases, what errors were common during pronunciation practice, or what grammatical mistakes are frequent. The collection unit may include AI processing. For example, the collection unit can analyze the user's learning history using AI and extract important data. The AI ​​can analyze the user's learning pattern and evaluate the acquisition status of specific words and phrases. In addition, the pronunciation practice data can be analyzed to identify sounds and accents that the user is particularly weak at. This allows the collection unit to grasp the user's learning history in detail and provide data according to individual learning needs. Furthermore, the collection unit stores the user's learning history on a cloud server so that other system components can access it. This allows the collected data to serve as a foundation for use by the evaluation and generation components, strengthening collaboration throughout the system.

[0065] The evaluation unit analyzes the data collected by the collection unit and evaluates the user's pronunciation and conversation ability. The evaluation is performed based on, for example, the accuracy of pronunciation, fluency, naturalness of conversation, etc., but is not limited to such examples. Specifically, the evaluation unit analyzes the user's pronunciation data and evaluates the accuracy of pronunciation using voice recognition technology. For example, the words and phrases pronounced by the user are compared with standard pronunciation and the degree of match is scored. The evaluation of fluency also includes the user's speaking speed, rhythm, intonation, etc. Regarding the naturalness of the conversation, how naturally the user can continue the conversation and whether they can respond at the appropriate time are evaluated. The evaluation unit may include AI processing or generation AI processing. For example, the evaluation unit can input the user's pronunciation data into the generation AI and evaluate the accuracy of the pronunciation. The generation AI analyzes the user's pronunciation, identifies differences from standard pronunciation, and presents specific improvements. In addition, for the evaluation of conversation ability, the generation AI can have a mock conversation with the user and evaluate the appropriateness and naturalness of the user's response in the mock conversation. This allows the assessor to evaluate the user's pronunciation and speaking ability in detail and provide feedback tailored to individual learning needs. Furthermore, the assessor can track the user's progress based on past assessment data and evaluate the long-term learning effect.

[0066] The generation unit generates a conversation scenario according to the user's weaknesses based on the evaluation results by the evaluation unit. The conversation scenarios to be generated include, for example, daily conversations, business conversations, and specific situations, but are not limited to such examples. Specifically, the generation unit analyzes the user's evaluation results and generates a conversation scenario focusing on areas and situations in which the user is particularly weak. For example, if the user is not good at a specific phrase or expression in business conversation, a scenario including the phrase or expression is generated. The generation unit includes processing of the generation AI. For example, the generation unit can input the user's evaluation results to the generation AI and generate a conversation scenario corresponding to the user's weaknesses. The generation AI automatically generates an appropriate scenario based on the user's evaluation data, enabling the user to study efficiently. The generated scenario is customized according to the user's learning level and goals, and corresponds to individual learning needs. In addition, the generation unit stores the generated scenario in a cloud server and allows the learning support unit to access it. As a result, the generation unit can provide an effective learning scenario based on the user's evaluation results, maximizing the user's learning effect. Furthermore, the generator can continually improve the scenario based on user feedback to provide a more effective learning experience.

[0067] The learning support unit interacts with the user using the conversation scenario generated by the generation unit. The learning support unit includes processing of the generation AI. Specifically, the learning support unit can input the generated conversation scenario to the generation AI and interact with the user. The generation AI provides appropriate feedback to the user's response, allowing the user to practice natural conversation. For example, if the user makes an error in pronunciation or expression, the generation AI suggests corrections on the spot and shows the correct pronunciation or expression. The learning support unit can also monitor the user's progress in real time and adjust the scenario as necessary. This allows the user to always continue practicing in an optimal learning environment. Furthermore, the learning support unit can also propose individual learning plans based on the user's learning history. For example, if the user is lagging behind in a particular area, the learning support unit can propose a learning plan that focuses on that area to support efficient learning. The learning support unit can also collect user feedback and use it to improve the entire system. This allows the learning support unit to provide effective learning support to the user and significantly improve the efficiency of foreign language learning. Furthermore, the learning support unit also has a function of providing rewards and a sense of accomplishment according to the user's learning progress in order to maintain the user's motivation. This allows users to continue learning in an enjoyable way and achieve long-term learning results.

[0068] The generation unit generates exercises based on the evaluation result by the evaluation unit, and the learning support unit can provide the exercises to the user. The generation unit generates exercises such as listening questions, speaking questions, and grammar questions based on the evaluation result of the user. The generation unit includes processing of the generation AI. For example, the generation unit can input the evaluation result of the user to the generation AI and generate exercises corresponding to the weak points of the user. The learning support unit provides the generated exercises to the user. The learning support unit includes processing of the generation AI. For example, the learning support unit can input the generated exercises to the generation AI and provide them to the user. As a result, the weak points of the user can be effectively overcome by generating exercises based on the evaluation result and providing them to the user. For example, the generation unit can input the evaluation result of the user to the generation AI and generate exercises corresponding to the weak points of the user. The learning support unit can input the generated exercises to the generation AI and provide them to the user. As a result, the foreign language learning support system can effectively overcome the weak points of the user by generating exercises based on the evaluation result of the user and providing them to the user.

[0069] The generation unit can generate a conversation scenario based on the user's future occupation or lifestyle. For example, if the user aims to be a doctor in the future, the generation unit generates a conversation scenario in a medical field. The generation unit includes a generation AI process. For example, the generation unit can generate a related conversation scenario based on the user's future occupation or lifestyle. This enables practical learning by generating a conversation scenario based on the user's future occupation or lifestyle. For example, the generation unit can generate a related conversation scenario based on the user's future occupation or lifestyle. This enables practical learning by the foreign language learning support system generating a conversation scenario based on the user's future occupation or lifestyle.

