System

Abstract

To discover a child's worry or abuse in early stages and respond appropriately.SOLUTION: A system according to an embodiment of the present invention comprises a reception unit, an analysis unit, a provision unit, a database unit, a determination unit, an alert unit, and a linkage unit. The reception unit consults a child's worry. The analysis unit analyzes information received by the reception unit. The provision unit provides an initial response measure on the basis of information analyzed by the analysis unit. The database unit organizes information provided by the provision unit into a database. The determination unit determines a serious case on the basis of information organized into a database by the database unit. The alert unit raises an alert for the case determined to be serious by the determination unit. The linkage unit causes an expert team to respond on the basis of information notified by the alert unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] Conventional technology does not adequately identify and respond to child distress and abuse early, and there is room for improvement.

[0005] The system according to the embodiment aims to detect child troubles and abuse at an early stage and respond appropriately. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a provision unit, a database unit, a judgment unit, an alert unit, and a collaboration unit. The reception unit consults with children about their worries. The analysis unit analyzes the information received by the reception unit. The provision unit provides initial countermeasures based on the information analyzed by the analysis unit. The database unit stores the information provided by the provision unit in a database. The judgment unit judges serious cases based on the information stored in the database by the database unit. The alert unit issues an alert for cases judged to be serious by the judgment unit. The collaboration unit has a specialized team respond based on the information notified by the alert unit. Effect of the Invention

[0007] The system according to the embodiment can detect child troubles and abuse at an early stage and respond appropriately. [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 system for early detection and early response to child abuse according to the embodiment of the present invention provides a mechanism for children to consult about their worries easily. In this system, children consult about their worries to an AI terminal, and the AI ​​listens to the worries and advises the first response measures. For example, if a child inputs content such as "I sometimes get hit at home" or "I am being bullied at school," the AI ​​analyzes the information and provides specific advice such as "Talk to your parents" or "Talk to your teacher." This advice can be implemented by the child immediately. Furthermore, the AI ​​stores the consultation content in a database and makes it available to instructors and staff nationwide. This allows instructors and staff to understand the children's worries and take appropriate measures. The AI ​​also analyzes the consultation content and judges serious cases. For example, if serious content such as "I am being abused at home" is input, the AI ​​judges the case to be "serious" and raises an alert. This alert is notified to a specialized unit, which responds in cooperation with the school and the police. This mechanism enables early detection and early response to child abuse, and protects the safety of children. This will enable the child abuse early detection and response system to efficiently receive, analyze, provide countermeasures, create a database of children's concerns, identify serious cases, issue alerts, and connect with others.

[0029] The system for early detection and early response to child abuse according to the embodiment includes a reception unit, an analysis unit, a provision unit, a database unit, a judgment unit, an alert unit, and a linking unit. The reception unit consults on the child's worries. The child's worries include, for example, bullying, family problems, and academic worries, but are not limited to such examples. The reception unit includes an interface such as a voice input and a touch panel. The voice input converts the child's voice into text data using, for example, voice recognition technology. The touch panel allows the child to directly input using, for example, a capacitance method or a resistive film method. The analysis unit analyzes the information received by the reception unit. The analysis is performed by, for example, a method such as text analysis, emotion analysis, and pattern recognition. The text analysis analyzes the input text data using, for example, natural language processing technology. The emotion analysis estimates emotions from the input text data. The pattern recognition analyzes, for example, the pattern of the input data to find a specific trend. The provision unit provides an initial response based on the information analyzed by the analysis unit. The initial countermeasures include, for example, a suggestion for counseling, provision of an emergency contact, etc., but are not limited to such examples. The providing unit provides, for example, specific advice that the child can immediately implement. The database unit databases the information provided by the providing unit. Database creation is performed according to criteria such as data format, storage method, and access rights. The database unit databases, for example, the contents of the consultation, and makes it possible for instructors and staff throughout the country to view it. The judging unit judges serious cases based on the information databased by the database unit. Serious cases are judged based on criteria such as the frequency of occurrence of specific keywords and emotion scores. The judging unit judges a case to be serious when, for example, a specific keyword or phrase is included. The alert unit issues an alert for a case judged to be serious by the judging unit. The alert is issued according to criteria such as a notification method, a notification destination, and a level of urgency. The alert unit issues an alert for a serious case, for example, and notifies a specialized unit. The coordinating unit allows the specialized unit to respond based on the information notified by the alert unit.The specialized unit is composed of, for example, psychological counselors, police, and school personnel. The liaison unit responds by coordinating with, for example, schools and police. As a result, the child abuse early detection and early response system according to the embodiment is capable of efficiently accepting, analyzing, providing countermeasures, creating a database, determining serious cases, issuing alerts, and coordinating with other parties regarding children's concerns.

[0030] The reception unit consults on the worries of children. The worries of children include, but are not limited to, bullying, family problems, and academic worries. The reception unit has an interface such as a voice input and a touch panel. The voice input converts the voice of the child into text data using, for example, voice recognition technology. The touch panel allows the child to directly input using, for example, a capacitance type or a resistive film type technology. Specifically, the voice input is equipped with a highly accurate voice recognition engine, and converts the child's speech into text in real time. As a result, the contents of the child's speech are instantly recorded as digital data. The touch panel is designed so that children can intuitively operate it, and information can be input with simple taps and swipes. Furthermore, the reception unit employs encryption technology for privacy protection so that children can consult with confidence. As a result, the children's personal information and consultation contents are safely managed without being leaked to the outside. Furthermore, the reception unit employs a friendly interface design so that children can easily consult. For example, a guide function using characters and animations is installed, providing an environment where children can relax and consult. This enables the reception department to efficiently receive various concerns from children and collect information at an early stage.

[0031] The analysis unit analyzes the information received by the reception unit. The analysis is performed by, for example, text analysis, emotion analysis, pattern recognition, and the like. The text analysis is performed by, for example, analyzing the input text data using natural language processing technology. The emotion analysis is performed by, for example, estimating emotions from the input text data. The pattern recognition is performed by, for example, analyzing the patterns of the input data and finding certain trends. Specifically, in the text analysis, the natural language processing technology is used to grammatically and semantically analyze the child's consultation content and extract important keywords and phrases. In the emotion analysis, the emotional tone is analyzed from the text data and the child's psychological state is estimated. For example, the emotion is classified into emotion categories such as positive, negative, and neutral, and the intensity of the emotion is scored. In the pattern recognition, specific patterns and abnormal trends are detected by comparing with past data. This allows the analysis unit to analyze the child's consultation content from multiple angles and to discover potential problems and risks at an early stage. Furthermore, the analysis unit utilizes AI technology to improve the accuracy of the analysis results. For example, a machine learning algorithm is used to learn from past data and continuously improve the analysis model. This enables the analysis unit to provide more accurate and reliable analysis results and quickly grasp the child's worries and problems.

[0032] The providing unit provides an initial response based on the information analyzed by the analyzing unit. The initial response includes, but is not limited to, counseling suggestions and emergency contact information. The providing unit provides, for example, specific advice that the child can immediately implement. Specifically, the providing unit suggests appropriate counseling services to the child based on the analysis results. For example, the providing unit supports the reservation of an online session with a psychological counselor or provides contact information for a local counseling center. In addition, in an emergency, the providing unit provides an emergency contact number that the child can contact immediately so that the necessary support can be received quickly. Furthermore, the providing unit provides specific advice and resources for the child to solve the problem on his or her own. For example, the providing unit provides practical advice for specific problems the child faces, such as methods for stress management, ways to deal with bullying, and solutions to family problems. This allows the providing unit to support the child in taking the first step to solve his or her problems. Furthermore, the providing unit provides information using easy-to-understand words and illustrations so that the child can easily understand and implement the provided information. This allows the providing unit to provide specific means for the child to solve his or her problems and support early problem solving.

[0033] The database unit makes a database of the information provided by the provision unit. The database is made according to standards such as data format, storage method, and access authority. For example, the database unit makes the consultation contents a database and makes it possible for instructors and staff nationwide to view them. Specifically, the database unit centrally manages the consultation contents of children and the countermeasures provided, and enables them to quickly search and refer to the necessary information. The data format supports a variety of formats such as text data, audio data, and image data, and each data is stored with appropriate metadata. The storage method uses cloud storage and distributed databases to ensure the safety and availability of data. In order to protect the confidentiality of the data, different permissions are set for each user, and only the necessary information is provided to the appropriate user. In this way, the database unit efficiently manages the consultation contents of children and countermeasures, and provides an environment in which instructors and staff nationwide can quickly share information. Furthermore, the database unit regularly updates and backs up the data, maintaining the consistency and reliability of the data. In this way, the database unit can store the consultation contents of children and countermeasures for the long term and use them for future analysis and improvement.

