System

Abstract

To provide a system that identifies children's stress factors and provides appropriate advice.SOLUTION: A system according to the embodiment comprises a reception unit, an analysis unit, an identification unit, and a provision unit. The reception unit receives a conversation. The analysis unit analyzes the content of the conversation received by the reception unit. The identification unit identifies a stress factor based on the content of the conversation analyzed by the analysis unit. The provision unit provides advice based on the stress factor identified by the identification unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to identify children's stress factors and provide appropriate advice.

[0005] The system according to the embodiment aims to identify stress factors in children and provide appropriate advice. [Means for solving the problem]

[0006] The system according to the embodiment includes a receiving unit, an analysis unit, an identification unit, and a providing unit. The receiving unit receives a conversation. The analysis unit analyzes the content of the conversation received by the receiving unit. The identification unit identifies a stress factor based on the content of the conversation analyzed by the analysis unit. The providing unit provides advice based on the stress factor identified by the identification unit. Effect of the Invention

[0007] The system according to the embodiment can identify a child's stress factors and provide appropriate advice. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The stress check system according to the embodiment of the present invention is a system that performs stress checks by installing an AI character that can converse on a device for children (such as a kids' phone or smartphone). This stress check system identifies the mental health condition and stress factors of a child by having the child converse with the AI ​​character, and provides advice to the child and the parent. For example, when a child talks about events at school or relationships with friends, the AI ​​analyzes the content and identifies the stress factors. Next, the AI ​​provides advice to the child and the parent based on the identified information. For example, if a child is feeling stressed at school, the AI ​​advises the parent, "The child seems to be stressed at school. Please listen to him / her." This system allows the child's mental health condition to be grasped early and appropriate measures to be taken. For example, a child converses with an AI character. For example, the stress factors are identified from the content of the child's conversation, such as events at school or relationships with friends. Next, the AI ​​provides advice to the child and the parent based on the identified information. For example, if a child is feeling stressed at school, the AI ​​advises the parent, "The child seems to be stressed at school. Please listen to him / her." This system allows the child's mental health condition to be grasped early and appropriate measures to be taken. This enables the stress check system to grasp a child's mental health state at an early stage and take appropriate measures.

[0029] The stress check system according to the embodiment includes a reception unit, an analysis unit, a determination unit, and a provision unit. The reception unit receives a conversation spoken by a child. The conversation includes, for example, voice conversation and text chat, but is not limited to such examples. The reception unit can convert the voice conversation into text using, for example, voice recognition technology. The reception unit can also directly receive text chat. The analysis unit analyzes the content of the conversation received by the reception unit. For example, natural language processing technology and emotion analysis technology are used for the analysis, but are not limited to such examples. For example, the analysis unit analyzes the content of the conversation using natural language processing technology and estimates the child's emotion using emotion analysis technology. The determination unit identifies a stress factor based on the content of the conversation analyzed by the analysis unit. The stress factor includes, for example, school problems and home problems, but are not limited to such examples. For example, the determination unit identifies whether the child is stressed by an incident at school based on the analysis result. The provision unit provides advice based on the stress factor identified by the determination unit. The advice includes, for example, text messages and voice messages, but are not limited to such examples. For example, if a child feels stressed at school, the providing unit provides the parent with advice such as, "My child seems to feel stressed at school. Please listen to him / her." In this way, the stress check system according to the embodiment can analyze the content of the child's conversation, identify the cause of stress, and provide appropriate advice.

[0030] The reception unit receives a conversation spoken by a child. The conversation includes, for example, a voice conversation and a text chat, but is not limited to such examples. The reception unit can convert the voice conversation into text, for example, using a voice recognition technology. Specifically, a voice recognition model using deep learning is used as the voice recognition technology. This model realizes highly accurate voice recognition by learning a large amount of voice data. When the voice conversation is input, the voice signal is first converted into digital data, and then converted into text by the voice recognition model. The voice recognition model not only recognizes phonemes and words, but also performs analysis taking into account the context, so that the natural flow of the conversation can be accurately converted into text. The reception unit can also directly receive text chat. In the case of text chat, the text data input by the user is sent as it is to the reception unit. The reception unit centrally manages these data and prepares them to be sent to the analysis unit. Furthermore, the reception unit provides an environment that is easy for children to use through a user interface. For example, in the case of voice input, the sensitivity of the microphone and the noise canceling function are adjusted to obtain clear voice data. In addition, in the case of text chat, the input assistance function and the use of emoticons are supported, allowing the child to continue the conversation naturally. This allows the reception unit to efficiently and accurately receive the child's conversation and provide the data required for subsequent analysis processing.

[0031] The analysis unit analyzes the conversation content received by the reception unit. For example, natural language processing technology and emotion analysis technology are used for the analysis, but the examples are not limited to these. Specifically, as the natural language processing technology, methods such as tokenization, morphological analysis, grammatical analysis, and semantic analysis are used. Tokenization is a process of dividing the input text into words and phrases, and morphological analysis is a process of identifying the part of speech and meaning of each token. Grammatical analysis is a process of analyzing the structure of a sentence, and semantic analysis is a process for understanding the meaning of the entire sentence. Through these processes, the overall picture of the conversation content can be grasped. Emotion analysis technology is a technology for estimating emotions from text data, and classifies emotions into emotion categories such as positive, negative, and neutral. Machine learning models and deep learning models are used for the emotion analysis, and emotions can be estimated from text data with high accuracy. For example, the analysis unit analyzes the conversation content of a child and estimates emotions based on specific keywords and phrases. If a child uses words expressing emotions such as "sad," "painful," and "fun," the emotion can be accurately identified. In addition, the analysis unit takes into account the context and tone of the conversation to perform more accurate emotion analysis, allowing the analysis unit to analyze the details of the child's conversation and accurately grasp emotions and signs of stress.

[0032] The identification unit identifies the stress factor based on the conversation content analyzed by the analysis unit. The stress factor includes, but is not limited to, school problems and family problems. Specifically, the identification unit identifies the situation in which the child feels stressed based on the analysis result. For example, when the child talks about a specific event such as "too much homework," "fighting with a friend," or "being scolded at home," the identification unit identifies the stress factor based on the content. The identification unit also refers to the emotion analysis result provided by the analysis unit and evaluates the degree of stress the child feels about a specific topic. Furthermore, the identification unit learns past conversation data and stress factor patterns and builds an algorithm for identifying new stress factors. For example, the identification unit learns from past data that specific keywords and phrases are related to stress factors, and applies the same pattern to new conversation content. This allows the identification unit to quickly and accurately identify the child's stress factors and provide information for taking appropriate measures.

[0033] The providing unit provides advice based on the stress factors identified by the identifying unit. Examples of advice include, but are not limited to, text messages and voice messages. Specifically, if a child is stressed at school, the providing unit provides advice to the parent such as "My child seems to be stressed at school. Please listen to him / her." The providing unit uses an algorithm to customize the content of the advice according to individual situations and provide optimal advice. For example, if a child is having trouble with a particular subject, the providing unit provides specific advice on that subject. The providing unit also has a function to evaluate the effectiveness of the advice and collect feedback. Based on feedback from parents and teachers, the content of the advice and the method of providing the advice are continuously improved. Furthermore, the providing unit reliably conveys the advice using multiple communication means. For example, not only text messages but also voice messages and video messages are used in combination to provide information in a form that is easy for parents and teachers to understand. This allows the providing unit to provide effective advice to reduce children's stress and support healthy growth.

[0034] The providing unit includes a parent-oriented providing unit that provides advice to a parent. The parent-oriented providing unit provides advice to a parent regarding, for example, a stress factor of a child. For example, when a child is stressed at school, the parent-oriented providing unit provides the parent with advice such as "The child seems to be stressed at school. Please listen to him / her." The parent-oriented providing unit can also provide advice in a manner that respects the child's privacy. For example, the parent-oriented providing unit provides detailed information to the parent with the child's consent. This allows the parent-oriented providing unit to provide appropriate advice to the parent. A part or all of the above-mentioned processing in the parent-oriented providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the parent-oriented providing unit can input information regarding the child's stress factor to AI, and the AI ​​can generate advice.

[0035] The providing unit includes a child-oriented providing unit that provides advice to the child. The child-oriented providing unit provides advice on stress factors to the child, for example. For example, if the child is feeling stressed at school, the child-oriented providing unit provides the child with advice such as "It seems like you're feeling stressed at school. Let's try a way to relax." The child-oriented providing unit can also adjust the way the advice is expressed based on the child's emotions. For example, if the child is sad, the advice is provided in gentle words. This allows the child-oriented providing unit to provide appropriate advice to the child. A part or all of the above-mentioned processing in the child-oriented providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the child-oriented providing unit can input information on the child's stress factors to the AI, and the AI ​​can generate advice.

[0036] The analysis unit includes a collection unit that analyzes the content of the conversation and collects data for grasping the child's mental health condition. The collection unit, for example, analyzes the content of the conversation and collects data for grasping the child's mental health condition. For example, the collection unit analyzes the content of the conversation using a natural language processing technique and estimates the child's emotions. The collection unit can also estimate the child's emotions using an emotion analysis technique. This allows the collection unit to collect data for grasping the child's mental health condition. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the collection unit can input the content of the conversation to the generation AI, and the generation AI can collect the data.

