System

Abstract

To allow a user who lives away from a parent to provide appropriate support and advice to the parent.SOLUTION: A system according to an embodiment includes a collection unit, a learning unit, a communication unit, and a provision unit. The collection unit collects features of a user's voice and text. The learning unit learns the features collected by the collection unit. The communication unit communicates with a parent, based on the features learned by the learning unit. The provision unit provides a piece of advice to the parent.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] Conventional technology has the problem that it is difficult for users who live far away from their parents to provide them with appropriate support and advice.

[0005] The system according to the embodiment aims to enable a user who lives apart from his / her parents to provide appropriate support and advice to the parents. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a learning unit, a communication unit, and a provision unit. The collection unit collects voice and text features of a user. The learning unit learns the features collected by the collection unit. The communication unit communicates with a parent based on the features learned by the learning unit. The provision unit provides advice to the parent. Effect of the Invention

[0007] The system according to the embodiment enables a user who lives apart from his / her parents to provide appropriate support and advice to the parents. [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 a 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 AI ​​filial piety system according to the embodiment of the present invention is a system that learns the characteristics of the user's voice and text, and functions as "you" who is by the parent's side 24 hours a day, 365 days a year. This system collects the characteristics of the user's voice and text, and the AI ​​learns them, allowing it to communicate with the parent. For example, if the parent encounters a fraud or illegal business practice, the AI ​​analyzes the content and issues a warning to the parent. Also, if the parent has trouble using a smartphone or electrical appliance, the AI ​​provides appropriate advice. In this way, the AI ​​acts as if it is by the parent's side, achieving filial piety. For example, the user records his or her own voice or text and provides it to the AI. This allows the AI ​​to accurately grasp the user's characteristics. Next, based on the learned characteristics, the AI ​​communicates with the parent on behalf of the user. For example, if the parent encounters a fraud or illegal business practice, the AI ​​analyzes the content and issues a warning to the parent. Specifically, the AI ​​analyzes the content of the phone call or email the parent receives, and issues a warning if there is a possibility of fraud. This protects the parent from fraud and illegal business practices. Furthermore, if a parent has trouble using a smartphone or electrical appliance, the AI ​​will provide appropriate advice. For example, if a parent has trouble setting up a smartphone or using an electrical appliance, the AI ​​will teach them the specific steps. This allows the parent to use the smartphone or electrical appliance correctly. This mechanism allows the AI ​​to act as if it is close to the parent, realizing filial piety. Even if the user is not close to the parent, the user can support the parent through the AI. For example, even if the user lives far away, the AI ​​being close to the parent can increase the parent's sense of security. This allows the AI ​​filial piety system to learn the characteristics of the user's voice and text, communicate with the parent, and realize filial piety.

[0029] The AI ​​filial piety system according to the embodiment includes a collection unit, a learning unit, a communication unit, and a provision unit. The collection unit collects features of the user's voice and text. The collection unit can collect features by, for example, recording the user's voice and inputting text. The collection unit can collect the user's voice using a microphone and collect the text using a keyboard. The learning unit learns the features collected by the collection unit. The learning unit can learn the features of the voice and text using, for example, a machine learning algorithm. The learning unit can also learn the features of the voice and text using, for example, deep learning technology. The communication unit communicates with the parent based on the features learned by the learning unit. The communication unit can communicate with the parent using, for example, a voice call or a text message. The communication unit can also communicate with the parent using, for example, a video call. The provision unit provides advice to the parent through the communication unit. The provision unit can provide, for example, a warning of fraud or illegal business practices to the parent. The provision unit can also provide, for example, advice on how to use a smartphone or an electrical appliance to the parent. As a result, the AI ​​filial piety system of the embodiment can learn the characteristics of the user's voice and text and communicate with their parents, thereby realizing filial piety.

[0030] The collection unit collects the voice and text features of the user. Specifically, the collection unit uses a microphone to record the user's voice and extracts features by analyzing the voice data. To collect the voice data, a noise canceling technology can be used to remove ambient noise and obtain clear voice. The collection unit also collects text data entered by the user using a keyboard. To collect the text data, a natural language processing technology can be used to analyze grammar and vocabulary features and grasp the user's language pattern. Furthermore, the collection unit can also collect non-verbal features such as the user's facial expressions and gestures. For example, a camera can be used to analyze the user's facial expressions and detect changes in emotions. This allows the collection unit to comprehensively collect voice, text, and non-verbal data and grasp the user's features in detail. The collected data is stored in a secure database and encrypted for privacy protection. The collection unit can periodically update the data and hold the latest user information. This allows the collection unit to efficiently collect various features of the user and improve the accuracy and reliability of the entire system.

[0031] The learning unit learns the features collected by the collection unit. Specifically, the learning unit learns the features of voice and text using a machine learning algorithm. For example, for voice data, speech recognition technology is used to analyze phoneme and intonation patterns, and the user's speaking style and voice features are learned. For text data, natural language processing technology is used to analyze context and meaning, and the user's language patterns and preferences are learned. Furthermore, the learning unit can use deep learning technology to learn the features of voice and text at a higher level. For example, a convolutional neural network (CNN) is used to extract features of voice data, and a recurrent neural network (RNN) is used to learn time series patterns of text data. This allows the learning unit to learn the features of users with high accuracy and respond to individual needs. The learning unit continuously updates the model using the collected data to improve the learning accuracy. For example, every time new voice data or text data is collected, the model is retrained and learning is performed based on the latest user information. This allows the learning unit to always provide high-accuracy learning based on the latest information, and improve the performance of the entire system.

[0032] The communication unit communicates with the parent based on the characteristics learned by the learning unit. Specifically, the communication unit can communicate with the parent using voice calls and text messages. For example, in voice calls, the communication unit can mimic the characteristics of the user's voice to provide a natural conversation to the parent. In text messages, the communication unit can generate messages that reflect the user's language patterns to provide friendly communication to the parent. Furthermore, the communication unit can also communicate with the parent using video calls. In video calls, the communication unit can mimic the user's facial expressions and gestures to provide visual communication to the parent. This allows the communication unit to provide various communication means using voice, text, and video to realize smooth communication with the parent. The communication unit can collect the parent's reactions and feedback and continuously improve the quality of communication. For example, the communication unit can analyze how the parent reacts to what kind of message and reflect this in the next communication. This allows the communication unit to communicate with the parent more effectively and realize filial piety.

[0033] The providing unit provides advice to the parent through the communication unit. Specifically, the providing unit can provide the parent with a warning about fraud or illegal business practices. For example, if the parent receives a suspicious phone call or email, the providing unit analyzes the contents and issues a warning if there is a possibility of fraud. The providing unit can also provide the parent with advice on how to use smartphones and electrical appliances. For example, if the parent is having trouble operating the smartphone, the providing unit guides the parent with specific operating procedures by voice or text. Furthermore, the providing unit can also provide advice on health management for the parent. For example, the providing unit monitors the parent's health condition and provides appropriate exercise and dietary advice. This allows the providing unit to provide various advice to the parent and support the parent's life. The providing unit can collect feedback from the parent and continuously improve the quality of the advice. For example, the providing unit can analyze what kind of advice the parent is likely to accept and reflect it in the next advice. The providing unit can also customize the content of the advice according to the parent's needs. This allows the providing unit to provide appropriate and effective advice to the parent and realize filial piety.

[0034] The collection unit includes a voice collection unit that collects the user's voice. The voice collection unit collects the user's voice using, for example, a microphone. For example, the voice collection unit can record and collect phrases and expressions that the user uses daily. The voice collection unit can also collect the user's voice in real time. For example, the voice collection unit can record and collect the contents of what the user speaks in real time. Furthermore, the voice collection unit can also collect the user's voice over a long period of time. For example, the voice collection unit can collect the contents of what the user speaks daily over a long period of time and grasp the characteristics. This allows the voice collection unit to learn more accurate characteristics by collecting the user's voice. Part or all of the above-mentioned processing in the voice collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice collection unit can collect the user's voice, input the voice data to the generation AI, and have the generation AI execute analysis of the voice data.

[0035] The collection unit includes a text collection unit that collects the user's text. The text collection unit collects the user's text using, for example, a keyboard. For example, the text collection unit can input and collect phrases and expressions that the user uses on a daily basis. The text collection unit can also collect the user's text in real time. For example, the text collection unit can collect the contents entered by the user in real time and grasp the characteristics. Furthermore, the text collection unit can also collect the user's text over a long period of time. For example, the text collection unit can collect the contents entered by the user on a daily basis over a long period of time and grasp the characteristics. This allows the text collection unit to learn more accurate characteristics by collecting the user's text. A part or all of the above-mentioned processing in the text collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the text collection unit can collect the user's text, input the text data to the generation AI, and have the generation AI execute an analysis of the text data.

[0036] The learning unit includes a voice learning unit that learns the collected voice. The voice learning unit learns the collected voice, for example, using a voice recognition algorithm. For example, the voice learning unit can analyze the tone and speed of the user's voice and learn the features. The voice learning unit can also learn the collected voice using a voice feature extraction technology. For example, the voice learning unit can analyze the pitch and intonation of the user's voice and learn the features. Furthermore, the voice learning unit can also learn the collected voice using a deep learning technology. For example, the voice learning unit can input the user's voice data into a deep learning model and learn the features. Thereby, the voice learning unit can grasp the features more accurately by learning the collected voice. A part or all of the above-mentioned processing in the voice learning unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the voice learning unit can input the collected voice data into a generation AI and cause the generation AI to execute learning of the voice data.