[0034] The judgment unit judges a serious case based on the information databased by the database unit. A serious case is judged based on criteria such as the frequency of occurrence of a specific keyword and an emotion score. The judgment unit judges a case to be serious when a specific keyword or phrase is included. Specifically, the judgment unit uses an algorithm that analyzes the information stored in the database and automatically detects serious cases. For example, when specific keywords such as "help me," "I want to die," and "violence" appear frequently or when the result of the emotion analysis is extremely negative, the judgment unit flags the case as serious. In addition, when an abnormal pattern is detected in comparison with past data, the judgment unit judges the case as serious. This allows the judgment unit to discover potential dangers early from the contents of the child's consultation and encourage a prompt response. Furthermore, the judgment unit has an interface for incorporating the opinions of experts, and allows experts such as psychological counselors and doctors to participate in the judgment process as necessary. This allows the judgment unit to make more accurate judgments and support appropriate responses to ensure the safety of children.

[0035] The alert unit issues an alert for cases that are judged to be serious by the judgment unit. The alert is issued according to criteria such as the notification method, notification destination, and level of urgency. For example, the alert unit issues an alert for serious cases and notifies a specialized unit. Specifically, the alert unit is equipped with a system that immediately notifies relevant parties when a serious case is detected. Notification methods are performed using various means such as email, SMS, and push notification. Notifications are sent to all relevant parties, such as the child's guardian, school personnel, psychological counselors, and police. The level of urgency is set according to the seriousness of the case, and in the most urgent cases, immediate response is required. This allows the alert unit to encourage prompt and appropriate response to serious cases and support actions to ensure the safety of children. Furthermore, the alert unit records the history of notifications so that they can be checked later. This makes it easier to track responses and identify areas for improvement, improving the reliability and effectiveness of the entire system.

[0036] In the Liaison Department, specialized units respond based on the information notified by the Alert Department. The specialized units are composed of, for example, psychological counselors, police, and school personnel. In the Liaison Department, the specialized units respond in cooperation with the school and police. Specifically, the Liaison Department supports information sharing and cooperation so that the specialized units that receive the alert can respond quickly. For example, it supports scheduling for psychological counselors to have direct interviews with children, and provides information for the police to rush to the scene quickly. In addition, it provides support for school personnel to grasp the situation of children and take appropriate measures. This allows the Liaison Department to support the specialized units to effectively cooperate and respond quickly to ensure the safety of children. In addition, the Liaison Department monitors the progress of the response and provides additional support as necessary. This allows the Liaison Department to maximize the effectiveness of the entire child abuse early detection and early response system and provide comprehensive support to protect the safety and welfare of children.

[0037] The reception unit may have at least one interface of voice input or touch panel. The voice input may convert the child's voice into text data using, for example, voice recognition technology. For example, the voice recognition technology may analyze the child's speech in real time and store it as text data. The voice input may vary depending on the type of microphone, but for example, by using a directional microphone, ambient noise may be eliminated and the child's voice may be clearly recognized. The touch panel may use, for example, a capacitance type or a resistive film type technology to allow the child to directly input. For example, a capacitive touch panel recognizes input by sensing static electricity on the child's finger. A resistive film type touch panel recognizes input by sensing pressure on the child's finger. This allows the reception unit to allow the child to consult about worries in various ways. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may cause AI to execute a process of converting the child's voice into text data using voice recognition technology.

[0038] The provision unit can provide specific advice that the child can immediately implement. The provision unit provides, for example, specific advice that the child can immediately implement. For example, the provision unit provides the child with specific guidelines for action, such as "consult with a parent" or "talk to a teacher." The provision unit can also provide the child with measures, such as "call an emergency contact" or "receive counseling." Furthermore, the provision unit can provide the child with resources, such as "contact a local support organization" or "use online resources." This allows the provision unit to enable the child to immediately implement countermeasures. Some or all of the above-mentioned processing in the provision unit may be performed, for example, using AI, or may be performed without using AI. For example, the provision unit can analyze the content of the child's consultation and cause AI to execute a process of generating appropriate advice.

[0039] The database unit can database the consultation contents and make them viewable by at least one of the instructors or staff nationwide. The database unit, for example, databases the consultation contents and makes them viewable by the instructors and staff nationwide. Database creation is performed according to standards such as data format, storage method, and access rights. For example, the database unit stores the consultation contents as text data and registers them in the database in a specific format. The database unit also sets access rights for the stored data so that instructors and staff nationwide can properly view it. Furthermore, the database unit provides a data search function so that instructors and staff can quickly obtain the necessary information. In this way, the database unit enables instructors and staff nationwide to understand the concerns of children and take appropriate measures. Some or all of the above-mentioned processing in the database unit may be performed using, for example, AI, or may be performed without using AI. For example, the database unit can cause AI to execute a process of registering the consultation contents in the database.

[0040] The judgment unit can determine that the case is serious when at least one of the specific keywords or phrases is included. The judgment unit, for example, determines that the case is serious when the specific keywords or phrases are included. The specific keywords or phrases include, but are not limited to, for example, "bullying," "suicide," and "help." The judgment unit, for example, analyzes the input consultation content and checks whether the specific keywords or phrases are included. The judgment unit can also determine that the case is serious based on criteria such as the frequency of appearance of the specific keywords or phrases and the emotion score. For example, the judgment unit determines that the case is serious when the input consultation content includes the keyword "bullying." The judgment unit can also determine that the case is serious when the input consultation content includes the phrase "suicide." This allows the judgment unit to quickly determine that the case is serious. Part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can analyze the input consultation content and cause AI to execute a process of checking whether the specific keywords or phrases are included.

[0041] The alert unit can raise an alert for a serious case and notify a specialized unit. The alert unit, for example, raises an alert for a serious case and notifies a specialized unit. The alert is made according to criteria such as a notification method, a notification destination, and a level of urgency. For example, when a serious case occurs, the alert unit notifies the specialized unit by a method such as email or SMS. In addition, the alert unit can specify a psychological counselor, police, or a school official as a notification destination. Furthermore, the alert unit can set a priority order for notifications according to the level of urgency and encourage a prompt response. For example, the alert unit immediately notifies a case with a high urgency and periodically notifies a case with a low urgency. This allows the alert unit to respond promptly to serious cases. A part or all of the above-mentioned processing in the alert unit may be performed, for example, using AI, or may be performed without using AI. For example, the alert unit can cause AI to execute a process of notifying when a serious case occurs.

[0042] The coordination unit can respond by having the specialized unit cooperate with the school and the police. The coordination unit, for example, cooperates with the specialized unit to respond with the school and the police. The specialized unit is composed of, for example, psychological counselors, police, and school personnel. The coordination unit, for example, provides procedures for the specialized unit to cooperate with the school and the police to respond quickly. For example, the coordination unit communicates with the school personnel and discusses specific measures to ensure the safety of children. The coordination unit can also cooperate with the police to take legal action in cases where child abuse is suspected. Furthermore, the coordination unit can cooperate with local support organizations to provide support to children and their families. This allows the specialized unit to respond quickly and protect the safety of children. Some or all of the above-mentioned processing in the coordination unit may be performed using, for example, AI, or may be performed without using AI. For example, the coordination unit can cause AI to execute procedures for the specialized unit to cooperate with the school and the police to respond.

[0043] The reception unit can analyze the past consultation history of the child and select the optimal input interface. The reception unit, for example, analyzes the past consultation history of the child and selects the optimal input interface. The past consultation history includes, for example, the input method (voice, text, etc.) used by the child in the past and the consultation content. The reception unit, for example, preferentially suggests the input method that the child frequently used in the past. The reception unit can also automatically display related input options based on the past consultation content of the child. Furthermore, the reception unit can predict and suggest the input method to be used in a specific time period from the past consultation history of the child. This allows the reception unit to provide the optimal input method for the child. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can analyze the past consultation history of the child and cause AI to execute the processing of selecting the optimal input interface.