[0037] The analysis unit provides information for the AI ​​character to give advice directly to the child. The analysis unit provides information for the AI ​​character to give advice directly to the child, for example. For example, the analysis unit analyzes the content of the conversation, identifies the child's stress factors, and provides the information to the AI ​​character. This allows the AI ​​character to give appropriate advice to the child. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the content of the conversation to the generation AI and provide information for the generation AI to generate advice.

[0038] The parent-oriented providing unit provides advice in a manner that respects the child's privacy. The parent-oriented providing unit provides advice in a manner that respects the child's privacy, for example. For example, the parent-oriented providing unit provides detailed information to the parent with the child's consent. The parent-oriented providing unit can also provide the parent with only the minimum necessary information. This allows the parent-oriented providing unit to provide advice to the parent while respecting the child's privacy. A part or all of the above-mentioned processing in the parent-oriented providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the parent-oriented providing unit can input information regarding the child's privacy to AI, and the AI ​​can generate advice.

[0039] The reception unit can analyze the child's past conversation history and select the reception method. The reception unit, for example, analyzes the child's past conversation history and selects the optimal reception method. For example, the reception unit preferentially accepts topics that the child liked to talk about in the past. The reception unit can also adjust the reception method so as to avoid topics that the child avoided in the past. Furthermore, if the child likes to talk during a specific time period, the reception unit can also perform reception according to that time period. This allows the reception unit to select the optimal reception method based on the child's past conversation history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the child's past conversation history into AI, which can select the optimal reception method.

[0040] The reception unit can filter the conversation based on the child's current living situation and areas of interest when receiving the conversation. The reception unit, for example, filters the conversation based on the child's current living situation and areas of interest when receiving the conversation. For example, immediately after the child returns home from school, the reception unit preferentially receives conversations about events at school. In addition, if the child is interested in a particular hobby, the reception unit can preferentially receive conversations related to the hobby. Furthermore, during the time period when the child is spending time with the family, the reception unit can preferentially receive conversations about the family. This allows the reception unit to filter the conversation based on the child's living situation and areas of interest. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit inputs information about the child's living situation and areas of interest into AI, and the AI ​​can filter the conversation.

[0041] The reception unit can preferentially receive a highly relevant conversation in consideration of the child's geographical location information when receiving a conversation. For example, the reception unit preferentially receives a highly relevant conversation in consideration of the child's geographical location information when receiving a conversation. For example, when a child is in a park, the reception unit preferentially receives a conversation about playing in the park. Also, when a child is at school, the reception unit can preferentially receive a conversation about events at school. Furthermore, when a child is at home, the reception unit can preferentially receive a conversation about events at home. This allows the reception unit to preferentially receive a highly relevant conversation based on the child's geographical location information. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit inputs the child's geographical location information into AI, and the AI ​​can preferentially receive a highly relevant conversation.

[0042] The reception unit can analyze the child's social media activity and receive the related conversation when receiving the conversation. For example, the reception unit analyzes the child's social media activity and receives the related conversation when receiving the conversation. For example, the reception unit receives the related conversation based on the content of the child's exchanges with friends on social media. The reception unit can also receive the related conversation based on the topic in which the child is interested on social media. Furthermore, the reception unit can also receive the related conversation based on the account the child follows on social media. In this way, the reception unit can receive the related conversation based on the child's social media activity. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input information on the child's social media activity to an AI, and the AI ​​can receive the related conversation.

[0043] The analysis unit can adjust the level of detail of the analysis based on the importance of the conversation during the analysis. The analysis unit, for example, adjusts the level of detail of the analysis based on the importance of the conversation during the analysis. For example, a detailed analysis is performed for important conversation contents. A simple analysis can also be performed for general conversation contents. Furthermore, a detailed analysis can be performed quickly for conversation contents with high urgency. This allows the analysis unit to adjust the level of detail of the analysis based on the importance of the conversation. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input information regarding the importance of the conversation to an AI, and the AI ​​can adjust the level of detail of the analysis.

[0044] The analysis unit can apply different analysis algorithms depending on the category of the conversation during analysis. The analysis unit, for example, applies different analysis algorithms depending on the category of the conversation during analysis. For example, a school-related analysis algorithm is applied to a conversation about school. A home-related analysis algorithm can also be applied to a conversation about home. Furthermore, a friend-related analysis algorithm can also be applied to a conversation about friends. This allows the analysis unit to apply different analysis algorithms depending on the category of the conversation. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input information regarding the category of the conversation to an AI, and the AI ​​can apply different analysis algorithms.

[0045] The analysis unit can determine the priority of the analysis based on the time of submission of the conversation during the analysis. The analysis unit, for example, determines the priority of the analysis based on the time of submission of the conversation during the analysis. For example, the analysis of recent conversation contents is prioritized. In addition, for past conversation contents, the priority of the analysis can be determined according to the importance. Furthermore, for conversation contents with high urgency, analysis can be performed quickly. This allows the analysis unit to determine the priority of the analysis based on the time of submission of the conversation. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input information regarding the time of submission of the conversation to AI, and the AI ​​can determine the priority of the analysis.

[0046] The analysis unit can adjust the order of analysis based on the relevance of the conversation during analysis. The analysis unit, for example, adjusts the order of analysis based on the relevance of the conversation during analysis. For example, highly relevant conversation contents are analyzed preferentially. Conversation contents with low relevance can also be analyzed later. Furthermore, the order of analysis can be dynamically adjusted based on the relevance of the conversation contents. This allows the analysis unit to adjust the order of analysis based on the relevance of the conversation. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input information regarding the relevance of the conversation to AI, and the AI ​​can adjust the order of analysis.

[0047] The identification unit can improve the accuracy of identification by considering the interrelationships of conversations at the time of identification. The identification unit can improve the accuracy of identification by considering the interrelationships of conversations at the time of identification, for example. For example, the identification unit can identify a stress factor by associating the contents of a plurality of conversations. The stress factor can also be identified by considering the context of the conversation. Furthermore, the content and frequency of the conversation can be analyzed to identify the stress factor. This allows the identification unit to improve the accuracy of identification by considering the interrelationships of conversations. A part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input information regarding the interrelationships of conversations to AI, and the AI ​​can improve the accuracy of identification.

[0048] The identification unit can perform the identification by considering the attribute information of the person who submitted the conversation at the time of identification. The identification unit can perform the identification by considering the attribute information of the person who submitted the conversation at the time of identification, for example. For example, the identification unit can identify the stress factor by considering the age and gender of the child. The stress factor can also be identified by considering the child's living environment. Furthermore, the stress factor can also be identified by considering the child's past stress history. Thereby, the identification unit can perform the identification by considering the attribute information of the person who submitted the conversation. A part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input the attribute information of the person who submitted the conversation to AI, and the AI ​​can perform the identification.

[0049] The identification unit can perform identification taking into consideration the geographical distribution of the conversation at the time of identification. The identification unit can perform identification taking into consideration the geographical distribution of the conversation at the time of identification, for example. For example, the identification unit can identify a stress factor felt by a child in a specific location. The identification unit can also identify a stress factor felt by a child while traveling. Furthermore, the identification unit can identify a stress factor felt by a child at home. This allows the identification unit to perform identification taking into consideration the geographical distribution of the conversation. A part or all of the above-mentioned processing in the identification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the identification unit can input information regarding the geographical distribution of the conversation to an AI, and the AI ​​can perform identification.

[0050] The identification unit can improve the accuracy of identification by referring to literature related to the conversation at the time of identification. The identification unit can improve the accuracy of identification by referring to literature related to the conversation at the time of identification, for example. For example, the identification unit can improve the accuracy of identification of the stress factor by referring to related literature. Also, the identification unit can improve the accuracy of identification of the stress factor by referring to academic papers. Furthermore, the identification unit can improve the accuracy of identification of the stress factor by referring to specialized books. Thereby, the identification unit can improve the accuracy of identification by referring to literature related to the conversation. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input information about literature related to the conversation to AI, and the AI ​​can improve the accuracy of identification.

[0051] The providing unit can adjust the level of detail of the advice based on the importance of the stress factor when providing the advice. The providing unit, for example, adjusts the level of detail of the advice based on the importance of the stress factor when providing the advice. For example, detailed advice is provided for important stress factors. Also, brief advice can be provided for general stress factors. Furthermore, detailed advice can be provided quickly for stress factors with high urgency. This allows the providing unit to adjust the level of detail of the advice based on the importance of the stress factor. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input information regarding the importance of the stress factor to an AI, and the AI ​​can adjust the level of detail of the advice.

[0052] The providing unit can apply different advice algorithms depending on the category of the stress factor when providing advice. For example, the providing unit applies different advice algorithms depending on the category of the stress factor when providing advice. For example, a school-related advice algorithm is applied to a stress factor related to school. A home-related advice algorithm can also be applied to a stress factor related to home. Furthermore, a friend-related advice algorithm can also be applied to a stress factor related to friends. This allows the providing unit to apply different advice algorithms depending on the category of the stress factor. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input information regarding the category of the stress factor to an AI, and the AI ​​can apply different advice algorithms.

[0053] The providing unit can determine the priority of advice based on the submission time of the stress factor when providing advice. The providing unit, for example, determines the priority of advice based on the submission time of the stress factor when providing advice. For example, advice is provided preferentially for recent stress factors. Also, for past stress factors, the priority of advice can be determined according to the importance. Furthermore, advice can be provided quickly for stress factors with high urgency. This allows the providing unit to determine the priority of advice based on the submission time of the stress factor. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input information regarding the submission time of the stress factor to AI, and the AI ​​can determine the priority of advice.