[0037] The learning unit includes a text learning unit that learns the collected text. The text learning unit learns the collected text, for example, using natural language processing technology. For example, the text learning unit can analyze keywords and contexts of the user's text and learn features. The text learning unit can also learn the collected text using text mining technology. For example, the text learning unit can analyze frequent words and co-occurrence relationships of the user's text and learn features. Furthermore, the text learning unit can also learn the collected text using deep learning technology. For example, the text learning unit can input the user's text data into a deep learning model and learn features. Thereby, the text learning unit can grasp more accurate features by learning the collected text. A part or all of the above-mentioned processing in the text learning unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the text learning unit can input the collected text data into a generation AI and cause the generation AI to execute learning of the text data.

[0038] The communication unit includes a voice communication unit that communicates with the parent by voice. The voice communication unit communicates with the parent by voice, for example, using a voice call technology. For example, the voice communication unit can have a conversation with the parent over the phone. The voice communication unit can also communicate with the parent by voice, using a voice synthesis technology. For example, the voice communication unit can send a voice message to the parent. Furthermore, the voice communication unit can also communicate with the parent by voice in real time. For example, the voice communication unit can have a conversation with the parent in real time. As a result, the voice communication unit can communicate with the parent by voice, enabling a more natural dialogue. A part or all of the above-mentioned processing in the voice communication unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the voice communication unit can input conversation data with the parent to the generation AI and have the generation AI analyze the content of the conversation.

[0039] The communication unit includes a text communication unit that communicates with the parent by text. The text communication unit communicates with the parent by text, for example, using chatbot technology. For example, the text communication unit can exchange text messages with the parent in real time. The text communication unit can also communicate with the parent by text using a messaging app. For example, the text communication unit can send a text message to the parent and receive a reply from the parent. Furthermore, the text communication unit can communicate with the parent by text over a long period of time. For example, the text communication unit can save a history of text messages with the parent and refer to past conversations. This allows the text communication unit to communicate with the parent by text, enabling more flexible dialogue. A part or all of the above-mentioned processing in the text communication unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the text communication unit can input a text message with the parent to the generation AI and have the generation AI analyze the content of the message.

[0040] The providing unit includes a warning providing unit that provides a warning of fraud or illegal business practices to the parent. The warning providing unit, for example, analyzes the contents of a phone call or email received by the parent, and issues a warning if there is a possibility of fraud. For example, the warning providing unit can analyze the voice of a phone call received by the parent and detect signs of fraud. The warning providing unit can also analyze the text of an email received by the parent and issue a warning if there is a possibility of illegal business practices. For example, the warning providing unit can analyze the contents of an email received by the parent using natural language processing technology and detect signs of illegal business practices. Furthermore, the warning providing unit can analyze the contents of a message received by the parent in real time and issue a warning immediately. For example, the warning providing unit can analyze a message received by the parent in real time and issue a warning immediately if there is a possibility of fraud. In this way, the warning providing unit can protect the parent by providing a warning of fraud or illegal business practices to the parent. A part or all of the above-mentioned processing in the warning providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the warning providing unit can input a message received by a parent to the generation AI and have the generation AI analyze the message.

[0041] The providing unit includes an advice providing unit that provides advice to the parent on how to use the smartphone or the electrical appliance. For example, when the parent is in trouble with how to set up the smartphone or how to use the electrical appliance, the advice providing unit teaches the specific procedure. For example, when the parent asks about how to set up the smartphone, the advice providing unit can provide the specific setting procedure in text or voice. In addition, when the parent asks about how to use the electrical appliance, the advice providing unit can also provide the specific operation procedure in text or voice. For example, when the parent asks about how to use a new electrical appliance, the advice providing unit can provide the specific operation procedure in video. Furthermore, the advice providing unit can provide advice in real time when the parent is in trouble. For example, when the parent asks about how to use the smartphone or the electrical appliance in real time, the advice providing unit can provide advice immediately. As a result, the advice providing unit can support the parent's life by providing advice on how to use the smartphone or the electrical appliance to the parent. A part or all of the above-mentioned processing in the advice providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the advice providing unit can input the content of a parent's question to the generation AI and cause the generation AI to generate advice.

[0042] The collection unit analyzes the user's past voice and text usage history and selects the optimal collection method. The collection unit analyzes the user's past voice and text usage history, for example, using log analysis technology. For example, the collection unit can analyze phrases and expressions frequently used by the user in the past and select the optimal collection method. The collection unit can also analyze the user's past voice and text usage history using behavioral pattern extraction technology. For example, the collection unit can analyze the tone and speed of the voice used by the user in the past and reflect it at the time of collection. Furthermore, the collection unit can analyze the style and expression of the text used by the user in the past and reflect it at the time of collection. For example, the collection unit can analyze the keywords and context of the text used by the user in the past and select the optimal collection method. This allows the collection unit to collect data more effectively by analyzing the past usage history. 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 the user's past usage history data to the generation AI and cause the generation AI to execute the analysis of the usage history.

[0043] The collection unit performs filtering based on the user's current activity status and field of interest when collecting voice and text. The collection unit performs filtering when collecting voice and text, for example, using a technology that evaluates the user's current activity status. For example, when the user is at work, the collection unit can preferentially collect voice and text related to the user's work. The collection unit can also perform filtering when collecting voice and text, using a technology that identifies the user's field of interest. For example, when the user is immersed in a hobby, the collection unit can collect voice and text related to the hobby. Furthermore, the collection unit can adjust the collection of voice and text in real time based on the user's activity status and field of interest. For example, when the user is on vacation, the collection unit can collect voice and text with relaxing content. This allows the collection unit to collect more relevant data by filtering based on the current activity status and field of interest. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data on the user's activity status and field of interest to the generation AI and cause the generation AI to perform filtering.

[0044] When collecting voice and text, the collection unit preferentially collects highly relevant data taking into account the geographical location information of the user. The collection unit, for example, acquires the geographical location information of the user using GPS data. For example, when the user is traveling, the collection unit can collect voice and text related to the travel destination. The collection unit can also acquire the geographical location information of the user using a location information service. For example, when the user is at home, the collection unit can collect voice and text related to conversations and activities in the home. Furthermore, the collection unit can adjust the collection of voice and text in real time based on the geographical location information of the user. For example, when the user is at work, the collection unit can collect voice and text related to work at the workplace. In this way, the collection unit can collect more relevant data by taking the geographical location information into account. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the geographical location information data of the user to the generation AI and cause the generation AI to perform an analysis of the location information.

[0045] The collection unit analyzes the user's social media activity and collects related data when collecting the voice and text. The collection unit analyzes the user's social media activity using, for example, social media analysis technology. For example, the collection unit can collect phrases and expressions frequently used by the user on social media. The collection unit can also collect voice and text related to content shared by the user on social media. For example, the collection unit can collect voice and text related to images and videos shared by the user on social media. Furthermore, the collection unit can adjust the collection of voice and text based on the user's social media activity time zone. For example, the collection unit can determine the optimal collection timing based on the user's social media activity time zone. This allows the collection unit to collect more relevant data by analyzing the social media activity. 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 the user's social media activity data to the generation AI and cause the generation AI to perform an analysis of the activity.

[0046] The learning unit optimizes the learning algorithm by referring to past learning data during learning. The learning unit optimizes the voice recognition algorithm, for example, based on voice data collected in the past. For example, the learning unit can analyze the voice data collected in the past and set optimal learning parameters. The learning unit can also optimize the natural language processing algorithm, based on text data collected in the past. For example, the learning unit can analyze the text data collected in the past and set optimal learning parameters. Furthermore, the learning unit can analyze past learning results and set optimal learning parameters. For example, the learning unit can set optimal learning parameters based on past learning results. This allows the learning unit to optimize the learning algorithm by referring to the past learning data. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input past learning data to the generation AI and cause the generation AI to optimize the learning algorithm.

[0047] During learning, the learning unit applies different learning algorithms depending on the categories of voice and text. For example, the learning unit applies a voice recognition algorithm to voice data and a natural language processing algorithm to text data. For example, the learning unit can apply different algorithms to conversational voice and instruction voice among voice data. In addition, the learning unit can apply different algorithms to daily conversation and technical terms among text data. For example, the learning unit can apply a natural language processing algorithm to text data of daily conversation and an algorithm specialized for technical terms to text data of technical terms. Furthermore, the learning unit can apply different learning algorithms depending on the categories of voice data and text data. For example, the learning unit can apply a voice recognition algorithm to voice data and a natural language processing algorithm to text data. As a result, the learning unit can apply different algorithms depending on the category, thereby enabling more effective learning. Part or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input voice data and text data to the generation AI and cause the generation AI to apply a learning algorithm according to the category.

[0048] During learning, the learning unit weights the learning data based on the time of submission of the voice or text. For example, the learning unit weights recently collected data highly and weights old data low. For example, the learning unit can weight recently collected voice data highly and weight old voice data low. The learning unit can also weight data collected during a specific event period highly. For example, the learning unit can weight text data collected during a specific event period highly. Furthermore, the learning unit can weight data collected during a specific time period highly based on the user's life rhythm. For example, the learning unit can weight voice data collected during a specific time period highly based on the user's life rhythm. This allows the learning unit to weight data based on the time of submission, thereby enabling more effective learning. Part or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input voice data and text data to the generation AI and cause the generation AI to perform weighting based on the time of submission.

