system

Abstract

The system according to the embodiment aims to provide immediate and appropriate answers to various questions that children have. [Solution] The system according to the embodiment comprises a voice input unit, an image receiving unit, an analysis unit, an answer generation unit, and an answer provision unit. The voice input unit receives the child's question by voice. The image receiving unit receives images taken by the child. The analysis unit analyzes the information input by the voice input unit and the image receiving unit. The answer generation unit generates an answer based on the information analyzed by the analysis unit. The answer provision unit provides the answer generated by the answer generation unit to the child.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem of making it difficult to provide immediate and appropriate answers to the various questions that children have.

[0005] The system according to the embodiment aims to provide immediate and appropriate answers to various questions that children have. [Means for solving the problem]

[0006] The system according to this embodiment comprises a voice input unit, an image receiving unit, an analysis unit, an answer generation unit, and an answer provision unit. The voice input unit receives the child's question by voice. The image receiving unit receives images taken by the child. The analysis unit analyzes the information input by the voice input unit and the image receiving unit. The answer generation unit generates an answer based on the information analyzed by the analysis unit. The answer provision unit provides the answer generated by the answer generation unit to the child. [Effects of the Invention]

[0007] The system according to the embodiment can provide immediate and appropriate answers to various questions that children have. [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 of form 1) The system according to an embodiment of the present invention is an IoT device equipped with AI tuned for children, enabling questions and answers via image attachment or voice input. The system begins with a child entering a question by voice or attaching an image. Next, the AI ​​analyzes the input information and generates an appropriate answer. Finally, the AI ​​provides the child with the generated answer. This system allows children to instantly obtain answers to their interests and questions, expanding their knowledge. Furthermore, in difficult situations such as arguments with parents, the AI ​​can provide appropriate advice, helping to care for the child's emotional well-being. For example, if a child wants to know information about a shop they saw in town, they take a picture of the shop and send it to the system. Also, if a child seeks advice after an argument with their parents, they describe the situation by voice. Next, the AI ​​analyzes the input information. In the case of an image, the AI ​​uses image recognition technology to identify objects and locations in the photograph. In the case of voice, the AI ​​uses voice recognition technology to understand the child's question. For example, if the child wants to know the name of an insect in a photograph, the AI ​​identifies the insect and provides its name. Furthermore, the AI ​​generates an appropriate answer based on the analysis results. For example, if a child asks for information about a shop they see in town, the AI ​​will provide information such as the shop's name, opening hours, and menu. Also, if a child asks for advice after an argument with their parents, the AI ​​will provide appropriate advice. Finally, the AI ​​provides the child with a generated response. When the response is given verbally, the AI ​​reads the answer aloud in a gentle tone. When the response is given in text, the AI ​​displays the answer in simple language that is easy for the child to understand. This system allows children to get instant answers to their interests and questions, expanding their knowledge. Furthermore, in difficult situations such as arguments with parents, the AI ​​can provide appropriate advice, helping to support the child's emotional well-being. Thus, an AI system tuned for children and integrated into an IoT device can provide quick and appropriate answers to children's questions. Furthermore, in difficult situations such as arguments with parents, the AI ​​can provide appropriate advice, helping to support the child's emotional well-being.

[0029] The AI ​​system tuned for children, installed in the IoT device according to the embodiment, comprises a voice input unit, an image reception unit, an analysis unit, an answer generation unit, and an answer provision unit. The voice input unit receives the child's question by voice. For example, if the child asks, "What is the name of this insect?", the voice input unit receives the voice. The voice input unit collects the voice using a microphone, for example, and converts it into text data using speech recognition technology. Speech recognition technology includes, for example, a speech recognition model using deep learning. The image reception unit receives images taken by the child. For example, the child takes a picture of a shop they see in town and sends it to the image reception unit. The image reception unit collects the image using a camera, for example, and converts it into analyzable data using image recognition technology. Image recognition technology includes, for example, a convolutional neural network (CNN). The analysis unit analyzes the information input by the voice input unit and the image reception unit. For example, it analyzes the text data from the voice input unit and the image data from the image reception unit to understand the content of the question. The analysis unit analyzes text data using, for example, natural language processing technology and analyzes image data using image recognition technology. The answer generation unit generates an appropriate answer based on the information analyzed by the analysis unit. For example, if the analysis unit understands the question "What is the name of this insect?", the answer generation unit generates the name of the insect as the answer. The answer generation unit generates the answer by referring to, for example, a knowledge base. The knowledge base includes, for example, encyclopedias and information on the internet. The answer provision unit provides the answer generated by the answer generation unit to the child. For example, if the answer is to be read aloud, the answer provision unit reads the answer aloud using speech synthesis technology. Speech synthesis technology includes, for example, text-to-speech (TTS). If the answer is to be displayed as text, the answer provision unit displays the answer on the display. As a result, the child-tuned AI system installed in the IoT device according to the embodiment can provide quick and appropriate answers to children's questions.

[0030] The analysis unit can identify objects and locations in a photograph using image recognition technology. Image recognition technology includes, for example, object recognition and location recognition. The analysis unit analyzes an image using, for example, a convolutional neural network (CNN) to identify objects and locations in the photograph. For example, when analyzing a photograph of an insect taken by a child, the analysis unit identifies the insect and provides its name to the answer generation unit. The analysis unit can also analyze a photograph of a shop seen in the city and identify information such as the shop's name, opening hours, and menu. In this way, by using image recognition technology, objects and locations in a photograph can be accurately identified.

[0031] The analysis unit can understand the content of a child's question using speech recognition technology. Speech recognition technology includes, for example, speech command recognition and natural language understanding. The analysis unit uses, for example, a deep learning-based speech recognition model to convert the child's question into text data and understand its content. For example, if a child asks, "Why is the sky blue?", the analysis unit understands the question and provides it to the answer generation unit. In this way, the content of the child's question can be accurately understood by using speech recognition technology.

[0032] The answer generation unit can generate appropriate answers based on the analysis results. The answer generation unit generates answers by referring to a knowledge base, for example. The knowledge base includes, for example, encyclopedias and information from the internet. For example, if the analysis unit understands the question "What is the name of this insect?", the answer generation unit retrieves the name of the insect from the knowledge base and generates it as an answer. Also, if the analysis unit understands the question "What should I do when I have a fight with my parents?", the answer generation unit retrieves appropriate advice from the knowledge base and generates it as an answer. In this way, by generating appropriate answers based on the analysis results, accurate answers can be provided to children's questions.