[0044] The reception unit can perform filtering based on the child's current living situation and field of interest when receiving the consultation content. The reception unit, for example, performs filtering based on the child's current living situation and field of interest when receiving the consultation content. The living situation includes, for example, the home environment, the school environment, etc. The field of interest includes, for example, hobbies, interests, etc. The reception unit preferentially receives related consultation content based on, for example, the child's current living situation. The reception unit can also filter related consultation content based on the child's field of interest. Furthermore, the reception unit can also suggest appropriate consultation content based on the child's living situation and field of interest. This allows the reception unit to receive appropriate consultation content according to the child's living situation and field of interest. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can cause AI to execute a process of filtering based on the child's living situation and field of interest.

[0045] The reception unit can preferentially receive highly relevant content in consideration of the child's geographical location information when receiving the consultation content. The reception unit, for example, preferentially receives highly relevant content in consideration of the child's geographical location information when receiving the consultation content. The geographical location information includes, for example, GPS data, IP address, and the like. The reception unit preferentially receives consultation content related to the region, for example, based on the child's current geographical location information. The reception unit can also preferentially receive consultation content related to specific problems in the region, in consideration of the child's geographical location information. Furthermore, the reception unit can also preferentially receive consultation content related to local support organizations, in consideration of the child's geographical location information. This allows the reception unit to receive appropriate consultation content based on the child's geographical location information. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can cause AI to execute a process of preferentially receiving highly relevant content in consideration of the child's geographical location information.

[0046] The reception unit can analyze the child's social media activity and receive related content when receiving the consultation content. The reception unit, for example, analyzes the child's social media activity and receives related content when receiving the consultation content. Social media activity includes, for example, analysis of posted content and followers. The reception unit, for example, analyzes the child's social media activity and receives related consultation content preferentially. The reception unit can also filter related consultation content based on the child's social media comments and posted content. Furthermore, the reception unit can also suggest consultation content related to a specific problem from the child's social media activity. This allows the reception unit to receive appropriate consultation content based on the child's social media activity. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can analyze the child's social media activity and cause AI to execute a process of receiving related content.

[0047] The analysis unit can adjust the level of detail of the analysis based on the importance of the consultation content during the analysis. The analysis unit, for example, adjusts the level of detail of the analysis based on the importance of the consultation content during the analysis. The importance of the consultation content is evaluated based on criteria such as the frequency of appearance of keywords and emotion scores. For example, the analysis unit performs a detailed analysis on consultation content with high importance. The analysis unit can also perform a simplified analysis on consultation content with low importance. Furthermore, the analysis unit can determine the priority of the analysis according to the importance of the consultation content. This allows the analysis unit to perform an appropriate analysis according to the importance of the consultation content. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can cause AI to execute a process of adjusting the level of detail of the analysis based on the importance of the consultation content.

[0048] The analysis unit can apply different analysis algorithms depending on the category of the consultation content during analysis. For example, the analysis unit applies different analysis algorithms depending on the category of the consultation content during analysis. The categories of the consultation content include, for example, bullying, family problems, and academic worries. For example, when the consultation content is related to family problems, the analysis unit applies an analysis algorithm specialized for family problems. In addition, when the consultation content is related to school problems, the analysis unit can also apply an analysis algorithm specialized for school problems. Furthermore, when the consultation content is related to friendships, the analysis unit can also apply an analysis algorithm specialized for friendships. This allows the analysis unit to perform an appropriate analysis depending on the category of the consultation content. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can cause AI to execute a process of applying different analysis algorithms depending on the category of the consultation content.

[0049] The analysis unit can determine the priority of the analysis based on the submission time of the consultation content at the time of analysis. The analysis unit, for example, determines the priority of the analysis based on the submission time of the consultation content at the time of analysis. The submission time includes, for example, a timestamp, a record of the submission date, and the like. For example, the analysis unit performs the analysis preferentially when the consultation content has been submitted recently. In addition, the analysis unit can perform the analysis later when the consultation content has been submitted in the past. Furthermore, the analysis unit can adjust the schedule of the analysis based on the submission time of the consultation content. This allows the analysis unit to perform an appropriate analysis according to the submission time of the consultation content. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can cause AI to execute a process of determining the priority of the analysis based on the submission time of the consultation content.

[0050] The analysis unit can adjust the order of analysis based on the relevance of the consultation contents during analysis. The analysis unit, for example, adjusts the order of analysis based on the relevance of the consultation contents during analysis. The relevance of the consultation contents is evaluated based on criteria such as common keywords and related topics. For example, the analysis unit performs analysis preferentially when the consultation contents are highly relevant to other consultation contents. In addition, the analysis unit can also perform analysis later when the consultation contents are less relevant to other consultation contents. Furthermore, the analysis unit can adjust the order of analysis based on the relevance of the consultation contents. This allows the analysis unit to perform appropriate analysis according to the relevance of the consultation contents. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can cause AI to execute processing to adjust the order of analysis based on the relevance of the consultation contents.

[0051] The providing unit can adjust the level of detail of the advice based on the importance of the consultation content when providing the advice. For example, the providing unit adjusts the level of detail of the advice based on the importance of the consultation content when providing the advice. The importance of the consultation content is evaluated based on criteria such as the frequency of appearance of keywords and an emotion score. For example, the providing unit provides detailed advice for consultation content with high importance. In addition, the providing unit can also provide simplified advice for consultation content with low importance. Furthermore, the providing unit can also determine the priority order of advice according to the importance of the consultation content. Thereby, the providing unit can provide appropriate advice according to the importance of the consultation content. 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 cause an AI to execute a process of adjusting the level of detail of the advice based on the importance of the consultation content.

[0052] The providing unit can apply different advice algorithms according to the category of the consultation content when providing advice. For example, the providing unit applies different advice algorithms according to the category of the consultation content when providing advice. The categories of the consultation content include, for example, bullying, family problems, and academic worries. For example, when the consultation content is related to family problems, the providing unit applies an advice algorithm specialized for family problems. In addition, when the consultation content is related to school problems, the providing unit can also apply an advice algorithm specialized for school problems. Furthermore, when the consultation content is related to friendships, the providing unit can also apply an advice algorithm specialized for friendships. This allows the providing unit to provide appropriate advice according to the category of the consultation content. 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 cause AI to execute a process of applying different advice algorithms according to the category of the consultation content.

[0053] The providing unit can determine the priority of advice based on the submission time of the consultation content when providing the advice. The providing unit, for example, determines the priority of advice based on the submission time of the consultation content when providing the advice. The submission time includes, for example, a timestamp, a record of the submission date, and the like. For example, the providing unit provides advice preferentially when the consultation content has been submitted recently. In addition, the providing unit can provide advice later when the consultation content has been submitted in the past. Furthermore, the providing unit can adjust the schedule of advice based on the submission time of the consultation content. This allows the providing unit to provide appropriate advice according to the submission time of the consultation content. 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 cause AI to execute processing for determining the priority of advice based on the submission time of the consultation content.

[0054] The providing unit can adjust the order of advice based on the relevance of the consultation contents when providing advice. For example, the providing unit adjusts the order of advice based on the relevance of the consultation contents when providing advice. The relevance of the consultation contents is evaluated based on criteria such as common keywords and related topics. For example, the providing unit provides advice preferentially when the consultation contents are highly relevant to other consultation contents. In addition, the providing unit can provide advice later when the consultation contents are less relevant to other consultation contents. Furthermore, the providing unit can adjust the order of advice based on the relevance of the consultation contents. Thereby, the providing unit can provide appropriate advice according to the relevance of the consultation contents. 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 cause AI to execute processing to adjust the order of advice based on the relevance of the consultation contents.

[0055] The database unit can optimize the database algorithm by referring to past data when creating a database. The database unit optimizes the database algorithm by referring to past data when creating a database, for example. The past data includes, for example, past consultation contents and past response results. The database unit, for example, analyzes past data and designs an optimal database structure. The database unit can also optimize the search algorithm of the database based on the past data. Furthermore, the database unit can also eliminate data duplication by referring to past data and perform efficient database creation. This allows the database unit to perform optimal database creation based on past data. Part or all of the above-mentioned processing in the database unit may be performed using, for example, AI, or may be performed without using AI. For example, the database unit can cause AI to execute a process of optimizing the database algorithm by referring to past data.

