system

Abstract

An object of a system according to an embodiment is to efficiently fix memory during sleep.SOLUTION: A system includes an input unit, a generation unit, a detection unit, and a reproduction unit. The input interface is configured to input character information and voice information learned by the subject before sleep to the generative AI. The generation unit analyzes the information input by the input unit and generates voice data that summarizes the content desired to be stored. The detection unit detects a non-REM sleep state of the subject. The reproduction unit reproduces the voice data in the non-REM sleep state detected by the detection unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem that memorization requires a lot of time and effort, making it difficult to progress with learning efficiently.

[0005] The system according to the embodiment aims to efficiently consolidate memories during sleep. [Means for solving the problem]

[0006] The system according to the embodiment includes an input unit, a generation unit, a detection unit, and a playback unit. The input unit inputs text information and audio information that the subject learned before falling asleep to the generation AI. The generation unit analyzes the information input by the input unit and generates audio data summarizing the content the subject wants to remember. The detection unit detects the subject's non-REM sleep state. The playback unit plays back the audio data when the subject is in the non-REM sleep state detected by the detection unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently consolidate memories during sleep. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention is a sleep learning system that utilizes a generative AI to reduce the time and labor required for memorization tasks such as studying for entrance exams, qualifications, and presentation practice. In this system, a subject inputs text and audio information learned before sleep into a generative AI, which then analyzes the information and generates audio data summarizing the content the subject wants to memorize. The generated audio data is played back when the subject is in a non-REM sleep state. The non-REM sleep state is detected by an IoT device. This promotes memory consolidation and significantly reduces study time. This allows the sleep learning system to efficiently consolidate memories while the subject is asleep, significantly reducing study time. For example, this can shorten study time before exams and streamline presentation preparation time.

[0029] A sleep learning system according to an embodiment includes an input unit, a generation unit, a detection unit, and a playback unit. The input unit inputs text and audio information that the subject studied before sleep to the generation AI. Examples of such information include the contents of a textbook for an exam or a presentation script. This information is analyzed by the generation AI. The generation unit uses the generation AI to analyze the input information and generate audio data summarizing the content the subject wants to memorize. For example, the generation AI summarizes the important points of a textbook or key points of a presentation. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and generates a summary based on the input information. For example, the generation AI receives a prompt such as "Please summarize the main points of this passage," extracts the main points, and creates a summary. The detection unit detects the subject's non-REM sleep state using an IoT device. For example, an IoT device such as a smartwatch or sleep tracker monitors the subject's sleep state and detects the non-REM sleep state. The playback unit plays back the audio data generated during the non-REM sleep state detected by the detection unit. For example, when a non-REM sleep state is detected, the generated audio data is played back to promote the subject's memory consolidation. As a result, the sleep learning system according to the embodiment can efficiently consolidate the subject's memory while they are asleep, significantly reducing the learning time.

[0030] The generation unit can analyze the input information using the generation AI and generate audio data that summarizes the content that the user wants to remember. For example, the generation unit can use the generation AI to analyze the input information and generate audio data that summarizes the content that the user wants to remember. For example, the generation AI can summarize the important points of a textbook or the key points of a presentation. The generation unit can also develop algorithms that allow the generation AI to generate summaries based on the input information. For example, the generation AI can receive a prompt such as "Please summarize the main points of this text," extract the main points, and create a summary. In this way, the generation AI can be used to efficiently generate audio data that summarizes the content that the user wants to remember.

[0031] The detection unit can detect the subject's non-REM sleep state using at least one IoT device, such as a smartwatch or a sleep tracker. The detection unit detects the subject's non-REM sleep state using, for example, an IoT device such as a smartwatch or a sleep tracker. For example, a smartwatch can detect the subject's non-REM sleep state by monitoring the subject's heart rate and movements. Furthermore, a sleep tracker can detect the subject's non-REM sleep state by analyzing the subject's sleep patterns. This allows the non-REM sleep state to be accurately detected using an IoT device.

[0032] The playback unit can play back audio data generated during non-REM sleep. For example, when a non-REM sleep state is detected, the playback unit plays back the generated audio data. For example, the playback unit plays back important points for an exam or key points of a presentation during sleep. In this way, playing back audio data during non-REM sleep can promote memory consolidation.

[0033] The generation unit can generate audio data summarizing important points from a textbook or key points from a presentation. The generation unit, for example, uses a generation AI to generate audio data summarizing important points from a textbook or key points from a presentation. For example, the generation AI analyzes the contents of a textbook, extracts important points, and creates a summary. The generation unit can also analyze a presentation script, extract key points, and create a summary. This can improve learning effectiveness by efficiently summarizing important points.

[0034] The playback unit can play back important points for an exam or key points of a presentation during sleep. For example, when a non-REM sleep state is detected, the playback unit plays back the generated audio data. For example, the playback unit plays back important points for an exam or key points of a presentation during sleep. This allows important points for an exam or a presentation to be efficiently memorized.

[0035] The input unit can analyze the subject's past learning history and select the optimal input method. The input unit, for example, analyzes the subject's past learning history and selects the optimal input method. For example, the input unit preferentially suggests learning methods that have been effective for the subject in the past. The input unit can also select the optimal input method based on learning materials that the subject has used in the past. The input unit can also suggest effective study time periods based on the subject's past learning history. In this way, the learning effect can be improved by selecting the optimal input method based on the subject's past learning history.

[0036] The input unit can filter information based on the subject's current learning situation and areas of interest at the time of input. For example, the input unit filters information based on the subject's current learning situation and areas of interest at the time of input. For example, the input unit preferentially inputs information related to the subject's current learning subject. The input unit can also filter related information based on the subject's areas of interest. The input unit can also filter necessary information according to the subject's learning progress. This makes it possible to improve learning effectiveness by filtering information based on the subject's current learning situation and areas of interest.