[0054] The providing unit can adjust the order of advice based on the relevance of the stress factors when providing advice. The providing unit, for example, adjusts the order of advice based on the relevance of the stress factors when providing advice. For example, advice is provided preferentially for highly relevant stress factors. Also, advice can be provided later for less relevant stress factors. Furthermore, the order of advice can be dynamically adjusted based on the relevance of the stress factors. This allows the providing unit to adjust the order of advice based on the relevance of the stress factors. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input information regarding the relevance of the stress factors to the AI, and the AI ​​can adjust the order of advice.

[0055] The parent-oriented providing unit can adjust the level of detail of the advice in a manner that respects the child's privacy when providing advice for parents. The parent-oriented providing unit can adjust the level of detail of the advice in a manner that respects the child's privacy when providing advice for parents. For example, the parent-oriented providing unit can respect the child's privacy and provide only the minimum amount of information to the parent. In addition, in order to protect the child's privacy, detailed information can be provided only after obtaining the child's consent. Furthermore, general advice can be provided to the parent in consideration of the child's privacy. This allows the parent-oriented providing unit to provide advice to the parent while respecting the child's privacy. A part or all of the above-mentioned processing in the parent-oriented providing unit can be performed, for example, using AI or can be performed without using AI. For example, the parent-oriented providing unit can input information regarding the child's privacy to AI, and the AI ​​can adjust the level of detail of the advice.

[0056] The parent-oriented providing unit can determine the priority of advice in a manner that respects the privacy of the child when providing advice for parents. The parent-oriented providing unit, for example, determines the priority of advice in a manner that respects the privacy of the child when providing advice for parents. For example, the parent-oriented providing unit respects the privacy of the child and provides information of high importance to the parent preferentially. In addition, in order to protect the privacy of the child, detailed information can be provided only after obtaining the consent of the child. Furthermore, in consideration of the privacy of the child, general advice can be preferentially provided to the parent. In this way, the parent-oriented providing unit can provide advice to the parent while respecting the privacy of the child. A part or all of the above-mentioned processing in the parent-oriented providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the parent-oriented providing unit can input information regarding the privacy of the child to AI, and the AI ​​can determine the priority of advice.

[0057] The child-oriented providing unit can adjust the level of detail of the advice based on the importance of the stress factor when providing advice for children. The child-oriented providing unit can adjust the level of detail of the advice based on the importance of the stress factor when providing advice for children. For example, detailed advice is provided for important stress factors. Brief advice can also be provided for general stress factors. Furthermore, detailed advice can be provided quickly for stress factors with high urgency. This allows the child-oriented providing unit to adjust the level of detail of the advice for children based on the importance of the stress factor. A part or all of the above-mentioned processing in the child-oriented providing unit can be performed, for example, using AI or can be performed without using AI. For example, the child-oriented providing unit can input information regarding the importance of the stress factor to AI, and the AI ​​can adjust the level of detail of the advice.

[0058] The child-oriented providing unit can determine the priority of advice based on the time of submission of a stress factor when providing advice for children. The child-oriented providing unit, for example, determines the priority of advice based on the time of submission of a stress factor when providing advice for children. For example, advice is provided preferentially for recent stress factors. Also, for past stress factors, the priority of advice can be determined according to the importance. Furthermore, advice can be provided quickly for stress factors with high urgency. This allows the child-oriented providing unit to determine the priority of advice for children based on the time of submission of a stress factor. A part or all of the above-mentioned processing in the child-oriented providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the child-oriented providing unit can input information regarding the time of submission of a stress factor to AI, and the AI ​​can determine the priority of advice.

[0059] The collection unit can improve the accuracy of data collection by considering the interrelationships of conversations when collecting data. The collection unit can improve the accuracy of data collection by considering the interrelationships of conversations when collecting data. For example, the collection unit can improve the accuracy of data collection by associating the contents of multiple conversations. The accuracy of data collection can also be improved by considering the context of the conversation. Furthermore, the accuracy of data collection can be improved by analyzing the contents and frequency of the conversation. This allows the collection unit to improve the accuracy of data collection by considering the interrelationships of conversations. Part or all of the above-mentioned processing in the collection unit can be performed, for example, using AI or can be performed without using AI. For example, the collection unit can input information regarding the interrelationships of conversations to AI, and the AI ​​can improve the accuracy of collection.

[0060] The collection unit can collect data while taking into consideration the geographical distribution of conversations. For example, the collection unit collects data while taking into consideration the geographical distribution of conversations. For example, the collection unit collects data related to stress factors felt by children in specific locations. Data related to stress factors felt by children while traveling can also be collected. Furthermore, data related to stress factors felt by children within the home can also be collected. This allows the collection unit to collect data while taking into consideration the geographical distribution of conversations. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input information related to the geographical distribution of conversations to AI, and the AI ​​can perform collection.

[0061] The collection unit can improve the accuracy of collection by referring to literature related to the conversation when collecting data. The collection unit can improve the accuracy of collection by referring to literature related to the conversation when collecting data, for example. For example, the collection unit can improve the accuracy of data collection by referring to related literature. The accuracy of data collection can also be improved by referring to academic papers. Furthermore, the accuracy of data collection can also be improved by referring to specialized books. Thereby, the collection unit can improve the accuracy of collection by referring to literature related to the conversation. Part or all of the above-mentioned processing in the collection unit can be performed, for example, using AI, or can be performed without using AI. For example, the collection unit can input information about literature related to the conversation to AI, and the AI ​​can improve the accuracy of collection.

[0062] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0063] When analyzing the content of a child's conversation, the analysis unit can adjust the analysis method based on the child's learning style. For example, for a child with a visual learning style, the analysis unit uses a method that visually represents the content of the conversation. For a child with an auditory learning style, emphasis can be placed on audio analysis. Furthermore, for a child with an experiential learning style, analysis can be performed based on actual experience. This allows the analysis unit to provide an optimal analysis method according to the child's learning style.

[0064] When providing advice to a parent, the parent-oriented providing unit can adjust the way in which the advice is expressed based on the parent's communication style. For example, if the parent prefers visual information, advice using graphs and diagrams can be provided. If the parent prefers auditory information, advice using audio messages can be provided. Furthermore, if the parent prefers experiential information, advice including specific examples can also be provided. This allows the parent-oriented providing unit to provide optimal advice according to the parent's communication style.

[0065] When providing advice to a child, the child-oriented provision unit can adjust the content of the advice based on the child's interests. For example, if a child is interested in sports, sports-related advice can be provided. If a child is interested in music, music-related advice can be provided. Furthermore, if a child is interested in science, science-related advice can be provided. This allows the child-oriented provision unit to provide optimal advice according to the child's interests.

[0066] When collecting the child's conversation content, the collection unit can adjust the collection timing based on the child's life rhythm. For example, if the child is active in the morning, the conversation content is collected in the morning hours. Also, if the child is relaxed at night, the conversation content can be collected in the evening hours. Furthermore, if the child is very active on weekends, the conversation content can be collected after the weekend activities. This allows the collection unit to provide optimal collection timing according to the child's life rhythm.

[0067] When analyzing the content of a child's conversation, the analysis unit can adjust the analysis method based on the child's cultural background. For example, in the case of a child from a different cultural background, the analysis is performed taking into account expressions and words specific to that culture. In addition, the analysis unit can emphasize the content of the conversation related to specific cultural events and customs. Furthermore, stress factors can be identified based on cultural values ​​and beliefs. This allows the analysis unit to provide an optimal analysis method according to the child's cultural background.

[0068] The process flow of the first embodiment will be briefly described below.

[0069] Step 1: The reception unit receives a conversation spoken by a child. The conversation includes voice conversation and text chat. The reception unit can convert the voice conversation into text using voice recognition technology, and can also directly receive the text chat. Step 2: The analysis unit analyzes the conversation content received by the reception unit. Natural language processing technology and emotion analysis technology are used for the analysis. For example, the analysis unit analyzes the conversation content using natural language processing technology and estimates the child's emotions using emotion analysis technology. Step 3: The identification unit identifies stress factors based on the conversation content analyzed by the analysis unit. Stress factors include problems at school, problems at home, etc. For example, the identification unit identifies whether a child is feeling stressed by events at school based on the analysis results. Step 4: The providing unit provides advice based on the stress factors identified by the identifying unit. The advice includes a text message, a voice message, etc. For example, if a child is feeling stressed at school, the providing unit provides advice to a parent such as "It seems like your child is feeling stressed at school. Please listen to him / her."

[0070] (Example 2) The stress check system according to the embodiment of the present invention is a system that performs stress checks by installing an AI character that can converse on a device for children (such as a kids' phone or smartphone). This stress check system identifies the mental health condition and stress factors of a child by having the child converse with the AI ​​character, and provides advice to the child and the parent. For example, when a child talks about events at school or relationships with friends, the AI ​​analyzes the content and identifies the stress factors. Next, the AI ​​provides advice to the child and the parent based on the identified information. For example, if a child is feeling stressed at school, the AI ​​advises the parent, "The child seems to be stressed at school. Please listen to him / her." This system allows the child's mental health condition to be grasped early and appropriate measures to be taken. For example, a child converses with an AI character. For example, the stress factors are identified from the content of the child's conversation, such as events at school or relationships with friends. Next, the AI ​​provides advice to the child and the parent based on the identified information. For example, if a child is feeling stressed at school, the AI ​​advises the parent, "The child seems to be stressed at school. Please listen to him / her." This system allows the child's mental health condition to be grasped early and appropriate measures to be taken. This enables the stress check system to grasp a child's mental health state at an early stage and take appropriate measures.