[0070] The learning support unit can provide the user with individually adjusted pronunciation practice based on the characteristics of the user's voice. The learning support unit provides, for example, pronunciation practice that matches the pitch and tone of the user's voice. The learning support unit includes processing of the generation AI. For example, the learning support unit can input the characteristics of the user's voice into the generation AI and provide individually adjusted pronunciation practice. This allows for more effective pronunciation practice by providing pronunciation practice based on the characteristics of the user's voice. For example, the learning support unit can input the characteristics of the user's voice into the generation AI and provide individually adjusted pronunciation practice. This allows the foreign language learning support system to provide more effective pronunciation practice by providing pronunciation practice based on the characteristics of the user's voice.

[0071] The generation unit can generate a conversation scenario that corresponds to a specific weakness of the user based on the behavior of the user's pet and is used to advance learning together with the pet. The generation unit generates, for example, a conversation scenario for the user to advance learning together with the pet. The generation unit includes a generation AI process. For example, the generation unit can generate a related conversation scenario based on the behavior of the user's pet. This allows the user to advance learning in a fun way by generating a conversation scenario based on the behavior of the user's pet. For example, the generation unit can generate a related conversation scenario based on the behavior of the user's pet. This allows the foreign language learning support system to advance learning in a fun way by generating a conversation scenario based on the behavior of the user's pet.

[0072] The collection unit can estimate the user's emotion and adjust the timing of collection of the learning history based on the estimated emotion of the user. For example, when the user is feeling stressed, the collection unit temporarily delays collection of the learning history. The collection unit is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the collection unit can input the user's facial expression data to the generation AI and estimate the emotion. In addition, the collection unit can frequently collect the learning history when the user is relaxed. For example, the collection unit can input the user's voice data to the generation AI and estimate the emotion. Furthermore, the collection unit can collect the learning history in real time when the user is concentrating. For example, the collection unit can input the user's biometric data (heart rate and skin electrodermal activity) to the generation AI and estimate the emotion. Thereby, by adjusting the timing of collection of the learning history according to the user's emotion, data can be collected at a more appropriate timing. For example, the collection unit can input facial expression data of the user to the generation AI and estimate the emotion. The collection unit can input voice data of the user to the generation AI and estimate the emotion. The collection unit can input biometric data of the user to the generation AI and estimate the emotion. This allows the foreign language learning support system to collect data at a more appropriate timing by adjusting the timing of collecting the learning history according to the user's emotion.

[0073] The collection unit can analyze the user's past learning history and select an appropriate collection method. For example, the collection unit prioritizes and collects learning methods that the user frequently used in the past. The collection unit may include AI processing. For example, the collection unit can analyze the user's past learning history using AI and select an optimal collection method. In addition, the collection unit can identify an effective learning method from the user's past learning history and collect the method with priority. For example, the collection unit can analyze the user's past learning history using AI and identify an effective learning method. Furthermore, the collection unit can analyze the user's past learning history and select the most efficient collection timing. For example, the collection unit can analyze the user's past learning history using AI and select the optimal collection timing. As a result, the optimal collection method can be selected by analyzing the user's past learning history. For example, the collection unit can analyze the user's past learning history using AI and select the optimal collection method. As a result, the foreign language learning support system can select the optimal collection method by analyzing the user's past learning history.

[0074] The collection unit can filter the learning history based on the user's current learning progress and field of interest when collecting the learning history. For example, the collection unit preferentially collects data related to a topic that the user is currently learning. The collection unit may include AI processing. For example, the collection unit can filter and collect related data based on the user's current learning progress and field of interest. In addition, the collection unit can filter and collect related learning history based on the user's field of interest. For example, the collection unit can identify the user's field of interest using AI and collect related data. Furthermore, the collection unit can collect only necessary data according to the user's learning progress. For example, the collection unit can evaluate the user's learning progress using AI and collect necessary data. As a result, more relevant data can be collected by filtering data based on the user's current learning progress and field of interest. For example, the collection unit can filter and collect related data based on the user's current learning progress and field of interest. As a result, the foreign language learning support system can collect more relevant data by filtering data based on the user's current learning progress and field of interest.

[0075] The collection unit can estimate the user's emotions and determine the priority of the learning history to be collected based on the estimated user's emotions. For example, when the user is feeling stressed, the collection unit postpones the collection of less important data. The collection unit is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. For example, the collection unit can input the user's facial expression data to the generation AI and estimate the emotion. In addition, when the user is relaxed, the collection unit can prioritize the collection of detailed data. For example, the collection unit can input the user's voice data to the generation AI and estimate the emotion. Furthermore, when the user is concentrating, the collection unit can prioritize the collection of important data in real time. For example, the collection unit can input the user's biometric data (heart rate and electrodermal activity) to the generation AI and estimate the emotion. This enables more effective data collection by determining the priority of the learning history based on the user's emotions. For example, the collection unit can input the user's facial expression data to the generation AI and estimate the emotion. The collection unit can input the user's voice data to the generation AI and estimate the emotion. The collection unit can input the user's biometric data to the generation AI and estimate the emotion. This enables the foreign language learning support system to collect data more effectively by determining the priority of learning history based on the user's emotion.