[0056] The database unit can weight data based on the time of submission of the consultation content when the data is compiled into a database. The database unit, for example, weights data based on the time of submission of the consultation content when the data is compiled into a database. The submission time includes, for example, a timestamp and a record of the submission date. For example, the database unit weights the consultation content submitted recently highly. The database unit can also weight the consultation content submitted in the past less highly. Furthermore, the database unit can adjust the weighting of data based on the time of submission of the consultation content. This allows the database unit to weight data appropriately according to the time of submission of the consultation content. A part or all of the above-mentioned processing in the database unit may be performed using, for example, AI, or may be performed without using AI. For example, the database unit can cause AI to execute a process of weighting data based on the time of submission of the consultation content.

[0057] The judgment unit can improve the accuracy of the judgment by considering the interrelationship of the consultation contents at the time of judgment. The judgment unit, for example, improves the accuracy of the judgment by considering the interrelationship of the consultation contents at the time of judgment. The interrelationship of the consultation contents is evaluated based on criteria such as common keywords and related topics. For example, when the consultation contents are highly related to other consultation contents, the judgment unit makes a judgment by considering the interrelationship. In addition, when the consultation contents are less related to other consultation contents, the judgment unit can make an individual judgment. Furthermore, the judgment unit can improve the accuracy of the judgment based on the interrelationship of the consultation contents. Thereby, the judgment unit can make an appropriate judgment based on the interrelationship of the consultation contents. Part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can cause AI to execute a process of improving the accuracy of the judgment by considering the interrelationship of the consultation contents.

[0058] The judgment unit can make a judgment while considering the attribute information of the person who submitted the consultation content. The judgment unit, for example, makes a judgment while considering the attribute information of the person who submitted the consultation content. The attribute information of the person who submitted the consultation content includes, for example, age, sex, and place of residence. For example, when the person who submitted the consultation content is a child, the judgment unit makes a judgment while considering specific attribute information (age, sex, etc.). In addition, when the person who submitted the consultation content is a guardian, the judgment unit can also make a judgment while considering the attribute information of the guardian. Furthermore, the judgment unit can improve the accuracy of the judgment based on the attribute information of the person who submitted the consultation content. This allows the judgment unit to make an appropriate judgment based on the attribute information of the person who submitted the consultation content. A part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can cause AI to execute a process of making a judgment while considering the attribute information of the person who submitted the consultation content.

[0059] The judgment unit can make a judgment while taking into consideration the geographical distribution of the consultation contents at the time of judgment. The judgment unit makes a judgment while taking into consideration the geographical distribution of the consultation contents at the time of judgment, for example. The geographical distribution includes, for example, GPS data, IP addresses, and the like. For example, when the consultation contents are concentrated in a specific region, the judgment unit makes a judgment while taking into consideration the characteristics of the region. In addition, when the consultation contents are distributed over a wide area, the judgment unit can also make a judgment while taking into consideration the characteristics of each region. Furthermore, the judgment unit can improve the accuracy of the judgment based on the geographical distribution of the consultation contents. This allows the judgment unit to make an appropriate judgment based on the geographical distribution of the consultation contents. A part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can cause AI to execute a process of making a judgment while taking into consideration the geographical distribution of the consultation contents.

[0060] The judgment unit can improve the accuracy of the judgment by referring to related literature of the consultation content at the time of judgment. The judgment unit can improve the accuracy of the judgment by referring to related literature of the consultation content at the time of judgment, for example. The related literature includes, for example, academic papers, past case studies, and the like. For example, the judgment unit can improve the accuracy of the judgment by referring to literature related to the consultation content. The judgment unit can also make a judgment based on research results related to the consultation content. Furthermore, the judgment unit can strengthen the basis of the judgment by referring to related literature of the consultation content. This allows the judgment unit to make an appropriate judgment based on the related literature. A part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can cause AI to execute a process of improving the accuracy of the judgment by referring to related literature of the consultation content.

[0061] The alert unit can optimize the current alert by referring to past alert data at the time of an alert. The alert unit optimizes the current alert by referring to past alert data, for example, at the time of an alert. The past alert data includes, for example, past alert contents and response results. For example, the alert unit analyzes past alert data and designs an optimal alert display method. The alert unit can also optimize the priority of the alert based on the past alert data. Furthermore, the alert unit can eliminate duplication of alerts by referring to past alert data and perform efficient alert display. This allows the alert unit to perform optimal alerts based on past alert data. Part or all of the above-mentioned processing in the alert unit may be performed, for example, using AI, or may be performed without using AI. For example, the alert unit can cause AI to execute processing to optimize the current alert by referring to past alert data.

[0062] The alert unit can determine the priority of the alert based on the submission time of the consultation content at the time of the alert. The alert unit determines the priority of the alert based on the submission time of the consultation content at the time of the alert. The submission time includes, for example, a timestamp, a record of the submission date, and the like. For example, the alert unit preferentially displays an alert when the consultation content has been submitted recently. In addition, the alert unit can also display an alert later when the consultation content has been submitted in the past. Furthermore, the alert unit can adjust the schedule of the alert based on the submission time of the consultation content. This allows the alert unit to perform an appropriate alert according to the submission time of the consultation content. A part or all of the above-mentioned processing in the alert unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the alert unit can cause an AI to execute a process of determining the priority of the alert based on the submission time of the consultation content.

[0063] The alert unit can analyze the alert by referring to market data related to the consultation content at the time of the alert. The alert unit can analyze the alert by referring to market data related to the consultation content at the time of the alert, for example. The related market data includes, for example, market research data, consumer behavior data, and the like. For example, the alert unit can improve the accuracy of the alert by referring to market data related to the consultation content. The alert unit can also display the alert based on market trends related to the consultation content. Furthermore, the alert unit can strengthen the basis of the alert by referring to market data related to the consultation content. This allows the alert unit to issue an appropriate alert based on the related market data. A part or all of the above-mentioned processing in the alert unit may be performed, for example, using AI, or may be performed without using AI. For example, the alert unit can cause AI to execute a process of analyzing the alert by referring to market data related to the consultation content.

[0064] The coordination unit can optimize the coordination algorithm by referring to past coordination data at the time of coordination. For example, the coordination unit optimizes the coordination algorithm by referring to past coordination data at the time of coordination. The past coordination data includes, for example, past coordination contents, response results, and the like. For example, the coordination unit analyzes the past coordination data and designs an optimal coordination method. The coordination unit can also optimize the priority order of coordination based on the past coordination data. Furthermore, the coordination unit can eliminate duplication of coordination by referring to the past coordination data and perform efficient coordination. This allows the coordination unit to perform optimal coordination based on the past coordination data. A part or all of the above-mentioned processing in the coordination unit may be performed using, for example, AI, or may be performed without using AI. For example, the coordination unit can cause AI to execute a process of optimizing the coordination algorithm by referring to the past coordination data.

[0065] The linking unit can weight the linked data based on the time of submission of the consultation content at the time of linking. For example, the linking unit weights the linked data based on the time of submission of the consultation content at the time of linking. The submission time includes, for example, a timestamp and a record of the submission date. For example, the linking unit weights the consultation content submitted recently highly. The linking unit can also weight the consultation content submitted in the past less highly. Furthermore, the linking unit can adjust the weighting of the linked data based on the time of submission of the consultation content. This allows the linking unit to perform appropriate weighting according to the time of submission of the consultation content. A part or all of the above-mentioned processing in the linking unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the linking unit can cause an AI to execute a process of weighting the linked data based on the time of submission of the consultation content.

[0066] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0067] When the child inputs the content of the consultation, the reception unit can provide a template according to the category of the content of the consultation. For example, in the case of a consultation about bullying, a template for inputting the specific circumstances and frequency of the bullying can be provided. In addition, in the case of a consultation about family problems, a template for inputting specific problems within the family and information on the people involved can also be provided. Furthermore, in the case of a consultation about academic worries, a template for inputting specific academic problems and the status of grades can also be provided. In this way, the reception unit allows the child to input the content of the consultation more specifically.

[0068] When analyzing the contents of a child's consultation, the analysis unit can apply an analysis algorithm according to the category of the consultation. For example, in the case of a consultation about bullying, an algorithm for analyzing the pattern and frequency of bullying can be applied. In addition, in the case of a consultation about family problems, an algorithm for analyzing the relationships within the family and the seriousness of the problem can be applied. Furthermore, in the case of a consultation about academic worries, an algorithm for analyzing academic performance and the learning environment can be applied. This allows the analysis unit to perform an appropriate analysis according to the contents of the consultation.

