system

Abstract

The system according to the embodiment aims to efficiently support language education for children with developmental disabilities. [Solution] A system according to an embodiment includes a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects a child's voice. The analysis unit analyzes the voice data collected by the collection unit. The generation unit generates a dialogue based on the analysis results obtained by the analysis unit. The provision unit provides the dialogue generated by the generation unit to the child.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, when parents provide language education to their children with developmental disorders, there was a problem in that it was difficult to analyze the developmental status and provide repeated education.

[0005] The system according to the embodiment aims to efficiently support language education for children with developmental disabilities. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects the child's voice. The analysis unit analyzes the voice data collected by the collection unit. The generation unit generates a dialogue based on the analysis result obtained by the analysis unit. The provision unit provides the dialogue generated by the generation unit to the child. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently support language education for children with developmental disorders. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) An AI system according to an embodiment of the present invention is a system that supports language education for children with developmental disabilities. This system collects a child's speech, analyzes it with a generation AI, and generates and provides appropriate dialogue. For example, the system collects a child's words and speech using a speech recognition function, analyzes it with a generation AI, and evaluates the child's level of development. Based on this evaluation, the generation AI generates appropriate dialogue tailored to the child's development and presents it to the child. Furthermore, the generation AI continuously monitors the child's responses and adjusts the content of the dialogue according to the child's level of development. This enables parents to provide appropriate education tailored to the child's developmental status, even while working. This allows the AI ​​system to support language education for children with developmental disabilities and provide appropriate education, even while working. For example, collecting a child's words and speech, analyzing them with a generation AI, and generating appropriate dialogue can promote a child's development.

[0029] The AI ​​system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects a child's voice. The child's voice may include, but is not limited to, speech, shouting, laughter, etc. The collection unit collects the voice using, for example, a microphone. The collection unit may also convert the voice data into text data using voice recognition technology. For example, the collection unit may analyze the voice using voice recognition software and save the text data. The analysis unit analyzes the voice data collected by the collection unit. The analysis may be performed using, for example, voice recognition technology or emotion analysis technology, but is not limited to these examples. For example, the analysis unit may analyze the voice data using voice recognition technology to evaluate the child's developmental level. The analysis unit may also analyze the child's emotions using emotion analysis technology. The generation unit generates a dialogue based on the analysis results obtained by the analysis unit. The generation may be performed using, for example, natural language generation technology or dialogue scenario generation technology, but is not limited to these examples. For example, the generation unit may use a generation AI to generate a dialogue according to the child's developmental level. The generation unit can also use the generation AI to monitor the child's reaction and adjust the content of the dialogue. The provision unit provides the dialogue generated by the generation unit to the child. The provision can be performed, for example, using audio output or screen display, but is not limited to these examples. For example, the provision unit provides the dialogue using audio output. The provision unit can also provide the dialogue using screen display. In this way, the AI ​​system according to the embodiment supports language education for children with developmental disabilities and enables parents to provide appropriate education even while working.

[0030] The generation unit can evaluate the child's developmental level using the generation AI. The generation unit evaluates the child's developmental level, for example, using the generation AI. The generation AI is realized using technologies such as a deep learning model or a reinforcement learning model. For example, the generation unit evaluates the child's developmental level using a deep learning model. The generation unit can also evaluate the child's developmental level using a reinforcement learning model. In this way, by evaluating the child's developmental level using the generation AI, more appropriate dialogue can be generated.

[0031] The providing unit can provide the generated dialogue to the child. For example, the providing unit provides the generated dialogue to the child using audio output. For example, the providing unit provides the dialogue by voice using a speaker. The providing unit can also provide the generated dialogue to the child using a screen display. For example, the providing unit displays the dialogue in text using a display. In this way, providing the generated dialogue to the child can support the child's development.

[0032] The generation unit can monitor the child's reactions using a generation AI and adjust the content of the dialogue. The generation unit, for example, monitors the child's reactions using a generation AI. The generation AI is realized using technologies such as a deep learning model or a reinforcement learning model. For example, the generation unit monitors the child's reactions using a deep learning model. The generation unit can also monitor the child's reactions using a reinforcement learning model. The generation unit, for example, adjusts the content of the dialogue using a generation AI. The generation AI is realized using technologies such as a deep learning model or a reinforcement learning model. For example, the generation unit adjusts the content of the dialogue using a deep learning model. The generation unit can also adjust the content of the dialogue using a reinforcement learning model. In this way, by monitoring the child's reactions and adjusting the content of the dialogue, more effective education is possible.

[0033] The collection unit can collect words or sounds uttered by the child. For example, the collection unit collects words or sounds uttered by the child using a microphone. For example, the collection unit collects the child's spoken words using the microphone. The collection unit can also collect the child's cries using the microphone. The collection unit can also collect the child's laughter using the microphone. In this way, appropriate data can be obtained by collecting the words and sounds uttered by the child.

[0034] The analysis unit can analyze the collected voice data and evaluate the child's development level. The analysis unit, for example, analyzes the collected voice data using voice recognition technology. For example, the analysis unit converts the collected voice data into text data using voice recognition technology. The analysis unit can also analyze the collected voice data using emotion analysis technology. For example, the analysis unit analyzes the child's emotions from the collected voice data using emotion analysis technology. The analysis unit, for example, evaluates the child's development level based on the collected voice data. The evaluation of the development level is performed based on criteria such as, for example, language ability and sociality, but is not limited to such examples. For example, the analysis unit evaluates the child's development level based on language ability. The analysis unit can also evaluate the child's development level based on sociality. In this way, by analyzing the collected voice data and evaluating the child's development level, an appropriate dialogue can be generated.

[0035] The collection unit can analyze the child's past voice data and select an appropriate collection method. The collection unit, for example, analyzes the child's past voice data. The past voice data includes, for example, recorded data and voice files, but is not limited to these examples. For example, the collection unit analyzes the past recorded data to identify topics that the child liked to talk about. The collection unit can also analyze the past voice files to identify time periods in which the child spoke. The collection unit selects an appropriate collection method based on the past voice data, for example. For example, the collection unit selects topics of voice data to collect based on topics that the child liked to talk about in the past. The collection unit can also select an optimal collection time based on time periods in which the child spoke in the past. The collection unit can also select a format of voice data to collect based on word patterns used by the child in the past. In this way, the optimal collection method can be selected by analyzing the past voice data.

[0036] The collection unit may filter the voice data based on the child's current activity status and environment when collecting the voice data. For example, the collection unit may monitor the child's current activity status when collecting the voice data. Examples of the activity status include, but are not limited to, the type of play and the progress of learning. For example, when the child is playing, the collection unit may preferentially collect voice data related to the activity. Furthermore, when the child is studying, the collection unit may also collect voice data related to the content of the study. For example, the collection unit may monitor the child's current environment when collecting the voice data. Examples of the environment include, but are not limited to, the ambient noise level and location. For example, when the child is out, the collection unit may select the voice data to be collected by filtering the ambient environmental sounds. Furthermore, when the child is at home, the collection unit may preferentially collect voice data within the home. In this way, by filtering based on the child's current activity status and environment, more relevant data can be collected.

[0037] When collecting voice data, the collection unit can select a collection means according to the frequency and pattern of the child's speech. The collection unit, for example, monitors the frequency and pattern of the child's speech. The frequency and pattern of speech include, but are not limited to, the number of times the child speaks and the rhythm of the speech. For example, if the child speaks frequently, the collection unit can collect voice data in real time. Furthermore, if the child speaks in a specific pattern, the collection unit can adjust the collection means to match the pattern. Furthermore, if the child does not speak for a long period of time, the collection unit can collect voice data periodically. In this way, efficient data collection is possible by selecting a collection means according to the frequency and pattern of speech.