[0049] The learning unit adjusts the order of the learning data based on the relevance of the voice and text during learning. For example, the learning unit preferentially learns data with high relevance and postpones data with low relevance. For example, the learning unit can preferentially learn voice data with high relevance and postpone voice data with low relevance. The learning unit can also continuously learn data of the same category to perform efficient learning. For example, the learning unit can continuously learn text data of the same category to perform efficient learning. Furthermore, the learning unit can also preferentially learn data that is frequently used by the user. For example, the learning unit can preferentially learn voice data that is frequently used by the user. As a result, the learning unit adjusts the order of the learning data based on the relevance, thereby enabling more efficient learning. Part or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input voice data and text data to the generation AI and cause the generation AI to perform order adjustment based on the relevance.

[0050] The communication unit selects the optimal communication method by referring to the parent's past reaction history at the time of communication. The communication unit, for example, analyzes past dialogue logs to refer to the parent's reaction history. For example, the communication unit can preferentially select a communication method to which the parent responded favorably in the past. The communication unit can also refer to the parent's reaction history using a reaction pattern analysis technique. For example, the communication unit can avoid a communication method to which the parent felt uncomfortable in the past. Furthermore, the communication unit can communicate at the optimal timing based on the parent's past reaction history. For example, the communication unit can analyze the parent's past reaction history and communicate at the optimal timing. As a result, the communication unit can communicate more effectively by referring to the parent's past reaction history. A part or all of the above-mentioned processing in the communication unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the communication unit can input the parent's reaction history data to the generation AI and cause the generation AI to execute an analysis of the reaction history.

[0051] The communication unit customizes the means of communication based on the parent's current situation at the time of communication. The communication unit customizes the means of communication, for example, by using a technology that evaluates the parent's physical condition and environment. For example, the communication unit can communicate with a short message when the parent is busy. The communication unit can also customize the means of communication by using a technology that evaluates the parent's current situation. For example, the communication unit can communicate with a longer conversation when the parent is relaxed. Furthermore, the communication unit can adjust the means of communication in real time based on the parent's current situation. For example, the communication unit can communicate with a text message when the parent is out. This enables the communication unit to customize the means of communication based on the parent's current situation, thereby enabling more appropriate communication. Part or all of the above-mentioned processing in the communication unit may be performed, for example, using AI, or may be performed without using AI. For example, the communication unit can input the parent's current situation data to the generation AI and cause the generation AI to evaluate the situation and customize the means.

[0052] The communication unit selects the optimal communication method in consideration of the geographical location information of the parent at the time of communication. The communication unit acquires the geographical location information, for example, using a technology that identifies the parent's current location. For example, the communication unit can communicate by voice call when the parent is at home. The communication unit can also acquire the geographical location information of the parent using a location information service. For example, the communication unit can communicate by text message when the parent is out. Furthermore, the communication unit can adjust the means of communication in real time based on the geographical location information of the parent. For example, the communication unit can communicate by video call when the parent is traveling. This allows the communication unit to select a more appropriate communication method by considering the geographical location information of the parent. A part or all of the above-mentioned processing in the communication unit may be performed, for example, using AI, or may be performed without using AI. For example, the communication unit can input the geographical location information data of the parent to the generation AI and cause the generation AI to execute an analysis of the location information.

[0053] The communication unit analyzes the parent's social media activity and suggests a means of communication at the time of communication. The communication unit analyzes the parent's social media activity using, for example, social media analysis technology. For example, the communication unit can communicate through a messaging app that the parent frequently uses on social media. The communication unit can also communicate on topics related to content shared by the parent on social media. For example, the communication unit can communicate on topics related to images and videos shared by the parent on social media. Furthermore, the communication unit can adjust the timing of communication based on the parent's social media activity time zone. For example, the communication unit can determine the optimal communication timing based on the parent's social media activity time zone. In this way, the communication unit can suggest a more appropriate means of communication by analyzing the parent's social media activity. A part or all of the above-mentioned processing in the communication unit may be performed using, for example, AI, or may be performed without using AI. For example, the communication unit can input the parent's social media activity data to the generation AI and cause the generation AI to perform an analysis of the activity.

[0054] The providing unit selects the most suitable advice by referring to the parent's past reaction history at the time of providing. The providing unit, for example, analyzes past dialogue logs and refers to the parent's reaction history. For example, the providing unit can preferentially select advice to which the parent responded favorably in the past. The providing unit can also refer to the parent's reaction history using a reaction pattern analysis technique. For example, the providing unit can avoid advice to which the parent felt uncomfortable in the past. Furthermore, the providing unit can provide advice at the most suitable timing based on the parent's past reaction history. For example, the providing unit can analyze the parent's past reaction history and provide advice at the most suitable timing. As a result, the providing unit can provide more effective advice by referring to the parent's past reaction history. 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 the parent's reaction history data to the generating AI and cause the generating AI to execute the analysis of the reaction history.

[0055] The providing unit customizes the means of advice based on the parent's current situation at the time of providing. The providing unit customizes the means of advice using, for example, a technology that evaluates the parent's physical condition and environment. For example, if the parent is busy, the providing unit can provide advice with a short message. The providing unit can also customize the means of advice using a technology that evaluates the parent's current situation. For example, if the parent is relaxed, the providing unit can provide advice including a detailed explanation. Furthermore, the providing unit can adjust the means of advice in real time based on the parent's current situation. For example, if the parent is out, the providing unit can provide advice by a text message. Thereby, the providing unit can provide more appropriate advice by customizing the means of advice based on the parent's current situation. 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 the parent's current situation data to the generating AI and cause the generating AI to evaluate the situation and customize the means.

[0056] The providing unit selects the most suitable advice in consideration of the geographical location information of the parent at the time of providing. The providing unit, for example, acquires the geographical location information using a technology for identifying the parent's current location. For example, when the parent is at home, the providing unit can provide advice that can be executed at home. The providing unit can also acquire the geographical location information of the parent using a location information service. For example, when the parent is out, the providing unit can provide advice that can be executed at the out-of-home location. Furthermore, the providing unit can adjust the means of advice in real time based on the geographical location information of the parent. For example, when the parent is traveling, the providing unit can provide advice that is useful at the travel destination. Thereby, the providing unit can select more appropriate advice by considering the geographical location information of the parent. 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 geographical location information data of the parent to the generating AI and cause the generating AI to execute an analysis of the location information.

[0057] The providing unit, at the time of providing, analyzes the social media activity of the parent and suggests a means of advice. The providing unit, for example, uses a social media analysis technology to analyze the social media activity of the parent. For example, the providing unit can provide advice through a messaging app that the parent frequently uses on social media. The providing unit can also provide advice related to content shared by the parent on social media. For example, the providing unit can provide advice related to images and videos shared by the parent on social media. Furthermore, the providing unit can adjust the timing of the advice based on the time period of the parent's social media activity. For example, the providing unit can determine the optimal timing of the advice based on the time period of the parent's social media activity. In this way, the providing unit can suggest a more appropriate means of advice by analyzing the parent's social media activity. 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 the parent's social media activity data to the generating AI and cause the generating AI to perform an analysis of the activity.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The AI ​​filial piety system can further include a health monitoring unit that monitors the parent's health condition. For example, the health monitoring unit can measure the parent's heart rate and blood pressure and issue a warning if an abnormality is detected. The health monitoring unit can also analyze the parent's sleep patterns and provide appropriate sleep advice. Furthermore, the health monitoring unit can record the parent's diet and provide advice on nutritional balance. This allows the AI ​​filial piety system to comprehensively support the parent's health.

[0060] The collection unit may have a function of filtering background sounds when collecting the user's voice. For example, the collection unit may use noise canceling technology to remove background sounds and collect only the user's voice. The collection unit may also preferentially collect voices in a specific frequency band. Furthermore, the collection unit may perform sound source localization using multiple microphones to more accurately collect the user's voice. This allows the collection unit to collect higher quality voice data.

[0061] The text collection unit may have a grammar check function when collecting the user's text. For example, the text collection unit may check the grammar of the text entered by the user in real time and point out any errors. The text collection unit may also automatically correct spelling mistakes in the text entered by the user. Furthermore, the text collection unit may analyze the style of the text entered by the user and suggest appropriate expressions. This allows the text collection unit to collect more accurate and refined text data.

[0062] The warning providing unit can refer to the parent's past reaction history when providing a warning of fraud or illegal business practices to the parent. For example, the warning providing unit can analyze how the parent responded to past warnings and select the optimal warning method. The warning providing unit can also preferentially select a warning method to which the parent responded favorably in the past. Furthermore, the warning providing unit can adjust the timing of the warning based on the parent's past reaction history. This enables the warning providing unit to provide a warning taking into account the parent's past reaction history.

[0063] The advice providing unit can take into account the parent's current situation when providing advice to the parent on how to use the smartphone or electrical appliance. For example, the advice providing unit can provide advice in the form of a short message when the parent is busy. Also, the advice providing unit can provide advice including detailed explanations when the parent is relaxed. Furthermore, the advice providing unit can adjust the means of advice in real time based on the parent's current situation. This enables the advice providing unit to provide advice taking into account the parent's current situation.

[0064] The process flow of the first embodiment will be briefly described below.