[0076] When collecting the learning history, the collection unit can preferentially collect a history with high relevance in consideration of the geographical location information of the user. For example, when the user is in a specific area, the collection unit preferentially collects a learning history related to the area. The collection unit may include AI processing. For example, the collection unit can analyze the geographical location information of the user using AI to collect highly relevant data. In addition, the collection unit can collect data on related cultures and languages ​​based on the geographical location information of the user. For example, the collection unit can analyze the geographical location information of the user using AI to collect related data. Furthermore, when the user is traveling, the collection unit can preferentially collect a learning history related to the travel destination. For example, the collection unit can analyze the geographical location information of the user using AI to collect related data. As a result, more effective learning is possible by collecting highly relevant data based on the geographical location information of the user. For example, the collection unit can analyze the geographical location information of the user using AI to collect highly relevant data. As a result, the foreign language learning support system can collect highly relevant data based on the geographical location information of the user, thereby enabling more effective learning.

[0077] The collection unit can analyze the user's social media activities and collect related histories when collecting the learning history. The collection unit, for example, collects learning contents shared by the user on social media. The collection unit may include AI processing. For example, the collection unit can analyze the user's social media activities using AI and collect related data. In addition, the collection unit can identify topics of interest from the user's social media activities and collect related data. For example, the collection unit can analyze the user's social media activities using AI and identify topics of interest. In addition, the collection unit can analyze the posted content of an account followed by the user and collect related learning history. For example, the collection unit can analyze the user's social media activities using AI and collect related data. As a result, more effective learning is possible by collecting related data based on the user's social media activities. For example, the collection unit can analyze the user's social media activities using AI and collect related data. As a result, the foreign language learning support system can collect related data based on the user's social media activities and collect related data.

[0078] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria of the pronunciation and conversation skills based on the estimated user's emotions. For example, if the user is nervous, the evaluation unit relaxes the evaluation criteria to reduce stress. The evaluation unit is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. For example, the evaluation unit can input the user's facial expression data to the generation AI and estimate the emotions. In addition, the evaluation unit can apply strict evaluation criteria when the user is relaxed. For example, the evaluation unit can input the user's voice data to the generation AI and estimate the emotions. Furthermore, the evaluation unit can apply detailed evaluation criteria when the user is focused. For example, the evaluation unit can input the user's biometric data (heart rate and electrodermal activity) to the generation AI and estimate the emotions. This allows for more appropriate evaluation by adjusting the evaluation criteria based on the user's emotions. For example, the evaluation unit can input the user's facial expression data to the generation AI and estimate the emotions. The evaluation unit can input the user's voice data to the generation AI and estimate the emotion. The evaluation unit can input the user's biometric data to the generation AI and estimate the emotion. This enables the foreign language learning support system to adjust the evaluation criteria based on the user's emotion, enabling more appropriate evaluation.

[0079] The evaluation unit can improve the accuracy of the evaluation by referring to the user's past learning data at the time of evaluation. The evaluation unit, for example, refers to the user's past pronunciation data and performs a current pronunciation evaluation. The evaluation unit may include AI processing or generation AI processing. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the user's past learning data using AI or generation AI. In addition, the evaluation unit can evaluate the conversation ability by referring to the user's past conversation data. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the user's past conversation data using AI or generation AI. Furthermore, the evaluation unit can perform a comprehensive evaluation by referring to the user's past learning history. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the user's past learning history using AI or generation AI. As a result, the accuracy of the evaluation is improved by referring to the user's past learning data. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the user's past learning data using AI or generation AI. As a result, the foreign language learning support system improves the accuracy of the evaluation by referring to the user's past learning data.

[0080] The evaluation unit can apply different evaluation algorithms depending on the learning style of the user at the time of evaluation. For example, when the user is a visual learner, the evaluation unit applies a visual evaluation algorithm. The evaluation unit may include AI processing or generation AI processing. For example, the evaluation unit can apply different evaluation algorithms using AI or generation AI depending on the learning style of the user. Also, when the user is an auditory learner, the evaluation unit can apply an auditory evaluation algorithm. For example, the evaluation unit can apply different evaluation algorithms using AI or generation AI depending on the learning style of the user. Furthermore, when the user is an experiential learner, the evaluation unit can apply an experiential evaluation algorithm. For example, the evaluation unit can apply different evaluation algorithms using AI or generation AI depending on the learning style of the user. As a result, more appropriate evaluation is possible by applying an evaluation algorithm according to the learning style of the user. For example, the evaluation unit can apply different evaluation algorithms using AI or generation AI depending on the learning style of the user. As a result, the foreign language learning support system can apply a more appropriate evaluation by applying an evaluation algorithm according to the learning style of the user.

[0081] The evaluation unit can estimate the user's emotion and adjust the display method of the evaluation result based on the estimated user's emotion. For example, when the user is nervous, the evaluation unit provides a simple and highly visible display method. The evaluation unit is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. For example, the evaluation unit can input the user's facial expression data to the generation AI and estimate the emotion. In addition, the evaluation unit can provide a display method including detailed information when the user is relaxed. For example, the evaluation unit can input the user's voice data to the generation AI and estimate the emotion. Furthermore, the evaluation unit can provide a display method that focuses on the main points when the user is in a hurry. For example, the evaluation unit can input the user's biometric data (heart rate and electrodermal activity) to the generation AI and estimate the emotion. This enables more appropriate feedback by adjusting the display method of the evaluation result based on the user's emotion. For example, the evaluation unit can input the user's facial expression data to the generation AI and estimate the emotion. The evaluation unit can input the user's voice data to the generation AI and estimate the emotion. The evaluation unit can input the user's biometric data to the generation AI and estimate the emotion. This enables the foreign language learning support system to provide more appropriate feedback by adjusting the method of displaying the evaluation results based on the user's emotion.