[0037] The input unit can select the optimal input means depending on the input method of the subject at the time of input. For example, the input unit selects the optimal input means depending on the input method of the subject (voice, text, image, etc.) at the time of input. For example, if the subject prefers voice input, the input unit can provide voice input preferentially. Also, if the subject prefers text input, the input unit can also provide text input preferentially. Also, if the subject prefers image input, the input unit can provide image input preferentially. In this way, by selecting the optimal means depending on the input method of the subject, input efficiency can be improved.

[0038] The input unit can, at the time of input, preferentially input highly relevant information based on the geographical location information of the subject. For example, at the time of input, the input unit preferentially inputs highly relevant information taking into account the geographical location information of the subject. For example, if the subject is in a specific area, information related to that area is preferentially provided. Furthermore, if the subject is traveling, the input unit can also preferentially provide information related to the travel destination. Furthermore, if the subject is at home, the input unit can also preferentially provide information related to the home. In this way, highly relevant information can be preferentially input by taking into account the geographical location information.

[0039] The input unit can input relevant information based on the social media activity of the subject at the time of input. For example, the input unit analyzes the social media activity of the subject at the time of input and inputs relevant information. For example, the input unit provides relevant information based on information shared by the subject on social media. The input unit can also analyze the subject's social media activity and provide relevant information. The input unit can also provide relevant information with reference to the activity of the subject's friends on social media. This allows for efficient input of relevant information by analyzing social media activity.

[0040] The input unit can customize the input method by reflecting the subject's past feedback at the time of input. The input unit, for example, customizes the input method by reflecting the subject's past feedback at the time of input. For example, the input unit suggests an optimal input method based on feedback provided by the subject in the past. The input unit can also select an effective input method from the subject's past feedback. The input unit can also customize the input method by reflecting the subject's feedback. In this way, the optimal input method can be provided by reflecting past feedback.

[0041] The generation unit can adjust the level of detail of the summary based on the importance of the information when generating the summary. For example, the generation unit adjusts the level of detail of the summary based on the importance of the information when generating the summary. For example, important information is summarized in detail, and less important information is summarized briefly. The generation unit can also adjust the length of the summary based on the importance of the information. The generation unit can also emphasize important points and add detailed explanations. In this way, adjusting the level of detail of the summary based on the importance of the information enables efficient learning.

[0042] The generation unit can apply different summarization algorithms depending on the category of information when generating summaries. For example, the generation unit can apply different summarization algorithms depending on the category of information when generating summaries. For example, the generation unit can apply a specialized summarization algorithm to scientific information. The generation unit can also apply a time-series-based summarization algorithm to historical information. The generation unit can also apply an emotion-focused summarization algorithm to literary information. This allows for efficient summarization by applying a summarization algorithm depending on the category of information.

[0043] The generation unit can improve the accuracy of the summary by referring to the subject's past summarization results when generating a summary. For example, the generation unit can improve the accuracy of the summary by referring to the subject's past summarization results when generating a summary. For example, the generation unit can improve the accuracy of the summary based on the subject's preferred summarization style in the past. The generation unit can also analyze the subject's past summarization results and suggest an optimal summarization method. The generation unit can also improve the accuracy of the summary by reflecting the subject's feedback. In this way, the accuracy of the summary is improved by referring to the past summarization results.

[0044] The generation unit can determine the priority of summaries based on the time of submission of information when generating summaries. For example, the generation unit determines the priority of summaries based on the time of submission of information when generating summaries. For example, the latest information is given priority in summarization. The generation unit can also give priority in summarization to information with an upcoming submission deadline. The generation unit can also summarize past information briefly and summarize the latest information in detail. In this way, by determining the priority of summaries based on the time of submission of information, efficient learning is possible.

[0045] The generation unit can adjust the order of summaries based on the relevance of information when generating summaries. For example, the generation unit adjusts the order of summaries based on the relevance of information when generating summaries. For example, highly relevant information is summarized preferentially. The generation unit can also postpone less relevant information. The generation unit can also adjust the order of summaries according to the relevance of information. As a result, adjusting the order of summaries based on the relevance of information enables efficient learning.

[0046] The generation unit can adjust the use of technical terms in the summary according to the subject's level of expertise when generating a summary. For example, the generation unit adjusts the use of technical terms in the summary according to the subject's level of expertise when generating a summary. For example, if the subject has specialized knowledge, the generation unit uses a lot of technical terms. The generation unit can also avoid technical terms if the subject is a beginner. The generation unit can also adjust the use of technical terms according to the subject's level of expertise. This allows for efficient learning by adjusting the use of technical terms according to the subject's level of expertise.

[0047] The detection unit can select the optimal detection method by referring to the subject's past sleep data during detection. For example, the detection unit selects the optimal detection method by referring to the subject's past sleep data during detection. For example, the optimal detection method is selected based on the subject's past sleep data. The detection unit can also analyze the subject's past sleep patterns and suggest the optimal detection method. The detection unit can also improve detection accuracy by referring to the subject's past sleep data. In this way, the optimal detection method can be selected by referring to the past sleep data.

[0048] The detection unit can analyze the subject's life rhythm during detection and adjust the timing of detecting the non-REM sleep state. For example, the detection unit can analyze the subject's life rhythm during detection and adjust the timing of detecting the non-REM sleep state. For example, the detection unit can analyze the subject's life rhythm and propose an optimal detection timing. The detection unit can also adjust the timing of detecting the non-REM sleep state based on the subject's life rhythm. The detection unit can also improve detection accuracy by taking the subject's life rhythm into consideration. In this way, the timing of detecting the non-REM sleep state can be optimized by analyzing the life rhythm.