[0065] Step 1: The collection unit collects the user's voice and text characteristics. For example, the collection unit can collect the user's voice using a microphone and collect text using a keyboard. Step 2: The learning unit learns the features collected by the collection unit. For example, the learning unit can learn voice and text features using machine learning algorithms or deep learning techniques. Step 3: The communication unit communicates with the parent based on the characteristics learned by the learning unit. For example, the communication unit can communicate with the parent using voice calls, text messages, or video calls. Step 4: The provision unit provides advice to the parent through the communication unit. For example, the provision unit can provide the parent with warnings about fraud and illegal business practices, and advice on how to use smartphones and electrical appliances.

[0066] (Example 2) The AI ​​filial piety system according to the embodiment of the present invention is a system that learns the characteristics of the user's voice and text, and functions as "you" who is by the parent's side 24 hours a day, 365 days a year. This system collects the characteristics of the user's voice and text, and the AI ​​learns them, allowing it to communicate with the parent. For example, if the parent encounters a fraud or illegal business practice, the AI ​​analyzes the content and issues a warning to the parent. Also, if the parent has trouble using a smartphone or electrical appliance, the AI ​​provides appropriate advice. In this way, the AI ​​acts as if it is by the parent's side, achieving filial piety. For example, the user records his or her own voice or text and provides it to the AI. This allows the AI ​​to accurately grasp the user's characteristics. Next, based on the learned characteristics, the AI ​​communicates with the parent on behalf of the user. For example, if the parent encounters a fraud or illegal business practice, the AI ​​analyzes the content and issues a warning to the parent. Specifically, the AI ​​analyzes the content of the phone call or email the parent receives, and issues a warning if there is a possibility of fraud. This protects the parent from fraud and illegal business practices. Furthermore, if a parent has trouble using a smartphone or electrical appliance, the AI ​​will provide appropriate advice. For example, if a parent has trouble setting up a smartphone or using an electrical appliance, the AI ​​will teach them the specific steps. This allows the parent to use the smartphone or electrical appliance correctly. This mechanism allows the AI ​​to act as if it is close to the parent, realizing filial piety. Even if the user is not close to the parent, the user can support the parent through the AI. For example, even if the user lives far away, the AI ​​being close to the parent can increase the parent's sense of security. This allows the AI ​​filial piety system to learn the characteristics of the user's voice and text, communicate with the parent, and realize filial piety.

[0067] The AI ​​filial piety system according to the embodiment includes a collection unit, a learning unit, a communication unit, and a provision unit. The collection unit collects features of the user's voice and text. The collection unit can collect features by, for example, recording the user's voice and inputting text. The collection unit can collect the user's voice using a microphone and collect the text using a keyboard. The learning unit learns the features collected by the collection unit. The learning unit can learn the features of the voice and text using, for example, a machine learning algorithm. The learning unit can also learn the features of the voice and text using, for example, deep learning technology. The communication unit communicates with the parent based on the features learned by the learning unit. The communication unit can communicate with the parent using, for example, a voice call or a text message. The communication unit can also communicate with the parent using, for example, a video call. The provision unit provides advice to the parent through the communication unit. The provision unit can provide, for example, a warning of fraud or illegal business practices to the parent. The provision unit can also provide, for example, advice on how to use a smartphone or an electrical appliance to the parent. As a result, the AI ​​filial piety system of the embodiment can learn the characteristics of the user's voice and text and communicate with their parents, thereby realizing filial piety.

[0068] The collection unit collects the voice and text features of the user. Specifically, the collection unit uses a microphone to record the user's voice and extracts features by analyzing the voice data. To collect the voice data, a noise canceling technology can be used to remove ambient noise and obtain clear voice. The collection unit also collects text data entered by the user using a keyboard. To collect the text data, a natural language processing technology can be used to analyze grammar and vocabulary features and grasp the user's language pattern. Furthermore, the collection unit can also collect non-verbal features such as the user's facial expressions and gestures. For example, a camera can be used to analyze the user's facial expressions and detect changes in emotions. This allows the collection unit to comprehensively collect voice, text, and non-verbal data and grasp the user's features in detail. The collected data is stored in a secure database and encrypted for privacy protection. The collection unit can periodically update the data and hold the latest user information. This allows the collection unit to efficiently collect various features of the user and improve the accuracy and reliability of the entire system.

[0069] The learning unit learns the features collected by the collection unit. Specifically, the learning unit learns the features of voice and text using a machine learning algorithm. For example, for voice data, speech recognition technology is used to analyze phoneme and intonation patterns, and the user's speaking style and voice features are learned. For text data, natural language processing technology is used to analyze context and meaning, and the user's language patterns and preferences are learned. Furthermore, the learning unit can use deep learning technology to learn the features of voice and text at a higher level. For example, a convolutional neural network (CNN) is used to extract features of voice data, and a recurrent neural network (RNN) is used to learn time series patterns of text data. This allows the learning unit to learn the features of users with high accuracy and respond to individual needs. The learning unit continuously updates the model using the collected data to improve the learning accuracy. For example, every time new voice data or text data is collected, the model is retrained and learning is performed based on the latest user information. This allows the learning unit to always provide high-accuracy learning based on the latest information, and improve the performance of the entire system.

[0070] The communication unit communicates with the parent based on the characteristics learned by the learning unit. Specifically, the communication unit can communicate with the parent using voice calls and text messages. For example, in voice calls, the communication unit can mimic the characteristics of the user's voice to provide a natural conversation to the parent. In text messages, the communication unit can generate messages that reflect the user's language patterns to provide friendly communication to the parent. Furthermore, the communication unit can also communicate with the parent using video calls. In video calls, the communication unit can mimic the user's facial expressions and gestures to provide visual communication to the parent. This allows the communication unit to provide various communication means using voice, text, and video to realize smooth communication with the parent. The communication unit can collect the parent's reactions and feedback and continuously improve the quality of communication. For example, the communication unit can analyze how the parent reacts to what kind of message and reflect this in the next communication. This allows the communication unit to communicate with the parent more effectively and realize filial piety.

[0071] The providing unit provides advice to the parent through the communication unit. Specifically, the providing unit can provide the parent with a warning about fraud or illegal business practices. For example, if the parent receives a suspicious phone call or email, the providing unit analyzes the contents and issues a warning if there is a possibility of fraud. The providing unit can also provide the parent with advice on how to use smartphones and electrical appliances. For example, if the parent is having trouble operating the smartphone, the providing unit guides the parent with specific operating procedures by voice or text. Furthermore, the providing unit can also provide advice on health management for the parent. For example, the providing unit monitors the parent's health condition and provides appropriate exercise and dietary advice. This allows the providing unit to provide various advice to the parent and support the parent's life. The providing unit can collect feedback from the parent and continuously improve the quality of the advice. For example, the providing unit can analyze what kind of advice the parent is likely to accept and reflect it in the next advice. The providing unit can also customize the content of the advice according to the parent's needs. This allows the providing unit to provide appropriate and effective advice to the parent and realize filial piety.

[0072] The collection unit includes a voice collection unit that collects the user's voice. The voice collection unit collects the user's voice using, for example, a microphone. For example, the voice collection unit can record and collect phrases and expressions that the user uses daily. The voice collection unit can also collect the user's voice in real time. For example, the voice collection unit can record and collect the contents of what the user speaks in real time. Furthermore, the voice collection unit can also collect the user's voice over a long period of time. For example, the voice collection unit can collect the contents of what the user speaks daily over a long period of time and grasp the characteristics. This allows the voice collection unit to learn more accurate characteristics by collecting the user's voice. Part or all of the above-mentioned processing in the voice collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice collection unit can collect the user's voice, input the voice data to the generation AI, and have the generation AI execute analysis of the voice data.

[0073] The collection unit includes a text collection unit that collects the user's text. The text collection unit collects the user's text using, for example, a keyboard. For example, the text collection unit can input and collect phrases and expressions that the user uses on a daily basis. The text collection unit can also collect the user's text in real time. For example, the text collection unit can collect the contents entered by the user in real time and grasp the characteristics. Furthermore, the text collection unit can also collect the user's text over a long period of time. For example, the text collection unit can collect the contents entered by the user on a daily basis over a long period of time and grasp the characteristics. This allows the text collection unit to learn more accurate characteristics by collecting the user's text. A part or all of the above-mentioned processing in the text collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the text collection unit can collect the user's text, input the text data to the generation AI, and have the generation AI execute an analysis of the text data.

[0074] The learning unit includes a voice learning unit that learns the collected voice. The voice learning unit learns the collected voice, for example, using a voice recognition algorithm. For example, the voice learning unit can analyze the tone and speed of the user's voice and learn the features. The voice learning unit can also learn the collected voice using a voice feature extraction technology. For example, the voice learning unit can analyze the pitch and intonation of the user's voice and learn the features. Furthermore, the voice learning unit can also learn the collected voice using a deep learning technology. For example, the voice learning unit can input the user's voice data into a deep learning model and learn the features. Thereby, the voice learning unit can grasp the features more accurately by learning the collected voice. A part or all of the above-mentioned processing in the voice learning unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the voice learning unit can input the collected voice data into a generation AI and cause the generation AI to execute learning of the voice data.

[0075] The learning unit includes a text learning unit that learns the collected text. The text learning unit learns the collected text, for example, using natural language processing technology. For example, the text learning unit can analyze keywords and contexts of the user's text and learn features. The text learning unit can also learn the collected text using text mining technology. For example, the text learning unit can analyze frequent words and co-occurrence relationships of the user's text and learn features. Furthermore, the text learning unit can also learn the collected text using deep learning technology. For example, the text learning unit can input the user's text data into a deep learning model and learn features. Thereby, the text learning unit can grasp more accurate features by learning the collected text. A part or all of the above-mentioned processing in the text learning unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the text learning unit can input the collected text data into a generation AI and cause the generation AI to execute learning of the text data.