[0038] When collecting voice data, the collection unit can prioritize collecting highly relevant data based on the child's geographical location information. The collection unit, for example, acquires the child's geographical location information using GPS data. For example, the collection unit identifies the child's current location using the GPS data. The collection unit can also acquire the child's geographical location information using a location information service. The collection unit, for example, prioritizes collecting highly relevant data based on the child's geographical location information. For example, when the child is in a park, the collection unit prioritizes collecting voice data related to the park. Furthermore, when the child is at school, the collection unit can also prioritize collecting voice data related to the school. Furthermore, when the child is at home, the collection unit can prioritize collecting voice data within the home. In this way, highly relevant data can be prioritized by taking the geographical location information into consideration.

[0039] When collecting the voice data, the collection unit can analyze the child's social media activities and collect related data. The collection unit, for example, analyzes the child's social media activities. Social media activities include, but are not limited to, posted content and comment history. For example, the collection unit analyzes content posted by the child on social media and collects related voice data. The collection unit can also analyze accounts the child follows on social media and collect related voice data. The collection unit can also analyze groups the child participates in on social media and collect related voice data. In this way, related data can be collected by analyzing social media activities.

[0040] The collection unit can customize the collection method by reflecting the child's past feedback when collecting voice data. The collection unit, for example, collects the child's past feedback. Past feedback includes, but is not limited to, survey results and user reviews. For example, the collection unit analyzes past survey results to identify a collection method that the child preferred. The collection unit can also analyze past user reviews to identify a collection method that the child disliked. The collection unit customizes the collection method based on, for example, the past feedback. For example, the collection unit customizes the current collection method based on the child's past preferred collection method. The collection unit can also adjust the current collection method to avoid a collection method that the child disliked in the past. The collection unit can also continuously improve the collection method based on the child's past feedback. In this way, the collection method can be customized by reflecting the past feedback.

[0041] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the audio data. The analysis unit, for example, evaluates the importance of the audio data. The importance of the audio data includes, but is not limited to, the importance of the content of the speech and the strength of the emotion. For example, the analysis unit evaluates the importance of the audio data based on the importance of the content of the speech. The analysis unit can also evaluate the importance of the audio data based on the strength of the emotion. The analysis unit adjusts the level of detail of the analysis based on, for example, the importance of the audio data. For example, the analysis unit performs a detailed analysis on important audio data. The analysis unit can also perform a concise analysis on general audio data. The analysis unit can also perform a focused analysis on audio data related to a specific topic. This enables efficient analysis by adjusting the level of detail of the analysis based on the importance of the audio data.

[0042] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the audio data. The analysis unit, for example, classifies the category of the audio data. The categories of the audio data include, but are not limited to, emotion categories and content categories. For example, the analysis unit classifies the audio data into emotion categories. The analysis unit can also classify the audio data into content categories. The analysis unit applies different analysis algorithms depending on the category of the audio data. For example, the analysis unit applies an educational analysis algorithm to audio data related to learning. The analysis unit can also apply a conversation analysis algorithm to audio data related to everyday conversations. The analysis unit can also apply an emotion analysis algorithm to audio data related to emotional expressions. In this way, applying different analysis algorithms depending on the category enables more accurate analysis.

[0043] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the child's past analysis results. The analysis unit, for example, collects the child's past analysis results. Past analysis results include, but are not limited to, past analysis reports and analysis databases. For example, the analysis unit analyzes the past analysis reports and adjusts the current analysis algorithm. The analysis unit can also improve the accuracy of the analysis by referring to the past analysis database. For example, the analysis unit optimizes analysis parameters based on the past analysis results. For example, the analysis unit adjusts parameters of the current analysis algorithm based on the past analysis results. The analysis unit can also add data to improve the accuracy of the analysis based on the past analysis results. In this way, the accuracy of the analysis can be improved by referring to the past analysis results.

[0044] During analysis, the analysis unit can determine the priority of analysis based on the time when the voice data was collected. The analysis unit, for example, records the time when the voice data was collected. The collection time includes, but is not limited to, for example, the collection date and time and the collection frequency. For example, the analysis unit records the collection date and time of the voice data and prioritizes analyzing the most recent voice data. The analysis unit can also prioritize analyzing voice data collected during a specific time period. The analysis unit can also analyze current voice data while referring to past voice data. In this way, by determining the priority of analysis based on the collection date and time, the most recent data can be prioritized for analysis.

[0045] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the audio data. The analysis unit, for example, evaluates the relevance of the audio data. The relevance of the audio data includes, but is not limited to, for example, content relevance and emotional relevance. For example, the analysis unit evaluates the relevance of the audio data based on content relevance. The analysis unit can also evaluate the relevance of the audio data based on emotional relevance. The analysis unit adjusts the order of analysis based on, for example, the relevance of the audio data. For example, the analysis unit prioritizes analyzing audio data related to important topics. The analysis unit can also prioritize analyzing audio data related to a child's interests. The analysis unit can also prioritize analyzing audio data related to a child's learning progress. In this way, by adjusting the order of analysis based on relevance, important data can be analyzed preferentially.

[0046] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the child's level of expertise. The analysis unit, for example, evaluates the child's level of expertise. Examples of the level of expertise include, but are not limited to, the child's grade and past learning history. For example, the analysis unit evaluates the level of expertise based on the child's grade. The analysis unit can also evaluate the level of expertise based on the child's past learning history. The analysis unit adjusts the use of technical terms in the analysis according to the child's level of expertise. For example, if the child is a beginner, the analysis unit can use simple technical terms. If the child is an intermediate learner, the analysis unit can use moderate technical terms. If the child is an advanced learner, the analysis unit can use detailed technical terms. In this way, by adjusting the use of technical terms according to the level of expertise, it is possible to provide analysis results that are suitable for the child.

[0047] When generating a dialogue, the generation unit can adjust the level of detail of the dialogue based on the child's level of development. The generation unit, for example, evaluates the child's level of development. The level of development includes, but is not limited to, language ability and sociality. For example, the generation unit evaluates the level of development based on the child's language ability. The generation unit can also evaluate the level of development based on the child's sociality. The generation unit adjusts the level of detail of the dialogue based on the child's level of development. For example, if the child is a beginner, the generation unit can generate a simple dialogue. If the child is an intermediate learner, the generation unit can also generate a dialogue with an appropriate level of detail. If the child is an advanced learner, the generation unit can also generate a detailed dialogue. In this way, by adjusting the level of detail of the dialogue based on the level of development, it is possible to provide a dialogue that is suitable for the child.

[0048] When generating a dialogue, the generation unit can apply different dialogue algorithms depending on the child's interests and concerns. The generation unit, for example, evaluates the child's interests and concerns. Interests and concerns include, but are not limited to, favorite topics and themes of interest. For example, the generation unit evaluates the child's interests and concerns based on topics the child likes. The generation unit can also evaluate the child's interests and concerns based on themes in which the child is interested. The generation unit applies different dialogue algorithms depending on the child's interests and concerns. For example, the generation unit generates dialogue related to topics in which the child is interested. The generation unit can also generate dialogue based on themes in which the child is interested. The generation unit can also generate dialogue that is likely to be interesting based on the child's past dialogue history. In this way, by applying a dialogue algorithm depending on the child's interests and concerns, it is possible to provide a dialogue that is suitable for the child.

[0049] When generating a dialogue, the generation unit can improve the accuracy of the dialogue by referring to past dialogue results of the child. The generation unit, for example, collects past dialogue results of the child. Past dialogue results include, but are not limited to, dialogue logs and dialogue histories. For example, the generation unit analyzes past dialogue logs and adjusts a current dialogue algorithm. The generation unit can also improve the accuracy of the dialogue by referring to the past dialogue history. The generation unit, for example, optimizes dialogue parameters based on past dialogue results. For example, the generation unit adjusts parameters of a current dialogue algorithm based on past dialogue results. The generation unit can also add data for improving the accuracy of the dialogue based on past dialogue results. In this way, the accuracy of the dialogue can be improved by referring to past dialogue results.