[0069] When a child inputs the details of a consultation, the providing unit can provide advice according to the category of the consultation. For example, in the case of a consultation about bullying, the providing unit can provide ways to deal with bullying and advice providers. In addition, in the case of a consultation about family problems, the providing unit can provide advice for resolving problems within the family and information on support organizations. Furthermore, in the case of a consultation about worries about schoolwork, the providing unit can provide information on ways to improve schoolwork and learning support. This allows the providing unit to provide the child with specific advice according to the details of the consultation.

[0070] When creating a database of the child's consultation content, the database unit can design a database structure according to the category of the consultation content. For example, in the case of a consultation about bullying, a database structure for recording the pattern and frequency of bullying can be designed. In addition, in the case of a consultation about family problems, a database structure for recording the relationships within the family and the seriousness of the problem can be designed. Furthermore, in the case of a consultation about academic worries, a database structure for recording academic results and the learning environment can be designed. In this way, the database unit can create an appropriate database according to the consultation content.

[0071] When judging the contents of the child's consultation, the judgment unit can apply judgment criteria according to the category of the consultation contents. For example, in the case of a consultation about bullying, the seriousness can be judged based on the pattern and frequency of bullying. In addition, in the case of a consultation about a family problem, the seriousness can be judged based on the relationships within the family and the seriousness of the problem. Furthermore, in the case of a consultation about academic worries, the seriousness can be judged based on academic performance and the learning environment. This allows the judgment unit to make an appropriate judgment according to the contents of the consultation.

[0072] The process flow of the first embodiment will be briefly described below.

[0073] Step 1: The reception desk consults with children about their concerns. Children's concerns may include bullying, family problems, and academic worries. The reception desk is equipped with interfaces such as voice input and a touch panel. The voice input uses voice recognition technology to convert the child's voice into text data, and the touch panel uses technologies such as capacitive and resistive membrane to allow the child to input directly. Step 2: The analysis unit analyzes the information received by the reception unit. The analysis is performed by methods such as text analysis, sentiment analysis, and pattern recognition. Text analysis analyzes the input text data using natural language processing technology, sentiment analysis estimates emotions from the input text data, and pattern recognition analyzes the patterns of the input data to find specific trends. Step 3: The provision unit provides initial countermeasures based on the information analyzed by the analysis unit. The initial countermeasures include suggesting counseling, providing emergency contact information, etc., and providing specific advice that the child can take immediately. Step 4: The Database Department will compile the information provided by the Service Department into a database. Database compilation will be carried out in accordance with standards for data format, storage method, access rights, etc., and the contents of consultations will be compiled into a database that can be viewed by instructors and staff nationwide. Step 5: The judgment unit judges whether a case is serious based on the information stored in the database by the database unit. A serious case is judged based on criteria such as the frequency of occurrence of specific keywords and emotion scores, and a case containing specific keywords or phrases is judged to be serious. Step 6: The Alerting Department raises an alert for cases that are judged to be serious by the Judgment Department. Alerts are issued according to criteria such as the notification method, notification recipient, and level of urgency, and raises an alert for serious cases and notifies the specialized team. Step 7: The Coordination Unit will respond with a specialized unit based on the information notified by the Alert Unit. The specialized unit will be composed of psychological counselors, police, school personnel, etc., and will respond in coordination with the school and police.

[0074] (Example 2) The system for early detection and early response to child abuse according to the embodiment of the present invention provides a mechanism for children to consult about their worries easily. In this system, children consult about their worries to an AI terminal, and the AI ​​listens to the worries and advises the first response measures. For example, if a child inputs content such as "I sometimes get hit at home" or "I am being bullied at school," the AI ​​analyzes the information and provides specific advice such as "Talk to your parents" or "Talk to your teacher." This advice can be implemented by the child immediately. Furthermore, the AI ​​stores the consultation content in a database and makes it available to instructors and staff nationwide. This allows instructors and staff to understand the children's worries and take appropriate measures. The AI ​​also analyzes the consultation content and judges serious cases. For example, if serious content such as "I am being abused at home" is input, the AI ​​judges the case to be "serious" and raises an alert. This alert is notified to a specialized unit, which responds in cooperation with the school and the police. This mechanism enables early detection and early response to child abuse, and protects the safety of children. This will enable the child abuse early detection and response system to efficiently receive, analyze, provide countermeasures, create a database of children's concerns, identify serious cases, issue alerts, and connect with others.

[0075] The system for early detection and early response to child abuse according to the embodiment includes a reception unit, an analysis unit, a provision unit, a database unit, a judgment unit, an alert unit, and a linking unit. The reception unit consults on the child's worries. The child's worries include, for example, bullying, family problems, and academic worries, but are not limited to such examples. The reception unit includes an interface such as a voice input and a touch panel. The voice input converts the child's voice into text data using, for example, voice recognition technology. The touch panel allows the child to directly input using, for example, a capacitance method or a resistive film method. The analysis unit analyzes the information received by the reception unit. The analysis is performed by, for example, a method such as text analysis, emotion analysis, and pattern recognition. The text analysis analyzes the input text data using, for example, natural language processing technology. The emotion analysis estimates emotions from the input text data. The pattern recognition analyzes, for example, the pattern of the input data to find a specific trend. The provision unit provides an initial response based on the information analyzed by the analysis unit. The initial countermeasures include, for example, a suggestion for counseling, provision of an emergency contact, etc., but are not limited to such examples. The providing unit provides, for example, specific advice that the child can immediately implement. The database unit databases the information provided by the providing unit. Database creation is performed according to criteria such as data format, storage method, and access rights. The database unit databases, for example, the contents of the consultation, and makes it possible for instructors and staff throughout the country to view it. The judging unit judges serious cases based on the information databased by the database unit. Serious cases are judged based on criteria such as the frequency of occurrence of specific keywords and emotion scores. The judging unit judges a case to be serious when, for example, a specific keyword or phrase is included. The alert unit issues an alert for a case judged to be serious by the judging unit. The alert is issued according to criteria such as a notification method, a notification destination, and a level of urgency. The alert unit issues an alert for a serious case, for example, and notifies a specialized unit. The coordinating unit allows the specialized unit to respond based on the information notified by the alert unit.The specialized unit is composed of, for example, psychological counselors, police, and school personnel. The liaison unit responds by coordinating with, for example, schools and police. As a result, the child abuse early detection and early response system according to the embodiment is capable of efficiently accepting, analyzing, providing countermeasures, creating a database, determining serious cases, issuing alerts, and coordinating with other parties regarding children's concerns.

[0076] The reception unit consults on the worries of children. The worries of children include, but are not limited to, bullying, family problems, and academic worries. The reception unit has an interface such as a voice input and a touch panel. The voice input converts the voice of the child into text data using, for example, voice recognition technology. The touch panel allows the child to directly input using, for example, a capacitance type or a resistive film type technology. Specifically, the voice input is equipped with a highly accurate voice recognition engine, and converts the child's speech into text in real time. As a result, the contents of the child's speech are instantly recorded as digital data. The touch panel is designed so that children can intuitively operate it, and information can be input with simple taps and swipes. Furthermore, the reception unit employs encryption technology for privacy protection so that children can consult with confidence. As a result, the children's personal information and consultation contents are safely managed without being leaked to the outside. Furthermore, the reception unit employs a friendly interface design so that children can easily consult. For example, a guide function using characters and animations is installed, providing an environment where children can relax and consult. This enables the reception department to efficiently receive various concerns from children and collect information at an early stage.

[0077] The analysis unit analyzes the information received by the reception unit. The analysis is performed by, for example, text analysis, emotion analysis, pattern recognition, and the like. The text analysis is performed by, for example, analyzing the input text data using natural language processing technology. The emotion analysis is performed by, for example, estimating emotions from the input text data. The pattern recognition is performed by, for example, analyzing the patterns of the input data and finding certain trends. Specifically, in the text analysis, the natural language processing technology is used to grammatically and semantically analyze the child's consultation content and extract important keywords and phrases. In the emotion analysis, the emotional tone is analyzed from the text data and the child's psychological state is estimated. For example, the emotion is classified into emotion categories such as positive, negative, and neutral, and the intensity of the emotion is scored. In the pattern recognition, specific patterns and abnormal trends are detected by comparing with past data. This allows the analysis unit to analyze the child's consultation content from multiple angles and to discover potential problems and risks at an early stage. Furthermore, the analysis unit utilizes AI technology to improve the accuracy of the analysis results. For example, a machine learning algorithm is used to learn from past data and continuously improve the analysis model. This enables the analysis unit to provide more accurate and reliable analysis results and quickly grasp the child's worries and problems.