[0033] The answer providing unit can read the answer aloud. The answer providing unit reads the answer aloud using, for example, speech synthesis technology. Speech synthesis technology includes, for example, text-to-speech synthesis (TTS). For example, if the answer generating unit generates an answer such as "The name of this insect is a rhinoceros beetle," the answer providing unit reads the answer aloud. The answer providing unit can also read the answer aloud in a gentle tone for children. In this way, by reading the answer aloud, the answer can be provided in a form that is easy for children to understand.

[0034] The answer providing unit can display the answer in text. The answer providing unit displays the answer, for example, on a display. For example, if the answer generation unit generates an answer such as "The name of this insect is a rhinoceros beetle," the answer providing unit displays the answer on a display. The answer providing unit can also display the answer in simple terms that are easy for children to understand. In this way, by displaying the answer in text, the answer can be provided in a form that is visually easy for children to understand.

[0035] The voice input unit can analyze the child's past voice input history and select the optimal voice input method. The voice input unit, for example, analyzes the past voice input history and selects the most effective voice input method. For example, it analyzes the voice input methods used by the child in the past and selects the most effective method. It can also suggest the optimal voice input method for a specific time period based on the child's past voice input history. Furthermore, it can improve the accuracy of voice input based on the child's past voice input history. In this way, the optimal voice input method can be selected by analyzing the past voice input history.

[0036] The voice input unit can filter voice input based on the child's current interests and concerns. The voice input unit filters voice input based on, for example, topics in which the child is currently interested. For example, the voice input unit filters voice input based on topics in which the child is currently interested. It can also preferentially accept voice input related to the child's current interests. Furthermore, it can customize the content of the voice input based on the child's interests and concerns. As a result, by filtering voice input based on the child's interests and concerns, it is possible to accept more relevant voice input.

[0037] The voice input unit can preferentially accept highly relevant voice inputs by taking into account the child's geographical location information when inputting voice. For example, if the child is in a specific location, the voice input unit preferentially accepts voice inputs related to that location. For example, if the child is at the zoo, the voice input unit preferentially accepts questions about animals. The voice input unit can also filter relevant voice inputs based on the child's current location. Furthermore, the voice input unit can suggest an optimal voice input method by taking into account the child's geographical location information. In this way, highly relevant voice inputs can be preferentially accepted by taking into account the geographical location information.

[0038] The voice input unit can analyze the child's social media activity and accept related voice inputs when receiving voice input. For example, the voice input unit analyzes the child's social media activity and preferentially accepts related voice inputs. For example, if the child posts a lot about animals on social media, the voice input unit preferentially accepts questions about animals. The voice input content can also be customized based on the child's social media activity. Furthermore, the optimal voice input method can be suggested taking the child's social media activity into consideration. In this way, by analyzing social media activity, related voice inputs can be preferentially accepted.

[0039] The image reception unit can analyze the child's past image reception history and select the optimal image reception method. The image reception unit, for example, analyzes the past image reception history and selects the most effective image reception method. For example, it analyzes the image reception methods used by the child in the past and selects the most effective method. It can also suggest the optimal image reception method for a specific time period based on the child's past image reception history. Furthermore, it can also improve the accuracy of image reception based on the child's past image reception history. In this way, the optimal image reception method can be selected by analyzing the past image reception history.

[0040] The image receiving unit can perform filtering based on the child's current interests and concerns when receiving images. The image receiving unit filters the image reception based on, for example, topics in which the child is currently interested. For example, the image reception unit filters the image reception based on topics in which the child is currently interested. It can also preferentially receive related images based on the child's current interests. Furthermore, it can also customize the content of the image reception based on the child's interests and concerns. In this way, by filtering the image reception based on the child's interests and concerns, it is possible to receive more relevant images.

[0041] When receiving images, the image receiving unit can preferentially receive highly relevant images by taking into account the child's geographical location information. For example, if the child is in a specific location, the image receiving unit preferentially receives images related to that location. For example, if the child is at a zoo, the image receiving unit preferentially receives images related to animals. The image receiving unit can also filter related images based on the child's current location. Furthermore, the image receiving unit can also propose an optimal image receiving method by taking into account the child's geographical location information. In this way, highly relevant images can be preferentially received by taking into account the geographical location information.

[0042] The image reception unit can analyze a child's social media activity when receiving images and accept relevant images. For example, the image reception unit can analyze a child's social media activity and prioritize accepting relevant images. For instance, if a child frequently posts about animals on social media, it will prioritize accepting images related to animals. It can also customize the content of image reception based on the child's social media activity. Furthermore, it can suggest the optimal image reception method considering the child's social media activity. This allows for the priority acceptance of relevant images by analyzing social media activity.

[0043] The analysis unit can improve the accuracy of the analysis by considering the interrelationships of the input information during the analysis. For example, the analysis unit analyzes the interrelationships of the input information to improve the accuracy of the analysis. For example, if a child asks, "What is the name of this insect?" and simultaneously sends a picture of the insect, the analysis unit will perform the analysis considering the interrelationships between the audio data and the image data. It can also improve the accuracy of the analysis by considering the relationships between the input information. Furthermore, it can improve the accuracy of the analysis based on the interrelationships of the input information. In this way, the accuracy of the analysis can be improved by considering the interrelationships of the input information.

[0044] The analysis unit can perform analysis while considering the child's attribute information. For example, the analysis unit can improve the accuracy of the analysis by considering attribute information such as the child's age and gender. For example, if the child is 7 years old, the analysis unit will consider age information to generate answers appropriate for that age. It can also customize the content of the analysis by considering the child's learning history and interests. Furthermore, it can select the optimal analysis method based on the child's attribute information. In this way, more appropriate analysis can be performed by considering the child's attribute information.