[0050] When generating a dialogue, the generation unit can determine the priority of the dialogue based on the time when the child spoke. The generation unit, for example, records the time when the child spoke. The time when the child spoke includes, but is not limited to, the timing of the speech and the frequency of the speech. For example, the generation unit records the timing of the child's speech and preferentially generates a dialogue related to a topic that was recently spoken. The generation unit can also record the frequency of the child's speech and generate a dialogue based on the content of speech made during a specific time period. The generation unit can also preferentially generate a dialogue related to a topic that the child frequently spoke about in the past. In this way, by determining the priority of the dialogue based on the time when the speech was made, important dialogues can be provided preferentially.

[0051] When generating dialogues, the generation unit can adjust the order of dialogues based on the relevance of the child. The generation unit, for example, evaluates the relevance of the child. Relevance includes, but is not limited to, content relevance and emotional relevance. For example, the generation unit evaluates the relevance of the child based on content relevance. The generation unit can also evaluate the relevance of the child based on emotional relevance. The generation unit adjusts the order of dialogues based on the relevance of the child. For example, the generation unit prioritizes generating dialogues related to topics in which the child is interested. The generation unit can also prioritize generating dialogues related to topics the child is studying. The generation unit can also prioritize generating dialogues related to words that the child frequently uses in daily life. In this way, by adjusting the order of dialogues based on relevance, important dialogues can be provided preferentially.

[0052] When generating a dialogue, the generation unit may adjust the use of technical terms in the dialogue according to the child's level of expertise. The generation unit, for example, evaluates the child's level of expertise. Examples of the level of expertise include, but are not limited to, the child's grade and past learning history. For example, the generation unit may evaluate the level of expertise based on the child's grade. The generation unit may also evaluate the level of expertise based on the child's past learning history. The generation unit may adjust the use of technical terms in the dialogue according to the child's level of expertise. For example, if the child is a beginner, the generation unit may generate a dialogue using simple technical terms. If the child is an intermediate learner, the generation unit may generate a dialogue using moderate technical terms. If the child is an advanced learner, the generation unit may generate a dialogue using detailed technical terms. In this way, by adjusting the use of technical terms according to the level of expertise, a dialogue suitable for the child can be provided.

[0053] The providing unit can select an appropriate delivery method by referring to the child's past responses when providing dialogue. The providing unit, for example, collects the child's past responses. Past responses include, but are not limited to, dialogue logs and feedback data. For example, the providing unit analyzes past dialogue logs to identify a delivery method that the child preferred. The providing unit can also analyze past feedback data to identify a delivery method that the child disliked. The providing unit selects a delivery method based on, for example, past responses. For example, the providing unit selects a current delivery method based on delivery methods that the child preferred in the past. The providing unit can also adjust the current delivery method to avoid delivery methods that the child disliked in the past. The providing unit can also continuously improve the delivery method based on the child's past responses. In this way, the optimal delivery method can be selected by referring to past responses.

[0054] When providing dialogue, the providing unit can customize the content to be provided based on the child's current activity status. The providing unit, for example, monitors the child's current activity status. The activity status includes, for example, the type of play and the progress of learning, but is not limited to such examples. For example, when the child is playing, the providing unit provides dialogue related to the activity. Furthermore, when the child is studying, the providing unit can also provide dialogue related to the content of the study. Furthermore, when the child is out and about, the providing unit can also provide dialogue related to the surrounding environment. The providing unit customizes the content to be provided based on the child's current activity status. For example, when the child is playing, the providing unit provides dialogue related to the activity. Furthermore, when the child is studying, the providing unit can also provide dialogue related to the content of the study. Furthermore, when the child is out and about, the providing unit can also provide dialogue related to the surrounding environment. In this way, by customizing the content to be provided based on the child's current activity status, dialogue suitable for the child can be provided.

[0055] The providing unit can improve the providing method by reflecting the child's feedback when providing dialogue. The providing unit, for example, collects the child's feedback. The feedback includes, for example, survey results and user reviews, but is not limited to these examples. For example, the providing unit analyzes the survey results to identify dialogue content that the child likes. The providing unit can also analyze the user reviews to identify dialogue content that the child dislikes. The providing unit improves the providing method based on the feedback, for example. For example, the providing unit improves the providing method based on the dialogue content that the child likes. The providing unit can also adjust the providing method to avoid dialogue content that the child dislikes. The providing unit can also continuously improve the providing method based on the child's feedback. In this way, the providing method can be continuously improved by reflecting the feedback.

[0056] When providing dialogue, the providing unit can select the optimal providing method by taking into consideration the geographical location information of the child. The providing unit, for example, acquires the geographical location information of the child using GPS data. For example, the providing unit identifies the child's current location using the GPS data. The providing unit can also acquire the child's geographical location information using a location information service. The providing unit selects the optimal providing method based on the child's geographical location information, for example. For example, if the child is in a park, the providing unit can provide dialogue related to the park. Also, if the child is at school, the providing unit can provide dialogue related to the school. Also, if the child is at home, the providing unit can provide dialogue within the home. In this way, the optimal providing method can be selected by taking into consideration the geographical location information.

[0057] The providing unit can analyze the child's social media activity to customize the content to be provided when providing dialogue. The providing unit, for example, analyzes the child's social media activity. Social media activity includes, for example, but is not limited to, posted content and comment history. For example, the providing unit can analyze content posted by the child on social media and provide related dialogue. The providing unit can also analyze accounts the child follows on social media and provide related dialogue. The providing unit can also analyze groups the child participates in on social media and provide related dialogue. In this way, related dialogue can be provided by analyzing social media activity.

[0058] The providing unit can customize the delivery method by reflecting the child's past feedback when providing dialogue. The providing unit, for example, collects the child's past feedback. Past feedback includes, but is not limited to, survey results and user reviews. For example, the providing unit analyzes the survey results to identify a delivery method that the child prefers. The providing unit can also analyze user reviews to identify a delivery method that the child dislikes. The providing unit customizes the delivery method based on, for example, the past feedback. For example, the providing unit customizes the current delivery method based on delivery methods that the child preferred in the past. The providing unit can also adjust the current delivery method to avoid delivery methods that the child disliked in the past. The providing unit can also continuously improve the delivery method based on the child's past feedback. In this way, the delivery method can be customized by reflecting past feedback.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The analysis unit can also analyze the child's physical movements and gestures when assessing the child's developmental level. For example, the analysis unit can capture the child's movements using a camera and analyze the child's physical movements using motion analysis technology. The analysis unit can also analyze the child's gestures and use them as auxiliary information for language development. This allows for a more comprehensive assessment of the child's developmental level by taking into account not only voice data but also physical movements and gestures.

[0061] When providing the generated dialogue, the providing unit can add visual elements to attract the child's interest. For example, it can display illustrations or animations related to the dialogue content. The providing unit can also incorporate interactive game elements depending on the dialogue content. In this way, adding visual and interactive elements can attract the child's interest and improve learning effectiveness.

[0062] The generator can also take into account data on a child's social interactions when using the generative AI to evaluate a child's level of development. For example, it can observe how a child communicates with other children and adults and analyze that data. The generator can also evaluate the child's level of social development based on data on their friendships and group activities. This allows for a comprehensive evaluation of not only language ability but also social development.

[0063] The collection unit may also have a function for filtering out environmental sounds when collecting the child's voice data. For example, the collection unit may remove ambient noise and clearly collect only the child's voice. The collection unit may also emphasize specific frequency bands to collect the child's voice more clearly. This minimizes the influence of environmental sounds and allows for more accurate collection of voice data.