[0082] At the time of evaluation, the evaluation unit can determine the priority of evaluation based on the time of submission of the user's learning history. For example, the evaluation unit prioritizes evaluation of the learning history recently submitted by the user. The evaluation unit may include processing of AI or processing of generation AI. For example, the evaluation unit can determine the priority of evaluation using AI or generation AI based on the time of submission of the user's learning history. In addition, the evaluation unit can prioritize evaluation of the learning history submitted by the user within a specific period. For example, the evaluation unit can determine the priority of evaluation using AI or generation AI based on the time of submission of the user's learning history. Furthermore, the evaluation unit can prioritize evaluation of the learning history that the user has not submitted for a long period of time. For example, the evaluation unit can determine the priority of evaluation using AI or generation AI based on the time of submission of the user's learning history. As a result, more effective evaluation is possible by determining the priority of evaluation based on the time of submission of the user's learning history. For example, the evaluation unit can determine the priority of evaluation using AI or generation AI based on the time of submission of the user's learning history. This enables the foreign language learning support system to determine the priority of evaluation based on the time of submission of the user's learning history, thereby enabling more effective evaluation.

[0083] The evaluation unit can improve the accuracy of the evaluation by referring to the user's related literature at the time of evaluation. The evaluation unit adjusts the evaluation criteria based on the literature referred to by the user, for example. The evaluation unit may include AI processing or generation AI processing. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the literature related to the user's learning content. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the literature related to the user's learning content. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the literature related to the user's learning content. Furthermore, the evaluation unit can improve the accuracy of the evaluation based on the literature referred to by the user in the past. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the user's related literature using AI or generation AI. As a result, the accuracy of the evaluation is improved by referring to the user's related literature. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the user's related literature using AI or generation AI. As a result, the foreign language learning support system improves the accuracy of the evaluation by referring to the user's related literature.

[0084] The generation unit can estimate the user's emotion and adjust the generation method of the conversation scenario based on the estimated user's emotion. For example, when the user is relaxed, the generation unit generates a conversation scenario that proceeds at a leisurely pace. The generation unit is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the generation unit can input the user's facial expression data to the generation AI and estimate the emotion. In addition, when the user is in a hurry, the generation unit can generate a conversation scenario that is completed in a short time. For example, the generation unit can input the user's voice data to the generation AI and estimate the emotion. Furthermore, when the user is excited, the generation unit can generate a conversation scenario with a visually stimulating effect added. For example, the generation unit can input the user's biometric data (heart rate and electrodermal activity) to the generation AI and estimate the emotion. As a result, a more appropriate scenario is generated by adjusting the generation method of the conversation scenario based on the user's emotion. For example, the generation unit can input the user's facial expression data to the generation AI and estimate the emotion. The generation unit can input the user's voice data to the generation AI and estimate the emotion. The generation unit can input the user's biometric data to the generation AI and estimate the emotion. In this way, the foreign language learning support system can generate a more appropriate scenario by adjusting the conversation scenario generation method based on the user's emotion.

[0085] The generation unit can generate an appropriate scenario by referring to the user's past learning data when generating a conversation scenario. The generation unit generates a conversation scenario including, for example, words and phrases that the user has learned in the past. The generation unit includes processing of the generation AI. For example, the generation unit can input the user's past learning data to the generation AI and generate an optimal conversation scenario. Furthermore, the generation unit can generate a conversation scenario including a pronunciation that the user is not good at from the user's past learning data. For example, the generation unit can input the user's past learning data to the generation AI and generate an optimal conversation scenario. Furthermore, the generation unit can generate the most effective conversation scenario by referring to the user's past learning history. For example, the generation unit can input the user's past learning data to the generation AI and generate an optimal conversation scenario. As a result, the optimal conversation scenario is generated by referring to the user's past learning data. For example, the generation unit can input the user's past learning data to the generation AI and generate an optimal conversation scenario. As a result, the foreign language learning support system generates an optimal conversation scenario by referring to the user's past learning data.

[0086] The generation unit can apply different scenario generation algorithms according to the user's learning style when generating a conversation scenario. For example, when the user is a visual learner, the generation unit generates a conversation scenario that includes many visual elements. The generation unit includes processing of the generation AI. For example, the generation unit can input different scenario generation algorithms to the generation AI according to the user's learning style and apply them. Furthermore, when the user is an auditory learner, the generation unit can generate a conversation scenario that includes many auditory elements. For example, the generation unit can input different scenario generation algorithms to the generation AI according to the user's learning style and apply them. Furthermore, when the user is an experiential learner, the generation unit can generate a conversation scenario that includes many experiential elements. For example, the generation unit can input different scenario generation algorithms to the generation AI according to the user's learning style and apply them. As a result, a more effective conversation scenario is generated by applying a scenario generation algorithm according to the user's learning style. For example, the generation unit can input different scenario generation algorithms to the generation AI according to the user's learning style and apply them. This allows the foreign language learning support system to generate more effective conversation scenarios by applying a scenario generation algorithm that suits the user's learning style.