[0045] The analysis unit can perform the analysis while taking into account the geographical distribution of the input information. For example, the analysis unit analyzes the geographical distribution of the input information to improve the accuracy of the analysis. For example, if a child asks a question about a specific region, the analysis unit prioritizes analysis of information related to that region. It is also possible to prioritize analysis of related information based on the geographical distribution. Furthermore, it is also possible to select the optimal analysis method by taking the geographical distribution into account. In this way, more appropriate analysis can be performed by taking the geographical distribution into account.

[0046] The analysis unit can improve the accuracy of the analysis by referring to related literature during analysis. For example, if a child asks, "Why is the sky blue?", the analysis unit will refer to related scientific literature to generate an accurate answer. The content of the analysis can also be customized based on information from related literature. Furthermore, the optimal analysis method can be selected taking related literature into consideration. In this way, the accuracy of the analysis can be improved by referring to related literature.

[0047] The answer generation unit can adjust the level of detail of the answer based on the importance of the analysis result when generating an answer. The answer generation unit adjusts the level of detail of the answer based on, for example, the importance of the analysis result. For example, a detailed answer is generated based on an important analysis result. A concise answer can also be generated based on an analysis result with a low importance. Furthermore, the optimal level of detail of the answer can be selected taking into account the importance of the analysis result. In this way, by adjusting the level of detail of the answer based on the importance of the analysis result, a more appropriate answer can be provided.

[0048] The answer generation unit can apply different answer algorithms depending on the question category when generating an answer. For example, the answer generation unit applies different answer algorithms depending on the question category. For example, a scientific answer algorithm can be applied to a question about science. A historical answer algorithm can also be applied to a question about history. Furthermore, a practical answer algorithm can be applied to a question about daily life. In this way, by applying different answer algorithms depending on the question category, more appropriate answers can be provided.

[0049] When generating an answer, the answer generation unit can determine the priority of the answers based on the time when the question was submitted. The answer generation unit determines the priority of the answers based on, for example, the time when the question was submitted. For example, if the question is urgent, the answer is generated preferentially. Also, if the question is from the past, the answer can be generated later. Furthermore, the optimal priority of the answers can be determined taking into account the time when the question was submitted. In this way, by determining the priority of the answers based on the time when the question was submitted, answers can be provided in a more appropriate order.

[0050] The answer generation unit can adjust the order of answers based on the relevance of the question when generating an answer. The answer generation unit adjusts the order of answers based on, for example, the relevance of the question. For example, if the question is highly relevant, the answer can be generated preferentially. Also, if the question is less relevant, the answer can be generated later. Furthermore, the optimal order of answers can be determined taking into account the relevance of the question. In this way, by adjusting the order of answers based on the relevance of the question, answers can be provided in a more appropriate order.

[0051] When providing an answer, the answer providing unit can select the optimal answer providing method by referring to the child's past question history. The answer providing unit, for example, selects the optimal answer providing method by referring to the past question history. For example, the optimal answer providing method is selected by referring to the answer providing method that the child has previously preferred. The answer providing unit can also suggest the optimal answer providing method based on the child's past question history. Furthermore, the answer providing method can be customized based on the child's past question history. In this way, the optimal answer providing method can be selected by referring to the past question history.

[0052] When providing an answer, the answer providing unit can select the optimal answer providing method by taking into consideration device information about the child. The answer providing unit selects the optimal answer providing method by taking into consideration, for example, information about the device the child is using. For example, if the child is using a smartphone, the answer providing unit selects a answer providing method that suits the screen size. Also, if the child is using a tablet, it can select a answer providing method that is optimized for a large screen. Furthermore, if the child is using a smartwatch, it can select a simple answer providing method with high visibility. In this way, it is possible to select the optimal answer providing method by taking into consideration device information.

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

[0054] The answer generation unit can analyze the child's past question history and generate the most appropriate answer. For example, if the child has asked the same question in the past, the unit can generate a new answer by referring to the answer. It can also generate an answer by extracting related information from the child's past question history. Furthermore, it can improve the accuracy of the answer based on the child's past question history. In this way, it is possible to provide a more appropriate answer by analyzing the past question history.

[0055] The analysis unit can evaluate the reliability of the input information and prioritize analysis of highly reliable information. For example, data from highly reliable information sources can be analyzed with priority. Data from less reliable information sources can also be analyzed later. Furthermore, the accuracy of the analysis can be improved based on the reliability of the input information. This makes it possible to provide more accurate information by prioritizing analysis of highly reliable information.

[0056] The analysis unit can improve the accuracy of the analysis by taking into account the interrelationships between the input information. For example, if a child asks, "What is the name of this insect?" and simultaneously sends a photo of the insect, the analysis unit will perform the analysis by taking into account the interrelationships between the voice data and image data. The accuracy of the analysis can also be improved by taking into account the relevance of the input information. Furthermore, the accuracy of the analysis can also be improved based on the interrelationships between the input information. In this way, the accuracy of the analysis can be improved by taking into account the interrelationships between the input information.

[0057] The analysis unit can perform analysis taking into account the geographical distribution of the input information. For example, if a child asks a question about a specific region, information related to that region is prioritized for analysis. It is also possible to prioritize analysis of related information based on geographical distribution. Furthermore, it is also possible to select the optimal analysis method taking geographical distribution into consideration. This allows for more appropriate analysis by taking geographical distribution into consideration.

[0058] The answer generation unit can apply different answering algorithms depending on the category of the question. For example, a scientific answering algorithm can be applied to a question about science. A historical answering algorithm can be applied to a question about history. Furthermore, a practical answering algorithm can be applied to a question about daily life. In this way, by applying different answering algorithms depending on the category of the question, more appropriate answers can be provided.