[0064] When analyzing the collected voice data, the analysis unit can also evaluate the rhythm and intonation of the child's speech. For example, the analysis unit can analyze the rhythm of the child's speech and use it as an indicator of language development. The analysis unit can also analyze the intonation of the child's speech to infer emotions and intentions. This allows for more accurate analysis by taking into account not only the content of the speech but also the rhythm and intonation.

[0065] The processing flow of the first embodiment will be briefly explained below.

[0066] Step 1: The collection unit collects the child's voice. The child's voice may include talking, shouting, laughing, etc. The collection unit may collect the voice using a microphone and convert the voice data into text data using voice recognition technology. For example, the collection unit may analyze the voice using voice recognition software and save it as text data. Step 2: The analysis unit analyzes the voice data collected by the collection unit. The analysis is performed using voice recognition technology and emotion analysis technology. For example, the analysis unit may analyze the voice data using voice recognition technology to evaluate the child's developmental level. The analysis unit may also analyze the child's emotions using emotion analysis technology. Step 3: The generation unit generates a dialogue based on the analysis results obtained by the analysis unit. This is done using natural language generation technology and dialogue scenario generation technology. For example, the generation unit uses a generation AI to generate dialogue that is appropriate for the child's level of development. The generation unit can also use a generation AI to monitor the child's reactions and adjust the content of the dialogue. Step 4: The providing unit provides the dialogue generated by the generating unit to the child. The providing unit provides the dialogue using audio output or a screen display. For example, the providing unit provides the dialogue using audio output. The providing unit can also provide the dialogue using a screen display.

[0067] (Example 2) An AI system according to an embodiment of the present invention is a system that supports language education for children with developmental disabilities. This system collects a child's speech, analyzes it with a generation AI, and generates and provides appropriate dialogue. For example, the system collects a child's words and speech using a speech recognition function, analyzes it with a generation AI, and evaluates the child's level of development. Based on this evaluation, the generation AI generates appropriate dialogue tailored to the child's development and presents it to the child. Furthermore, the generation AI continuously monitors the child's responses and adjusts the content of the dialogue according to the child's level of development. This enables parents to provide appropriate education tailored to the child's developmental status, even while working. This allows the AI ​​system to support language education for children with developmental disabilities and provide appropriate education, even while working. For example, collecting a child's words and speech, analyzing them with a generation AI, and generating appropriate dialogue can promote a child's development.

[0068] The AI ​​system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects a child's voice. The child's voice may include, but is not limited to, speech, shouting, laughter, etc. The collection unit collects the voice using, for example, a microphone. The collection unit may also convert the voice data into text data using voice recognition technology. For example, the collection unit may analyze the voice using voice recognition software and save the text data. The analysis unit analyzes the voice data collected by the collection unit. The analysis may be performed using, for example, voice recognition technology or emotion analysis technology, but is not limited to these examples. For example, the analysis unit may analyze the voice data using voice recognition technology to evaluate the child's developmental level. The analysis unit may also analyze the child's emotions using emotion analysis technology. The generation unit generates a dialogue based on the analysis results obtained by the analysis unit. The generation may be performed using, for example, natural language generation technology or dialogue scenario generation technology, but is not limited to these examples. For example, the generation unit may use a generation AI to generate a dialogue according to the child's developmental level. The generation unit can also use the generation AI to monitor the child's reaction and adjust the content of the dialogue. The provision unit provides the dialogue generated by the generation unit to the child. The provision can be performed, for example, using audio output or screen display, but is not limited to these examples. For example, the provision unit provides the dialogue using audio output. The provision unit can also provide the dialogue using screen display. In this way, the AI ​​system according to the embodiment supports language education for children with developmental disabilities and enables parents to provide appropriate education even while working.

[0069] The generation unit can evaluate the child's developmental level using the generation AI. The generation unit evaluates the child's developmental level, for example, using the generation AI. The generation AI is realized using technologies such as a deep learning model or a reinforcement learning model. For example, the generation unit evaluates the child's developmental level using a deep learning model. The generation unit can also evaluate the child's developmental level using a reinforcement learning model. In this way, by evaluating the child's developmental level using the generation AI, more appropriate dialogue can be generated.

[0070] The providing unit can provide the generated dialogue to the child. For example, the providing unit provides the generated dialogue to the child using audio output. For example, the providing unit provides the dialogue by voice using a speaker. The providing unit can also provide the generated dialogue to the child using a screen display. For example, the providing unit displays the dialogue in text using a display. In this way, providing the generated dialogue to the child can support the child's development.

[0071] The generation unit can monitor the child's reactions using a generation AI and adjust the content of the dialogue. The generation unit, for example, monitors the child's reactions using a generation AI. The generation AI is realized using technologies such as a deep learning model or a reinforcement learning model. For example, the generation unit monitors the child's reactions using a deep learning model. The generation unit can also monitor the child's reactions using a reinforcement learning model. The generation unit, for example, adjusts the content of the dialogue using a generation AI. The generation AI is realized using technologies such as a deep learning model or a reinforcement learning model. For example, the generation unit adjusts the content of the dialogue using a deep learning model. The generation unit can also adjust the content of the dialogue using a reinforcement learning model. In this way, by monitoring the child's reactions and adjusting the content of the dialogue, more effective education is possible.

[0072] The collection unit can collect words or sounds uttered by the child. For example, the collection unit collects words or sounds uttered by the child using a microphone. For example, the collection unit collects the child's spoken words using the microphone. The collection unit can also collect the child's cries using the microphone. The collection unit can also collect the child's laughter using the microphone. In this way, appropriate data can be obtained by collecting the words and sounds uttered by the child.

[0073] The analysis unit can analyze the collected voice data and evaluate the child's development level. The analysis unit, for example, analyzes the collected voice data using voice recognition technology. For example, the analysis unit converts the collected voice data into text data using voice recognition technology. The analysis unit can also analyze the collected voice data using emotion analysis technology. For example, the analysis unit analyzes the child's emotions from the collected voice data using emotion analysis technology. The analysis unit, for example, evaluates the child's development level based on the collected voice data. The evaluation of the development level is performed based on criteria such as, for example, language ability and sociality, but is not limited to such examples. For example, the analysis unit evaluates the child's development level based on language ability. The analysis unit can also evaluate the child's development level based on sociality. In this way, by analyzing the collected voice data and evaluating the child's development level, an appropriate dialogue can be generated.

[0074] The collection unit can estimate the child's emotion and adjust the timing of collecting voice data based on the estimated child's emotion. The collection unit, for example, estimates the child's emotion using facial expression recognition technology. For example, the collection unit captures the child's facial expression using a camera and estimates the emotion using facial expression recognition technology. The collection unit can also estimate the child's emotion using voice analysis technology. For example, the collection unit analyzes the tone and speed of the child's voice using voice recognition technology to estimate the emotion. The collection unit adjusts the timing of collecting voice data based on the estimated child's emotion. For example, if the child is relaxed, the collection unit collects voice data during natural conversation. If the child is excited, the collection unit can wait until the child calms down before collecting voice data. If the child is tired, the collection unit can collect voice data after a break. In this way, by adjusting the timing of collecting voice data based on the child's emotion, more natural data collection is possible.

[0075] The collection unit can analyze the child's past voice data and select an appropriate collection method. The collection unit, for example, analyzes the child's past voice data. The past voice data includes, for example, recorded data and voice files, but is not limited to these examples. For example, the collection unit analyzes the past recorded data to identify topics that the child liked to talk about. The collection unit can also analyze the past voice files to identify time periods in which the child spoke. The collection unit selects an appropriate collection method based on the past voice data, for example. For example, the collection unit selects topics of voice data to collect based on topics that the child liked to talk about in the past. The collection unit can also select an optimal collection time based on time periods in which the child spoke in the past. The collection unit can also select a format of voice data to collect based on word patterns used by the child in the past. In this way, the optimal collection method can be selected by analyzing the past voice data.