[0049] The detection unit can improve the detection method by reflecting the subject's feedback during detection. The detection unit, for example, improves the detection method by reflecting the subject's feedback during detection. For example, the detection method is improved based on the subject's feedback. The detection unit can also improve detection accuracy by reflecting the subject's feedback. The detection unit can also suggest an optimal detection method by referring to the subject's feedback. In this way, the detection method can be improved and accuracy can be improved by reflecting the feedback.

[0050] The detection unit can improve detection accuracy by taking into account the geographical location information of the subject at the time of detection. The detection unit can improve detection accuracy by taking into account the geographical location information of the subject at the time of detection, for example. For example, if the subject is in a specific area, the detection unit can improve detection accuracy based on information related to the area. Furthermore, if the subject is traveling, the detection unit can improve detection accuracy based on information related to the travel destination. Furthermore, if the subject is at home, the detection unit can improve detection accuracy based on information related to the home. In this way, detection accuracy can be improved by taking into account the geographical location information.

[0051] The detection unit can analyze the social media activities of the subject at the time of detection and use related data for detection. For example, the detection unit can analyze the social media activities of the subject at the time of detection and use related data for detection. For example, the detection accuracy can be improved based on information shared by the subject on social media. The detection unit can also analyze the social media activities of the subject and use related data for detection. The detection unit can also improve detection accuracy by referring to the activities of the subject's friends on social media. In this way, by analyzing social media activities, related data can be efficiently used for detection.

[0052] The detection unit can customize the detection method by reflecting the subject's past feedback at the time of detection. The detection unit, for example, customizes the detection method by reflecting the subject's past feedback at the time of detection. For example, the detection unit proposes an optimal detection method based on the subject's past feedback. The detection unit can also improve detection accuracy by reflecting the subject's past feedback. The detection unit can also customize the detection method by referring to the subject's feedback. In this way, the optimal detection method can be provided by reflecting the past feedback.

[0053] The playback unit can select the optimal playback method by referring to the subject's past learning data during playback. The playback unit, for example, selects the optimal playback method by referring to the subject's past learning data during playback. For example, the playback unit proposes the optimal playback method based on the subject's past learning data. The playback unit can also analyze the subject's past learning history and select the optimal playback method. The playback unit can also improve playback accuracy by referring to the subject's past learning data. In this way, the optimal playback method can be selected by referring to the past learning data.

[0054] The playback unit can customize the playback content based on the subject's current learning situation during playback. The playback unit, for example, customizes the playback content based on the subject's current learning situation during playback. For example, the playback unit analyzes the subject's current learning situation and suggests optimal playback content. The playback unit can also customize the playback content according to the subject's learning progress. The playback unit can also improve playback accuracy by taking the subject's current learning situation into consideration. This enables efficient learning by customizing the playback content based on the subject's current learning situation.

[0055] The playback unit can improve the playback method by reflecting the subject's feedback during playback. The playback unit, for example, improves the playback method by reflecting the subject's feedback during playback. For example, the playback method is improved based on the subject's feedback. The playback unit can also improve playback accuracy by reflecting the subject's feedback. The playback unit can also suggest an optimal playback method by referring to the subject's feedback. In this way, the playback method can be improved and accuracy can be improved by reflecting the feedback.

[0056] The playback unit can select the optimal playback method during playback by taking into consideration the geographical location information of the subject. For example, during playback, the playback unit selects the optimal playback method by taking into consideration the geographical location information of the subject. For example, if the subject is in a specific area, the playback unit can prioritize playback of information related to that area. Furthermore, if the subject is traveling, the playback unit can also prioritize playback of information related to the travel destination. Furthermore, if the subject is at home, the playback unit can also prioritize playback of information related to the home. In this way, the optimal playback method can be provided by taking into consideration the geographical location information.

[0057] The playback unit can analyze the social media activity of the subject and play back related audio data during playback. The playback unit, for example, analyzes the social media activity of the subject and plays back related audio data during playback. For example, the playback unit plays back related audio data based on information shared by the subject on social media. The playback unit can also analyze the subject's social media activity and play back related audio data. The playback unit can also play back related audio data with reference to the activity of the subject's friends on social media. In this way, related audio data can be efficiently played back by analyzing social media activity.

[0058] The playback unit can customize the playback method by reflecting the subject's past feedback during playback. The playback unit, for example, customizes the playback method by reflecting the subject's past feedback during playback. For example, the playback unit proposes an optimal playback method based on the subject's past feedback. The playback unit can also improve playback accuracy by reflecting the subject's past feedback. The playback unit can also customize the playback method by referring to the subject's feedback. In this way, the optimal playback method can be provided by reflecting the 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 input unit can also analyze the learning style of the subject and suggest the most suitable learning method. For example, for a subject who prefers visual learning, it can suggest a learning method using images or videos. For a subject who prefers auditory learning, it can also suggest a learning method using audio data. Furthermore, it can suggest interactive learning materials to a subject who prefers tactile learning. In this way, it is possible to improve learning effectiveness by providing the most suitable learning method according to the subject's learning style.

[0061] When generating summaries, the generation unit can also adjust the content of the summary based on the learning goals of the target person. For example, for a target person aiming to pass an exam, the summary can focus on points that are likely to appear on the exam. For a target person preparing a presentation, the summary can focus on the key points of the presentation. Furthermore, for a target person studying based on a hobby or interest, the summary can include a wide range of related information. This makes it possible to improve learning effectiveness by providing summaries that meet the target person's learning goals.

[0062] The detection unit can also monitor the subject's physiological data in real time to improve the accuracy of detecting non-REM sleep states. For example, by monitoring heart rate and breathing patterns, non-REM sleep states can be detected more accurately. Changes in sleep state can also be detected by monitoring body temperature and electrodermal activity. Furthermore, non-REM sleep states can be detected with high accuracy by analyzing electroencephalogram data. This makes it possible to improve the accuracy of detecting non-REM sleep states by utilizing physiological data.