[0071] The stress check system according to the embodiment includes a reception unit, an analysis unit, a determination unit, and a provision unit. The reception unit receives a conversation spoken by a child. The conversation includes, for example, voice conversation and text chat, but is not limited to such examples. The reception unit can convert the voice conversation into text using, for example, voice recognition technology. The reception unit can also directly receive text chat. The analysis unit analyzes the content of the conversation received by the reception unit. For example, natural language processing technology and emotion analysis technology are used for the analysis, but are not limited to such examples. For example, the analysis unit analyzes the content of the conversation using natural language processing technology and estimates the child's emotion using emotion analysis technology. The determination unit identifies a stress factor based on the content of the conversation analyzed by the analysis unit. The stress factor includes, for example, school problems and home problems, but are not limited to such examples. For example, the determination unit identifies whether the child is stressed by an incident at school based on the analysis result. The provision unit provides advice based on the stress factor identified by the determination unit. The advice includes, for example, text messages and voice messages, but are not limited to such examples. For example, if a child feels stressed at school, the providing unit provides the parent with advice such as, "My child seems to feel stressed at school. Please listen to him / her." In this way, the stress check system according to the embodiment can analyze the content of the child's conversation, identify the cause of stress, and provide appropriate advice.

[0072] The reception unit receives a conversation spoken by a child. The conversation includes, for example, a voice conversation and a text chat, but is not limited to such examples. The reception unit can convert the voice conversation into text, for example, using a voice recognition technology. Specifically, a voice recognition model using deep learning is used as the voice recognition technology. This model realizes highly accurate voice recognition by learning a large amount of voice data. When the voice conversation is input, the voice signal is first converted into digital data, and then converted into text by the voice recognition model. The voice recognition model not only recognizes phonemes and words, but also performs analysis taking into account the context, so that the natural flow of the conversation can be accurately converted into text. The reception unit can also directly receive text chat. In the case of text chat, the text data input by the user is sent as it is to the reception unit. The reception unit centrally manages these data and prepares them to be sent to the analysis unit. Furthermore, the reception unit provides an environment that is easy for children to use through a user interface. For example, in the case of voice input, the sensitivity of the microphone and the noise canceling function are adjusted to obtain clear voice data. In addition, in the case of text chat, the input assistance function and the use of emoticons are supported, allowing the child to continue the conversation naturally. This allows the reception unit to efficiently and accurately receive the child's conversation and provide the data required for subsequent analysis processing.

[0073] The analysis unit analyzes the conversation content received by the reception unit. For example, natural language processing technology and emotion analysis technology are used for the analysis, but the examples are not limited to these. Specifically, as the natural language processing technology, methods such as tokenization, morphological analysis, grammatical analysis, and semantic analysis are used. Tokenization is a process of dividing the input text into words and phrases, and morphological analysis is a process of identifying the part of speech and meaning of each token. Grammatical analysis is a process of analyzing the structure of a sentence, and semantic analysis is a process for understanding the meaning of the entire sentence. Through these processes, the overall picture of the conversation content can be grasped. Emotion analysis technology is a technology for estimating emotions from text data, and classifies emotions into emotion categories such as positive, negative, and neutral. Machine learning models and deep learning models are used for the emotion analysis, and emotions can be estimated from text data with high accuracy. For example, the analysis unit analyzes the conversation content of a child and estimates emotions based on specific keywords and phrases. If a child uses words expressing emotions such as "sad," "painful," and "fun," the emotion can be accurately identified. In addition, the analysis unit takes into account the context and tone of the conversation to perform more accurate emotion analysis, allowing the analysis unit to analyze the details of the child's conversation and accurately grasp emotions and signs of stress.

[0074] The identification unit identifies the stress factor based on the conversation content analyzed by the analysis unit. The stress factor includes, but is not limited to, school problems and family problems. Specifically, the identification unit identifies the situation in which the child feels stressed based on the analysis result. For example, when the child talks about a specific event such as "too much homework," "fighting with a friend," or "being scolded at home," the identification unit identifies the stress factor based on the content. The identification unit also refers to the emotion analysis result provided by the analysis unit and evaluates the degree of stress the child feels about a specific topic. Furthermore, the identification unit learns past conversation data and stress factor patterns and builds an algorithm for identifying new stress factors. For example, the identification unit learns from past data that specific keywords and phrases are related to stress factors, and applies the same pattern to new conversation content. This allows the identification unit to quickly and accurately identify the child's stress factors and provide information for taking appropriate measures.

[0075] The providing unit provides advice based on the stress factors identified by the identifying unit. Examples of advice include, but are not limited to, text messages and voice messages. Specifically, if a child is stressed at school, the providing unit provides advice to the parent such as "My child seems to be stressed at school. Please listen to him / her." The providing unit uses an algorithm to customize the content of the advice according to individual situations and provide optimal advice. For example, if a child is having trouble with a particular subject, the providing unit provides specific advice on that subject. The providing unit also has a function to evaluate the effectiveness of the advice and collect feedback. Based on feedback from parents and teachers, the content of the advice and the method of providing the advice are continuously improved. Furthermore, the providing unit reliably conveys the advice using multiple communication means. For example, not only text messages but also voice messages and video messages are used in combination to provide information in a form that is easy for parents and teachers to understand. This allows the providing unit to provide effective advice to reduce children's stress and support healthy growth.

[0076] The providing unit includes a parent-oriented providing unit that provides advice to a parent. The parent-oriented providing unit provides advice to a parent regarding, for example, a stress factor of a child. For example, when a child is stressed at school, the parent-oriented providing unit provides the parent with advice such as "The child seems to be stressed at school. Please listen to him / her." The parent-oriented providing unit can also provide advice in a manner that respects the child's privacy. For example, the parent-oriented providing unit provides detailed information to the parent with the child's consent. This allows the parent-oriented providing unit to provide appropriate advice to the parent. A part or all of the above-mentioned processing in the parent-oriented providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the parent-oriented providing unit can input information regarding the child's stress factor to AI, and the AI ​​can generate advice.

[0077] The providing unit includes a child-oriented providing unit that provides advice to the child. The child-oriented providing unit provides advice on stress factors to the child, for example. For example, if the child is feeling stressed at school, the child-oriented providing unit provides the child with advice such as "It seems like you're feeling stressed at school. Let's try a way to relax." The child-oriented providing unit can also adjust the way the advice is expressed based on the child's emotions. For example, if the child is sad, the advice is provided in gentle words. This allows the child-oriented providing unit to provide appropriate advice to the child. A part or all of the above-mentioned processing in the child-oriented providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the child-oriented providing unit can input information on the child's stress factors to the AI, and the AI ​​can generate advice.

[0078] The analysis unit includes a collection unit that analyzes the content of the conversation and collects data for grasping the child's mental health condition. The collection unit, for example, analyzes the content of the conversation and collects data for grasping the child's mental health condition. For example, the collection unit analyzes the content of the conversation using a natural language processing technique and estimates the child's emotions. The collection unit can also estimate the child's emotions using an emotion analysis technique. This allows the collection unit to collect data for grasping the child's mental health condition. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the collection unit can input the content of the conversation to the generation AI, and the generation AI can collect the data.

[0079] The analysis unit provides information for the AI ​​character to give advice directly to the child. The analysis unit provides information for the AI ​​character to give advice directly to the child, for example. For example, the analysis unit analyzes the content of the conversation, identifies the child's stress factors, and provides the information to the AI ​​character. This allows the AI ​​character to give appropriate advice to the child. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the content of the conversation to the generation AI and provide information for the generation AI to generate advice.

[0080] The parent-oriented providing unit provides advice in a manner that respects the child's privacy. The parent-oriented providing unit provides advice in a manner that respects the child's privacy, for example. For example, the parent-oriented providing unit provides detailed information to the parent with the child's consent. The parent-oriented providing unit can also provide the parent with only the minimum necessary information. This allows the parent-oriented providing unit to provide advice to the parent while respecting the child's privacy. A part or all of the above-mentioned processing in the parent-oriented providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the parent-oriented providing unit can input information regarding the child's privacy to AI, and the AI ​​can generate advice.

[0081] The reception unit can estimate the child's emotion and adjust the timing of conversation acceptance based on the estimated child's emotion. The reception unit, for example, estimates the child's emotion and adjusts the timing of conversation acceptance based on the estimated child's emotion. For example, if the child is stressed, the reception unit delays the acceptance of the conversation and waits until the child relaxes. Also, if the child is excited, the reception unit can immediately accept the conversation and start a conversation to calm the child's emotions. Furthermore, if the child is tired, the reception unit can refrain from accepting the conversation and ensure time for the child to rest. This allows the reception unit to adjust the timing of conversation acceptance according to the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit inputs the child's emotion data to the generation AI, and the generation AI can adjust the timing of conversation acceptance.