[0076] The collection unit may filter the voice data based on the child's current activity status and environment when collecting the voice data. For example, the collection unit may monitor the child's current activity status when collecting the voice data. Examples of the activity status include, but are not limited to, the type of play and the progress of learning. For example, when the child is playing, the collection unit may preferentially collect voice data related to the activity. Furthermore, when the child is studying, the collection unit may also collect voice data related to the content of the study. For example, the collection unit may monitor the child's current environment when collecting the voice data. Examples of the environment include, but are not limited to, the ambient noise level and location. For example, when the child is out, the collection unit may select the voice data to be collected by filtering the ambient environmental sounds. Furthermore, when the child is at home, the collection unit may preferentially collect voice data within the home. In this way, by filtering based on the child's current activity status and environment, more relevant data can be collected.

[0077] When collecting voice data, the collection unit can select a collection means according to the frequency and pattern of the child's speech. The collection unit, for example, monitors the frequency and pattern of the child's speech. The frequency and pattern of speech include, but are not limited to, the number of times the child speaks and the rhythm of the speech. For example, if the child speaks frequently, the collection unit can collect voice data in real time. Furthermore, if the child speaks in a specific pattern, the collection unit can adjust the collection means to match the pattern. Furthermore, if the child does not speak for a long period of time, the collection unit can collect voice data periodically. In this way, efficient data collection is possible by selecting a collection means according to the frequency and pattern of speech.

[0078] The collection unit can estimate the child's emotion and determine the priority of the voice data to be collected based on the estimated emotion of the child. The collection unit, for example, estimates the child's emotion using facial expression recognition technology. For example, the collection unit captures the child's facial expression using a camera and estimates the emotion using facial expression recognition technology. The collection unit can also estimate the child's emotion using voice analysis technology. For example, the collection unit analyzes the tone and speed of the child's voice using voice recognition technology to estimate the emotion. The collection unit determines the priority of the voice data to be collected based on the estimated emotion of the child. For example, if the child is excited, the collection unit can prioritize collecting voice data related to the emotion. If the child is relaxed, the collection unit can prioritize collecting voice data of everyday conversation. If the child is sad, the collection unit can prioritize collecting voice data expressing the emotion. In this way, by prioritizing the voice data based on the emotion, important data can be collected preferentially.

[0079] When collecting voice data, the collection unit can prioritize collecting highly relevant data based on the child's geographical location information. The collection unit, for example, acquires the child's geographical location information using GPS data. For example, the collection unit identifies the child's current location using the GPS data. The collection unit can also acquire the child's geographical location information using a location information service. The collection unit, for example, prioritizes collecting highly relevant data based on the child's geographical location information. For example, when the child is in a park, the collection unit prioritizes collecting voice data related to the park. Furthermore, when the child is at school, the collection unit can also prioritize collecting voice data related to the school. Furthermore, when the child is at home, the collection unit can prioritize collecting voice data within the home. In this way, highly relevant data can be prioritized by taking the geographical location information into consideration.

[0080] When collecting the voice data, the collection unit can analyze the child's social media activities and collect related data. The collection unit, for example, analyzes the child's social media activities. Social media activities include, but are not limited to, posted content and comment history. For example, the collection unit analyzes content posted by the child on social media and collects related voice data. The collection unit can also analyze accounts the child follows on social media and collect related voice data. The collection unit can also analyze groups the child participates in on social media and collect related voice data. In this way, related data can be collected by analyzing social media activities.

[0081] The collection unit can customize the collection method by reflecting the child's past feedback when collecting voice data. The collection unit, for example, collects the child's past feedback. Past feedback includes, but is not limited to, survey results and user reviews. For example, the collection unit analyzes past survey results to identify a collection method that the child preferred. The collection unit can also analyze past user reviews to identify a collection method that the child disliked. The collection unit customizes the collection method based on, for example, the past feedback. For example, the collection unit customizes the current collection method based on the child's past preferred collection method. The collection unit can also adjust the current collection method to avoid a collection method that the child disliked in the past. The collection unit can also continuously improve the collection method based on the child's past feedback. In this way, the collection method can be customized by reflecting the past feedback.

[0082] The analysis unit can estimate the child's emotion and adjust the expression method of the analysis based on the estimated emotion of the child. The analysis unit, for example, estimates the child's emotion using facial expression recognition technology. For example, the analysis unit captures the child's facial expression using a camera and estimates the emotion using facial expression recognition technology. The analysis unit can also estimate the child's emotion using voice analysis technology. For example, the analysis unit analyzes the tone and speed of the child's voice using voice recognition technology to estimate the emotion. The analysis unit adjusts the expression method of the analysis based on the estimated emotion of the child. For example, the analysis unit can provide a detailed analysis result if the child is relaxed. The analysis unit can also provide a concise analysis result if the child is excited. The analysis unit can also provide a gentle analysis result if the child is sad. In this way, by adjusting the expression method of the analysis based on the emotion, it is possible to provide an analysis result that is suitable for the child.

[0083] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the audio data. The analysis unit, for example, evaluates the importance of the audio data. The importance of the audio data includes, but is not limited to, the importance of the content of the speech and the strength of the emotion. For example, the analysis unit evaluates the importance of the audio data based on the importance of the content of the speech. The analysis unit can also evaluate the importance of the audio data based on the strength of the emotion. The analysis unit adjusts the level of detail of the analysis based on, for example, the importance of the audio data. For example, the analysis unit performs a detailed analysis on important audio data. The analysis unit can also perform a concise analysis on general audio data. The analysis unit can also perform a focused analysis on audio data related to a specific topic. This enables efficient analysis by adjusting the level of detail of the analysis based on the importance of the audio data.

[0084] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the audio data. The analysis unit, for example, classifies the category of the audio data. The categories of the audio data include, but are not limited to, emotion categories and content categories. For example, the analysis unit classifies the audio data into emotion categories. The analysis unit can also classify the audio data into content categories. The analysis unit applies different analysis algorithms depending on the category of the audio data. For example, the analysis unit applies an educational analysis algorithm to audio data related to learning. The analysis unit can also apply a conversation analysis algorithm to audio data related to everyday conversations. The analysis unit can also apply an emotion analysis algorithm to audio data related to emotional expressions. In this way, applying different analysis algorithms depending on the category enables more accurate analysis.

[0085] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the child's past analysis results. The analysis unit, for example, collects the child's past analysis results. Past analysis results include, but are not limited to, past analysis reports and analysis databases. For example, the analysis unit analyzes the past analysis reports and adjusts the current analysis algorithm. The analysis unit can also improve the accuracy of the analysis by referring to the past analysis database. For example, the analysis unit optimizes analysis parameters based on the past analysis results. For example, the analysis unit adjusts parameters of the current analysis algorithm based on the past analysis results. The analysis unit can also add data to improve the accuracy of the analysis based on the past analysis results. In this way, the accuracy of the analysis can be improved by referring to the past analysis results.

[0086] The analysis unit can estimate the child's emotion and adjust the length of the analysis based on the estimated emotion of the child. The analysis unit, for example, estimates the child's emotion using facial expression recognition technology. For example, the analysis unit captures the child's facial expression using a camera and estimates the emotion using facial expression recognition technology. The analysis unit can also estimate the child's emotion using voice analysis technology. For example, the analysis unit uses voice recognition technology to analyze the tone and speed of the child's voice and estimate the emotion. The analysis unit adjusts the length of the analysis based on the estimated emotion of the child. For example, the analysis unit can perform a detailed analysis if the child is relaxed. The analysis unit can also perform a brief analysis if the child is excited. The analysis unit can also perform a short analysis if the child is tired. In this way, by adjusting the length of the analysis based on the emotion, it is possible to provide an analysis result that is suitable for the child.