[0059] When providing an answer, the answer providing unit can select the optimal answer providing method by taking into consideration device information about the child. For example, the optimal answer providing method is selected by taking into consideration information about the device the child is using. For example, if the child is using a smartphone, a method of providing answers that matches the screen size can be selected. Also, if the child is using a tablet, a method of providing answers that is optimized for a large screen can be selected. Furthermore, if the child is using a smartwatch, a method of providing answers that is concise and highly visible can be selected. In this way, the optimal answer providing method can be selected by taking into consideration device information.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The voice input unit inputs the child's question by voice. For example, if a child asks, "What is the name of this insect?", the voice input unit accepts the voice. The voice input unit collects the voice using a microphone and converts it into text data using voice recognition technology. The voice recognition technology includes a voice recognition model that uses deep learning. Step 2: The image reception unit receives images taken by the child. For example, the child may take a photo of a shop they see in town and send it to the image reception unit. The image reception unit collects images using a camera and converts them into analyzable data using image recognition technology, which includes convolutional neural networks (CNN). Step 3: The analysis unit analyzes the information input by the voice input unit and the image reception unit. For example, it analyzes the text data from the voice input unit and the image data from the image reception unit to understand the content of the question. The analysis unit analyzes the text data using natural language processing technology and the image data using image recognition technology. Step 4: The answer generator generates an appropriate answer based on the information analyzed by the analyzer. For example, if the analyzer understands the question "What is the name of this insect?", the answer generator generates the name of the insect as the answer. The answer generator generates the answer by referring to a knowledge base. The knowledge base includes information from encyclopedias and the Internet. Step 5: The answer provider provides the child with the answer generated by the answer generation unit. For example, if the answer is to be read aloud, the answer provider uses speech synthesis technology to read the answer aloud. Speech synthesis technology includes text-to-speech (TTS). If the answer is to be displayed as text, the answer provider displays the answer on the display.

[0062] (Example 2) The system according to an embodiment of the present invention is an IoT device equipped with AI tuned for children, enabling questions and answers via image attachment or voice input. The system begins with a child entering a question by voice or attaching an image. Next, the AI ​​analyzes the input information and generates an appropriate answer. Finally, the AI ​​provides the child with the generated answer. This system allows children to instantly obtain answers to their interests and questions, expanding their knowledge. Furthermore, in difficult situations such as arguments with parents, the AI ​​can provide appropriate advice, helping to care for the child's emotional well-being. For example, if a child wants to know information about a shop they saw in town, they take a picture of the shop and send it to the system. Also, if a child seeks advice after an argument with their parents, they describe the situation by voice. Next, the AI ​​analyzes the input information. In the case of an image, the AI ​​uses image recognition technology to identify objects and locations in the photograph. In the case of voice, the AI ​​uses voice recognition technology to understand the child's question. For example, if the child wants to know the name of an insect in a photograph, the AI ​​identifies the insect and provides its name. Furthermore, the AI ​​generates an appropriate answer based on the analysis results. For example, if a child asks for information about a shop they see in town, the AI ​​will provide information such as the shop's name, opening hours, and menu. Also, if a child asks for advice after an argument with their parents, the AI ​​will provide appropriate advice. Finally, the AI ​​provides the child with a generated response. When the response is given verbally, the AI ​​reads the answer aloud in a gentle tone. When the response is given in text, the AI ​​displays the answer in simple language that is easy for the child to understand. This system allows children to get instant answers to their interests and questions, expanding their knowledge. Furthermore, in difficult situations such as arguments with parents, the AI ​​can provide appropriate advice, helping to support the child's emotional well-being. Thus, an AI system tuned for children and integrated into an IoT device can provide quick and appropriate answers to children's questions. Furthermore, in difficult situations such as arguments with parents, the AI ​​can provide appropriate advice, helping to support the child's emotional well-being.

[0063] The AI ​​system tuned for children, installed in the IoT device according to the embodiment, comprises a voice input unit, an image reception unit, an analysis unit, an answer generation unit, and an answer provision unit. The voice input unit receives the child's question by voice. For example, if the child asks, "What is the name of this insect?", the voice input unit receives the voice. The voice input unit collects the voice using a microphone, for example, and converts it into text data using speech recognition technology. Speech recognition technology includes, for example, a speech recognition model using deep learning. The image reception unit receives images taken by the child. For example, the child takes a picture of a shop they see in town and sends it to the image reception unit. The image reception unit collects the image using a camera, for example, and converts it into analyzable data using image recognition technology. Image recognition technology includes, for example, a convolutional neural network (CNN). The analysis unit analyzes the information input by the voice input unit and the image reception unit. For example, it analyzes the text data from the voice input unit and the image data from the image reception unit to understand the content of the question. The analysis unit analyzes text data using, for example, natural language processing technology and analyzes image data using image recognition technology. The answer generation unit generates an appropriate answer based on the information analyzed by the analysis unit. For example, if the analysis unit understands the question "What is the name of this insect?", the answer generation unit generates the name of the insect as the answer. The answer generation unit generates the answer by referring to, for example, a knowledge base. The knowledge base includes, for example, encyclopedias and information on the internet. The answer provision unit provides the answer generated by the answer generation unit to the child. For example, if the answer is to be read aloud, the answer provision unit reads the answer aloud using speech synthesis technology. Speech synthesis technology includes, for example, text-to-speech (TTS). If the answer is to be displayed as text, the answer provision unit displays the answer on the display. As a result, the child-tuned AI system installed in the IoT device according to the embodiment can provide quick and appropriate answers to children's questions.

[0064] The analysis unit can identify objects and locations in a photograph using image recognition technology. Image recognition technology includes, for example, object recognition and location recognition. The analysis unit analyzes an image using, for example, a convolutional neural network (CNN) to identify objects and locations in the photograph. For example, when analyzing a photograph of an insect taken by a child, the analysis unit identifies the insect and provides its name to the answer generation unit. The analysis unit can also analyze a photograph of a shop seen in the city and identify information such as the shop's name, opening hours, and menu. In this way, by using image recognition technology, objects and locations in a photograph can be accurately identified.

[0065] The analysis unit can understand the content of a child's question using speech recognition technology. Speech recognition technology includes, for example, speech command recognition and natural language understanding. The analysis unit uses, for example, a deep learning-based speech recognition model to convert the child's question into text data and understand its content. For example, if a child asks, "Why is the sky blue?", the analysis unit understands the question and provides it to the answer generation unit. In this way, the content of the child's question can be accurately understood by using speech recognition technology.

[0066] The answer generation unit can generate appropriate answers based on the analysis results. The answer generation unit generates answers by referring to a knowledge base, for example. The knowledge base includes, for example, encyclopedias and information from the internet. For example, if the analysis unit understands the question "What is the name of this insect?", the answer generation unit retrieves the name of the insect from the knowledge base and generates it as an answer. Also, if the analysis unit understands the question "What should I do when I have a fight with my parents?", the answer generation unit retrieves appropriate advice from the knowledge base and generates it as an answer. In this way, by generating appropriate answers based on the analysis results, accurate answers can be provided to children's questions.