[0076] The communication unit includes a voice communication unit that communicates with the parent by voice. The voice communication unit communicates with the parent by voice, for example, using a voice call technology. For example, the voice communication unit can have a conversation with the parent over the phone. The voice communication unit can also communicate with the parent by voice, using a voice synthesis technology. For example, the voice communication unit can send a voice message to the parent. Furthermore, the voice communication unit can also communicate with the parent by voice in real time. For example, the voice communication unit can have a conversation with the parent in real time. As a result, the voice communication unit can communicate with the parent by voice, enabling a more natural dialogue. A part or all of the above-mentioned processing in the voice communication unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the voice communication unit can input conversation data with the parent to the generation AI and have the generation AI analyze the content of the conversation.

[0077] The communication unit includes a text communication unit that communicates with the parent by text. The text communication unit communicates with the parent by text, for example, using chatbot technology. For example, the text communication unit can exchange text messages with the parent in real time. The text communication unit can also communicate with the parent by text using a messaging app. For example, the text communication unit can send a text message to the parent and receive a reply from the parent. Furthermore, the text communication unit can communicate with the parent by text over a long period of time. For example, the text communication unit can save a history of text messages with the parent and refer to past conversations. This allows the text communication unit to communicate with the parent by text, enabling more flexible dialogue. A part or all of the above-mentioned processing in the text communication unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the text communication unit can input a text message with the parent to the generation AI and have the generation AI analyze the content of the message.

[0078] The providing unit includes a warning providing unit that provides a warning of fraud or illegal business practices to the parent. The warning providing unit, for example, analyzes the contents of a phone call or email received by the parent, and issues a warning if there is a possibility of fraud. For example, the warning providing unit can analyze the voice of a phone call received by the parent and detect signs of fraud. The warning providing unit can also analyze the text of an email received by the parent and issue a warning if there is a possibility of illegal business practices. For example, the warning providing unit can analyze the contents of an email received by the parent using natural language processing technology and detect signs of illegal business practices. Furthermore, the warning providing unit can analyze the contents of a message received by the parent in real time and issue a warning immediately. For example, the warning providing unit can analyze a message received by the parent in real time and issue a warning immediately if there is a possibility of fraud. In this way, the warning providing unit can protect the parent by providing a warning of fraud or illegal business practices to the parent. A part or all of the above-mentioned processing in the warning providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the warning providing unit can input a message received by a parent to the generation AI and have the generation AI analyze the message.

[0079] The providing unit includes an advice providing unit that provides advice to the parent on how to use the smartphone or the electrical appliance. For example, when the parent is in trouble with how to set up the smartphone or how to use the electrical appliance, the advice providing unit teaches the specific procedure. For example, when the parent asks about how to set up the smartphone, the advice providing unit can provide the specific setting procedure in text or voice. In addition, when the parent asks about how to use the electrical appliance, the advice providing unit can also provide the specific operation procedure in text or voice. For example, when the parent asks about how to use a new electrical appliance, the advice providing unit can provide the specific operation procedure in video. Furthermore, the advice providing unit can provide advice in real time when the parent is in trouble. For example, when the parent asks about how to use the smartphone or the electrical appliance in real time, the advice providing unit can provide advice immediately. As a result, the advice providing unit can support the parent's life by providing advice on how to use the smartphone or the electrical appliance to the parent. A part or all of the above-mentioned processing in the advice providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the advice providing unit can input the content of a parent's question to the generation AI and cause the generation AI to generate advice.

[0080] The collection unit estimates the user's emotion and adjusts the timing of collecting voice and text based on the estimated user's emotion. The collection unit estimates the user's emotion using, for example, voice analysis technology. For example, the collection unit can analyze the tone and speed of the user's voice to estimate the emotion. The collection unit can also estimate the user's emotion using facial expression recognition technology. For example, the collection unit can capture the user's facial expression with a camera and analyze changes in the facial expression to estimate the emotion. Furthermore, the collection unit can also estimate the user's emotion using text analysis technology. For example, the collection unit can analyze the content of the user's text and estimate the emotion. This allows the collection unit to estimate the user's emotion and adjust the timing of collecting voice and text based on the estimated emotion. For example, when the user is relaxed, the collection unit collects voice and text for a long time. Furthermore, when the user is stressed, the collection unit can end collection in a short time and try collection again at a later date. Furthermore, when the user is busy, the collection unit can temporarily suspend collection and resume it when the user has calmed down. This allows the collection unit to adjust the collection timing based on the user's emotions, thereby enabling more appropriate data collection. 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 (e.g., 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 the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the user's voice data to the generation AI and have the generation AI execute emotion estimation.

[0081] The collection unit analyzes the user's past voice and text usage history and selects the optimal collection method. The collection unit analyzes the user's past voice and text usage history, for example, using log analysis technology. For example, the collection unit can analyze phrases and expressions frequently used by the user in the past and select the optimal collection method. The collection unit can also analyze the user's past voice and text usage history using behavioral pattern extraction technology. For example, the collection unit can analyze the tone and speed of the voice used by the user in the past and reflect it at the time of collection. Furthermore, the collection unit can analyze the style and expression of the text used by the user in the past and reflect it at the time of collection. For example, the collection unit can analyze the keywords and context of the text used by the user in the past and select the optimal collection method. This allows the collection unit to collect data more effectively by analyzing the past usage history. 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 the user's past usage history data to the generation AI and cause the generation AI to execute the analysis of the usage history.

[0082] The collection unit performs filtering based on the user's current activity status and field of interest when collecting voice and text. The collection unit performs filtering when collecting voice and text, for example, using a technology that evaluates the user's current activity status. For example, when the user is at work, the collection unit can preferentially collect voice and text related to the user's work. The collection unit can also perform filtering when collecting voice and text, using a technology that identifies the user's field of interest. For example, when the user is immersed in a hobby, the collection unit can collect voice and text related to the hobby. Furthermore, the collection unit can adjust the collection of voice and text in real time based on the user's activity status and field of interest. For example, when the user is on vacation, the collection unit can collect voice and text with relaxing content. This allows the collection unit to collect more relevant data by filtering based on the current activity status and field of interest. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data on the user's activity status and field of interest to the generation AI and cause the generation AI to perform filtering.

[0083] The collection unit estimates the user's emotion and determines the priority of the voice and text to be collected based on the estimated user's emotion. The collection unit estimates the user's emotion using, for example, a voice analysis technology. For example, the collection unit can analyze the tone and speed of the user's voice to estimate the emotion. The collection unit can also estimate the user's emotion using facial expression recognition technology. For example, the collection unit can capture the user's facial expression with a camera and estimate the emotion by analyzing the change in the facial expression. Furthermore, the collection unit can also estimate the user's emotion using a text analysis technology. For example, the collection unit can analyze the content of the user's text and estimate the emotion. Thereby, the collection unit can estimate the user's emotion and determine the priority of the voice and text to be collected based on the estimated emotion. For example, when the user is excited, the collection unit preferentially collects voice and text that reflect the heightened emotion. Furthermore, when the user is calm, the collection unit can preferentially collect voice and text with calm content. Furthermore, when the user is sad, the collection unit can preferentially collect voice and text that soothes the emotion. This allows the collection unit to prioritize collection of more important data by determining priorities based on the user's emotions. The estimation of emotions 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 (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the user's voice data to the generation AI and have the generation AI execute emotion estimation.

[0084] When collecting voice and text, the collection unit preferentially collects highly relevant data taking into account the geographical location information of the user. The collection unit, for example, acquires the geographical location information of the user using GPS data. For example, when the user is traveling, the collection unit can collect voice and text related to the travel destination. The collection unit can also acquire the geographical location information of the user using a location information service. For example, when the user is at home, the collection unit can collect voice and text related to conversations and activities in the home. Furthermore, the collection unit can adjust the collection of voice and text in real time based on the geographical location information of the user. For example, when the user is at work, the collection unit can collect voice and text related to work at the workplace. In this way, the collection unit can collect more relevant data by taking the geographical location information into account. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the geographical location information data of the user to the generation AI and cause the generation AI to perform an analysis of the location information.

[0085] The collection unit analyzes the user's social media activity and collects related data when collecting the voice and text. The collection unit analyzes the user's social media activity using, for example, social media analysis technology. For example, the collection unit can collect phrases and expressions frequently used by the user on social media. The collection unit can also collect voice and text related to content shared by the user on social media. For example, the collection unit can collect voice and text related to images and videos shared by the user on social media. Furthermore, the collection unit can adjust the collection of voice and text based on the user's social media activity time zone. For example, the collection unit can determine the optimal collection timing based on the user's social media activity time zone. This allows the collection unit to collect more relevant data by analyzing the social media activity. 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 the user's social media activity data to the generation AI and cause the generation AI to perform an analysis of the activity.