[0063] The playback unit can also dynamically adjust the playback content based on the learning progress of the subject. For example, if the learning progresses, more advanced content can be played. Alternatively, if the learning has stagnated, basic content can be played. Furthermore, if the understanding of a particular field has deepened, applied content related to that field can be played. In this way, the learning effect can be improved by providing playback content that matches the learning progress of the subject.

[0064] The input unit can also analyze the learning environment of the subject and suggest optimal learning conditions. For example, it can suggest a noise canceling function to a subject who prefers to study in a quiet environment. It can also suggest appropriate lighting conditions to a subject who prefers to study in a bright environment. It can also suggest environmental adjustments to a subject who prefers to study under specific temperature or humidity conditions. This makes it possible to improve learning effectiveness by providing optimal learning conditions according to the subject's learning environment.

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

[0066] Step 1: The input section inputs the text and audio information the subject learned before sleep into the generation AI. For example, this could be the contents of a textbook for an exam or a presentation script. Step 2: The generator uses a generation AI to analyze the input information and generate audio data summarizing the content to be memorized. For example, the generation AI may summarize the important points of a textbook or the key points of a presentation. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and generates a summary based on the input information. Step 3: The detector detects the subject's non-REM sleep state using an IoT device, such as a smartwatch or sleep tracker, to monitor the subject's sleep state and detect the non-REM sleep state. Step 4: The playback unit plays back the audio data generated during the non-REM sleep state detected by the detection unit. For example, when a non-REM sleep state is detected, the generated audio data is played back to promote memory consolidation in the subject.

[0067] (Example 2) A system according to an embodiment of the present invention is a sleep learning system that utilizes a generative AI to reduce the time and labor required for memorization tasks such as studying for entrance exams, qualifications, and presentation practice. In this system, a subject inputs text and audio information learned before sleep into a generative AI, which then analyzes the information and generates audio data summarizing the content the subject wants to memorize. The generated audio data is played back when the subject is in a non-REM sleep state. The non-REM sleep state is detected by an IoT device. This promotes memory consolidation and significantly reduces study time. This allows the sleep learning system to efficiently consolidate memories while the subject is asleep, significantly reducing study time. For example, this can shorten study time before exams and streamline presentation preparation time.

[0068] A sleep learning system according to an embodiment includes an input unit, a generation unit, a detection unit, and a playback unit. The input unit inputs text and audio information that the subject studied before sleep to the generation AI. Examples of such information include the contents of a textbook for an exam or a presentation script. This information is analyzed by the generation AI. The generation unit uses the generation AI to analyze the input information and generate audio data summarizing the content the subject wants to memorize. For example, the generation AI summarizes the important points of a textbook or key points of a presentation. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and generates a summary based on the input information. For example, the generation AI receives a prompt such as "Please summarize the main points of this passage," extracts the main points, and creates a summary. The detection unit detects the subject's non-REM sleep state using an IoT device. For example, an IoT device such as a smartwatch or sleep tracker monitors the subject's sleep state and detects the non-REM sleep state. The playback unit plays back the audio data generated during the non-REM sleep state detected by the detection unit. For example, when a non-REM sleep state is detected, the generated audio data is played back to promote the subject's memory consolidation. As a result, the sleep learning system according to the embodiment can efficiently consolidate the subject's memory while they are asleep, significantly reducing the learning time.

[0069] The generation unit can analyze the input information using the generation AI and generate audio data that summarizes the content that the user wants to remember. For example, the generation unit can use the generation AI to analyze the input information and generate audio data that summarizes the content that the user wants to remember. For example, the generation AI can summarize the important points of a textbook or the key points of a presentation. The generation unit can also develop algorithms that allow the generation AI to generate summaries based on the input information. For example, the generation AI can receive a prompt such as "Please summarize the main points of this text," extract the main points, and create a summary. In this way, the generation AI can be used to efficiently generate audio data that summarizes the content that the user wants to remember.

[0070] The detection unit can detect the subject's non-REM sleep state using at least one IoT device, such as a smartwatch or a sleep tracker. The detection unit detects the subject's non-REM sleep state using, for example, an IoT device such as a smartwatch or a sleep tracker. For example, a smartwatch can detect the subject's non-REM sleep state by monitoring the subject's heart rate and movements. Furthermore, a sleep tracker can detect the subject's non-REM sleep state by analyzing the subject's sleep patterns. This allows the non-REM sleep state to be accurately detected using an IoT device.

[0071] The playback unit can play back audio data generated during non-REM sleep. For example, when a non-REM sleep state is detected, the playback unit plays back the generated audio data. For example, the playback unit plays back important points for an exam or key points of a presentation during sleep. In this way, playing back audio data during non-REM sleep can promote memory consolidation.

[0072] The generation unit can generate audio data summarizing important points from a textbook or key points from a presentation. The generation unit, for example, uses a generation AI to generate audio data summarizing important points from a textbook or key points from a presentation. For example, the generation AI analyzes the contents of a textbook, extracts important points, and creates a summary. The generation unit can also analyze a presentation script, extract key points, and create a summary. This can improve learning effectiveness by efficiently summarizing important points.

[0073] The playback unit can play back important points for an exam or key points of a presentation during sleep. For example, when a non-REM sleep state is detected, the playback unit plays back the generated audio data. For example, the playback unit plays back important points for an exam or key points of a presentation during sleep. This allows important points for an exam or a presentation to be efficiently memorized.