[0067] The answer providing unit can read the answer aloud. The answer providing unit reads the answer aloud using, for example, speech synthesis technology. Speech synthesis technology includes, for example, text-to-speech synthesis (TTS). For example, if the answer generating unit generates an answer such as "The name of this insect is a rhinoceros beetle," the answer providing unit reads the answer aloud. The answer providing unit can also read the answer aloud in a gentle tone for children. In this way, by reading the answer aloud, the answer can be provided in a form that is easy for children to understand.

[0068] The answer providing unit can display the answer in text. The answer providing unit displays the answer, for example, on a display. For example, if the answer generation unit generates an answer such as "The name of this insect is a rhinoceros beetle," the answer providing unit displays the answer on a display. The answer providing unit can also display the answer in simple terms that are easy for children to understand. In this way, by displaying the answer in text, the answer can be provided in a form that is visually easy for children to understand.

[0069] The voice input unit can estimate the child's emotion and adjust the timing of voice input based on the estimated emotion of the child. The voice input unit estimates the child's emotion using, for example, facial expression recognition or voice tone analysis. For example, if the child is excited, the timing of voice input can be delayed to wait until the child calms down. Also, if the child is tired, the timing of voice input can be advanced to complete input in a short time. Furthermore, if the child is concentrating, the timing of voice input can be adjusted to maintain concentration. In this way, by adjusting the timing of voice input according to the child's emotion, voice input can be performed at a more appropriate timing.

[0070] The voice input unit can analyze the child's past voice input history and select the optimal voice input method. The voice input unit, for example, analyzes the past voice input history and selects the most effective voice input method. For example, it analyzes the voice input methods used by the child in the past and selects the most effective method. It can also suggest the optimal voice input method for a specific time period based on the child's past voice input history. Furthermore, it can improve the accuracy of voice input based on the child's past voice input history. In this way, the optimal voice input method can be selected by analyzing the past voice input history.

[0071] The voice input unit can filter voice input based on the child's current interests and concerns. The voice input unit filters voice input based on, for example, topics in which the child is currently interested. For example, the voice input unit filters voice input based on topics in which the child is currently interested. It can also preferentially accept voice input related to the child's current interests. Furthermore, it can customize the content of the voice input based on the child's interests and concerns. As a result, by filtering voice input based on the child's interests and concerns, it is possible to accept more relevant voice input.

[0072] The voice input unit can estimate a child's emotions and determine the priority of voice input based on those emotions. For example, the voice input unit estimates a child's emotions using facial recognition and voice tone analysis. If a child is excited, the priority of voice input can be lowered, and the system can wait until the child calms down. If a child is tired, the priority of voice input can be increased, allowing the input to be completed in a shorter time. Furthermore, if a child is concentrating, the priority of voice input can be adjusted to maintain their concentration. In this way, by determining the priority of voice input according to the child's emotions, voice input can be performed in a more appropriate order.

[0073] The voice input unit can preferentially accept highly relevant voice inputs by taking into account the child's geographical location information when inputting voice. For example, if the child is in a specific location, the voice input unit preferentially accepts voice inputs related to that location. For example, if the child is at the zoo, the voice input unit preferentially accepts questions about animals. The voice input unit can also filter relevant voice inputs based on the child's current location. Furthermore, the voice input unit can suggest an optimal voice input method by taking into account the child's geographical location information. In this way, highly relevant voice inputs can be preferentially accepted by taking into account the geographical location information.

[0074] The voice input unit can analyze the child's social media activity and accept related voice inputs when receiving voice input. For example, the voice input unit analyzes the child's social media activity and preferentially accepts related voice inputs. For example, if the child posts a lot about animals on social media, the voice input unit preferentially accepts questions about animals. The voice input content can also be customized based on the child's social media activity. Furthermore, the optimal voice input method can be suggested taking the child's social media activity into consideration. In this way, by analyzing social media activity, related voice inputs can be preferentially accepted.

[0075] The image reception unit can estimate the child's emotions and adjust the timing of image reception based on the estimated child's emotions. The image reception unit estimates the child's emotions using, for example, facial expression recognition or voice tone analysis. For example, if the child is excited, the timing of image reception can be delayed to wait until the child calms down. Also, if the child is tired, the timing of image reception can be accelerated to complete reception in a short time. Furthermore, if the child is concentrating, the timing of image reception can be adjusted to maintain concentration. In this way, by adjusting the timing of image reception according to the child's emotions, images can be received at a more appropriate timing.

[0076] The image reception unit can analyze the child's past image reception history and select the optimal image reception method. The image reception unit, for example, analyzes the past image reception history and selects the most effective image reception method. For example, it analyzes the image reception methods used by the child in the past and selects the most effective method. It can also suggest the optimal image reception method for a specific time period based on the child's past image reception history. Furthermore, it can also improve the accuracy of image reception based on the child's past image reception history. In this way, the optimal image reception method can be selected by analyzing the past image reception history.

[0077] The image receiving unit can perform filtering based on the child's current interests and concerns when receiving images. The image receiving unit filters the image reception based on, for example, topics in which the child is currently interested. For example, the image reception unit filters the image reception based on topics in which the child is currently interested. It can also preferentially receive related images based on the child's current interests. Furthermore, it can also customize the content of the image reception based on the child's interests and concerns. In this way, by filtering the image reception based on the child's interests and concerns, it is possible to receive more relevant images.

[0078] The image reception unit can estimate a child's emotions and determine the priority of images to receive based on those emotions. For example, the image reception unit estimates a child's emotions using facial recognition or voice tone analysis. If a child is excited, the priority of images to receive is lowered, and the system waits until the child calms down. If a child is tired, the priority of images to receive is increased, allowing the reception to be completed quickly. Furthermore, if a child is concentrating, the priority of images to receive is adjusted to maintain their concentration. In this way, by determining the priority of images to receive according to the child's emotions, images can be received in a more appropriate order.