[0086] The learning unit estimates the user's emotion and selects learning data based on the estimated user's emotion. The learning unit estimates the user's emotion using, for example, a voice analysis technique. For example, the learning unit can analyze the tone and speed of the user's voice to estimate the emotion. The learning unit can also estimate the user's emotion using a facial expression recognition technique. For example, the learning unit can capture the user's facial expression with a camera and estimate the emotion by analyzing the change in the facial expression. Furthermore, the learning unit can estimate the user's emotion using a text analysis technique. For example, the learning unit can analyze the content of the user's text and estimate the emotion. This allows the learning unit to estimate the user's emotion and select learning data based on the estimated emotion. For example, when the user is relaxed, the learning unit selects voice and text in the relaxed state as learning data. Furthermore, when the user is excited, the learning unit can select voice and text in the excited state as learning data. Furthermore, when the user is sad, the learning unit can select voice and text in the sad state as learning data. This allows the learning unit to select learning data based on the user's emotions, enabling more effective learning. 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 (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the learning unit can input the user's voice data to the generation AI and cause the generation AI to execute emotion estimation.

[0087] The learning unit optimizes the learning algorithm by referring to past learning data during learning. The learning unit optimizes the voice recognition algorithm, for example, based on voice data collected in the past. For example, the learning unit can analyze the voice data collected in the past and set optimal learning parameters. The learning unit can also optimize the natural language processing algorithm, based on text data collected in the past. For example, the learning unit can analyze the text data collected in the past and set optimal learning parameters. Furthermore, the learning unit can analyze past learning results and set optimal learning parameters. For example, the learning unit can set optimal learning parameters based on past learning results. This allows the learning unit to optimize the learning algorithm by referring to the past learning data. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input past learning data to the generation AI and cause the generation AI to optimize the learning algorithm.

[0088] During learning, the learning unit applies different learning algorithms depending on the categories of voice and text. For example, the learning unit applies a voice recognition algorithm to voice data and a natural language processing algorithm to text data. For example, the learning unit can apply different algorithms to conversational voice and instruction voice among voice data. In addition, the learning unit can apply different algorithms to daily conversation and technical terms among text data. For example, the learning unit can apply a natural language processing algorithm to text data of daily conversation and an algorithm specialized for technical terms to text data of technical terms. Furthermore, the learning unit can apply different learning algorithms depending on the categories of voice data and text data. For example, the learning unit can apply a voice recognition algorithm to voice data and a natural language processing algorithm to text data. As a result, the learning unit can apply different algorithms depending on the category, thereby enabling more effective learning. Part or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input voice data and text data to the generation AI and cause the generation AI to apply a learning algorithm according to the category.

[0089] The learning unit estimates the user's emotion and adjusts the frequency of learning based on the estimated user's emotion. The learning unit estimates the user's emotion using, for example, a voice analysis technique. For example, the learning unit can analyze the tone and speed of the user's voice to estimate the emotion. The learning unit can also estimate the user's emotion using facial expression recognition technique. For example, the learning unit can capture the user's facial expression with a camera and estimate the emotion by analyzing the change in the facial expression. Furthermore, the learning unit can also estimate the user's emotion using a text analysis technique. For example, the learning unit can analyze the contents of the user's text and estimate the emotion. This allows the learning unit to estimate the user's emotion and adjust the frequency of learning based on the estimated emotion. For example, the learning unit increases the frequency of learning when the user is relaxed. Also, the learning unit can reduce the frequency of learning when the user is stressed. Furthermore, the learning unit can temporarily reduce the frequency of learning when the user is busy and repeat the learning at a later date. This allows the learning unit to adjust the frequency of learning based on the user's emotion, thereby enabling more effective learning. The emotion estimation is realized by 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 (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the learning unit can input the user's voice data to the generation AI and cause the generation AI to estimate the emotion.

[0090] During learning, the learning unit weights the learning data based on the time of submission of the voice or text. For example, the learning unit weights recently collected data highly and weights old data low. For example, the learning unit can weight recently collected voice data highly and weight old voice data low. The learning unit can also weight data collected during a specific event period highly. For example, the learning unit can weight text data collected during a specific event period highly. Furthermore, the learning unit can weight data collected during a specific time period highly based on the user's life rhythm. For example, the learning unit can weight voice data collected during a specific time period highly based on the user's life rhythm. This allows the learning unit to weight data based on the time of submission, thereby enabling more effective learning. Part or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input voice data and text data to the generation AI and cause the generation AI to perform weighting based on the time of submission.

[0091] The learning unit adjusts the order of the learning data based on the relevance of the voice and text during learning. For example, the learning unit preferentially learns data with high relevance and postpones data with low relevance. For example, the learning unit can preferentially learn voice data with high relevance and postpone voice data with low relevance. The learning unit can also continuously learn data of the same category to perform efficient learning. For example, the learning unit can continuously learn text data of the same category to perform efficient learning. Furthermore, the learning unit can also preferentially learn data that is frequently used by the user. For example, the learning unit can preferentially learn voice data that is frequently used by the user. As a result, the learning unit adjusts the order of the learning data based on the relevance, thereby enabling more efficient learning. Part or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input voice data and text data to the generation AI and cause the generation AI to perform order adjustment based on the relevance.

[0092] The communication unit estimates the user's emotion and adjusts the expression method of communication based on the estimated user's emotion. The communication unit estimates the user's emotion using, for example, voice analysis technology. For example, the communication unit can analyze the tone and speed of the user's voice to estimate the emotion. The communication unit can also estimate the user's emotion using facial expression recognition technology. For example, the communication unit can capture the user's facial expression with a camera and estimate the emotion by analyzing the change in the facial expression. Furthermore, the communication unit can also estimate the user's emotion using text analysis technology. For example, the communication unit can analyze the content of the user's text and estimate the emotion. This allows the communication unit to estimate the user's emotion and adjust the expression method of communication based on the estimated emotion. For example, the communication unit communicates in a gentle tone when the user is relaxed. Also, the communication unit can communicate in a lively tone when the user is excited. Furthermore, the communication unit can communicate in a gentle tone when the user is sad. This allows the communication unit to adjust the expression method of communication based on the user's emotion, thereby enabling more appropriate communication. The emotion estimation is realized by 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 (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the communication unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the communication unit can input the user's voice data to the generation AI and cause the generation AI to estimate the emotion.

[0093] The communication unit selects the optimal communication method by referring to the parent's past reaction history at the time of communication. The communication unit, for example, analyzes past dialogue logs to refer to the parent's reaction history. For example, the communication unit can preferentially select a communication method to which the parent responded favorably in the past. The communication unit can also refer to the parent's reaction history using a reaction pattern analysis technique. For example, the communication unit can avoid a communication method to which the parent felt uncomfortable in the past. Furthermore, the communication unit can communicate at the optimal timing based on the parent's past reaction history. For example, the communication unit can analyze the parent's past reaction history and communicate at the optimal timing. As a result, the communication unit can communicate more effectively by referring to the parent's past reaction history. A part or all of the above-mentioned processing in the communication unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the communication unit can input the parent's reaction history data to the generation AI and cause the generation AI to execute an analysis of the reaction history.

[0094] The communication unit customizes the means of communication based on the parent's current situation at the time of communication. The communication unit customizes the means of communication, for example, by using a technology that evaluates the parent's physical condition and environment. For example, the communication unit can communicate with a short message when the parent is busy. The communication unit can also customize the means of communication by using a technology that evaluates the parent's current situation. For example, the communication unit can communicate with a longer conversation when the parent is relaxed. Furthermore, the communication unit can adjust the means of communication in real time based on the parent's current situation. For example, the communication unit can communicate with a text message when the parent is out. This enables the communication unit to customize the means of communication based on the parent's current situation, thereby enabling more appropriate communication. Part or all of the above-mentioned processing in the communication unit may be performed, for example, using AI, or may be performed without using AI. For example, the communication unit can input the parent's current situation data to the generation AI and cause the generation AI to evaluate the situation and customize the means.

[0095] The communication unit estimates the user's emotion and determines the priority of communication based on the estimated user's emotion. The communication unit estimates the user's emotion using, for example, a voice analysis technique. For example, the communication unit can analyze the tone and speed of the user's voice to estimate the emotion. The communication unit can also estimate the user's emotion using a facial expression recognition technique. For example, the communication unit can capture the user's facial expression with a camera and estimate the emotion by analyzing the change in the facial expression. Furthermore, the communication unit can also estimate the user's emotion using a text analysis technique. For example, the communication unit can analyze the content of the user's text and estimate the emotion. This allows the communication unit to estimate the user's emotion and determine the priority of communication based on the estimated emotion. For example, the communication unit immediately communicates when the user is in an emergency situation. Also, the communication unit can communicate with normal priority when the user is relaxed. Furthermore, the communication unit can lower the priority of communication that can be postponed when the user is busy. This allows the communication unit to prioritize more important communication by determining the priority based on the user's emotion. The emotion estimation is realized by 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 (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the communication unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the communication unit can input the user's voice data to the generation AI and cause the generation AI to estimate the emotion.

[0096] The communication unit selects the optimal communication method in consideration of the geographical location information of the parent at the time of communication. The communication unit acquires the geographical location information, for example, using a technology that identifies the parent's current location. For example, the communication unit can communicate by voice call when the parent is at home. The communication unit can also acquire the geographical location information of the parent using a location information service. For example, the communication unit can communicate by text message when the parent is out. Furthermore, the communication unit can adjust the means of communication in real time based on the geographical location information of the parent. For example, the communication unit can communicate by video call when the parent is traveling. This allows the communication unit to select a more appropriate communication method by considering the geographical location information of the parent. A part or all of the above-mentioned processing in the communication unit may be performed, for example, using AI, or may be performed without using AI. For example, the communication unit can input the geographical location information data of the parent to the generation AI and cause the generation AI to execute an analysis of the location information.