[0087] During analysis, the analysis unit can determine the priority of analysis based on the time when the voice data was collected. The analysis unit, for example, records the time when the voice data was collected. The collection time includes, but is not limited to, for example, the collection date and time and the collection frequency. For example, the analysis unit records the collection date and time of the voice data and prioritizes analyzing the most recent voice data. The analysis unit can also prioritize analyzing voice data collected during a specific time period. The analysis unit can also analyze current voice data while referring to past voice data. In this way, by determining the priority of analysis based on the collection date and time, the most recent data can be prioritized for analysis.

[0088] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the audio data. The analysis unit, for example, evaluates the relevance of the audio data. The relevance of the audio data includes, but is not limited to, for example, content relevance and emotional relevance. For example, the analysis unit evaluates the relevance of the audio data based on content relevance. The analysis unit can also evaluate the relevance of the audio data based on emotional relevance. The analysis unit adjusts the order of analysis based on, for example, the relevance of the audio data. For example, the analysis unit prioritizes analyzing audio data related to important topics. The analysis unit can also prioritize analyzing audio data related to a child's interests. The analysis unit can also prioritize analyzing audio data related to a child's learning progress. In this way, by adjusting the order of analysis based on relevance, important data can be analyzed preferentially.

[0089] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the child's level of expertise. The analysis unit, for example, evaluates the child's level of expertise. Examples of the level of expertise include, but are not limited to, the child's grade and past learning history. For example, the analysis unit evaluates the level of expertise based on the child's grade. The analysis unit can also evaluate the level of expertise based on the child's past learning history. The analysis unit adjusts the use of technical terms in the analysis according to the child's level of expertise. For example, if the child is a beginner, the analysis unit can use simple technical terms. If the child is an intermediate learner, the analysis unit can use moderate technical terms. If the child is an advanced learner, the analysis unit can use detailed technical terms. In this way, by adjusting the use of technical terms according to the level of expertise, it is possible to provide analysis results that are suitable for the child.

[0090] The generation unit can estimate the child's emotion and adjust the dialogue expression method based on the estimated child's emotion. The generation unit, for example, estimates the child's emotion using facial expression recognition technology. For example, the generation unit captures the child's facial expression using a camera and estimates the emotion using facial expression recognition technology. The generation unit can also estimate the child's emotion using voice analysis technology. For example, the generation unit analyzes the tone and speed of the child's voice using voice recognition technology to estimate the emotion. The generation unit adjusts the dialogue expression method based on the estimated child's emotion. For example, the generation unit can generate dialogue in a gentle tone if the child is relaxed. Also, the generation unit can generate dialogue in a calm tone if the child is excited. Also, the generation unit can generate dialogue in an encouraging tone if the child is sad. In this way, by adjusting the dialogue expression method based on the emotion, it is possible to provide a dialogue that is suitable for the child.

[0091] When generating a dialogue, the generation unit can adjust the level of detail of the dialogue based on the child's level of development. The generation unit, for example, evaluates the child's level of development. The level of development includes, but is not limited to, language ability and sociality. For example, the generation unit evaluates the level of development based on the child's language ability. The generation unit can also evaluate the level of development based on the child's sociality. The generation unit adjusts the level of detail of the dialogue based on the child's level of development. For example, if the child is a beginner, the generation unit can generate a simple dialogue. If the child is an intermediate learner, the generation unit can also generate a dialogue with an appropriate level of detail. If the child is an advanced learner, the generation unit can also generate a detailed dialogue. In this way, by adjusting the level of detail of the dialogue based on the level of development, it is possible to provide a dialogue that is suitable for the child.

[0092] When generating a dialogue, the generation unit can apply different dialogue algorithms depending on the child's interests and concerns. The generation unit, for example, evaluates the child's interests and concerns. Interests and concerns include, but are not limited to, favorite topics and themes of interest. For example, the generation unit evaluates the child's interests and concerns based on topics the child likes. The generation unit can also evaluate the child's interests and concerns based on themes in which the child is interested. The generation unit applies different dialogue algorithms depending on the child's interests and concerns. For example, the generation unit generates dialogue related to topics in which the child is interested. The generation unit can also generate dialogue based on themes in which the child is interested. The generation unit can also generate dialogue that is likely to be interesting based on the child's past dialogue history. In this way, by applying a dialogue algorithm depending on the child's interests and concerns, it is possible to provide a dialogue that is suitable for the child.

[0093] When generating a dialogue, the generation unit can improve the accuracy of the dialogue by referring to past dialogue results of the child. The generation unit, for example, collects past dialogue results of the child. Past dialogue results include, but are not limited to, dialogue logs and dialogue histories. For example, the generation unit analyzes past dialogue logs and adjusts a current dialogue algorithm. The generation unit can also improve the accuracy of the dialogue by referring to the past dialogue history. The generation unit, for example, optimizes dialogue parameters based on past dialogue results. For example, the generation unit adjusts parameters of a current dialogue algorithm based on past dialogue results. The generation unit can also add data for improving the accuracy of the dialogue based on past dialogue results. In this way, the accuracy of the dialogue can be improved by referring to past dialogue results.

[0094] The generation unit can estimate the child's emotion and adjust the length of the dialogue based on the estimated emotion of the child. The generation unit, for example, estimates the child's emotion using facial expression recognition technology. For example, the generation unit captures the child's facial expression using a camera and estimates the emotion using facial expression recognition technology. The generation unit can also estimate the child's emotion using voice analysis technology. For example, the generation unit analyzes the tone and speed of the child's voice using voice recognition technology to estimate the emotion. The generation unit adjusts the length of the dialogue based on the estimated emotion of the child. For example, the generation unit can generate a longer dialogue if the child is relaxed. The generation unit can also generate a shorter dialogue if the child is excited. The generation unit can also generate a concise dialogue if the child is tired. In this way, by adjusting the length of the dialogue based on the emotion, it is possible to provide a dialogue that is suitable for the child.

[0095] When generating a dialogue, the generation unit can determine the priority of the dialogue based on the time when the child spoke. The generation unit, for example, records the time when the child spoke. The time when the child spoke includes, but is not limited to, the timing of the speech and the frequency of the speech. For example, the generation unit records the timing of the child's speech and preferentially generates a dialogue related to a topic that was recently spoken. The generation unit can also record the frequency of the child's speech and generate a dialogue based on the content of speech made during a specific time period. The generation unit can also preferentially generate a dialogue related to a topic that the child frequently spoke about in the past. In this way, by determining the priority of the dialogue based on the time when the speech was made, important dialogues can be provided preferentially.

[0096] When generating dialogues, the generation unit can adjust the order of dialogues based on the relevance of the child. The generation unit, for example, evaluates the relevance of the child. Relevance includes, but is not limited to, content relevance and emotional relevance. For example, the generation unit evaluates the relevance of the child based on content relevance. The generation unit can also evaluate the relevance of the child based on emotional relevance. The generation unit adjusts the order of dialogues based on the relevance of the child. For example, the generation unit prioritizes generating dialogues related to topics in which the child is interested. The generation unit can also prioritize generating dialogues related to topics the child is studying. The generation unit can also prioritize generating dialogues related to words that the child frequently uses in daily life. In this way, by adjusting the order of dialogues based on relevance, important dialogues can be provided preferentially.