[0079] When receiving images, the image receiving unit can preferentially receive highly relevant images by taking into account the child's geographical location information. For example, if the child is in a specific location, the image receiving unit preferentially receives images related to that location. For example, if the child is at a zoo, the image receiving unit preferentially receives images related to animals. The image receiving unit can also filter related images based on the child's current location. Furthermore, the image receiving unit can also propose an optimal image receiving method by taking into account the child's geographical location information. In this way, highly relevant images can be preferentially received by taking into account the geographical location information.

[0080] The image reception unit can analyze a child's social media activity when receiving images and accept relevant images. For example, the image reception unit can analyze a child's social media activity and prioritize accepting relevant images. For instance, if a child frequently posts about animals on social media, it will prioritize accepting images related to animals. It can also customize the content of image reception based on the child's social media activity. Furthermore, it can suggest the optimal image reception method considering the child's social media activity. This allows for the priority acceptance of relevant images by analyzing social media activity.

[0081] The analysis unit can estimate the child's emotions and adjust the analysis criteria based on the estimated child's emotions. The analysis unit estimates the child's emotions using, for example, facial expression recognition or voice tone analysis. For example, if the child is excited, the analysis criteria can be relaxed to perform a flexible analysis. Also, if the child is tired, the analysis criteria can be tightened to complete the analysis in a short time. Furthermore, if the child is concentrating, the analysis criteria can be adjusted to maintain concentration. In this way, by adjusting the analysis criteria according to the child's emotions, more appropriate analysis can be performed.

[0082] The analysis unit can improve the accuracy of the analysis by considering the interrelationships of the input information during the analysis. For example, the analysis unit analyzes the interrelationships of the input information to improve the accuracy of the analysis. For example, if a child asks, "What is the name of this insect?" and simultaneously sends a picture of the insect, the analysis unit will perform the analysis considering the interrelationships between the audio data and the image data. It can also improve the accuracy of the analysis by considering the relationships between the input information. Furthermore, it can improve the accuracy of the analysis based on the interrelationships of the input information. In this way, the accuracy of the analysis can be improved by considering the interrelationships of the input information.

[0083] The analysis unit can perform analysis while considering the child's attribute information. For example, the analysis unit can improve the accuracy of the analysis by considering attribute information such as the child's age and gender. For example, if the child is 7 years old, the analysis unit will consider age information to generate answers appropriate for that age. It can also customize the content of the analysis by considering the child's learning history and interests. Furthermore, it can select the optimal analysis method based on the child's attribute information. In this way, more appropriate analysis can be performed by considering the child's attribute information.

[0084] The analysis unit can estimate a child's emotions and adjust the display order of the analysis results based on the estimated emotions. For example, the analysis unit estimates a child's emotions using facial recognition or voice tone analysis. For instance, if a child is excited, important information is displayed first. If a child is tired, concise information can be displayed first. Furthermore, if a child is concentrating, detailed information can be displayed first. By adjusting the display order of the analysis results according to the child's emotions, information can be provided in a more appropriate order.

[0085] The analysis unit can perform the analysis while taking into account the geographical distribution of the input information. For example, the analysis unit analyzes the geographical distribution of the input information to improve the accuracy of the analysis. For example, if a child asks a question about a specific region, the analysis unit prioritizes analysis of information related to that region. It is also possible to prioritize analysis of related information based on the geographical distribution. Furthermore, it is also possible to select the optimal analysis method by taking the geographical distribution into account. In this way, more appropriate analysis can be performed by taking the geographical distribution into account.

[0086] The analysis unit can improve the accuracy of the analysis by referring to related literature during analysis. For example, if a child asks, "Why is the sky blue?", the analysis unit will refer to related scientific literature to generate an accurate answer. The content of the analysis can also be customized based on information from related literature. Furthermore, the optimal analysis method can be selected taking related literature into consideration. In this way, the accuracy of the analysis can be improved by referring to related literature.

[0087] The response generation unit can estimate the child's emotions and adjust the way the response is expressed based on the estimated emotions. For example, the response generation unit estimates the child's emotions using facial recognition or voice tone analysis. For instance, if the child is excited, it uses concise and easy-to-understand language. If the child is tired, it can provide a short sentence in the response. Furthermore, if the child is concentrating, it can provide a response that includes detailed explanations. In this way, by adjusting the way the response is expressed according to the child's emotions, it can provide a more appropriate response.

[0088] The answer generation unit can adjust the level of detail of the answer based on the importance of the analysis result when generating an answer. The answer generation unit adjusts the level of detail of the answer based on, for example, the importance of the analysis result. For example, a detailed answer is generated based on an important analysis result. A concise answer can also be generated based on an analysis result with a low importance. Furthermore, the optimal level of detail of the answer can be selected taking into account the importance of the analysis result. In this way, by adjusting the level of detail of the answer based on the importance of the analysis result, a more appropriate answer can be provided.

[0089] The answer generation unit can apply different answer algorithms depending on the question category when generating an answer. For example, the answer generation unit applies different answer algorithms depending on the question category. For example, a scientific answer algorithm can be applied to a question about science. A historical answer algorithm can also be applied to a question about history. Furthermore, a practical answer algorithm can be applied to a question about daily life. In this way, by applying different answer algorithms depending on the question category, more appropriate answers can be provided.

[0090] The answer generation unit can estimate the child's emotion and adjust the length of the answer based on the estimated emotion of the child. The answer generation unit estimates the child's emotion using, for example, facial expression recognition or voice tone analysis. For example, if the child is excited, a short answer can be provided. Also, if the child is tired, a concise answer can be provided. Furthermore, if the child is concentrating, a detailed answer can be provided. In this way, by adjusting the length of the answer according to the child's emotion, a more appropriate answer can be provided.

[0091] When generating an answer, the answer generation unit can determine the priority of the answers based on the time when the question was submitted. The answer generation unit determines the priority of the answers based on, for example, the time when the question was submitted. For example, if the question is urgent, the answer is generated preferentially. Also, if the question is from the past, the answer can be generated later. Furthermore, the optimal priority of the answers can be determined taking into account the time when the question was submitted. In this way, by determining the priority of the answers based on the time when the question was submitted, answers can be provided in a more appropriate order.