[0082] The reception unit can analyze the child's past conversation history and select the reception method. The reception unit, for example, analyzes the child's past conversation history and selects the optimal reception method. For example, the reception unit preferentially accepts topics that the child liked to talk about in the past. The reception unit can also adjust the reception method so as to avoid topics that the child avoided in the past. Furthermore, if the child likes to talk during a specific time period, the reception unit can also perform reception according to that time period. This allows the reception unit to select the optimal reception method based on the child's past conversation history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the child's past conversation history into AI, which can select the optimal reception method.

[0083] The reception unit can filter the conversation based on the child's current living situation and areas of interest when receiving the conversation. The reception unit, for example, filters the conversation based on the child's current living situation and areas of interest when receiving the conversation. For example, immediately after the child returns home from school, the reception unit preferentially receives conversations about events at school. In addition, if the child is interested in a particular hobby, the reception unit can preferentially receive conversations related to the hobby. Furthermore, during the time period when the child is spending time with the family, the reception unit can preferentially receive conversations about the family. This allows the reception unit to filter the conversation based on the child's living situation and areas of interest. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit inputs information about the child's living situation and areas of interest into AI, and the AI ​​can filter the conversation.

[0084] The reception unit can estimate the child's emotion and determine the priority of the conversation to be received based on the estimated child's emotion. The reception unit, for example, estimates the child's emotion and determines the priority of the conversation to be received based on the estimated child's emotion. For example, if the child is sad, a conversation to comfort the child is preferentially received. Also, if the child is happy, a conversation to share the joy can be preferentially received. Furthermore, if the child is anxious, a conversation to ease the anxiety can be preferentially received. This allows the reception unit to determine the priority of the conversation based on the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the child's emotion data to the generation AI, and the generation AI can determine the priority of the conversation.

[0085] The reception unit can preferentially receive a highly relevant conversation in consideration of the child's geographical location information when receiving a conversation. For example, the reception unit preferentially receives a highly relevant conversation in consideration of the child's geographical location information when receiving a conversation. For example, when a child is in a park, the reception unit preferentially receives a conversation about playing in the park. Also, when a child is at school, the reception unit can preferentially receive a conversation about events at school. Furthermore, when a child is at home, the reception unit can preferentially receive a conversation about events at home. This allows the reception unit to preferentially receive a highly relevant conversation based on the child's geographical location information. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit inputs the child's geographical location information into AI, and the AI ​​can preferentially receive a highly relevant conversation.

[0086] The reception unit can analyze the child's social media activity and receive the related conversation when receiving the conversation. For example, the reception unit analyzes the child's social media activity and receives the related conversation when receiving the conversation. For example, the reception unit receives the related conversation based on the content of the child's exchanges with friends on social media. The reception unit can also receive the related conversation based on the topic in which the child is interested on social media. Furthermore, the reception unit can also receive the related conversation based on the account the child follows on social media. In this way, the reception unit can receive the related conversation based on the child's social media activity. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input information on the child's social media activity to an AI, and the AI ​​can receive the related conversation.

[0087] The analysis unit can estimate the child's emotion and adjust the expression method of the analysis based on the estimated child's emotion. The analysis unit, for example, estimates the child's emotion and adjusts the expression method of the analysis based on the estimated child's emotion. For example, if the child is sad, the analysis result can be expressed in gentle words. Also, if the child is excited, the analysis result can be expressed in cheerful words. Furthermore, if the child is anxious, the analysis result can be expressed in reassuring words. This allows the analysis unit to adjust the expression method of the analysis based on the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit inputs the child's emotion data into the generation AI, and the generation AI can adjust the expression method of the analysis.

[0088] The analysis unit can adjust the level of detail of the analysis based on the importance of the conversation during the analysis. The analysis unit, for example, adjusts the level of detail of the analysis based on the importance of the conversation during the analysis. For example, a detailed analysis is performed for important conversation contents. A simple analysis can also be performed for general conversation contents. Furthermore, a detailed analysis can be performed quickly for conversation contents with high urgency. This allows the analysis unit to adjust the level of detail of the analysis based on the importance of the conversation. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input information regarding the importance of the conversation to an AI, and the AI ​​can adjust the level of detail of the analysis.

[0089] The analysis unit can apply different analysis algorithms depending on the category of the conversation during analysis. The analysis unit, for example, applies different analysis algorithms depending on the category of the conversation during analysis. For example, a school-related analysis algorithm is applied to a conversation about school. A home-related analysis algorithm can also be applied to a conversation about home. Furthermore, a friend-related analysis algorithm can also be applied to a conversation about friends. This allows the analysis unit to apply different analysis algorithms depending on the category of the conversation. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input information regarding the category of the conversation to an AI, and the AI ​​can apply different analysis algorithms.

[0090] The analysis unit can estimate the child's emotion and adjust the length of the analysis based on the estimated child's emotion. The analysis unit, for example, estimates the child's emotion and adjusts the length of the analysis based on the estimated child's emotion. For example, if the child is in a hurry, a short and to the point analysis is performed. Also, if the child is relaxed, a detailed analysis can be performed. Furthermore, if the child is excited, a visually stimulating analysis can be performed. This allows the analysis unit to adjust the length of the analysis based on the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the child's emotion data to the generation AI, and the generation AI can adjust the length of the analysis.

[0091] The analysis unit can determine the priority of the analysis based on the time of submission of the conversation during the analysis. The analysis unit, for example, determines the priority of the analysis based on the time of submission of the conversation during the analysis. For example, the analysis of recent conversation contents is prioritized. In addition, for past conversation contents, the priority of the analysis can be determined according to the importance. Furthermore, for conversation contents with high urgency, analysis can be performed quickly. This allows the analysis unit to determine the priority of the analysis based on the time of submission of the conversation. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input information regarding the time of submission of the conversation to AI, and the AI ​​can determine the priority of the analysis.

[0092] The analysis unit can adjust the order of analysis based on the relevance of the conversation during analysis. The analysis unit, for example, adjusts the order of analysis based on the relevance of the conversation during analysis. For example, highly relevant conversation contents are analyzed preferentially. Conversation contents with low relevance can also be analyzed later. Furthermore, the order of analysis can be dynamically adjusted based on the relevance of the conversation contents. This allows the analysis unit to adjust the order of analysis based on the relevance of the conversation. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input information regarding the relevance of the conversation to AI, and the AI ​​can adjust the order of analysis.

[0093] The identification unit can estimate the child's emotion and adjust the method of identifying the stress factor based on the estimated child's emotion. The identification unit, for example, estimates the child's emotion and adjusts the method of identifying the stress factor based on the estimated child's emotion. For example, if the child is sad, the stress factor can be identified by placing emphasis on emotional factors. Also, if the child is excited, the stress factor can be identified by placing emphasis on environmental factors. Furthermore, if the child feels anxious, the stress factor can be identified by placing emphasis on psychological factors. This allows the identification unit to adjust the method of identifying the stress factor based on the child's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the identification unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the identification unit can input the child's emotion data to the generation AI, and the generation AI can adjust the method of identifying the stress factor.

[0094] The identification unit can improve the accuracy of identification by considering the interrelationships of conversations at the time of identification. The identification unit can improve the accuracy of identification by considering the interrelationships of conversations at the time of identification, for example. For example, the identification unit can identify a stress factor by associating the contents of a plurality of conversations. The stress factor can also be identified by considering the context of the conversation. Furthermore, the content and frequency of the conversation can be analyzed to identify the stress factor. This allows the identification unit to improve the accuracy of identification by considering the interrelationships of conversations. A part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input information regarding the interrelationships of conversations to AI, and the AI ​​can improve the accuracy of identification.

[0095] The identification unit can perform the identification by considering the attribute information of the person who submitted the conversation at the time of identification. The identification unit can perform the identification by considering the attribute information of the person who submitted the conversation at the time of identification, for example. For example, the identification unit can identify the stress factor by considering the age and gender of the child. The stress factor can also be identified by considering the child's living environment. Furthermore, the stress factor can also be identified by considering the child's past stress history. Thereby, the identification unit can perform the identification by considering the attribute information of the person who submitted the conversation. A part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input the attribute information of the person who submitted the conversation to AI, and the AI ​​can perform the identification.

[0096] The identification unit can estimate the child's emotion and determine the priority of the stress factors to be identified based on the estimated child's emotion. The identification unit, for example, estimates the child's emotion and determines the priority of the stress factors to be identified based on the estimated child's emotion. For example, if the child is sad, emotional stress factors are preferentially identified. Also, if the child is excited, environmental stress factors can be preferentially identified. Furthermore, if the child is anxious, psychological stress factors can be preferentially identified. This allows the identification unit to determine the priority of the stress factors based on the child's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the identification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the identification unit can input the child's emotion data to the generation AI, and the generation AI can determine the priority of the stress factors.

[0097] The identification unit can perform identification taking into consideration the geographical distribution of the conversation at the time of identification. The identification unit can perform identification taking into consideration the geographical distribution of the conversation at the time of identification, for example. For example, the identification unit can identify a stress factor felt by a child in a specific location. The identification unit can also identify a stress factor felt by a child while traveling. Furthermore, the identification unit can identify a stress factor felt by a child at home. This allows the identification unit to perform identification taking into consideration the geographical distribution of the conversation. A part or all of the above-mentioned processing in the identification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the identification unit can input information regarding the geographical distribution of the conversation to an AI, and the AI ​​can perform identification.