[0097] When generating a dialogue, the generation unit may adjust the use of technical terms in the dialogue according to the child's level of expertise. The generation unit, for example, evaluates the child's level of expertise. Examples of the level of expertise include, but are not limited to, the child's grade and past learning history. For example, the generation unit may evaluate the level of expertise based on the child's grade. The generation unit may also evaluate the level of expertise based on the child's past learning history. The generation unit may adjust the use of technical terms in the dialogue according to the child's level of expertise. For example, if the child is a beginner, the generation unit may generate a dialogue using simple technical terms. If the child is an intermediate learner, the generation unit may generate a dialogue using moderate technical terms. If the child is an advanced learner, the generation unit may generate a dialogue using detailed technical terms. In this way, by adjusting the use of technical terms according to the level of expertise, a dialogue suitable for the child can be provided.

[0098] The providing unit can estimate the child's emotions and adjust the dialogue provision method based on the estimated child's emotions. The providing unit, for example, estimates the child's emotions using facial expression recognition technology. For example, the providing unit captures the child's facial expression using a camera and estimates the emotion using facial expression recognition technology. The providing unit can also estimate the child's emotions using voice analysis technology. For example, the providing unit uses voice recognition technology to analyze the tone and speed of the child's voice and estimate the emotion. The providing unit adjusts the dialogue provision method based on the estimated child's emotions. For example, the providing unit can provide the dialogue in a gentle tone if the child is relaxed. Also, the providing unit can provide the dialogue in a calm tone if the child is excited. Also, the providing unit can provide the dialogue in an encouraging tone if the child is sad. In this way, by adjusting the dialogue provision method based on the emotion, it is possible to provide a dialogue that is appropriate for the child.

[0099] The providing unit can select an appropriate delivery method by referring to the child's past responses when providing dialogue. The providing unit, for example, collects the child's past responses. Past responses include, but are not limited to, dialogue logs and feedback data. For example, the providing unit analyzes past dialogue logs to identify a delivery method that the child preferred. The providing unit can also analyze past feedback data to identify a delivery method that the child disliked. The providing unit selects a delivery method based on, for example, past responses. For example, the providing unit selects a current delivery method based on delivery methods that the child preferred in the past. The providing unit can also adjust the current delivery method to avoid delivery methods that the child disliked in the past. The providing unit can also continuously improve the delivery method based on the child's past responses. In this way, the optimal delivery method can be selected by referring to past responses.

[0100] When providing dialogue, the providing unit can customize the content to be provided based on the child's current activity status. The providing unit, for example, monitors the child's current activity status. The activity status includes, for example, the type of play and the progress of learning, but is not limited to such examples. For example, when the child is playing, the providing unit provides dialogue related to the activity. Furthermore, when the child is studying, the providing unit can also provide dialogue related to the content of the study. Furthermore, when the child is out and about, the providing unit can also provide dialogue related to the surrounding environment. The providing unit customizes the content to be provided based on the child's current activity status. For example, when the child is playing, the providing unit provides dialogue related to the activity. Furthermore, when the child is studying, the providing unit can also provide dialogue related to the content of the study. Furthermore, when the child is out and about, the providing unit can also provide dialogue related to the surrounding environment. In this way, by customizing the content to be provided based on the child's current activity status, dialogue suitable for the child can be provided.

[0101] The providing unit can improve the providing method by reflecting the child's feedback when providing dialogue. The providing unit, for example, collects the child's feedback. The feedback includes, for example, survey results and user reviews, but is not limited to these examples. For example, the providing unit analyzes the survey results to identify dialogue content that the child likes. The providing unit can also analyze the user reviews to identify dialogue content that the child dislikes. The providing unit improves the providing method based on the feedback, for example. For example, the providing unit improves the providing method based on the dialogue content that the child likes. The providing unit can also adjust the providing method to avoid dialogue content that the child dislikes. The providing unit can also continuously improve the providing method based on the child's feedback. In this way, the providing method can be continuously improved by reflecting the feedback.

[0102] The providing unit can estimate the child's emotions and determine a priority order for providing dialogues based on the estimated child's emotions. The providing unit, for example, estimates the child's emotions using facial expression recognition technology. For example, the providing unit captures the child's facial expression using a camera and estimates the emotion using facial expression recognition technology. The providing unit can also estimate the child's emotions using voice analysis technology. For example, the providing unit can analyze the tone and speed of the child's voice using voice recognition technology to estimate the emotion. The providing unit determines a priority order for providing dialogues based on the estimated child's emotions. For example, if the child is excited, the providing unit can prioritize providing dialogues related to the emotion. Also, if the child is relaxed, the providing unit can prioritize providing dialogues of everyday conversation. Also, if the child is sad, the providing unit can prioritize providing dialogues that express the emotion. In this way, by determining the priority order for providing dialogues based on emotions, important dialogues can be prioritized.

[0103] When providing dialogue, the providing unit can select the optimal providing method by taking into consideration the geographical location information of the child. The providing unit, for example, acquires the geographical location information of the child using GPS data. For example, the providing unit identifies the child's current location using the GPS data. The providing unit can also acquire the child's geographical location information using a location information service. The providing unit selects the optimal providing method based on the child's geographical location information, for example. For example, if the child is in a park, the providing unit can provide dialogue related to the park. Also, if the child is at school, the providing unit can provide dialogue related to the school. Also, if the child is at home, the providing unit can provide dialogue within the home. In this way, the optimal providing method can be selected by taking into consideration the geographical location information.

[0104] The providing unit can analyze the child's social media activity to customize the content to be provided when providing dialogue. The providing unit, for example, analyzes the child's social media activity. Social media activity includes, for example, but is not limited to, posted content and comment history. For example, the providing unit can analyze content posted by the child on social media and provide related dialogue. The providing unit can also analyze accounts the child follows on social media and provide related dialogue. The providing unit can also analyze groups the child participates in on social media and provide related dialogue. In this way, related dialogue can be provided by analyzing social media activity.

[0105] The providing unit can customize the delivery method by reflecting the child's past feedback when providing dialogue. The providing unit, for example, collects the child's past feedback. Past feedback includes, but is not limited to, survey results and user reviews. For example, the providing unit analyzes the survey results to identify a delivery method that the child prefers. The providing unit can also analyze user reviews to identify a delivery method that the child dislikes. The providing unit customizes the delivery method based on, for example, the past feedback. For example, the providing unit customizes the current delivery method based on delivery methods that the child preferred in the past. The providing unit can also adjust the current delivery method to avoid delivery methods that the child disliked in the past. The providing unit can also continuously improve the delivery method based on the child's past feedback. In this way, the delivery method can be customized by reflecting past feedback. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and provision unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects the child's voice using the microphone 38B of the smart device 14 and converts the voice data into text data using voice recognition technology. The analysis unit analyzes the voice data using, for example, the specific processing unit 290 of the data processing device 12 and evaluates the child's developmental level and emotions. The generation unit generates a dialogue using, for example, a generation AI using the specific processing unit 290 of the data processing device 12, and adjusts the content of the dialogue by monitoring the child's reaction. The provision unit provides the generated dialogue to the child using, for example, the speaker 40B or the display 40A of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and provision unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects the child's voice using the microphone 238 of the smart glasses 214 and converts the voice data into text data using voice recognition technology. The analysis unit analyzes the voice data using, for example, the specific processing unit 290 of the data processing device 12 and evaluates the child's developmental level and emotions. The generation unit generates a dialogue using, for example, a generation AI using the specific processing unit 290 of the data processing device 12 and monitors the child's response to adjust the content of the dialogue. The provision unit provides the generated dialogue to the child using, for example, the speaker 240 or display of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, analysis unit, generation unit, and provision unit described above is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit collects the child's voice using the microphone 238 of the headset-type terminal 314 and converts the voice data into text data using voice recognition technology. The analysis unit analyzes the voice data using, for example, the specific processing unit 290 of the data processing device 12 and evaluates the child's level of development and emotions. The generation unit generates a dialogue using, for example, a generation AI using the specific processing unit 290 of the data processing device 12 and monitors the child's reaction to adjust the content of the dialogue. The provision unit provides the generated dialogue to the child using, for example, the speaker 240 or display 343 of the headset-type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, analysis unit, generation unit, and provision unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects the child's voice using the microphone 238 of the robot 414 and converts the voice data into text data using voice recognition technology. The analysis unit analyzes the voice data using, for example, the specific processing unit 290 of the data processing device 12 and evaluates the child's level of development and emotions. The generation unit generates a dialogue using, for example, a generation AI using the specific processing unit 290 of the data processing device 12 and monitors the child's reaction to adjust the content of the dialogue. The provision unit provides the generated dialogue to the child using, for example, the speaker 240 or display of the robot 414.