[0087] The generation unit can estimate the user's emotion and determine the priority of the conversation scenario to be generated based on the estimated user's emotion. For example, when the user is feeling stressed, the generation unit generates a conversation scenario that allows the user to relax with priority. The generation unit is realized by using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the generation unit can input the user's facial expression data to the generation AI and estimate the emotion. Furthermore, when the user is relaxed, the generation unit can generate a challenging conversation scenario with priority. For example, the generation unit can input the user's voice data to the generation AI and estimate the emotion. Furthermore, when the user is concentrating, the generation unit can generate a conversation scenario with a high learning effect with priority. For example, the generation unit can input the user's biometric data (heart rate and electrodermal activity) to the generation AI and estimate the emotion. As a result, a more appropriate scenario can be generated by determining the priority of the conversation scenario based on the user's emotion. For example, the generation unit can input facial expression data of the user to the generation AI and estimate emotions. The generation unit can input voice data of the user to the generation AI and estimate emotions. The generation unit can input biometric data of the user to the generation AI and estimate emotions. In this way, the foreign language learning support system can generate more appropriate scenarios by determining the priority order of conversation scenarios based on the user's emotions.

[0088] The generation unit can generate an appropriate scenario in consideration of the geographical location information of the user when generating a conversation scenario. For example, when the user is in a specific region, the generation unit generates a conversation scenario related to the culture and language of that region. The generation unit includes processing of the generation AI. For example, the generation unit can input the geographical location information of the user to the generation AI and generate an optimal conversation scenario. In addition, the generation unit can generate a conversation scenario including a related topic based on the geographical location information of the user. For example, the generation unit can input the geographical location information of the user to the generation AI and generate an optimal conversation scenario. Furthermore, when the user is traveling, the generation unit can generate a conversation scenario related to the travel destination. For example, the generation unit can input the geographical location information of the user to the generation AI and generate an optimal conversation scenario. As a result, more effective learning is possible by generating an optimal conversation scenario based on the geographical location information of the user. For example, the generation unit can input the geographical location information of the user to the generation AI and generate an optimal conversation scenario. As a result, the foreign language learning support system can generate an optimal conversation scenario based on the geographical location information of the user, thereby enabling more effective learning.

[0089] The generation unit can generate a related scenario by analyzing the social media activity of the user when generating a conversation scenario. The generation unit generates, for example, a conversation scenario related to a topic shared by the user on social media. The generation unit includes processing of the generation AI. For example, the generation unit can input the social media activity of the user to the generation AI and generate a related conversation scenario. In addition, the generation unit can identify a topic of interest from the social media activity of the user and generate a related scenario. For example, the generation unit can input the social media activity of the user to the generation AI and generate a related conversation scenario. Furthermore, the generation unit can analyze the posted content of an account followed by the user and generate a related conversation scenario. For example, the generation unit can input the social media activity of the user to the generation AI and generate a related conversation scenario. As a result, more effective learning is possible by generating a related conversation scenario based on the social media activity of the user. For example, the generation unit can input the social media activity of the user to the generation AI and generate a related conversation scenario. As a result, the foreign language learning support system can generate a related conversation scenario based on the social media activity of the user, thereby enabling more effective learning.

[0090] The learning support unit can estimate the user's emotion and adjust the learning support method based on the estimated user's emotion. For example, when the user is feeling stressed, the learning support unit provides a learning support method that allows the user to relax. The learning support unit is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. For example, the learning support unit can input the user's facial expression data to the generation AI and estimate the emotion. In addition, the learning support unit can provide a challenging learning support method when the user is relaxed. For example, the learning support unit can input the user's voice data to the generation AI and estimate the emotion. Furthermore, the learning support unit can provide an efficient learning support method when the user is concentrating. For example, the learning support unit can input the user's biometric data (heart rate and skin electrodermal activity) to the generation AI and estimate the emotion. This enables more effective learning support by adjusting the learning support method based on the user's emotion. For example, the learning support unit can input the user's facial expression data to the generation AI and estimate the emotion. The learning support unit can input the user's voice data to the generation AI and estimate the emotion. The learning support unit can input the user's biometric data to the generation AI and estimate the emotion. This enables the foreign language learning support system to provide more effective learning support by adjusting the learning support method based on the user's emotion.

[0091] The learning support unit can select the optimal support method by referring to the user's past learning data when providing learning support. For example, the learning support unit preferentially provides the user with a learning method that was effective in the past. The learning support unit includes processing of the generation AI. For example, the learning support unit can input the user's past learning data into the generation AI and select the optimal support method. In addition, the learning support unit can identify the optimal support method from the user's past learning data and provide the method. For example, the learning support unit can input the user's past learning data into the generation AI and select the optimal support method. Furthermore, the learning support unit can select the most effective support method by referring to the user's past learning history. For example, the learning support unit can input the user's past learning data into the generation AI and select the optimal support method. As a result, the optimal support method can be selected by referring to the user's past learning data. For example, the learning support unit can input the user's past learning data into the generation AI and select the optimal support method. As a result, the foreign language learning support system can select the optimal support method by referring to the user's past learning data.