[0074] The input unit can estimate the subject's emotions and determine the priority of information to be input based on the estimated subject's emotions. The input unit, for example, estimates the subject's emotions and determines the priority of information to be input based on the estimated subject's emotions. For example, if the subject is feeling stressed, it can prioritize input of relaxing content. Also, if the subject is concentrating, it can prioritize input of important information. Also, if the subject is tired, it can prioritize input of simple content. This allows optimal information to be input preferentially according to the subject's emotions, thereby improving learning effectiveness. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0075] The input unit can analyze the subject's past learning history and select the optimal input method. The input unit, for example, analyzes the subject's past learning history and selects the optimal input method. For example, the input unit preferentially suggests learning methods that have been effective for the subject in the past. The input unit can also select the optimal input method based on learning materials that the subject has used in the past. The input unit can also suggest effective study time periods based on the subject's past learning history. In this way, the learning effect can be improved by selecting the optimal input method based on the subject's past learning history.

[0076] The input unit can filter information based on the subject's current learning situation and areas of interest at the time of input. For example, the input unit filters information based on the subject's current learning situation and areas of interest at the time of input. For example, the input unit preferentially inputs information related to the subject's current learning subject. The input unit can also filter related information based on the subject's areas of interest. The input unit can also filter necessary information according to the subject's learning progress. This makes it possible to improve learning effectiveness by filtering information based on the subject's current learning situation and areas of interest.

[0077] The input unit can select the optimal input means depending on the input method of the subject at the time of input. For example, the input unit selects the optimal input means depending on the input method of the subject (voice, text, image, etc.) at the time of input. For example, if the subject prefers voice input, the input unit can provide voice input preferentially. Also, if the subject prefers text input, the input unit can also provide text input preferentially. Also, if the subject prefers image input, the input unit can provide image input preferentially. In this way, by selecting the optimal means depending on the input method of the subject, input efficiency can be improved.

[0078] The input unit can estimate the subject's emotion and adjust the format of the information to be input based on the estimated subject's emotion. The input unit, for example, estimates the subject's emotion and adjusts the format of the information to be input based on the estimated subject's emotion. For example, if the subject is relaxed, detailed information can be provided. If the subject is nervous, concise information can be provided. If the subject is excited, visually stimulating information can be provided. This can improve learning effectiveness by adjusting the format of information according to the subject's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0079] The input unit can, at the time of input, preferentially input highly relevant information based on the geographical location information of the subject. For example, at the time of input, the input unit preferentially inputs highly relevant information taking into account the geographical location information of the subject. For example, if the subject is in a specific area, information related to that area is preferentially provided. Furthermore, if the subject is traveling, the input unit can also preferentially provide information related to the travel destination. Furthermore, if the subject is at home, the input unit can also preferentially provide information related to the home. In this way, highly relevant information can be preferentially input by taking into account the geographical location information.

[0080] The input unit can input relevant information based on the social media activity of the subject at the time of input. For example, the input unit analyzes the social media activity of the subject at the time of input and inputs relevant information. For example, the input unit provides relevant information based on information shared by the subject on social media. The input unit can also analyze the subject's social media activity and provide relevant information. The input unit can also provide relevant information with reference to the activity of the subject's friends on social media. This allows for efficient input of relevant information by analyzing social media activity.

[0081] The input unit can customize the input method by reflecting the subject's past feedback at the time of input. The input unit, for example, customizes the input method by reflecting the subject's past feedback at the time of input. For example, the input unit suggests an optimal input method based on feedback provided by the subject in the past. The input unit can also select an effective input method from the subject's past feedback. The input unit can also customize the input method by reflecting the subject's feedback. In this way, the optimal input method can be provided by reflecting past feedback.

[0082] The generation unit can estimate the subject's emotions and adjust the summary presentation style based on the estimated subject's emotions. The generation unit, for example, estimates the subject's emotions and adjusts the summary presentation style based on the estimated subject's emotions. For example, if the subject is relaxed, a detailed summary can be provided. If the subject is nervous, a concise summary can be provided. If the subject is excited, a visually stimulating summary can be provided. This allows for adjusting the summary presentation style according to the subject's emotions, thereby improving learning effectiveness. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0083] The generation unit can adjust the level of detail of the summary based on the importance of the information when generating the summary. For example, the generation unit adjusts the level of detail of the summary based on the importance of the information when generating the summary. For example, important information is summarized in detail, and less important information is summarized briefly. The generation unit can also adjust the length of the summary based on the importance of the information. The generation unit can also emphasize important points and add detailed explanations. In this way, adjusting the level of detail of the summary based on the importance of the information enables efficient learning.

[0084] The generation unit can apply different summarization algorithms depending on the category of information when generating summaries. For example, the generation unit can apply different summarization algorithms depending on the category of information when generating summaries. For example, the generation unit can apply a specialized summarization algorithm to scientific information. The generation unit can also apply a time-series-based summarization algorithm to historical information. The generation unit can also apply an emotion-focused summarization algorithm to literary information. This allows for efficient summarization by applying a summarization algorithm depending on the category of information.

[0085] The generation unit can improve the accuracy of the summary by referring to the subject's past summarization results when generating a summary. For example, the generation unit can improve the accuracy of the summary by referring to the subject's past summarization results when generating a summary. For example, the generation unit can improve the accuracy of the summary based on the subject's preferred summarization style in the past. The generation unit can also analyze the subject's past summarization results and suggest an optimal summarization method. The generation unit can also improve the accuracy of the summary by reflecting the subject's feedback. In this way, the accuracy of the summary is improved by referring to the past summarization results.

[0086] The generation unit can estimate the subject's emotion and adjust the length of the summary based on the estimated subject's emotion. The generation unit, for example, estimates the subject's emotion and adjusts the length of the summary based on the estimated subject's emotion. For example, if the subject is relaxed, a longer summary can be provided. Also, if the subject is nervous, a shorter summary can be provided. Also, if the subject is excited, a visually stimulating summary can be provided. This allows for adjusting the length of the summary according to the subject's emotion, thereby improving learning effectiveness. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0087] The generation unit can determine the priority of summaries based on the time of submission of information when generating summaries. For example, the generation unit determines the priority of summaries based on the time of submission of information when generating summaries. For example, the latest information is given priority in summarization. The generation unit can also give priority in summarization to information with an upcoming submission deadline. The generation unit can also summarize past information briefly and summarize the latest information in detail. In this way, by determining the priority of summaries based on the time of submission of information, efficient learning is possible.