[0106] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0107] The analysis unit can also analyze the child's physical movements and gestures when assessing the child's developmental level. For example, the analysis unit can capture the child's movements using a camera and analyze the child's physical movements using motion analysis technology. The analysis unit can also analyze the child's gestures and use them as auxiliary information for language development. This allows for a more comprehensive assessment of the child's developmental level by taking into account not only voice data but also physical movements and gestures.

[0108] When providing the generated dialogue, the providing unit can add visual elements to attract the child's interest. For example, it can display illustrations or animations related to the dialogue content. The providing unit can also incorporate interactive game elements depending on the dialogue content. In this way, adding visual and interactive elements can attract the child's interest and improve learning effectiveness.

[0109] The generator can also take into account data on a child's social interactions when using the generative AI to evaluate a child's level of development. For example, it can observe how a child communicates with other children and adults and analyze that data. The generator can also evaluate the child's level of social development based on data on their friendships and group activities. This allows for a comprehensive evaluation of not only language ability but also social development.

[0110] The collection unit may also have a function for filtering out environmental sounds when collecting the child's voice data. For example, the collection unit may remove ambient noise and clearly collect only the child's voice. The collection unit may also emphasize specific frequency bands to collect the child's voice more clearly. This minimizes the influence of environmental sounds and allows for more accurate collection of voice data.

[0111] When analyzing the collected voice data, the analysis unit can also evaluate the rhythm and intonation of the child's speech. For example, the analysis unit can analyze the rhythm of the child's speech and use it as an indicator of language development. The analysis unit can also analyze the intonation of the child's speech to infer emotions and intentions. This allows for more accurate analysis by taking into account not only the content of the speech but also the rhythm and intonation.

[0112] The analysis unit can estimate the child's emotions and adjust the way the analysis is presented based on the estimated child's emotions. For example, the analysis unit can provide a detailed analysis result if the child is relaxed. The analysis unit can also provide a concise analysis result if the child is excited. The analysis unit can also provide a gentle analysis result if the child is sad. In this way, by adjusting the way the analysis is presented based on emotions, it is possible to provide an analysis result that is suitable for the child.

[0113] The collection unit can estimate the child's emotions and adjust the timing of collecting voice data based on the estimated child's emotions. For example, if the child is relaxed, the collection unit collects voice data during natural conversation. If the child is excited, the collection unit can wait until the child calms down before collecting voice data. If the child is tired, the collection unit can collect voice data after a break. This allows for more natural data collection by adjusting the timing of collecting voice data based on the child's emotions.

[0114] The generation unit can estimate the child's emotions and adjust the way the dialogue is expressed based on the estimated child's emotions. For example, if the child is relaxed, the generation unit can generate dialogue in a gentle tone. If the child is excited, the generation unit can also generate dialogue in a calm tone. If the child is sad, the generation unit can also generate dialogue in an encouraging tone. In this way, by adjusting the way the dialogue is expressed based on emotions, it is possible to provide dialogue that is appropriate for the child.

[0115] The providing unit can estimate the child's emotions and adjust the dialogue provision method based on the estimated child's emotions. For example, if the child is relaxed, the providing unit can provide the dialogue in a gentle tone. If the child is excited, the providing unit can also provide the dialogue in a calm tone. If the child is sad, the providing unit can also provide the dialogue in an encouraging tone. In this way, by adjusting the dialogue provision method based on the child's emotions, it is possible to provide a dialogue that is appropriate for the child.

[0116] The providing unit can estimate the child's emotions and determine the priority of dialogue provision based on the estimated child's emotions. For example, if the child is excited, the providing unit can provide preferentially dialogue related to the child's emotions. Also, if the child is relaxed, the providing unit can provide preferentially dialogue of everyday conversation. Also, if the child is sad, the providing unit can provide preferentially dialogue expressing the child's emotions. In this way, by determining the priority of dialogue provision based on emotions, important dialogue can be provided preferentially.

[0117] The processing flow of the second embodiment will be briefly explained below.

[0118] Step 1: The collection unit collects the child's voice. The child's voice may include talking, shouting, laughing, etc. The collection unit may collect the voice using a microphone and convert the voice data into text data using voice recognition technology. For example, the collection unit may analyze the voice using voice recognition software and save it as text data. Step 2: The analysis unit analyzes the voice data collected by the collection unit. The analysis is performed using voice recognition technology and emotion analysis technology. For example, the analysis unit may analyze the voice data using voice recognition technology to evaluate the child's developmental level. The analysis unit may also analyze the child's emotions using emotion analysis technology. Step 3: The generation unit generates a dialogue based on the analysis results obtained by the analysis unit. This is done using natural language generation technology and dialogue scenario generation technology. For example, the generation unit uses a generation AI to generate dialogue that is appropriate for the child's level of development. The generation unit can also use a generation AI to monitor the child's reactions and adjust the content of the dialogue. Step 4: The providing unit provides the dialogue generated by the generating unit to the child. The providing unit provides the dialogue using audio output or a screen display. For example, the providing unit provides the dialogue using audio output. The providing unit can also provide the dialogue using a screen display.

[0119] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0120] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0121] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0122] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0123] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0124] 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.

[0125] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0126] 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.

[0127] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0129] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0130] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0131] 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.

[0132] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0133] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0134] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0135] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0136] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0137] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0138] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0139] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0140] 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.

[0141] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0142] 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.

[0143] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0145] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0146] 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.

[0147] 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.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0149] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0150] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0151] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0153] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0156] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0157] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0158] 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.

[0159] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0160] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0161] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0162] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0163] 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.

[0164] 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.

[0165] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0166] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0167] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0168] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0169] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0170] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0171] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0172] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0173] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0174] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0175] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0176] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0177] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0178] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0179] 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.

[0180] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0181] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0182] 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.

[0183] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0184] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0185] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0186] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0187] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0188] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0189] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0190] [Explanation of symbols]

[0191] 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 the child's voice; an analysis unit that analyzes the voice data collected by the collection unit; a generation unit that generates a dialogue based on the analysis result obtained by the analysis unit; a providing unit that provides the dialogue generated by the generating unit to a child. A system characterized by:

2. The generation unit Evaluating children's developmental level using generative AI 2. The system of claim 1.

3. The providing unit Providing the generated dialogue to the child 2. The system of claim 1.

4. The generation unit Generative AI monitors children's reactions and adjusts the content of the dialogue 2. The system of claim 1.

5. The collecting unit Collecting words or sounds made by the child 2. The system of claim 1.

6. The analysis unit Analyzing collected voice data to assess the child's development 2. The system of claim 1.

7. The collecting unit The system estimates the child's emotions and adjusts the timing of voice data collection based on the estimated emotions.

2. The system of claim 1.

8. The collecting unit Analyze your child's past voice data and select the appropriate collection method 2. The system of claim 1.

Images