[0098] The identification unit can improve the accuracy of identification by referring to literature related to the conversation at the time of identification. The identification unit can improve the accuracy of identification by referring to literature related to the conversation at the time of identification, for example. For example, the identification unit can improve the accuracy of identification of the stress factor by referring to related literature. Also, the identification unit can improve the accuracy of identification of the stress factor by referring to academic papers. Furthermore, the identification unit can improve the accuracy of identification of the stress factor by referring to specialized books. Thereby, the identification unit can improve the accuracy of identification by referring to literature related to the conversation. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input information about literature related to the conversation to AI, and the AI ​​can improve the accuracy of identification.

[0099] The providing unit can estimate the child's emotion and adjust the way of expressing advice based on the estimated child's emotion. The providing unit, for example, estimates the child's emotion and adjusts the way of expressing advice based on the estimated child's emotion. For example, if the child is sad, the advice is provided in gentle words. Also, if the child is excited, the advice can be provided in cheerful words. Furthermore, if the child is anxious, the advice can be provided in reassuring words. This allows the providing unit to adjust the way of expressing advice based on the child's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the child's emotion data to the generation AI, and the generation AI can adjust the way of expressing advice.

[0100] The providing unit can adjust the level of detail of the advice based on the importance of the stress factor when providing the advice. The providing unit, for example, adjusts the level of detail of the advice based on the importance of the stress factor when providing the advice. For example, detailed advice is provided for important stress factors. Also, brief advice can be provided for general stress factors. Furthermore, detailed advice can be provided quickly for stress factors with high urgency. This allows the providing unit to adjust the level of detail of the advice based on the importance of the stress factor. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input information regarding the importance of the stress factor to an AI, and the AI ​​can adjust the level of detail of the advice.

[0101] The providing unit can apply different advice algorithms depending on the category of the stress factor when providing advice. For example, the providing unit applies different advice algorithms depending on the category of the stress factor when providing advice. For example, a school-related advice algorithm is applied to a stress factor related to school. A home-related advice algorithm can also be applied to a stress factor related to home. Furthermore, a friend-related advice algorithm can also be applied to a stress factor related to friends. This allows the providing unit to apply different advice algorithms depending on the category of the stress factor. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input information regarding the category of the stress factor to an AI, and the AI ​​can apply different advice algorithms.

[0102] The providing unit can estimate the child's emotion and adjust the length of the advice based on the estimated child's emotion. The providing unit, for example, estimates the child's emotion and adjusts the length of the advice based on the estimated child's emotion. For example, if the child is in a hurry, short and to the point advice is provided. Also, if the child is relaxed, detailed advice can be provided. Furthermore, if the child is excited, visually stimulating advice can be provided. This allows the providing unit to adjust the length of the advice based on the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the providing unit can input the child's emotion data to the generation AI, and the generation AI can adjust the length of the advice.

[0103] The providing unit can determine the priority of advice based on the submission time of the stress factor when providing advice. The providing unit, for example, determines the priority of advice based on the submission time of the stress factor when providing advice. For example, advice is provided preferentially for recent stress factors. Also, for past stress factors, the priority of advice can be determined according to the importance. Furthermore, advice can be provided quickly for stress factors with high urgency. This allows the providing unit to determine the priority of advice based on the submission time of the stress factor. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input information regarding the submission time of the stress factor to AI, and the AI ​​can determine the priority of advice.

[0104] The providing unit can adjust the order of advice based on the relevance of the stress factors when providing advice. The providing unit, for example, adjusts the order of advice based on the relevance of the stress factors when providing advice. For example, advice is provided preferentially for highly relevant stress factors. Also, advice can be provided later for less relevant stress factors. Furthermore, the order of advice can be dynamically adjusted based on the relevance of the stress factors. This allows the providing unit to adjust the order of advice based on the relevance of the stress factors. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input information regarding the relevance of the stress factors to the AI, and the AI ​​can adjust the order of advice.

[0105] The parent-oriented providing unit can estimate the child's emotion and adjust the way of expressing the parent-oriented advice based on the estimated child's emotion. The parent-oriented providing unit can, for example, estimate the child's emotion and adjust the way of expressing the parent-oriented advice based on the estimated child's emotion. For example, if the child is sad, the advice can be provided to the parent in gentle words. Also, if the child is excited, the advice can be provided to the parent in cheerful words. Furthermore, if the child is anxious, the advice can be provided to the parent in reassuring words. This allows the parent-oriented providing unit to adjust the way of expressing the parent-oriented advice based on the child's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the parent-oriented providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the parent-oriented providing unit can input the child's emotion data to the generation AI, and the generation AI can adjust the way of expressing the parent-oriented advice.

[0106] The parent-oriented providing unit can adjust the level of detail of the advice in a manner that respects the child's privacy when providing advice for parents. The parent-oriented providing unit can adjust the level of detail of the advice in a manner that respects the child's privacy when providing advice for parents. For example, the parent-oriented providing unit can respect the child's privacy and provide only the minimum amount of information to the parent. In addition, in order to protect the child's privacy, detailed information can be provided only after obtaining the child's consent. Furthermore, general advice can be provided to the parent in consideration of the child's privacy. This allows the parent-oriented providing unit to provide advice to the parent while respecting the child's privacy. A part or all of the above-mentioned processing in the parent-oriented providing unit can be performed, for example, using AI or can be performed without using AI. For example, the parent-oriented providing unit can input information regarding the child's privacy to AI, and the AI ​​can adjust the level of detail of the advice.

[0107] The parent-oriented providing unit can estimate the child's emotion and adjust the length of the parent-oriented advice based on the estimated child's emotion. The parent-oriented providing unit can, for example, estimate the child's emotion and adjust the length of the parent-oriented advice based on the estimated child's emotion. For example, if the child is in a hurry, the parent can be provided with short, to-the-point advice. Also, if the child is relaxed, detailed advice can be provided to the parent. Furthermore, if the child is excited, visually stimulating advice can be provided to the parent. This allows the parent-oriented providing unit to adjust the length of the parent-oriented advice based on the child's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the parent-oriented providing unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the parent-oriented providing unit can input the child's emotion data to the generation AI, and the generation AI can adjust the length of the parent-oriented advice.

[0108] The parent-oriented providing unit can determine the priority of advice in a manner that respects the privacy of the child when providing advice for parents. The parent-oriented providing unit, for example, determines the priority of advice in a manner that respects the privacy of the child when providing advice for parents. For example, the parent-oriented providing unit respects the privacy of the child and provides information of high importance to the parent preferentially. In addition, in order to protect the privacy of the child, detailed information can be provided only after obtaining the consent of the child. Furthermore, in consideration of the privacy of the child, general advice can be preferentially provided to the parent. In this way, the parent-oriented providing unit can provide advice to the parent while respecting the privacy of the child. A part or all of the above-mentioned processing in the parent-oriented providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the parent-oriented providing unit can input information regarding the privacy of the child to AI, and the AI ​​can determine the priority of advice.

[0109] The child-oriented providing unit can estimate the child's emotion and adjust the expression method of the child-oriented advice based on the estimated child's emotion. The child-oriented providing unit can, for example, estimate the child's emotion and adjust the expression method of the child-oriented advice based on the estimated child's emotion. For example, if the child is sad, the advice can be provided in gentle words. Also, if the child is excited, the advice can be provided in cheerful words. Furthermore, if the child is anxious, the advice can be provided in reassuring words. This allows the child-oriented providing unit to adjust the expression method of the child-oriented advice based on the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the child-oriented providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the child-oriented providing unit can input the child's emotion data to the generation AI, and the generation AI can adjust the expression method of the child-oriented advice.

[0110] The child-oriented providing unit can adjust the level of detail of the advice based on the importance of the stress factor when providing advice for children. The child-oriented providing unit can adjust the level of detail of the advice based on the importance of the stress factor when providing advice for children. For example, detailed advice is provided for important stress factors. Brief advice can also be provided for general stress factors. Furthermore, detailed advice can be provided quickly for stress factors with high urgency. This allows the child-oriented providing unit to adjust the level of detail of the advice for children based on the importance of the stress factor. A part or all of the above-mentioned processing in the child-oriented providing unit can be performed, for example, using AI or can be performed without using AI. For example, the child-oriented providing unit can input information regarding the importance of the stress factor to AI, and the AI ​​can adjust the level of detail of the advice.

[0111] The child-oriented providing unit can estimate the child's emotion and adjust the length of the child-oriented advice based on the estimated child's emotion. The child-oriented providing unit can, for example, estimate the child's emotion and adjust the length of the child-oriented advice based on the estimated child's emotion. For example, if the child is in a hurry, short and to the point advice is provided. Also, if the child is relaxed, detailed advice can be provided. Furthermore, if the child is excited, visually stimulating advice can be provided. This allows the child-oriented providing unit to adjust the length of the child-oriented advice based on the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the child-oriented providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the child-oriented providing unit can input the child's emotion data to the generation AI, and the generation AI can adjust the length of the child-oriented advice.

[0112] The child-oriented providing unit can determine the priority of advice based on the time of submission of a stress factor when providing advice for children. The child-oriented providing unit, for example, determines the priority of advice based on the time of submission of a stress factor when providing advice for children. For example, advice is provided preferentially for recent stress factors. Also, for past stress factors, the priority of advice can be determined according to the importance. Furthermore, advice can be provided quickly for stress factors with high urgency. This allows the child-oriented providing unit to determine the priority of advice for children based on the time of submission of a stress factor. A part or all of the above-mentioned processing in the child-oriented providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the child-oriented providing unit can input information regarding the time of submission of a stress factor to AI, and the AI ​​can determine the priority of advice.