[0092] The answer generation unit can adjust the order of answers based on the relevance of the question when generating an answer. The answer generation unit adjusts the order of answers based on, for example, the relevance of the question. For example, if the question is highly relevant, the answer can be generated preferentially. Also, if the question is less relevant, the answer can be generated later. Furthermore, the optimal order of answers can be determined taking into account the relevance of the question. In this way, by adjusting the order of answers based on the relevance of the question, answers can be provided in a more appropriate order.

[0093] The answer providing unit can estimate the child's emotions and adjust the method of providing the answers based on the estimated child's emotions. The answer providing unit estimates the child's emotions using, for example, facial expression recognition or voice tone analysis. For example, if the child is excited, the answer can be provided in a calm voice. Also, if the child is tired, the answer can be provided in simple words. Furthermore, if the child is concentrating, the answer can be provided with detailed explanations. In this way, by adjusting the method of providing the answers according to the child's emotions, the answer can be provided in a more appropriate manner.

[0094] When providing an answer, the answer providing unit can select the optimal answer providing method by referring to the child's past question history. The answer providing unit, for example, selects the optimal answer providing method by referring to the past question history. For example, the optimal answer providing method is selected by referring to the answer providing method that the child has previously preferred. The answer providing unit can also suggest the optimal answer providing method based on the child's past question history. Furthermore, the answer providing method can be customized based on the child's past question history. In this way, the optimal answer providing method can be selected by referring to the past question history.

[0095] The answer providing unit can estimate the child's emotions and adjust the procedure for providing the answers based on the estimated child's emotions. The answer providing unit estimates the child's emotions using, for example, facial expression recognition or voice tone analysis. For example, if the child is excited, the answer can be provided using calm procedures. Also, if the child is tired, the answer can be provided using simple procedures. Furthermore, if the child is concentrating, the answer can be provided using detailed procedures. In this way, by adjusting the procedure for providing the answers according to the child's emotions, it is possible to provide answers using more appropriate procedures.

[0096] When providing an answer, the answer providing unit can select the optimal answer providing method by taking into consideration device information about the child. The answer providing unit selects the optimal answer providing method by taking into consideration, for example, information about the device the child is using. For example, if the child is using a smartphone, the answer providing unit selects a answer providing method that suits the screen size. Also, if the child is using a tablet, it can select a answer providing method that is optimized for a large screen. Furthermore, if the child is using a smartwatch, it can select a simple answer providing method with high visibility. In this way, it is possible to select the optimal answer providing method by taking into consideration device information. === Hard Collateral 1-1 === Each of the multiple elements, including the voice input unit, image receiving unit, analysis unit, answer generation unit, and answer providing 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 voice input unit collects voice using the microphone 38B of the smart device 14 and converts it into text data using voice recognition technology by the control unit 46A. The image receiving unit collects images using the camera 42 of the smart device 14 and converts them into analyzable data using image recognition technology by the control unit 46A. The analysis unit analyzes the voice data and image data using the specific processing unit 290 of the data processing device 12 to understand the content of the question. The answer generating unit generates an appropriate answer by referring to a knowledge base using the specific processing unit 290 of the data processing device 12. The answer providing unit reads out the answer using voice synthesis technology using the speaker 40B of the smart device 14, or displays the answer on the display 40A. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned voice input unit, image receiving unit, analysis unit, answer generation unit, and answer providing unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the voice input unit collects voice using the microphone 238 of the smart glasses 214 and converts it into text data using voice recognition technology by the control unit 46A. The image receiving unit collects images using the camera 42 of the smart glasses 214 and converts them into analyzable data using image recognition technology by the control unit 46A. The analysis unit analyzes the voice data and image data using the specific processing unit 290 of the data processing device 12 to understand the content of the question. The answer generation unit generates an appropriate answer by referring to a knowledge base using the specific processing unit 290 of the data processing device 12. The answer providing unit reads out the answer using voice synthesis technology using the speaker 240 of the smart glasses 214, or displays the answer on a display. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned voice input unit, image receiving unit, analysis unit, answer generation unit, and answer providing unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the voice input unit collects voice using the microphone 238 of the headset-type terminal 314 and converts it into text data using voice recognition technology by the control unit 46A. The image receiving unit collects images using the camera 42 of the headset-type terminal 314 and converts them into analyzable data using image recognition technology by the control unit 46A. The analysis unit analyzes the voice data and image data using the specific processing unit 290 of the data processing device 12 to understand the content of the question. The answer generation unit generates an appropriate answer by referring to a knowledge base using the specific processing unit 290 of the data processing device 12. The answer providing unit reads out the answer using voice synthesis technology using the speaker 240 of the headset-type terminal 314, or displays the answer on the display 343. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned voice input unit, image receiving unit, analysis unit, answer generation unit, and answer providing unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the voice input unit collects voice using the microphone 238 of the robot 414 and converts it into text data using voice recognition technology by the control unit 46A. The image receiving unit collects images using the camera 42 of the robot 414 and converts them into analyzable data using image recognition technology by the control unit 46A. The analysis unit analyzes the voice data and image data using the specific processing unit 290 of the data processing device 12 to understand the content of the question. The answer generation unit generates an appropriate answer by referring to a knowledge base using the specific processing unit 290 of the data processing device 12. The answer providing unit reads out the answer using voice synthesis technology using the speaker 240 of the robot 414, or displays the answer on a display.

[0097] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0098] The analysis unit can estimate the child's emotions and adjust the analysis priority based on the estimated emotions. For example, if the child is excited, the analysis unit can prioritize analyzing information with high importance. Also, if the child is tired, the analysis unit can prioritize analyzing brief information. Furthermore, if the child is concentrating, the analysis unit can prioritize analyzing detailed information. In this way, by adjusting the analysis priority according to the child's emotions, more appropriate information can be provided.

[0099] The answer generation unit can analyze the child's past question history and generate the most appropriate answer. For example, if the child has asked the same question in the past, the unit can generate a new answer by referring to the answer. It can also generate an answer by extracting related information from the child's past question history. Furthermore, it can improve the accuracy of the answer based on the child's past question history. In this way, it is possible to provide a more appropriate answer by analyzing the past question history.