[0092] The learning support unit can apply different support algorithms according to the learning style of the user during learning support. For example, when the user is a visual learner, the learning support unit applies a visual support algorithm. The learning support unit includes processing of the generation AI. For example, the learning support unit can input different support algorithms to the generation AI according to the learning style of the user and apply them. In addition, when the user is an auditory learner, the learning support unit can apply an auditory support algorithm. For example, the learning support unit can input different support algorithms to the generation AI according to the learning style of the user and apply them. In addition, when the user is an experiential learner, the learning support unit can apply an experiential support algorithm. For example, the learning support unit can input different support algorithms to the generation AI according to the learning style of the user and apply them. As a result, more effective learning support is possible by applying a support algorithm according to the learning style of the user. For example, the learning support unit can input different support algorithms to the generation AI according to the learning style of the user and apply them. As a result, the foreign language learning support system can provide more effective learning support by applying a support algorithm according to the learning style of the user.

[0093] The learning support unit can estimate the user's emotion and determine the priority of learning support based on the estimated user's emotion. For example, when the user is feeling stressed, the learning support unit provides support that allows the user to relax with priority. The learning support unit is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the learning support unit can input the user's facial expression data to the generation AI and estimate the emotion. In addition, when the user is relaxed, the learning support unit can provide challenging support with priority. For example, the learning support unit can input the user's voice data to the generation AI and estimate the emotion. Furthermore, when the user is concentrating, the learning support unit can provide efficient support with priority. For example, the learning support unit can input the user's biometric data (heart rate and electrodermal activity) to the generation AI and estimate the emotion. This enables more effective learning support by determining the priority of learning support based on the user's emotion. For example, the learning support unit can input the user's facial expression data to the generation AI and estimate the emotion. The learning support unit can input the user's voice data to the generation AI and estimate the emotion. The learning support unit can input the user's biometric data to the generation AI and estimate the emotion. This enables the foreign language learning support system to provide more effective learning support by determining the priority of learning support based on the user's emotion.

[0094] The learning support unit can select an appropriate support method in consideration of the geographical location information of the user when providing learning support. For example, when the user is in a specific area, the learning support unit provides a learning support method related to the area. The learning support unit includes processing of the generation AI. For example, the learning support unit can input the geographical location information of the user to the generation AI and select an optimal support method. In addition, the learning support unit can provide a support method of a related culture or language based on the geographical location information of the user. For example, the learning support unit can input the geographical location information of the user to the generation AI and select an optimal support method. Furthermore, when the user is traveling, the learning support unit can provide a learning support method related to the travel destination. For example, the learning support unit can input the geographical location information of the user to the generation AI and select an optimal support method. As a result, more effective learning support is possible by selecting the optimal support method based on the geographical location information of the user. For example, the learning support unit can input the geographical location information of the user to the generation AI and select an optimal support method. As a result, the foreign language learning support system can provide more effective learning support by selecting the optimal support method based on the geographical location information of the user.

[0095] The learning support unit can provide a related support method by analyzing the user's social media activity during learning support. The learning support unit provides a support method based on, for example, learning content shared by the user on social media. The learning support unit includes processing of the generation AI. For example, the learning support unit can input the user's social media activity to the generation AI and provide a related support method. In addition, the learning support unit can provide a support method related to a topic of interest from the user's social media activity. For example, the learning support unit can input the user's social media activity to the generation AI and provide a related support method. In addition, the learning support unit can analyze the posted content of an account followed by the user and provide a related learning support method. For example, the learning support unit can input the user's social media activity to the generation AI and provide a related support method. As a result, more effective learning support can be provided by providing a related support method based on the user's social media activity. For example, the learning support unit can input the user's social media activity to the generation AI and provide a related support method. As a result, the foreign language learning support system can provide a more effective learning support by providing a related support method based on the user's social media activity.

[0096] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0097] When collecting the user's learning history, the collection unit can collect data taking into consideration the user's learning environment. For example, if the user is learning in a quiet environment, it can prioritize collection of pronunciation practice data. Also, if the user is learning while on the move, it can prioritize collection of listening data. Furthermore, if the user is learning in a group, it can prioritize collection of conversation data. This makes it possible to collect data according to the user's learning environment, thereby realizing more effective learning support.

[0098] The generator can generate exercises optimized for the user's learning style based on the user's learning history. For example, exercises including many images and diagrams can be generated for visual learners. Also, exercises including many audio can be generated for auditory learners. Furthermore, exercises including practical scenarios can be generated for experiential learners. This provides exercises according to the user's learning style, improving the learning effect.

[0099] The generation unit can generate a conversation scenario that attracts the user's interest based on the user's future occupation and lifestyle. For example, if the user hopes to work in the travel industry in the future, a conversation scenario related to travel can be generated. Also, if the user hopes to enjoy cooking as a future hobby, a conversation scenario related to cooking can be generated. Furthermore, if the user hopes to be involved in sports as a future goal, a conversation scenario related to sports can be generated. In this way, a conversation scenario according to the user's interests and goals is provided, improving motivation to learn.

[0100] The learning support unit can provide the user with optimal pronunciation practice based on the characteristics of the user's voice. For example, it can provide pronunciation practice that matches the pitch and tone of the user's voice. It can also provide pronunciation practice that matches the strength and weakness of the user's voice. It can also provide pronunciation practice that matches the rhythm of the user's voice. This provides pronunciation practice that matches the characteristics of the user's voice, improving the accuracy of pronunciation.

[0101] The generation unit can generate a conversation scenario that the user and the pet can enjoy together, based on the behavior of the user's pet. For example, when the user is walking with the pet, a conversation scenario that matches the situation can be generated. Also, when the user is playing with the pet, a conversation scenario that matches the situation can be generated. Furthermore, when the user is taking care of the pet, a conversation scenario that matches the situation can be generated. This provides a conversation scenario that the user and the pet can enjoy together, making learning more fun.