[0078] The providing unit provides an initial response based on the information analyzed by the analyzing unit. The initial response includes, but is not limited to, counseling suggestions and emergency contact information. The providing unit provides, for example, specific advice that the child can immediately implement. Specifically, the providing unit suggests appropriate counseling services to the child based on the analysis results. For example, the providing unit supports the reservation of an online session with a psychological counselor or provides contact information for a local counseling center. In addition, in an emergency, the providing unit provides an emergency contact number that the child can contact immediately so that the necessary support can be received quickly. Furthermore, the providing unit provides specific advice and resources for the child to solve the problem on his or her own. For example, the providing unit provides practical advice for specific problems the child faces, such as methods for stress management, ways to deal with bullying, and solutions to family problems. This allows the providing unit to support the child in taking the first step to solve his or her problems. Furthermore, the providing unit provides information using easy-to-understand words and illustrations so that the child can easily understand and implement the provided information. This allows the providing unit to provide specific means for the child to solve his or her problems and support early problem solving.

[0079] The database unit makes a database of the information provided by the provision unit. The database is made according to standards such as data format, storage method, and access authority. For example, the database unit makes the consultation contents a database and makes it possible for instructors and staff nationwide to view them. Specifically, the database unit centrally manages the consultation contents of children and the countermeasures provided, and enables them to quickly search and refer to the necessary information. The data format supports a variety of formats such as text data, audio data, and image data, and each data is stored with appropriate metadata. The storage method uses cloud storage and distributed databases to ensure the safety and availability of data. In order to protect the confidentiality of the data, different permissions are set for each user, and only the necessary information is provided to the appropriate user. In this way, the database unit efficiently manages the consultation contents of children and countermeasures, and provides an environment in which instructors and staff nationwide can quickly share information. Furthermore, the database unit regularly updates and backs up the data, maintaining the consistency and reliability of the data. In this way, the database unit can store the consultation contents of children and countermeasures for the long term and use them for future analysis and improvement.

[0080] The judgment unit judges a serious case based on the information databased by the database unit. A serious case is judged based on criteria such as the frequency of occurrence of a specific keyword and an emotion score. The judgment unit judges a case to be serious when a specific keyword or phrase is included. Specifically, the judgment unit uses an algorithm that analyzes the information stored in the database and automatically detects serious cases. For example, when specific keywords such as "help me," "I want to die," and "violence" appear frequently or when the result of the emotion analysis is extremely negative, the judgment unit flags the case as serious. In addition, when an abnormal pattern is detected in comparison with past data, the judgment unit judges the case as serious. This allows the judgment unit to discover potential dangers early from the contents of the child's consultation and encourage a prompt response. Furthermore, the judgment unit has an interface for incorporating the opinions of experts, and allows experts such as psychological counselors and doctors to participate in the judgment process as necessary. This allows the judgment unit to make more accurate judgments and support appropriate responses to ensure the safety of children.

[0081] The alert unit issues an alert for cases that are judged to be serious by the judgment unit. The alert is issued according to criteria such as the notification method, notification destination, and level of urgency. For example, the alert unit issues an alert for serious cases and notifies a specialized unit. Specifically, the alert unit is equipped with a system that immediately notifies relevant parties when a serious case is detected. Notification methods are performed using various means such as email, SMS, and push notification. Notifications are sent to all relevant parties, such as the child's guardian, school personnel, psychological counselors, and police. The level of urgency is set according to the seriousness of the case, and in the most urgent cases, immediate response is required. This allows the alert unit to encourage prompt and appropriate response to serious cases and support actions to ensure the safety of children. Furthermore, the alert unit records the history of notifications so that they can be checked later. This makes it easier to track responses and identify areas for improvement, improving the reliability and effectiveness of the entire system.

[0082] In the Liaison Department, specialized units respond based on the information notified by the Alert Department. The specialized units are composed of, for example, psychological counselors, police, and school personnel. In the Liaison Department, the specialized units respond in cooperation with the school and police. Specifically, the Liaison Department supports information sharing and cooperation so that the specialized units that receive the alert can respond quickly. For example, it supports scheduling for psychological counselors to have direct interviews with children, and provides information for the police to rush to the scene quickly. In addition, it provides support for school personnel to grasp the situation of children and take appropriate measures. This allows the Liaison Department to support the specialized units to effectively cooperate and respond quickly to ensure the safety of children. In addition, the Liaison Department monitors the progress of the response and provides additional support as necessary. This allows the Liaison Department to maximize the effectiveness of the entire child abuse early detection and early response system and provide comprehensive support to protect the safety and welfare of children.

[0083] The reception unit may have at least one interface of voice input or touch panel. The voice input may convert the child's voice into text data using, for example, voice recognition technology. For example, the voice recognition technology may analyze the child's speech in real time and store it as text data. The voice input may vary depending on the type of microphone, but for example, by using a directional microphone, ambient noise may be eliminated and the child's voice may be clearly recognized. The touch panel may use, for example, a capacitance type or a resistive film type technology to allow the child to directly input. For example, a capacitive touch panel recognizes input by sensing static electricity on the child's finger. A resistive film type touch panel recognizes input by sensing pressure on the child's finger. This allows the reception unit to allow the child to consult about worries in various ways. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may cause AI to execute a process of converting the child's voice into text data using voice recognition technology.

[0084] The provision unit can provide specific advice that the child can immediately implement. The provision unit provides, for example, specific advice that the child can immediately implement. For example, the provision unit provides the child with specific guidelines for action, such as "consult with a parent" or "talk to a teacher." The provision unit can also provide the child with measures, such as "call an emergency contact" or "receive counseling." Furthermore, the provision unit can provide the child with resources, such as "contact a local support organization" or "use online resources." This allows the provision unit to enable the child to immediately implement countermeasures. Some or all of the above-mentioned processing in the provision unit may be performed, for example, using AI, or may be performed without using AI. For example, the provision unit can analyze the content of the child's consultation and cause AI to execute a process of generating appropriate advice.

[0085] The database unit can database the consultation contents and make them viewable by at least one of the instructors or staff nationwide. The database unit, for example, databases the consultation contents and makes them viewable by the instructors and staff nationwide. Database creation is performed according to standards such as data format, storage method, and access rights. For example, the database unit stores the consultation contents as text data and registers them in the database in a specific format. The database unit also sets access rights for the stored data so that instructors and staff nationwide can properly view it. Furthermore, the database unit provides a data search function so that instructors and staff can quickly obtain the necessary information. In this way, the database unit enables instructors and staff nationwide to understand the concerns of children and take appropriate measures. Some or all of the above-mentioned processing in the database unit may be performed using, for example, AI, or may be performed without using AI. For example, the database unit can cause AI to execute a process of registering the consultation contents in the database.

[0086] The judgment unit can determine that the case is serious when at least one of the specific keywords or phrases is included. The judgment unit, for example, determines that the case is serious when the specific keywords or phrases are included. The specific keywords or phrases include, but are not limited to, for example, "bullying," "suicide," and "help." The judgment unit, for example, analyzes the input consultation content and checks whether the specific keywords or phrases are included. The judgment unit can also determine that the case is serious based on criteria such as the frequency of appearance of the specific keywords or phrases and the emotion score. For example, the judgment unit determines that the case is serious when the input consultation content includes the keyword "bullying." The judgment unit can also determine that the case is serious when the input consultation content includes the phrase "suicide." This allows the judgment unit to quickly determine that the case is serious. Part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can analyze the input consultation content and cause AI to execute a process of checking whether the specific keywords or phrases are included.

[0087] The alert unit can raise an alert for a serious case and notify a specialized unit. The alert unit, for example, raises an alert for a serious case and notifies a specialized unit. The alert is made according to criteria such as a notification method, a notification destination, and a level of urgency. For example, when a serious case occurs, the alert unit notifies the specialized unit by a method such as email or SMS. In addition, the alert unit can specify a psychological counselor, police, or a school official as a notification destination. Furthermore, the alert unit can set a priority order for notifications according to the level of urgency and encourage a prompt response. For example, the alert unit immediately notifies a case with a high urgency and periodically notifies a case with a low urgency. This allows the alert unit to respond promptly to serious cases. A part or all of the above-mentioned processing in the alert unit may be performed, for example, using AI, or may be performed without using AI. For example, the alert unit can cause AI to execute a process of notifying when a serious case occurs.