[0097] The communication unit analyzes the parent's social media activity and suggests a means of communication at the time of communication. The communication unit analyzes the parent's social media activity using, for example, social media analysis technology. For example, the communication unit can communicate through a messaging app that the parent frequently uses on social media. The communication unit can also communicate on topics related to content shared by the parent on social media. For example, the communication unit can communicate on topics related to images and videos shared by the parent on social media. Furthermore, the communication unit can adjust the timing of communication based on the parent's social media activity time zone. For example, the communication unit can determine the optimal communication timing based on the parent's social media activity time zone. In this way, the communication unit can suggest a more appropriate means of communication by analyzing the parent's social media activity. A part or all of the above-mentioned processing in the communication unit may be performed using, for example, AI, or may be performed without using AI. For example, the communication unit can input the parent's social media activity data to the generation AI and cause the generation AI to perform an analysis of the activity.

[0098] The providing unit estimates the user's emotion and adjusts the expression method of the advice to be provided based on the estimated emotion of the user. The providing unit estimates the user's emotion using, for example, a voice analysis technology. For example, the providing unit can analyze the tone and speed of the user's voice to estimate the emotion. The providing unit can also estimate the user's emotion using a facial expression recognition technology. For example, the providing unit can capture the user's facial expression with a camera and estimate the emotion by analyzing the change in the facial expression. Furthermore, the providing unit can also estimate the user's emotion using a text analysis technology. For example, the providing unit can analyze the content of the user's text and estimate the emotion. Thereby, the providing unit can estimate the user's emotion and adjust the expression method of the advice to be provided based on the estimated emotion. For example, the providing unit provides the advice in a gentle tone when the user is relaxed. Also, the providing unit can provide the advice in a lively tone when the user is excited. Furthermore, the providing unit can provide the advice in a gentle tone when the user is sad. Thereby, the providing unit can provide more appropriate advice by adjusting the expression method of the advice based on the user's emotion. The estimation of emotions 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 (e.g., 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 the generation AI, or may be performed without using the generation AI. For example, the providing unit can input the user's voice data to the generation AI and cause the generation AI to execute emotion estimation.

[0099] The providing unit selects the most suitable advice by referring to the parent's past reaction history at the time of providing. The providing unit, for example, analyzes past dialogue logs and refers to the parent's reaction history. For example, the providing unit can preferentially select advice to which the parent responded favorably in the past. The providing unit can also refer to the parent's reaction history using a reaction pattern analysis technique. For example, the providing unit can avoid advice to which the parent felt uncomfortable in the past. Furthermore, the providing unit can provide advice at the most suitable timing based on the parent's past reaction history. For example, the providing unit can analyze the parent's past reaction history and provide advice at the most suitable timing. As a result, the providing unit can provide more effective advice by referring to the parent's past reaction history. 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 the parent's reaction history data to the generating AI and cause the generating AI to execute the analysis of the reaction history.

[0100] The providing unit customizes the means of advice based on the parent's current situation at the time of providing. The providing unit customizes the means of advice using, for example, a technology that evaluates the parent's physical condition and environment. For example, if the parent is busy, the providing unit can provide advice with a short message. The providing unit can also customize the means of advice using a technology that evaluates the parent's current situation. For example, if the parent is relaxed, the providing unit can provide advice including a detailed explanation. Furthermore, the providing unit can adjust the means of advice in real time based on the parent's current situation. For example, if the parent is out, the providing unit can provide advice by a text message. Thereby, the providing unit can provide more appropriate advice by customizing the means of advice based on the parent's current situation. 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 the parent's current situation data to the generating AI and cause the generating AI to evaluate the situation and customize the means.

[0101] The providing unit estimates the user's emotion and determines the priority of advice to be provided based on the estimated user's emotion. The providing unit estimates the user's emotion using, for example, a voice analysis technique. For example, the providing unit can analyze the tone and speed of the user's voice to estimate the emotion. The providing unit can also estimate the user's emotion using facial expression recognition technique. For example, the providing unit can capture the user's facial expression with a camera and estimate the emotion by analyzing the change in the facial expression. Furthermore, the providing unit can also estimate the user's emotion using a text analysis technique. For example, the providing unit can analyze the content of the user's text and estimate the emotion. Thereby, the providing unit can estimate the user's emotion and determine the priority of advice to be provided based on the estimated emotion. For example, the providing unit immediately provides advice when the user is in an emergency situation. Also, the providing unit can provide advice with normal priority when the user is relaxed. Furthermore, the providing unit can lower the priority of advice that can be put off if the user is busy. Thereby, the providing unit can provide more important advice preferentially by determining the priority of advice based on the user's emotion. The estimation of emotions 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 (e.g., 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 the generation AI, or may be performed without using the generation AI. For example, the providing unit can input the user's voice data to the generation AI and cause the generation AI to execute emotion estimation.

[0102] The providing unit selects the most suitable advice in consideration of the geographical location information of the parent at the time of providing. The providing unit, for example, acquires the geographical location information using a technology for identifying the parent's current location. For example, when the parent is at home, the providing unit can provide advice that can be executed at home. The providing unit can also acquire the geographical location information of the parent using a location information service. For example, when the parent is out, the providing unit can provide advice that can be executed at the out-of-home location. Furthermore, the providing unit can adjust the means of advice in real time based on the geographical location information of the parent. For example, when the parent is traveling, the providing unit can provide advice that is useful at the travel destination. Thereby, the providing unit can select more appropriate advice by considering the geographical location information of the parent. 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 geographical location information data of the parent to the generating AI and cause the generating AI to execute an analysis of the location information.

[0103] The providing unit, at the time of providing, analyzes the social media activity of the parent and suggests a means of advice. The providing unit, for example, uses a social media analysis technology to analyze the social media activity of the parent. For example, the providing unit can provide advice through a messaging app that the parent frequently uses on social media. The providing unit can also provide advice related to content shared by the parent on social media. For example, the providing unit can provide advice related to images and videos shared by the parent on social media. Furthermore, the providing unit can adjust the timing of the advice based on the time period of the parent's social media activity. For example, the providing unit can determine the optimal timing of the advice based on the time period of the parent's social media activity. In this way, the providing unit can suggest a more appropriate means of advice by analyzing the parent's social media activity. 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 the parent's social media activity data to the generating AI and cause the generating AI to perform an analysis of the activity.

[0104] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0105] The AI ​​filial piety system can further include a health monitoring unit that monitors the parent's health condition. For example, the health monitoring unit can measure the parent's heart rate and blood pressure and issue a warning if an abnormality is detected. The health monitoring unit can also analyze the parent's sleep patterns and provide appropriate sleep advice. Furthermore, the health monitoring unit can record the parent's diet and provide advice on nutritional balance. This allows the AI ​​filial piety system to comprehensively support the parent's health.

[0106] The collection unit may have a function of filtering background sounds when collecting the user's voice. For example, the collection unit may use noise canceling technology to remove background sounds and collect only the user's voice. The collection unit may also preferentially collect voices in a specific frequency band. Furthermore, the collection unit may perform sound source localization using multiple microphones to more accurately collect the user's voice. This allows the collection unit to collect higher quality voice data.

[0107] The text collection unit may have a grammar check function when collecting the user's text. For example, the text collection unit may check the grammar of the text entered by the user in real time and point out any errors. The text collection unit may also automatically correct spelling mistakes in the text entered by the user. Furthermore, the text collection unit may analyze the style of the text entered by the user and suggest appropriate expressions. This allows the text collection unit to collect more accurate and refined text data.

[0108] The voice learning unit can have an emotion recognition function when learning the collected voice. For example, the voice learning unit can analyze the tone and speed of the user's voice to estimate emotions. The voice learning unit can also analyze the pitch and intonation of the user's voice to detect changes in emotions. Furthermore, the voice learning unit can input the user's voice data into a deep learning model to learn emotion patterns. This enables the voice learning unit to learn voice data that takes the user's emotions into account.

[0109] The text learning unit can have an emotion recognition function when learning the collected text. For example, the text learning unit can analyze keywords and contexts of the user's text to estimate emotions. The text learning unit can also analyze frequent words and co-occurrence relationships in the user's text to detect changes in emotions. Furthermore, the text learning unit can input the user's text data into a deep learning model to learn emotion patterns. This enables the text learning unit to learn text data taking into account the user's emotions.

[0110] The voice communication unit can have an emotion recognition function when communicating with the parent by voice. For example, the voice communication unit can analyze the tone and speed of the parent's voice to estimate the emotion. The voice communication unit can also analyze the pitch and intonation of the parent's voice to detect changes in emotion. Furthermore, the voice communication unit can input the parent's voice data into a deep learning model to learn emotion patterns. This enables the voice communication unit to take the parent's emotions into account in voice communication.

[0111] The text communication unit can have an emotion recognition function when communicating with the parent through text. For example, the text communication unit can analyze keywords and contexts in the parent's text to estimate emotions. The text communication unit can also analyze frequent words and co-occurrence relationships in the parent's text to detect changes in emotions. Furthermore, the text communication unit can input the parent's text data into a deep learning model to learn patterns of emotions. This enables the text communication unit to take the parent's emotions into consideration when communicating through text.