[0113] The collection unit can estimate the child's emotion and adjust the data collection method based on the estimated child's emotion. The collection unit, for example, estimates the child's emotion and adjusts the data collection method based on the estimated child's emotion. For example, if the child is sad, emotional data is collected with emphasis. If the child is excited, environmental data can be collected with emphasis. If the child is anxious, psychological data can be collected with emphasis. This allows the collection unit to adjust the data collection method based on the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the child's emotion data to the generation AI, and the generation AI can adjust the data collection method.

[0114] The collection unit can improve the accuracy of data collection by considering the interrelationships of conversations when collecting data. The collection unit can improve the accuracy of data collection by considering the interrelationships of conversations when collecting data. For example, the collection unit can improve the accuracy of data collection by associating the contents of multiple conversations. The accuracy of data collection can also be improved by considering the context of the conversation. Furthermore, the accuracy of data collection can be improved by analyzing the contents and frequency of the conversation. This allows the collection unit to improve the accuracy of data collection by considering the interrelationships of conversations. Part or all of the above-mentioned processing in the collection unit can be performed, for example, using AI or can be performed without using AI. For example, the collection unit can input information regarding the interrelationships of conversations to AI, and the AI ​​can improve the accuracy of collection.

[0115] The collection unit can estimate the child's emotion and determine the priority of data to be collected based on the estimated child's emotion. The collection unit, for example, estimates the child's emotion and determines the priority of data to be collected based on the estimated child's emotion. For example, if the child is sad, emotional data is preferentially collected. Also, if the child is excited, environmental data can be preferentially collected. Furthermore, if the child is anxious, psychological data can be preferentially collected. This allows the collection unit to determine the priority of data to be collected based on the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the collection unit can input the child's emotion data to the generation AI and determine the priority of data to be collected by the generation AI.

[0116] The collection unit can collect data while taking into consideration the geographical distribution of conversations. For example, the collection unit collects data while taking into consideration the geographical distribution of conversations. For example, the collection unit collects data related to stress factors felt by children in specific locations. Data related to stress factors felt by children while traveling can also be collected. Furthermore, data related to stress factors felt by children within the home can also be collected. This allows the collection unit to collect data while taking into consideration the geographical distribution of conversations. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input information related to the geographical distribution of conversations to AI, and the AI ​​can perform collection.

[0117] The collection unit can improve the accuracy of collection by referring to literature related to the conversation when collecting data. The collection unit can improve the accuracy of collection by referring to literature related to the conversation when collecting data, for example. For example, the collection unit can improve the accuracy of data collection by referring to related literature. The accuracy of data collection can also be improved by referring to academic papers. Furthermore, the accuracy of data collection can also be improved by referring to specialized books. Thereby, the collection unit can improve the accuracy of collection by referring to literature related to the conversation. Part or all of the above-mentioned processing in the collection unit can be performed, for example, using AI, or can be performed without using AI. For example, the collection unit can input information about literature related to the conversation to AI, and the AI ​​can improve the accuracy of collection.

[0118] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0119] When analyzing the content of a child's conversation, the analysis unit can adjust the analysis method based on the child's learning style. For example, for a child with a visual learning style, the analysis unit uses a method that visually represents the content of the conversation. For a child with an auditory learning style, emphasis can be placed on audio analysis. Furthermore, for a child with an experiential learning style, analysis can be performed based on actual experience. This allows the analysis unit to provide an optimal analysis method according to the child's learning style.

[0120] When providing advice to a parent, the parent-oriented providing unit can adjust the way in which the advice is expressed based on the parent's communication style. For example, if the parent prefers visual information, advice using graphs and diagrams can be provided. If the parent prefers auditory information, advice using audio messages can be provided. Furthermore, if the parent prefers experiential information, advice including specific examples can also be provided. This allows the parent-oriented providing unit to provide optimal advice according to the parent's communication style.

[0121] When providing advice to a child, the child-oriented provision unit can adjust the content of the advice based on the child's interests. For example, if a child is interested in sports, sports-related advice can be provided. If a child is interested in music, music-related advice can be provided. Furthermore, if a child is interested in science, science-related advice can be provided. This allows the child-oriented provision unit to provide optimal advice according to the child's interests.

[0122] When collecting the child's conversation content, the collection unit can adjust the collection timing based on the child's life rhythm. For example, if the child is active in the morning, the conversation content is collected in the morning hours. Also, if the child is relaxed at night, the conversation content can be collected in the evening hours. Furthermore, if the child is very active on weekends, the conversation content can be collected after the weekend activities. This allows the collection unit to provide optimal collection timing according to the child's life rhythm.

[0123] When analyzing the content of a child's conversation, the analysis unit can adjust the analysis method based on the child's cultural background. For example, in the case of a child from a different cultural background, the analysis is performed taking into account expressions and words specific to that culture. In addition, the analysis unit can emphasize the content of the conversation related to specific cultural events and customs. Furthermore, stress factors can be identified based on cultural values ​​and beliefs. This allows the analysis unit to provide an optimal analysis method according to the child's cultural background.

[0124] The reception unit can estimate the child's emotion and adjust the conversation reception method based on the estimated child's emotion. For example, if the child is nervous, the reception unit can receive a conversation while playing music to relax the child. If the child is excited, the reception unit can receive a conversation in a gentle voice to calm the child. If the child is sad, the reception unit can also receive a conversation in kind words. In this way, the reception unit can provide an optimal conversation reception method according to the child's emotion.

[0125] The analysis unit can estimate the child's emotions and adjust the analysis feedback method based on the estimated child's emotions. For example, if the child feels anxious, feedback to reassure the child can be provided. If the child is happy, feedback to share the child's joy can be provided. Furthermore, if the child is angry, feedback to calm the child can be provided. In this way, the analysis unit can provide the optimal feedback method according to the child's emotions.

[0126] The identification unit can estimate the child's emotion and improve the accuracy of identifying the stress factor based on the estimated child's emotion. For example, if the child is sad, the stress factor can be identified by placing emphasis on emotional factors. Also, if the child is excited, the stress factor can be identified by placing emphasis on environmental factors. Furthermore, if the child is anxious, the stress factor can be identified by placing emphasis on psychological factors. This allows the identification unit to improve the accuracy of identifying the stress factor based on the child's emotion.

[0127] The providing unit can estimate the child's emotion and adjust the timing of advice based on the estimated child's emotion. For example, if the child is relaxed, the advice can be provided immediately. Also, if the child is busy, the advice can be provided at an appropriate timing. Furthermore, if the child is emotionally unstable, the advice can be provided after waiting until the child calms down. In this way, the providing unit can provide the optimal timing of advice according to the child's emotion.

[0128] The providing unit can estimate the child's emotion and adjust the content of the advice based on the estimated child's emotion. For example, if the child is sad, advice to comfort the child can be provided. Also, if the child is happy, advice to further enhance the child's joy can be provided. Furthermore, if the child is feeling anxious, advice to reassure the child can be provided. In this way, the providing unit can provide optimal advice content according to the child's emotion.

[0129] The process flow of the second embodiment will be briefly described below.

[0130] Step 1: The reception unit receives a conversation spoken by a child. The conversation includes voice conversation and text chat. The reception unit can convert the voice conversation into text using voice recognition technology, and can also directly receive the text chat. Step 2: The analysis unit analyzes the conversation content received by the reception unit. Natural language processing technology and emotion analysis technology are used for the analysis. For example, the analysis unit analyzes the conversation content using natural language processing technology and estimates the child's emotions using emotion analysis technology. Step 3: The identification unit identifies stress factors based on the conversation content analyzed by the analysis unit. Stress factors include problems at school, problems at home, etc. For example, the identification unit identifies whether a child is feeling stressed by events at school based on the analysis results. Step 4: The providing unit provides advice based on the stress factors identified by the identifying unit. The advice includes a text message, a voice message, etc. For example, if a child is feeling stressed at school, the providing unit provides advice to a parent such as "It seems like your child is feeling stressed at school. Please listen to him / her."

[0131] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0132] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0133] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0134] Each of the multiple elements including the above-mentioned reception unit, analysis unit, identification unit, provision unit, parent-oriented provision unit, child-oriented provision unit, and collection unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives a conversation spoken by a child. The analysis unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and analyzes the content of the conversation received by the reception unit. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and identifies a stress factor based on the analyzed conversation content. The provision unit is realized, for example, by the control unit 46A of the smart device 14 and provides advice based on the identified stress factor. The parent-oriented provision unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and provides advice to a parent. The child-oriented provision unit is realized, for example, by the control unit 46A of the smart device 14 and provides advice to a child. The collection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the contents of the conversation and collects data for understanding the mental health condition of the child. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0135] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0136] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0137] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0138] 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.

[0139] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0141] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0142] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0143] 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.

[0144] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0145] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0146] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0147] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0148] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0149] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0150] Each of the multiple elements including the above-mentioned reception unit, analysis unit, identification unit, provision unit, parent-oriented provision unit, child-oriented provision unit, and collection unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives a conversation spoken by a child. The analysis unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and analyzes the content of the conversation received by the reception unit. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and identifies a stress factor based on the analyzed conversation content. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214 and provides advice based on the identified stress factor. The parent-oriented provision unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and provides advice to a parent. The child-oriented provision unit is realized, for example, by the control unit 46A of the smart glasses 214 and provides advice to a child. The collection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the contents of the conversation and collects data for understanding the mental health condition of the child. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0151] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0152] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0153] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0154] 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.