[0102] The collection unit can estimate the user's emotions and adjust the timing of collection of the learning history based on the estimated user's emotions. For example, when the user is stressed, collection of the learning history can be temporarily delayed. Also, when the user is relaxed, collection of the learning history can be performed frequently. Furthermore, when the user is concentrating, collection of the learning history can be performed in real time. In this way, by adjusting the timing of collection of the learning history according to the user's emotions, data can be collected at a more appropriate timing.

[0103] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria for pronunciation and conversation skills based on the estimated user's emotions. For example, if the user is nervous, the evaluation criteria can be relaxed to reduce stress. If the user is relaxed, strict evaluation criteria can be applied. Furthermore, if the user is focused, detailed evaluation criteria can be applied. This allows for more appropriate evaluation by adjusting the evaluation criteria based on the user's emotions.

[0104] The generation unit can estimate the user's emotions and adjust the generation method of the conversation scenario based on the estimated user's emotions. For example, when the user is relaxed, a conversation scenario that proceeds at a leisurely pace can be generated. When the user is in a hurry, a conversation scenario that is completed in a short time can be generated. Furthermore, when the user is excited, a conversation scenario that includes visually stimulating effects can be generated. In this way, a more appropriate scenario can be generated by adjusting the generation method of the conversation scenario based on the user's emotions.

[0105] The generation unit can estimate the user's emotions and determine the priority of conversation scenarios to be generated based on the estimated user's emotions. For example, if the user is feeling stressed, a relaxing conversation scenario can be generated with priority. Also, if the user is relaxed, a challenging conversation scenario can be generated with priority. Furthermore, if the user is concentrating, a conversation scenario with a high learning effect can be generated with priority. In this way, by determining the priority of conversation scenarios based on the user's emotions, more appropriate scenarios can be generated.

[0106] The learning support unit can estimate the user's emotions and adjust the learning support method based on the estimated user's emotions. For example, when the user is stressed, a relaxing learning support method can be provided. When the user is relaxed, a challenging learning support method can be provided. Furthermore, when the user is concentrating, an efficient learning support method can be provided. Thus, by adjusting the learning support method based on the user's emotions, more effective learning support can be provided.

[0107] The process flow of the second embodiment will be briefly described below.

[0108] Step 1: The collection unit collects the user's learning history. The user's learning history includes study time, study content, study results, words and phrases learned in the past, pronunciation practice data, etc. The collection unit can analyze this data using AI and extract important data. Step 2: The evaluation unit analyzes the data collected by the collection unit and evaluates the user's pronunciation and speaking ability. The evaluation is based on pronunciation accuracy, fluency, naturalness of the conversation, etc. The evaluation unit includes AI processing or generation AI processing, and can input the user's pronunciation data into the generation AI to evaluate the pronunciation accuracy. Step 3: The generation unit generates a conversation scenario according to the user's weaknesses based on the evaluation results by the evaluation unit. The generated conversation scenarios include daily conversations, business conversations, specific situations, etc. The generation unit includes processing of the generation AI, and can generate a conversation scenario by inputting the user's evaluation results to the generation AI. Step 4: The learning support unit has a dialogue with the user using the conversation scenario generated by the generation unit. The learning support unit includes processing of the generation AI, and can input the generated conversation scenario to the generation AI to have a dialogue with the user.

[0109] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0110] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0111] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0112] For example, the collection unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the evaluation unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the generation unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the learning support unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0113] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0114] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0115] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0116] The 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.

[0117] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0118] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0119] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0120] Fig. 4 shows an example of 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.

[0121] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0122] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0123] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0124] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0125] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0126] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0127] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0128] For example, the collection unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the evaluation unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the generation unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the learning support unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0129] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0130] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0131] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0132] 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.

[0133] 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 the voice according to instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0135] 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 performed in a secure state.

[0136] 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.

[0137] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0138] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0139] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific 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.

[0140] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0141] 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 voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0142] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0143] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0144] For example, the collection unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the evaluation unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the generation unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the learning support unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0145] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0146] 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.

[0147] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0148] 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.

[0149] 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 the voice according to instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0151] 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 performed in a secure state.

[0152] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0153] 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.

[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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0156] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0158] 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 a voice indicating a user input for 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.

[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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0160] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0161] For example, the collection unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the evaluation unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the generation unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the learning support unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0162] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0163] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0164] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0165] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0166] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0167] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0168] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0169] 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.

[0170] 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 Universal Serial Bus (USB) 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.

[0171] In addition, 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 upon request from the data processing device 12.

[0172] 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.