[0088] The coordination unit can respond by having the specialized unit cooperate with the school and the police. The coordination unit, for example, cooperates with the specialized unit to respond with the school and the police. The specialized unit is composed of, for example, psychological counselors, police, and school personnel. The coordination unit, for example, provides procedures for the specialized unit to cooperate with the school and the police to respond quickly. For example, the coordination unit communicates with the school personnel and discusses specific measures to ensure the safety of children. The coordination unit can also cooperate with the police to take legal action in cases where child abuse is suspected. Furthermore, the coordination unit can cooperate with local support organizations to provide support to children and their families. This allows the specialized unit to respond quickly and protect the safety of children. Some or all of the above-mentioned processing in the coordination unit may be performed using, for example, AI, or may be performed without using AI. For example, the coordination unit can cause AI to execute procedures for the specialized unit to cooperate with the school and the police to respond.

[0089] The reception unit can estimate the child's emotions and adjust the input method of the consultation content based on the estimated child's emotions. The reception unit, for example, estimates the child's emotions and adjusts the input method of the consultation content based on the estimated child's emotions. Methods for estimating the child's emotions include, for example, facial expression analysis, voice analysis, and text analysis. For example, the facial expression analysis uses a camera to analyze the child's facial expression and estimate the emotion. The voice analysis analyzes the tone and speed of the child's voice and estimates the emotion. The text analysis analyzes the text data entered by the child and estimates the emotion. For example, when the child is nervous, the reception unit provides a simple and intuitive interface and minimizes the input procedure. In addition, when the child is relaxed, the reception unit can provide detailed input options and suggest a customizable input method. Furthermore, when the child is in a hurry, the reception unit can prioritize voice input and enable the child to quickly input the consultation content. This allows the reception unit to provide an appropriate input method according to the child's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be 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 reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit may cause the AI ​​to execute a process of estimating the child's emotion and adjusting the input method based on the estimated emotion.

[0090] The reception unit can analyze the past consultation history of the child and select the optimal input interface. The reception unit, for example, analyzes the past consultation history of the child and selects the optimal input interface. The past consultation history includes, for example, the input method (voice, text, etc.) used by the child in the past and the consultation content. The reception unit, for example, preferentially suggests the input method that the child frequently used in the past. The reception unit can also automatically display related input options based on the past consultation content of the child. Furthermore, the reception unit can predict and suggest the input method to be used in a specific time period from the past consultation history of the child. This allows the reception unit to provide the optimal input method for the child. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can analyze the past consultation history of the child and cause AI to execute the processing of selecting the optimal input interface.

[0091] The reception unit can perform filtering based on the child's current living situation and field of interest when receiving the consultation content. The reception unit, for example, performs filtering based on the child's current living situation and field of interest when receiving the consultation content. The living situation includes, for example, the home environment, the school environment, etc. The field of interest includes, for example, hobbies, interests, etc. The reception unit preferentially receives related consultation content based on, for example, the child's current living situation. The reception unit can also filter related consultation content based on the child's field of interest. Furthermore, the reception unit can also suggest appropriate consultation content based on the child's living situation and field of interest. This allows the reception unit to receive appropriate consultation content according to the child's living situation and field of interest. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can cause AI to execute a process of filtering based on the child's living situation and field of interest.

[0092] The reception unit can estimate the child's emotions and determine the priority of consultation contents to be received based on the estimated child's emotions. The reception unit, for example, estimates the child's emotions and determines the priority of consultation contents to be received based on the estimated child's emotions. Methods for estimating the child's emotions include, for example, facial expression analysis, voice analysis, and text analysis. For example, the facial expression analysis uses a camera to analyze the child's facial expression and estimate the emotion. The voice analysis analyzes the tone and speed of the child's voice and estimates the emotion. The text analysis analyzes the text data entered by the child and estimates the emotion. For example, the reception unit preferentially receives consultation contents with a high urgency when the child is nervous. In addition, the reception unit can also preferentially receive detailed consultation contents when the child is relaxed. Furthermore, the reception unit can also preferentially receive consultation contents that require a quick response when the child is in a hurry. This allows the reception unit to receive consultation contents with appropriate priorities according to the child's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be 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 reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit may cause AI to execute a process of estimating the child's emotions and determining the priority order of consultation contents based on the estimated emotions.

[0093] The reception unit can preferentially receive highly relevant content in consideration of the child's geographical location information when receiving the consultation content. The reception unit, for example, preferentially receives highly relevant content in consideration of the child's geographical location information when receiving the consultation content. The geographical location information includes, for example, GPS data, IP address, and the like. The reception unit preferentially receives consultation content related to the region, for example, based on the child's current geographical location information. The reception unit can also preferentially receive consultation content related to specific problems in the region, in consideration of the child's geographical location information. Furthermore, the reception unit can also preferentially receive consultation content related to local support organizations, in consideration of the child's geographical location information. This allows the reception unit to receive appropriate consultation content based on the child's geographical location information. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can cause AI to execute a process of preferentially receiving highly relevant content in consideration of the child's geographical location information.

[0094] The reception unit can analyze the child's social media activity and receive related content when receiving the consultation content. The reception unit, for example, analyzes the child's social media activity and receives related content when receiving the consultation content. Social media activity includes, for example, analysis of posted content and followers. The reception unit, for example, analyzes the child's social media activity and receives related consultation content preferentially. The reception unit can also filter related consultation content based on the child's social media comments and posted content. Furthermore, the reception unit can also suggest consultation content related to a specific problem from the child's social media activity. This allows the reception unit to receive appropriate consultation content based on the child's social media activity. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can analyze the child's social media activity and cause AI to execute a process of receiving related content.

[0095] The analysis unit can estimate the child's emotions and adjust the expression method of the analysis based on the estimated child's emotions. The analysis unit, for example, estimates the child's emotions and adjusts the expression method of the analysis based on the estimated child's emotions. Methods for estimating the child's emotions include, for example, facial expression analysis, voice analysis, text analysis, and the like. For example, facial expression analysis uses a camera to analyze the child's facial expressions and estimate the emotions. Voice analysis analyzes the tone and speed of the child's voice and estimates the emotions. Text analysis analyzes text data entered by the child and estimates the emotions. For example, the analysis unit provides a simple and highly visible analysis result when the child is nervous. In addition, the analysis unit can also provide a detailed analysis result when the child is relaxed. Furthermore, the analysis unit can also provide an analysis result that covers the main points when the child is in a hurry. This allows the analysis unit to provide an appropriate analysis result according to the child'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 may be 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 analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit may cause the AI ​​to execute a process of estimating the child's emotions and adjusting the expression method of the analysis based on the estimated emotions.

[0096] The analysis unit can adjust the level of detail of the analysis based on the importance of the consultation content during the analysis. The analysis unit, for example, adjusts the level of detail of the analysis based on the importance of the consultation content during the analysis. The importance of the consultation content is evaluated based on criteria such as the frequency of appearance of keywords and emotion scores. For example, the analysis unit performs a detailed analysis on consultation content with high importance. The analysis unit can also perform a simplified analysis on consultation content with low importance. Furthermore, the analysis unit can determine the priority of the analysis according to the importance of the consultation content. This allows the analysis unit to perform an appropriate analysis according to the importance of the consultation content. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can cause AI to execute a process of adjusting the level of detail of the analysis based on the importance of the consultation content.

[0097] The analysis unit can apply different analysis algorithms depending on the category of the consultation content during analysis. For example, the analysis unit applies different analysis algorithms depending on the category of the consultation content during analysis. The categories of the consultation content include, for example, bullying, family problems, and academic worries. For example, when the consultation content is related to family problems, the analysis unit applies an analysis algorithm specialized for family problems. In addition, when the consultation content is related to school problems, the analysis unit can also apply an analysis algorithm specialized for school problems. Furthermore, when the consultation content is related to friendships, the analysis unit can also apply an analysis algorithm specialized for friendships. This allows the analysis unit to perform an appropriate analysis depending on the category of the consultation content. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can cause AI to execute a process of applying different analysis algorithms depending on the category of the consultation content.