[0088] The generation unit can adjust the order of summaries based on the relevance of information when generating summaries. For example, the generation unit adjusts the order of summaries based on the relevance of information when generating summaries. For example, highly relevant information is summarized preferentially. The generation unit can also postpone less relevant information. The generation unit can also adjust the order of summaries according to the relevance of information. As a result, adjusting the order of summaries based on the relevance of information enables efficient learning.

[0089] The generation unit can adjust the use of technical terms in the summary according to the subject's level of expertise when generating a summary. For example, the generation unit adjusts the use of technical terms in the summary according to the subject's level of expertise when generating a summary. For example, if the subject has specialized knowledge, the generation unit uses a lot of technical terms. The generation unit can also avoid technical terms if the subject is a beginner. The generation unit can also adjust the use of technical terms according to the subject's level of expertise. This allows for efficient learning by adjusting the use of technical terms according to the subject's level of expertise.

[0090] The detection unit can estimate the subject's emotion and improve the accuracy of detecting the non-REM sleep state based on the estimated emotion of the subject. The detection unit, for example, estimates the subject's emotion and improves the accuracy of detecting the non-REM sleep state based on the estimated emotion of the subject. For example, if the subject is relaxed, the accuracy of detecting the non-REM sleep state can be improved. Also, if the subject is nervous, the accuracy of detecting the non-REM sleep state can be improved. Also, if the subject is excited, the accuracy of detecting the non-REM sleep state can be improved. In this way, accurate detection is possible by improving the accuracy of detecting the non-REM sleep state according to the subject's emotion. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0091] The detection unit can select the optimal detection method by referring to the subject's past sleep data during detection. For example, the detection unit selects the optimal detection method by referring to the subject's past sleep data during detection. For example, the optimal detection method is selected based on the subject's past sleep data. The detection unit can also analyze the subject's past sleep patterns and suggest the optimal detection method. The detection unit can also improve detection accuracy by referring to the subject's past sleep data. In this way, the optimal detection method can be selected by referring to the past sleep data.

[0092] The detection unit can analyze the subject's life rhythm during detection and adjust the timing of detecting the non-REM sleep state. For example, the detection unit can analyze the subject's life rhythm during detection and adjust the timing of detecting the non-REM sleep state. For example, the detection unit can analyze the subject's life rhythm and propose an optimal detection timing. The detection unit can also adjust the timing of detecting the non-REM sleep state based on the subject's life rhythm. The detection unit can also improve detection accuracy by taking the subject's life rhythm into consideration. In this way, the timing of detecting the non-REM sleep state can be optimized by analyzing the life rhythm.

[0093] The detection unit can improve the detection method by reflecting the subject's feedback during detection. The detection unit, for example, improves the detection method by reflecting the subject's feedback during detection. For example, the detection method is improved based on the subject's feedback. The detection unit can also improve detection accuracy by reflecting the subject's feedback. The detection unit can also suggest an optimal detection method by referring to the subject's feedback. In this way, the detection method can be improved and accuracy can be improved by reflecting the feedback.

[0094] The detection unit can estimate the subject's emotion and adjust the display method of the detection result based on the estimated subject's emotion. The detection unit, for example, estimates the subject's emotion and adjusts the display method of the detection result based on the estimated subject's emotion. For example, if the subject is relaxed, detailed detection results can be displayed. If the subject is nervous, concise detection results can be displayed. If the subject is excited, visually stimulating detection results can be displayed. In this way, by adjusting the display method of the detection result according to the subject's emotion, it is possible to display an easy-to-understand display. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0095] The detection unit can improve detection accuracy by taking into account the geographical location information of the subject at the time of detection. The detection unit can improve detection accuracy by taking into account the geographical location information of the subject at the time of detection, for example. For example, if the subject is in a specific area, the detection unit can improve detection accuracy based on information related to the area. Furthermore, if the subject is traveling, the detection unit can improve detection accuracy based on information related to the travel destination. Furthermore, if the subject is at home, the detection unit can improve detection accuracy based on information related to the home. In this way, detection accuracy can be improved by taking into account the geographical location information.

[0096] The detection unit can analyze the social media activities of the subject at the time of detection and use related data for detection. For example, the detection unit can analyze the social media activities of the subject at the time of detection and use related data for detection. For example, the detection accuracy can be improved based on information shared by the subject on social media. The detection unit can also analyze the social media activities of the subject and use related data for detection. The detection unit can also improve detection accuracy by referring to the activities of the subject's friends on social media. In this way, by analyzing social media activities, related data can be efficiently used for detection.

[0097] The detection unit can customize the detection method by reflecting the subject's past feedback at the time of detection. The detection unit, for example, customizes the detection method by reflecting the subject's past feedback at the time of detection. For example, the detection unit proposes an optimal detection method based on the subject's past feedback. The detection unit can also improve detection accuracy by reflecting the subject's past feedback. The detection unit can also customize the detection method by referring to the subject's feedback. In this way, the optimal detection method can be provided by reflecting the past feedback.