[0173] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0174] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0175] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0176] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0177] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0178] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0179] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0180] (Appendix 1) A collection unit that collects a user's learning history; an evaluation unit that analyzes the data collected by the collection unit and evaluates the pronunciation and conversation ability of the user; a generation unit that generates a conversation scenario corresponding to a specific weakness of the user based on a result of the evaluation by the evaluation unit; a learning support unit that has a dialogue with the user based on the dialogue scenario generated by the generation unit; A system characterized by: (Appendix 2) The generation unit is generating exercises based on the evaluation results by the evaluation unit; The learning support unit includes: Providing the user with the exercises 2. The system of claim 1, (Appendix 3) The generation unit is Generate a conversation scenario based on the user's future occupation or lifestyle 2. The system of claim 1, (Appendix 4) The learning support unit includes: Providing individually tailored pronunciation exercises to the user based on the characteristics of the user's voice 2. The system of claim 1, (Appendix 5) The generation unit is Generate a conversation scenario that corresponds to a specific weakness of the user based on the behavior of the user's pet and that is used to advance learning together with the pet. 2. The system of claim 1, (Appendix 6) The collecting unit includes: A method for estimating a user's emotions and adjusting the timing of collecting learning history based on the estimated user's emotions 2. The system of claim 1, (Appendix 7) The collecting unit includes: Analyze the user's past learning history and select the appropriate collection method 2. The system of claim 1, (Appendix 8) The collecting unit includes: When collecting learning history, filtering is performed based on the user's current learning progress and areas of interest. 2. The system of claim 1, (Appendix 9) The collecting unit includes: A user's emotion is estimated, and a priority order of learning histories to be collected is determined based on the estimated user's emotion. 2. The system of claim 1, (Appendix 10) The collecting unit includes: When collecting learning history, the system prioritizes collection of history that is more relevant by taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 11) The collecting unit includes: When collecting learning history, analyze the user's social media activity and collect related history. 2. The system of claim 1, (Appendix 12) The evaluation unit is Estimating a user's emotion and adjusting evaluation criteria for pronunciation and speaking ability based on the estimated user's emotion 2. The system of claim 1, (Appendix 13) The evaluation unit is During evaluation, the accuracy of the evaluation is improved by referring to the user's past learning data. 2. The system of claim 1, (Appendix 14) The evaluation unit is During evaluation, different evaluation algorithms are applied depending on the user's learning style. 2. The system of claim 1, (Appendix 15) The evaluation unit is Inferring a user's emotion and adjusting the way in which the evaluation results are displayed based on the estimated user's emotion 2. The system of claim 1, (Appendix 16) The evaluation unit is During evaluation, prioritize evaluations based on when users submitted their learning history 2. The system of claim 1, (Appendix 17) The evaluation unit is During evaluation, the accuracy of the evaluation is improved by referring to the user's related literature. 2. The system of claim 1, (Appendix 18) The generation unit is Estimating a user's emotions and adjusting a method for generating a conversation scenario based on the estimated user's emotions 2. The system of claim 1, (Appendix 19) The generation unit is When generating a conversation scenario, the system generates an appropriate scenario by referring to the user's past learning data. 2. The system of claim 1, (Appendix 20) The generation unit is When generating conversation scenarios, different scenario generation algorithms are applied depending on the user's learning style. 2. The system of claim 1, (Appendix 21) The generation unit is Estimating a user's emotions and determining the priority of conversation scenarios to be generated based on the estimated user's emotions 2. The system of claim 1, (Appendix 22) The generation unit is When generating conversation scenarios, appropriate scenarios are generated taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 23) The generation unit is When generating conversation scenarios, the system analyzes users' social media activities to generate relevant scenarios. 2. The system of claim 1, (Appendix 24) The learning support unit includes: Estimating a user's emotions and adjusting a learning support method based on the estimated user's emotions 2. The system of claim 1, (Appendix 25) The learning support unit includes: When providing learning support, the system selects the most appropriate support method by referring to the user's past learning data. 2. The system of claim 1, (Appendix 26) The learning support unit includes: When providing learning assistance, different assistance algorithms are applied according to the user's learning style. 2. The system of claim 1, (Appendix 27) The learning support unit includes: Estimating a user's emotions and determining the priority of learning support based on the estimated user's emotions 2. The system of claim 1, (Appendix 28) The learning support unit includes: When providing learning support, the system selects an appropriate support method by taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 29) The learning support unit includes: Analyzing users' social media activities to provide relevant support during learning 2. The system of claim 1, [Explanation of symbols]

[0181] 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 collection unit that collects a user's learning history; an evaluation unit that analyzes the data collected by the collection unit and evaluates the pronunciation and conversation ability of the user; a generation unit that generates a conversation scenario corresponding to a specific weakness of the user based on a result of the evaluation by the evaluation unit; a learning support unit that has a dialogue with the user based on the dialogue scenario generated by the generation unit; A system characterized by:

2. The generation unit is generating exercises based on the evaluation results by the evaluation unit; The learning support unit includes: Providing the user with the exercises 2. The system of claim 1 .

3. The generation unit is Generate a conversation scenario based on the user's future occupation or lifestyle 2. The system of claim 1 .

4. The learning support unit includes: Providing individually tailored pronunciation exercises for the user based on the characteristics of the user's voice 2. The system of claim 1 .

5. The generation unit is A conversation scenario is generated based on the behavior of the user's pet, the conversation scenario being adapted to a specific weakness of the user and for advancing learning together with the pet.

2. The system of claim 1 .

6. The collecting unit includes: The user's emotion is estimated, and a timing for collecting a learning history is adjusted based on the estimated emotion of the user.

2. The system of claim 1 .

7. The collecting unit includes: Analyze the user's past learning history and select an appropriate collection method.

2. The system of claim 1 .

8. The collecting unit includes: When collecting learning history, filtering is performed based on the user's current learning progress and areas of interest.

2. The system of claim 1 .

9. The collecting unit includes: A feeling of the user is estimated, and a priority order of learning histories to be collected is determined based on the estimated feeling of the user.

2. The system of claim 1 .

10. The collecting unit includes: When collecting learning histories, the geographical location information of the user is taken into consideration to preferentially collect histories that are highly relevant.

2. The system of claim 1 .

Images