[0100] The answer providing unit can estimate the child's emotions and adjust the way in which the answer is provided based on the estimated emotions. For example, if the child is excited, the answer can be provided in a calm voice. If the child is tired, the answer can be provided in simple words. Furthermore, if the child is concentrating, the answer can be provided with detailed explanations. In this way, by adjusting the way in which the answer is provided according to the child's emotions, the answer can be provided in a more appropriate manner.

[0101] The analysis unit can evaluate the reliability of the input information and prioritize analysis of highly reliable information. For example, data from highly reliable information sources can be analyzed with priority. Data from less reliable information sources can also be analyzed later. Furthermore, the accuracy of the analysis can be improved based on the reliability of the input information. This makes it possible to provide more accurate information by prioritizing analysis of highly reliable information.

[0102] The answer generation unit can estimate the child's emotions and adjust the way the answer is expressed based on the estimated emotions. For example, if the child is excited, concise and easy-to-understand expressions can be used. If the child is tired, an answer can be provided in short sentences. Furthermore, if the child is concentrating, an answer including detailed explanations can be provided. In this way, by adjusting the way the answer is expressed based on the child's emotions, more appropriate answers can be provided.

[0103] The analysis unit can improve the accuracy of the analysis by taking into account the interrelationships between the input information. For example, if a child asks, "What is the name of this insect?" and simultaneously sends a photo of the insect, the analysis unit will perform the analysis by taking into account the interrelationships between the voice data and image data. The accuracy of the analysis can also be improved by taking into account the relevance of the input information. Furthermore, the accuracy of the analysis can also be improved based on the interrelationships between the input information. In this way, the accuracy of the analysis can be improved by taking into account the interrelationships between the input information.

[0104] The answer providing unit can estimate the child's emotions and adjust the answer providing procedure based on the estimated emotions. For example, if the child is excited, the answer can be provided in a calm manner. If the child is tired, the answer can be provided in a concise manner. Furthermore, if the child is concentrating, the answer can be provided in a detailed manner. In this way, by adjusting the answer providing procedure according to the child's emotions, it is possible to provide an answer in a more appropriate manner.

[0105] The analysis unit can perform analysis taking into account the geographical distribution of the input information. For example, if a child asks a question about a specific region, information related to that region is prioritized for analysis. It is also possible to prioritize analysis of related information based on geographical distribution. Furthermore, it is also possible to select the optimal analysis method taking geographical distribution into consideration. This allows for more appropriate analysis by taking geographical distribution into consideration.

[0106] The answer generation unit can apply different answering algorithms depending on the category of the question. For example, a scientific answering algorithm can be applied to a question about science. A historical answering algorithm can be applied to a question about history. Furthermore, a practical answering algorithm can be applied to a question about daily life. In this way, by applying different answering algorithms depending on the category of the question, more appropriate answers can be provided.

[0107] When providing an answer, the answer providing unit can select the optimal answer providing method by taking into consideration device information about the child. For example, the optimal answer providing method is selected by taking into consideration information about the device the child is using. For example, if the child is using a smartphone, a method of providing answers that matches the screen size can be selected. Also, if the child is using a tablet, a method of providing answers that is optimized for a large screen can be selected. Furthermore, if the child is using a smartwatch, a method of providing answers that is concise and highly visible can be selected. In this way, the optimal answer providing method can be selected by taking into consideration device information.

[0108] The processing flow of the second embodiment will be briefly explained below.

[0109] Step 1: The voice input unit inputs the child's question by voice. For example, if a child asks, "What is the name of this insect?", the voice input unit accepts the voice. The voice input unit collects the voice using a microphone and converts it into text data using voice recognition technology. The voice recognition technology includes a voice recognition model that uses deep learning. Step 2: The image reception unit receives images taken by the child. For example, the child may take a photo of a shop they see in town and send it to the image reception unit. The image reception unit collects images using a camera and converts them into analyzable data using image recognition technology, which includes convolutional neural networks (CNN). Step 3: The analysis unit analyzes the information input by the voice input unit and the image reception unit. For example, it analyzes the text data from the voice input unit and the image data from the image reception unit to understand the content of the question. The analysis unit analyzes the text data using natural language processing technology and the image data using image recognition technology. Step 4: The answer generator generates an appropriate answer based on the information analyzed by the analyzer. For example, if the analyzer understands the question "What is the name of this insect?", the answer generator generates the name of the insect as the answer. The answer generator generates the answer by referring to a knowledge base. The knowledge base includes information from encyclopedias and the Internet. Step 5: The answer providing unit provides the answer generated by the answer generating unit to the child. For example, if the answer is to be read aloud, the answer providing unit uses speech synthesis technology to read the answer aloud. Speech synthesis technology includes text-to-speech synthesis (TTS). If the answer is to be displayed as text, the answer providing unit displays the answer on a display.

[0110] 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.

[0111] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0112] 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.

[0113] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0114] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0115] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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).

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0128] 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.

[0129] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0130] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0144] 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.

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

[0146] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0147] 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.

[0148] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0149] The 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.

[0150] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS 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).

[0152] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0161] 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.

[0162] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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).

[0167] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0168] 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."

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] [Explanation of symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A voice input unit for entering children's questions by voice, A photo reception area that accepts images taken by children, An analysis unit that analyzes the information input by the voice input unit and the image receiving unit, A response generation unit that generates a response based on the information analyzed by the analysis unit, The system includes a response providing unit that provides the response generated by the response generation unit to the child. A system characterized by:

2. The analysis unit Using image recognition technology to identify objects and locations in a photograph. The system of claim 1 .

3. The analysis unit Using speech recognition technology to understand the content of children's questions The system of claim 1 .

4. The answer generation unit Generate an appropriate answer based on the analysis results. The system of claim 1 .

5. The answer providing unit Read answers aloud The system of claim 1 .

6. The answer providing unit Display answers in text The system of claim 1 .

7. The voice input unit It estimates the child's emotions and adjusts the timing of voice input based on the estimated emotions. The system of claim 1 .

8. The voice input unit Analyze the child's past voice input history and select the appropriate voice input method. The system of claim 1 .

9. The voice input unit When using voice input, filtering is performed based on the child's current interests and concerns. The system of claim 1 .

10. The voice input unit It estimates the child's emotions and prioritizes voice input based on the estimated emotions. The system of claim 1 .

Images