[0098] The playback unit can estimate the emotion of the subject and adjust the playback timing of the audio data based on the estimated emotion of the subject. The playback unit, for example, estimates the emotion of the subject and adjusts the playback timing of the audio data based on the estimated emotion of the subject. For example, if the subject is relaxed, the audio data can be played slowly. If the subject is nervous, the audio data can be played short. If the subject is excited, the audio data can be played in a visually stimulating manner. This enables efficient learning by adjusting the playback timing according to the emotion of the subject. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0099] The playback unit can select the optimal playback method by referring to the subject's past learning data during playback. The playback unit, for example, selects the optimal playback method by referring to the subject's past learning data during playback. For example, the playback unit proposes the optimal playback method based on the subject's past learning data. The playback unit can also analyze the subject's past learning history and select the optimal playback method. The playback unit can also improve playback accuracy by referring to the subject's past learning data. In this way, the optimal playback method can be selected by referring to the past learning data.

[0100] The playback unit can customize the playback content based on the subject's current learning situation during playback. The playback unit, for example, customizes the playback content based on the subject's current learning situation during playback. For example, the playback unit analyzes the subject's current learning situation and suggests optimal playback content. The playback unit can also customize the playback content according to the subject's learning progress. The playback unit can also improve playback accuracy by taking the subject's current learning situation into consideration. This enables efficient learning by customizing the playback content based on the subject's current learning situation.

[0101] The playback unit can improve the playback method by reflecting the subject's feedback during playback. The playback unit, for example, improves the playback method by reflecting the subject's feedback during playback. For example, the playback method is improved based on the subject's feedback. The playback unit can also improve playback accuracy by reflecting the subject's feedback. The playback unit can also suggest an optimal playback method by referring to the subject's feedback. In this way, the playback method can be improved and accuracy can be improved by reflecting the feedback.

[0102] The playback unit can estimate the subject's emotion and determine the priority of the audio data to be played back based on the estimated subject's emotion. The playback unit, for example, estimates the subject's emotion and determines the priority of the audio data to be played back based on the estimated subject's emotion. For example, if the subject is relaxed, important information can be played back preferentially. Also, if the subject is nervous, brief information can be played back preferentially. Also, if the subject is excited, visually stimulating information can be played back preferentially. This enables efficient learning by determining the priority of audio data according to the subject's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0103] The playback unit can select the optimal playback method during playback by taking into consideration the geographical location information of the subject. For example, during playback, the playback unit selects the optimal playback method by taking into consideration the geographical location information of the subject. For example, if the subject is in a specific area, the playback unit can prioritize playback of information related to that area. Furthermore, if the subject is traveling, the playback unit can also prioritize playback of information related to the travel destination. Furthermore, if the subject is at home, the playback unit can also prioritize playback of information related to the home. In this way, the optimal playback method can be provided by taking into consideration the geographical location information.

[0104] The playback unit can analyze the social media activity of the subject and play back related audio data during playback. The playback unit, for example, analyzes the social media activity of the subject and plays back related audio data during playback. For example, the playback unit plays back related audio data based on information shared by the subject on social media. The playback unit can also analyze the subject's social media activity and play back related audio data. The playback unit can also play back related audio data with reference to the activity of the subject's friends on social media. In this way, related audio data can be efficiently played back by analyzing social media activity.

[0105] The playback unit can customize the playback method by reflecting the subject's past feedback during playback. The playback unit, for example, customizes the playback method by reflecting the subject's past feedback during playback. For example, the playback unit proposes an optimal playback method based on the subject's past feedback. The playback unit can also improve playback accuracy by reflecting the subject's past feedback. The playback unit can also customize the playback method by referring to the subject's feedback. In this way, the optimal playback method can be provided by reflecting the past feedback. === Hard Collateral 1-1 === Each of the multiple elements, including the input unit, generation unit, detection unit, and playback 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 input unit can estimate the subject's emotions using the reception device 38 and microphone 38B of the smart device 14 and determine the priority of input information based on the estimated emotions. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the input information using a generation AI to generate audio data summarizing the content to be memorized. The detection unit detects the subject's non-REM sleep state using the camera 42 and sensors of the smart device 14. The playback unit uses the output device 40 of the smart device 14 to play back the audio data generated during the detected non-REM sleep state. === Hard Collateral 1-2 === Each of the multiple elements, including the input unit, generation unit, detection unit, and playback 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 input unit can estimate the subject's emotion using the microphone 238 of the smart glasses 214 and determine the priority of information to be input based on the estimated emotion. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the input information using a generation AI to generate audio data summarizing the content to be memorized. The detection unit detects the subject's non-REM sleep state using the camera 42 and sensors of the smart glasses 214. The playback unit uses the speaker 240 of the smart glasses 214 to play back the audio data generated during the detected non-REM sleep state. === Hard Collateral 1-3 === Each of the multiple elements, including the input unit, generation unit, detection unit, and playback 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 input unit can estimate the subject's emotion using the microphone 238 of the headset-type terminal 314 and determine the priority of information to be input based on the estimated emotion. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the input information using a generation AI to generate audio data summarizing the content to be memorized. The detection unit detects the subject's non-REM sleep state using the camera 42 and sensors of the headset-type terminal 314. The playback unit uses the speaker 240 of the headset-type terminal 314 to play back the audio data generated during the detected non-REM sleep state. === Hard Collateral 1-4 === Each of the multiple elements, including the input unit, generation unit, detection unit, and playback unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the input unit can estimate the subject's emotions using the microphone 238 of the robot 414 and determine the priority of information to be input based on the estimated emotions. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the input information using a generation AI to generate audio data summarizing the content to be memorized. The detection unit detects the subject's non-REM sleep state using the camera 42 and sensors of the robot 414. The playback unit uses the speaker 240 of the robot 414 to play back the audio data generated during the detected non-REM sleep state.

[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 input unit can also analyze the learning style of the subject and suggest the most suitable learning method. For example, for a subject who prefers visual learning, it can suggest a learning method using images or videos. For a subject who prefers auditory learning, it can also suggest a learning method using audio data. Furthermore, it can suggest interactive learning materials to a subject who prefers tactile learning. In this way, it is possible to improve learning effectiveness by providing the most suitable learning method according to the subject's learning style.