[0112] The warning providing unit can refer to the parent's past reaction history when providing a warning of fraud or illegal business practices to the parent. For example, the warning providing unit can analyze how the parent responded to past warnings and select the optimal warning method. The warning providing unit can also preferentially select a warning method to which the parent responded favorably in the past. Furthermore, the warning providing unit can adjust the timing of the warning based on the parent's past reaction history. This enables the warning providing unit to provide a warning taking into account the parent's past reaction history.

[0113] The advice providing unit can take into account the parent's current situation when providing advice to the parent on how to use the smartphone or electrical appliance. For example, the advice providing unit can provide advice in the form of a short message when the parent is busy. Also, the advice providing unit can provide advice including detailed explanations when the parent is relaxed. Furthermore, the advice providing unit can adjust the means of advice in real time based on the parent's current situation. This enables the advice providing unit to provide advice taking into account the parent's current situation.

[0114] The collection unit can estimate the user's emotions and determine the priority of the voices and texts to be collected based on the estimated user's emotions. For example, when the user is excited, the collection unit preferentially collects voices and texts that reflect the heightened emotions. When the user is calm, the collection unit can preferentially collect voices and texts with calm content. Furthermore, when the user is sad, the collection unit can preferentially collect voices and texts that soothe the emotions. In this way, the collection unit can preferentially collect more important data by determining the priority based on the user's emotions.

[0115] The process flow of the second embodiment will be briefly described below.

[0116] Step 1: The collection unit collects the user's voice and text characteristics. For example, the collection unit can collect the user's voice using a microphone and collect text using a keyboard. Step 2: The learning unit learns the features collected by the collection unit. For example, the learning unit can learn voice and text features using machine learning algorithms or deep learning techniques. Step 3: The communication unit communicates with the parent based on the characteristics learned by the learning unit. For example, the communication unit can communicate with the parent using voice calls, text messages, or video calls. Step 4: The provision unit provides advice to the parent through the communication unit. For example, the provision unit can provide the parent with warnings about fraud and illegal business practices, and advice on how to use smartphones and electrical appliances.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] Each of the multiple elements including the above-mentioned collection unit, learning unit, communication unit, and provision unit is realized, for example, in at least one of the smart device 14 and the data processing device 12. For example, the collection unit can collect the user's voice and text using the microphone and keyboard of the smart device 14. The learning unit can learn the characteristics of the voice and text collected by the specific processing unit 290 of the data processing device 12. The communication unit can communicate with the parent using the voice call and text message functions of the smart device 14. The provision unit can provide advice to the parent through the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device and control unit is not limited to the above-mentioned example, and various changes are possible.

[0121] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] Each of the multiple elements including the above-mentioned collection unit, learning unit, communication unit, and provision unit is realized, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit can collect the user's voice and text using the microphone and keyboard of the smart glasses 214. The learning unit can learn the characteristics of the voice and text collected by the specific processing unit 290 of the data processing device 12. The communication unit can communicate with the parent using the voice call and text message functions of the smart glasses 214. The provision unit can provide advice to the parent through the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device and control unit is not limited to the above-mentioned example, and various changes are possible.

[0137] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] Each of the multiple elements including the above-mentioned collection unit, learning unit, communication unit, and provision unit is realized, for example, in at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit can collect the user's voice and text using the microphone and keyboard of the headset type terminal 314. The learning unit can learn the features of the voice and text collected by the specific processing unit 290 of the data processing device 12. The communication unit can communicate with the parent using the voice call and text message functions of the headset type terminal 314. The provision unit can provide advice to the parent through the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device and control unit is not limited to the above-mentioned example, and various changes are possible.

[0153] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] Each of the multiple elements including the above-mentioned collection unit, learning unit, communication unit, and provision unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit can collect the user's voice and text using a microphone and keyboard of the robot 414. The learning unit can learn the characteristics of the voice and text collected by the specific processing unit 290 of the data processing device 12. The communication unit can communicate with the parent using the voice call and text message functions of the robot 414. The provision unit can provide advice to the parent through the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device and control unit is not limited to the above-mentioned example, and various changes are possible.

[0170] 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.

[0171] 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.

[0172] These emotions are distributed in the three 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.

[0173] 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).

[0174] 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.

[0175] 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."

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] (Appendix 1) A collection unit for collecting voice and text characteristics of a user; a learning unit that learns the features collected by the collection unit; a communication unit that communicates with a parent based on the characteristics learned by the learning unit; A providing unit that provides advice to a parent. A system characterized by: (Appendix 2) The collecting unit includes: A voice collecting unit is provided for collecting the voice of the user. 2. The system of claim 1, (Appendix 3) The collecting unit includes: A text collection unit is provided for collecting user text. 2. The system of claim 1, (Appendix 4) The learning unit is A voice learning unit is provided to learn the collected voices. 2. The system of claim 1, (Appendix 5) The learning unit is A text learning unit is provided to learn the collected text. 2. The system of claim 1, (Appendix 6) The communication unit includes: Equipped with a voice communication section that communicates with parents by voice 2. The system of claim 1, (Appendix 7) The communication unit includes: Have a text communication department to communicate with parents via text 2. The system of claim 1, (Appendix 8) The providing unit is Equipping a warning provision section that provides warnings to parents about fraudulent or illegal business practices 2. The system of claim 1, (Appendix 9) The providing unit is Equipped with an advice providing section that gives parents advice on how to use smartphones and electrical appliances 2. The system of claim 1, (Appendix 10) The collecting unit includes: Estimate user emotions and adjust the timing of voice and text collection based on the estimated user emotions 2. The system of claim 1, (Appendix 11) The collecting unit includes: Analyze the user's past voice and text usage history to select the optimal collection method 2. The system of claim 1, (Appendix 12) The collecting unit includes: Filtering voice and text collection based on the user's current activity and interests 2. The system of claim 1, (Appendix 13) The collecting unit includes: Estimate user emotions and prioritize voice and text to be collected based on the estimated user emotions 2. The system of claim 1, (Appendix 14) The collecting unit includes: When collecting voice and text, the system takes into account the user's geographic location to prioritize collection of relevant data. 2. The system of claim 1, (Appendix 15) The collecting unit includes: When collecting voice and text, analyze your social media activity and collect related data. 2. The system of claim 1, (Appendix 16) The learning unit is Estimate the user's emotions and select learning data based on the estimated user emotions. 2. The system of claim 1, (Appendix 17) The learning unit is During training, the learning algorithm is optimized by referencing past training data. 2. The system of claim 1, (Appendix 18) The learning unit is During training, different training algorithms are applied depending on the audio or text category. 2. The system of claim 1, (Appendix 19) The learning unit is Infer user emotions and adjust the frequency of learning based on the estimated user emotions. 2. The system of claim 1, (Appendix 20) The learning unit is During training, training data is weighted based on when audio and text were submitted 2. The system of claim 1, (Appendix 21) The learning unit is During training, the order of training data is adjusted based on audio and text relevance 2. The system of claim 1, (Appendix 22) The communication unit includes: Estimate the user's emotions and adjust the way of expressing communication based on the estimated user's emotions 2. The system of claim 1, (Appendix 23) The communication unit includes: When communicating, select the most appropriate communication method by referring to the parent's past response history 2. The system of claim 1, (Appendix 24) The communication unit includes: When communicating, customize the means of communication based on the parent's current situation 2. The system of claim 1, (Appendix 25) The communication unit includes: Estimate user emotions and prioritize communications based on the estimated user emotions 2. The system of claim 1, (Appendix 26) The communication unit includes: When communicating, choose the most appropriate communication method by taking into account the parent's geographic location information 2. The system of claim 1, (Appendix 27) The communication unit includes: When communicating, analyze parents' social media activity to suggest communication avenues 2. The system of claim 1, (Appendix 28) The providing unit is Estimate the user's emotions and adjust the way advice is presented based on the estimated user's emotions 2. The system of claim 1, (Appendix 29) The providing unit is When providing advice, the most appropriate advice is selected by referring to the parent's past reaction history. 2. The system of claim 1, (Appendix 30) The providing unit is At the time of delivery, tailor advice measures based on the parent's current situation 2. The system of claim 1, (Appendix 31) The providing unit is Estimate the user's emotions and prioritize advice based on the estimated user emotions. 2. The system of claim 1, (Appendix 32) The providing unit is At the time of provision, the most appropriate advice is selected taking into account the parent's geographic location information 2. The system of claim 1, (Appendix 33) The providing unit is At the time of delivery, the service analyzes parents' social media activity to suggest advice measures 2. The system of claim 1, [Explanation of symbols]

[0189] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection unit for collecting voice and text characteristics of a user; a learning unit that learns the features collected by the collection unit; a communication unit that communicates with a parent based on the characteristics learned by the learning unit; A providing unit that provides advice to a parent. A system characterized by:

2. The collecting unit includes: A voice collecting unit is provided for collecting the voice of the user.

2. The system of claim 1 .

3. The collecting unit includes: A text collection unit is provided for collecting user text.

2. The system of claim 1 .

4. The learning unit is A voice learning unit is provided to learn the collected voices.

2. The system of claim 1 .

5. The learning unit is A text learning unit is provided to learn the collected text.

2. The system of claim 1 .

6. The communication unit includes: Equipped with a voice communication section that communicates with parents by voice 2. The system of claim 1 .

7. The communication unit includes: Have a text communication department to communicate with parents via text 2. The system of claim 1 .

8. The providing unit is Equipping a warning provision section that provides warnings to parents about fraudulent or illegal business practices 2. The system of claim 1 .

Images