[0155] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0156] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0157] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0158] 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.

[0159] 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.

[0160] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0161] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0162] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0163] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0164] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0165] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0166] Each of the multiple elements including the above-mentioned reception unit, analysis unit, identification unit, provision unit, parent-oriented provision unit, child-oriented provision unit, and collection unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314 and receives a conversation spoken by a child. The analysis unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and analyzes the content of the conversation received by the reception unit. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and identifies a stress factor based on the analyzed conversation content. The provision unit is realized, for example, by the control unit 46A of the headset type terminal 314 and provides advice based on the identified stress factor. The parent-oriented provision unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and provides advice to a parent. The child-oriented provision unit is realized, for example, by the control unit 46A of the headset type terminal 314 and provides advice to a child. The collection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the contents of the conversation and collects data for understanding the mental health condition of the child. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0167] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0168] 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.

[0169] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0170] 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.

[0171] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0172] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0173] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0174] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0175] 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.

[0176] 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.

[0177] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0178] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0179] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0180] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0181] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0182] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0183] Each of the multiple elements including the above-mentioned reception unit, analysis unit, identification unit, provision unit, parent-oriented provision unit, child-oriented provision unit, and collection unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives a conversation spoken by a child. The analysis unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and analyzes the content of the conversation received by the reception unit. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and identifies a stress factor based on the analyzed conversation content. The provision unit is realized, for example, by the control unit 46A of the robot 414 and provides advice based on the identified stress factor. The parent-oriented provision unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and provides advice to parents. The child-oriented provision unit is realized, for example, by the control unit 46A of the robot 414 and provides advice to children. The collection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the contents of the conversation and collects data for understanding the mental health condition of the child. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0184] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0185] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0186] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0187] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0188] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0189] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0190] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0191] 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.

[0192] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0193] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0194] 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.

[0195] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0196] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0197] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0198] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0199] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0200] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0201] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0202] (Appendix 1) A reception unit that accepts conversations; an analysis unit that analyzes the conversation content received by the reception unit; an identification unit that identifies a stress factor based on the conversation content analyzed by the analysis unit; a providing unit that provides advice based on the stress factor identified by the identifying unit. A system characterized by: (Appendix 2) Equipped with a parent-oriented section that provides advice to parents 2. The system of claim 1, (Appendix 3) Equipping a child-oriented service department that provides advice to children 2. The system of claim 1, (Appendix 4) Equipped with a data collection unit that analyzes the content of conversations and collects data to understand the mental health status of children 2. The system of claim 1, (Appendix 5) The analysis unit is Provide information for AI characters to give direct advice to children 2. The system of claim 1, (Appendix 6) The parent-oriented providing unit includes: Offer advice in a way that respects children's privacy 3. The system of claim 2, (Appendix 7) The reception unit is Estimate the child's emotions and adjust the timing of conversation acceptance based on the estimated child's emotions 2. The system of claim 1, (Appendix 8) The reception unit is Analyze the child's past conversation history and choose the reception method 2. The system of claim 1, (Appendix 9) The reception unit is Filter incoming conversations based on your child's current life situation and interests 2. The system of claim 1, (Appendix 10) The reception unit is Estimate the child's emotions and prioritize incoming conversations based on the estimated child's emotions 2. The system of claim 1, (Appendix 11) The reception unit is When accepting conversations, the system takes into account the child's geographic location to prioritize relevant conversations. 2. The system of claim 1, (Appendix 12) The reception unit is When a conversation is received, analyze the child's social media activity and receive related conversations. 2. The system of claim 1, (Appendix 13) The analysis unit is Infer the child's emotions and adjust the way the analysis is presented based on the estimated child's emotions 2. The system of claim 1, (Appendix 14) The analysis unit is During analysis, adjust the level of analysis detail based on the importance of the conversation 2. The system of claim 1, (Appendix 15) The analysis unit is During analysis, different analysis algorithms are applied depending on the category of the conversation. 2. The system of claim 1, (Appendix 16) The analysis unit is Infer the child's emotions and adjust the length of the analysis based on the estimated child's emotions 2. The system of claim 1, (Appendix 17) The analysis unit is During analysis, prioritize analysis based on when the conversation was submitted 2. The system of claim 1, (Appendix 18) The analysis unit is During analysis, adjust the order of analysis based on conversation relevance 2. The system of claim 1, (Appendix 19) The identification unit is Estimate the child's emotions and adjust the stressor identification method based on the estimated child's emotions 2. The system of claim 1, (Appendix 20) The identification unit is During identification, conversation correlation is taken into account to improve identification accuracy. 2. The system of claim 1, (Appendix 21) The identification unit is When identifying a person, the attribute information of the person who submitted the conversation is taken into consideration. 2. The system of claim 1, (Appendix 22) The identification unit is Estimate the child's emotions and prioritize identified stressors based on the estimated child's emotions 2. The system of claim 1, (Appendix 23) The identification unit is During identification, geographical distribution of conversations is taken into account. 2. The system of claim 1, (Appendix 24) The identification unit is During identification, refer to related literature on the conversation to improve the accuracy of identification. 2. The system of claim 1, (Appendix 25) The providing unit is Infer the child's emotions and adjust the way the advice is presented based on the child's emotions 2. The system of claim 1, (Appendix 26) The providing unit is When providing advice, adjust the level of detail of the advice based on the importance of the stressor 2. The system of claim 1, (Appendix 27) The providing unit is When providing advice, different advice algorithms are applied depending on the category of stressor. 2. The system of claim 1, (Appendix 28) The providing unit is Infer the child's emotions and adjust the length of the advice based on the estimated child's emotions 2. The system of claim 1, (Appendix 29) The providing unit is When providing advice, prioritize advice based on when the stressor was submitted 2. The system of claim 1, (Appendix 30) The providing unit is When providing advice, adjust the order of advice based on the relevance of stressors 2. The system of claim 1, (Appendix 31) The parent-oriented providing unit includes: Inferring a child's emotions and tailoring parental advice based on the inferred child's emotions 3. The system of claim 2, (Appendix 32) The parent-oriented providing unit includes: When providing advice to parents, adjust the level of detail in a way that respects children's privacy 3. The system of claim 2, (Appendix 33) The parent-oriented providing unit includes: Inferring a child's emotions and adjusting the length of parental advice based on the estimated child's emotions 3. The system of claim 2, (Appendix 34) The parent-oriented providing unit includes: Prioritize advice for parents in a way that respects children's privacy 3. The system of claim 2, (Appendix 35) The child-oriented provision unit includes: Inferring a child's emotions and tailoring advice to the child based on the estimated child's emotions 4. The system of claim 3. (Appendix 36) The child-oriented provision unit includes: When providing advice to children, adjust the level of detail of the advice based on the importance of the stressor 4. The system of claim 3. (Appendix 37) The child-oriented provision unit includes: Inferring a child's emotions and adjusting the length of the advice given to the child based on the estimated child's emotions 4. The system of claim 3. (Appendix 38) The child-oriented provision unit includes: Prioritize child advice based on when stressors were submitted 4. The system of claim 3. (Appendix 39) The collecting unit includes: Estimate the child's emotions and adjust data collection methods based on the estimated child's emotions. 5. The system of claim 4. (Appendix 40) The collecting unit includes: When collecting data, improve the accuracy of collection by taking into account the correlation of conversations. 5. The system of claim 4. (Appendix 41) The collecting unit includes: Inferring a child's emotions and prioritizing data collection based on the inferred emotions 5. The system of claim 4. (Appendix 42) The collecting unit includes: When collecting data, take into account the geographical distribution of conversations. 5. The system of claim 4. (Appendix 43) The collecting unit includes: When collecting data, refer to related literature on the conversation to improve the accuracy of the data. 5. The system of claim 4. [Explanation of symbols]

[0203] 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 reception unit that accepts conversations; an analysis unit that analyzes the conversation content received by the reception unit; an identification unit that identifies a stress factor based on the conversation content analyzed by the analysis unit; a providing unit that provides advice based on the stress factor identified by the identifying unit. A system characterized by:

2. Equipped with a parent-oriented section that provides advice to parents 2. The system of claim 1 .

3. Equipping a child-oriented service department that provides advice to children 2. The system of claim 1 .

4. Equipped with a data collection unit that analyzes the content of conversations and collects data to understand the mental health status of children 2. The system of claim 1 .

5. The analysis unit is Providing information for AI characters to give direct advice to children 2. The system of claim 1 .

6. The parent-oriented providing unit includes: Offer advice in a way that respects children's privacy 3. The system of claim 2.

7. The reception unit is Estimate the child's emotions and adjust the timing of conversation acceptance based on the estimated child's emotions 2. The system of claim 1 .

8. The reception unit is Analyze the child's past conversation history and choose the reception method 2. The system of claim 1 .

9. The reception unit is Filter incoming conversations based on your child's current life situation and interests 2. The system of claim 1 .

10. The reception unit is Estimate the child's emotions and prioritize incoming conversations based on the estimated child's emotions 2. The system of claim 1 .

Images