[0108] When generating summaries, the generation unit can also adjust the content of the summary based on the learning goals of the target person. For example, for a target person aiming to pass an exam, the summary can focus on points that are likely to appear on the exam. For a target person preparing a presentation, the summary can focus on the key points of the presentation. Furthermore, for a target person studying based on a hobby or interest, the summary can include a wide range of related information. This makes it possible to improve learning effectiveness by providing summaries that meet the target person's learning goals.

[0109] The detection unit can also monitor the subject's physiological data in real time to improve the accuracy of detecting non-REM sleep states. For example, by monitoring heart rate and breathing patterns, non-REM sleep states can be detected more accurately. Changes in sleep state can also be detected by monitoring body temperature and electrodermal activity. Furthermore, non-REM sleep states can be detected with high accuracy by analyzing electroencephalogram data. This makes it possible to improve the accuracy of detecting non-REM sleep states by utilizing physiological data.

[0110] The playback unit can also dynamically adjust the playback content based on the learning progress of the subject. For example, if the learning progresses, more advanced content can be played. Alternatively, if the learning has stagnated, basic content can be played. Furthermore, if the understanding of a particular field has deepened, applied content related to that field can be played. In this way, the learning effect can be improved by providing playback content that matches the learning progress of the subject.

[0111] The input unit can also analyze the learning environment of the subject and suggest optimal learning conditions. For example, it can suggest a noise canceling function to a subject who prefers to study in a quiet environment. It can also suggest appropriate lighting conditions to a subject who prefers to study in a bright environment. It can also suggest environmental adjustments to a subject who prefers to study under specific temperature or humidity conditions. This makes it possible to improve learning effectiveness by providing optimal learning conditions according to the subject's learning environment.

[0112] The input unit can also estimate the subject's emotions and adjust the difficulty of the learning content based on the estimated subject's emotions. For example, if the subject is relaxed, more difficult content can be provided. If the subject is nervous, less difficult content can be provided. Furthermore, if the subject is excited, more challenging content can be provided. In this way, the learning effect can be improved by adjusting the difficulty of the learning content according to the subject's emotions.

[0113] The generation unit can also estimate the subject's emotions and adjust the visual presentation of the summary based on the estimated subject's emotions. For example, if the subject is relaxed, a colorful and visually appealing summary can be provided. If the subject is nervous, a summary with a simple and calm design can be provided. Furthermore, if the subject is excited, a summary using dynamic animation can be provided. This makes it possible to improve learning effectiveness by adjusting the visual presentation according to the subject's emotions.

[0114] The detection unit can also estimate the subject's emotions and adjust the timing of detecting the non-REM sleep state based on the estimated emotions of the subject. For example, if the subject is relaxed, the non-REM sleep state can be detected earlier. Also, if the subject is tense, the non-REM sleep state can be detected later. Furthermore, if the subject is excited, the detection timing can be flexibly adjusted according to changes in emotions. This allows for accurate detection by adjusting the detection timing according to the subject's emotions.

[0115] The playback unit can also estimate the subject's emotions and adjust the playback speed of the audio data based on the estimated subject's emotions. For example, if the subject is relaxed, the audio data can be played back at a slow playback speed. If the subject is nervous, the audio data can be played back at a faster playback speed. Furthermore, if the subject is excited, the audio data can be played back at a variable playback speed. In this way, the learning effect can be improved by adjusting the playback speed according to the subject's emotions.

[0116] The playback unit can also estimate the subject's emotions and customize the playback content of the audio data based on the estimated subject's emotions. For example, if the subject is relaxed, detailed information can be played back. If the subject is nervous, brief information can be played back. Furthermore, if the subject is excited, visually stimulating information can be played back. In this way, customizing the playback content according to the subject's emotions can improve learning effectiveness.

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

[0118] Step 1: The input section inputs the text and audio information the subject learned before sleep into the generation AI. For example, this could be the contents of a textbook for an exam or a presentation script. Step 2: The generator uses a generation AI to analyze the input information and generate audio data summarizing the content to be memorized. For example, the generation AI may summarize the important points of a textbook or the key points of a presentation. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and generates a summary based on the input information. Step 3: The detector detects the subject's non-REM sleep state using an IoT device, such as a smartwatch or sleep tracker, to monitor the subject's sleep state and detect the non-REM sleep state. Step 4: The playback unit plays back the audio data generated during the non-REM sleep state detected by the detection unit. For example, when a non-REM sleep state is detected, the generated audio data is played back to promote memory consolidation in the subject.

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

[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 AI 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, 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. An input unit that inputs text information and audio information that the subject learned before sleeping into the generation AI; a generation unit that analyzes the information input by the input unit and generates audio data that summarizes the content to be stored; a detection unit that detects a non-REM sleep state of a subject; a playback unit that plays back audio data when the non-REM sleep state is detected by the detection unit; Equipped with A system characterized by:

2. The generation unit The generated AI analyzes the input information and generates audio data summarizing the content you want to remember.

2. The system of claim 1.

3. The detection unit Detect the subject's non-REM sleep state using at least one IoT device, either a smartwatch or a sleep tracker.

2. The system of claim 1.

4. The playback unit Playing back audio data generated during non-REM sleep 2. The system of claim 1.

5. The generation unit Generate audio summaries of key points from a textbook or presentation 2. The system of claim 1.

6. The playback unit Have important points for an exam or key points from a presentation played while you sleep 2. The system of claim 1.

7. The input unit Estimate the target person's emotions and prioritize the information to be input based on the estimated emotions of the target person.

2. The system of claim 1.

8. The input unit Analyze the target person's past learning history and select the optimal input method 2. The system of claim 1.

9. The input unit As you type, filter based on your audience's current learning status and interests 2. The system of claim 1.

Images