[0098] The analysis unit can estimate the child's emotion and adjust the length of the analysis based on the estimated child's emotion. The analysis unit, for example, estimates the child's emotion and adjusts the length of the analysis based on the estimated child's emotion. Methods for estimating the child's emotion include, for example, facial expression analysis, voice analysis, text analysis, and the like. For example, facial expression analysis uses a camera to analyze the child's facial expression and estimate the emotion. Voice analysis analyzes the tone and speed of the child's voice and estimates the emotion. Text analysis analyzes text data entered by the child and estimates the emotion. For example, the analysis unit provides a short and to the point analysis result when the child is in a hurry. The analysis unit can also provide a detailed analysis result when the child is relaxed. Furthermore, the analysis unit can provide an analysis result with a visually stimulating effect added when the child is excited. This allows the analysis unit to provide an appropriate analysis result according to the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be 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 analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit may cause the AI ​​to execute a process of estimating the child's emotion and adjusting the length of the analysis based on the estimated emotion.

[0099] The analysis unit can determine the priority of the analysis based on the submission time of the consultation content at the time of analysis. The analysis unit, for example, determines the priority of the analysis based on the submission time of the consultation content at the time of analysis. The submission time includes, for example, a timestamp, a record of the submission date, and the like. For example, the analysis unit performs the analysis preferentially when the consultation content has been submitted recently. In addition, the analysis unit can perform the analysis later when the consultation content has been submitted in the past. Furthermore, the analysis unit can adjust the schedule of the analysis based on the submission time of the consultation content. This allows the analysis unit to perform an appropriate analysis according to the submission time of the consultation content. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can cause AI to execute a process of determining the priority of the analysis based on the submission time of the consultation content.

[0100] The analysis unit can adjust the order of analysis based on the relevance of the consultation contents during analysis. The analysis unit, for example, adjusts the order of analysis based on the relevance of the consultation contents during analysis. The relevance of the consultation contents is evaluated based on criteria such as common keywords and related topics. For example, the analysis unit performs analysis preferentially when the consultation contents are highly relevant to other consultation contents. In addition, the analysis unit can also perform analysis later when the consultation contents are less relevant to other consultation contents. Furthermore, the analysis unit can adjust the order of analysis based on the relevance of the consultation contents. This allows the analysis unit to perform appropriate analysis according to the relevance of the consultation contents. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can cause AI to execute processing to adjust the order of analysis based on the relevance of the consultation contents.

[0101] The providing unit can estimate the child's emotion and adjust the way of expressing advice based on the estimated child's emotion. The providing unit, for example, estimates the child's emotion and adjusts the way of expressing advice based on the estimated child's emotion. Methods for estimating the child's emotion include, for example, facial expression analysis, voice analysis, text analysis, and the like. For example, the facial expression analysis uses a camera to analyze the child's facial expression and estimate the emotion. The voice analysis analyzes the tone and speed of the child's voice and estimates the emotion. The text analysis analyzes the text data entered by the child and estimates the emotion. For example, the providing unit provides simple and highly visible advice when the child is nervous. In addition, the providing unit can also provide detailed advice when the child is relaxed. Furthermore, the providing unit can also provide advice that covers the main points when the child is in a hurry. This allows the providing unit to provide appropriate advice according to the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the providing unit may cause an AI to execute a process of estimating the child's emotions and adjusting the way the advice is expressed based on the estimated emotions.

[0102] The providing unit can adjust the level of detail of the advice based on the importance of the consultation content when providing the advice. For example, the providing unit adjusts the level of detail of the advice based on the importance of the consultation content when providing the advice. The importance of the consultation content is evaluated based on criteria such as the frequency of appearance of keywords and an emotion score. For example, the providing unit provides detailed advice for consultation content with high importance. In addition, the providing unit can also provide simplified advice for consultation content with low importance. Furthermore, the providing unit can also determine the priority order of advice according to the importance of the consultation content. Thereby, the providing unit can provide appropriate advice according to the importance of the consultation content. 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 cause an AI to execute a process of adjusting the level of detail of the advice based on the importance of the consultation content.

[0103] The providing unit can apply different advice algorithms according to the category of the consultation content when providing advice. For example, the providing unit applies different advice algorithms according to the category of the consultation content when providing advice. The categories of the consultation content include, for example, bullying, family problems, and academic worries. For example, when the consultation content is related to family problems, the providing unit applies an advice algorithm specialized for family problems. In addition, when the consultation content is related to school problems, the providing unit can also apply an advice algorithm specialized for school problems. Furthermore, when the consultation content is related to friendships, the providing unit can also apply an advice algorithm specialized for friendships. This allows the providing unit to provide appropriate advice according to the category of the consultation content. 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 cause AI to execute a process of applying different advice algorithms according to the category of the consultation content.

[0104] The providing unit can estimate the child's emotion and adjust the length of the advice based on the estimated emotion of the child. The providing unit, for example, estimates the child's emotion and adjusts the length of the advice based on the estimated emotion of the child. Methods for estimating the emotion of the child include, for example, facial expression analysis, voice analysis, text analysis, and the like. For example, the facial expression analysis uses a camera to analyze the child's facial expression and estimate the emotion. The voice analysis analyzes the tone and speed of the child's voice and estimates the emotion. The text analysis analyzes the text data entered by the child and estimates the emotion. For example, the providing unit provides short, to-the-point advice when the child is in a hurry. In addition, the providing unit can provide longer advice including detailed explanations when the child is relaxed. Furthermore, the providing unit can provide advice with a visually stimulating effect when the child is excited. This allows the providing unit to provide appropriate advice according to the emotion of the child. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be 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 providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit may cause the AI ​​to execute a process of estimating the child's emotion and adjusting the length of advice based on the estimated emotion.

[0105] The providing unit can determine the priority of advice based on the submission time of the consultation content when providing the advice. The providing unit, for example, determines the priority of advice based on the submission time of the consultation content when providing the advice. The submission time includes, for example, a timestamp, a record of the submission date, and the like. For example, the providing unit provides advice preferentially when the consultation content has been submitted recently. In addition, the providing unit can provide advice later when the consultation content has been submitted in the past. Furthermore, the providing unit can adjust the schedule of advice based on the submission time of the consultation content. This allows the providing unit to provide appropriate advice according to the submission time of the consultation content. 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 cause AI to execute processing for determining the priority of advice based on the submission time of the consultation content.

[0106] The providing unit can adjust the order of advice based on the relevance of the consultation contents when providing advice. For example, the providing unit adjusts the order of advice based on the relevance of the consultation contents when providing advice. The relevance of the consultation contents is evaluated based on criteria such as common keywords and related topics. For example, the providing unit provides advice preferentially when the consultation contents are highly relevant to other consultation contents. In addition, the providing unit can provide advice later when the consultation contents are less relevant to other consultation contents. Furthermore, the providing unit can adjust the order of advice based on the relevance of the consultation contents. Thereby, the providing unit can provide appropriate advice according to the relevance of the consultation contents. 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 cause AI to execute processing to adjust the order of advice based on the relevance of the consultation contents.

[0107] The database unit can estimate the child's emotion and select information to be stored in the database based on the estimated child's emotion. The database unit, for example, estimates the child's emotion and selects information to be stored in the database based on the estimated child's emotion. Methods for estimating the child's emotion include, for example, facial expression analysis, voice analysis, and text analysis. For example, facial expression analysis uses a camera to analyze the child's facial expression and estimate the emotion. Voice analysis analyzes the tone and speed of the child's voice and estimates the emotion. Text analysis analyzes text data entered by the child and estimates the emotion. For example, when the child is nervous, the database unit prioritizes database of information of high importance. In addition, when the child is relaxed, the database unit can also database detailed information. Furthermore, when the child is in a hurry, the database unit can also database information that covers the main points. This allows the database unit to database appropriate information according to the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be 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 database unit may be performed, for example, using AI, or may be performed without using AI. For example, the database unit may cause AI to execute a process of estimating a child's emotion and selecting information to be stored in the database based on the estimated emotion.

[0108] The database unit can optimize the database algorithm by referring to past data when creating a database. The database unit optimizes the database algorithm by referring to past data when creating a database, for example. The past data includes, for example, past consultation contents and past response results. The database unit, for example, analyzes past data and designs an optimal database structure. The database unit can also optimize the search algorithm of the database based on the past data. Furthermore, the database unit can also eliminate data duplication by referring to past data and perform efficient database creation. This allows the database unit to perform optimal database creation based on past data. Part or all of the above-mentioned processing in the database unit may be performed using, for example, AI, or may be performed without using AI. For example, the database unit can cause AI to execute a process of optimizing the database algorithm by referring to past data.

[0109] The database unit can estimate the child's emotion and adjust the frequency of database creation based on the estimated child's emotion. The database unit, for example, estimates the child's emotion and adjusts the frequency of database creation based on the estimated child's emotion. Methods for estimating the child's emotion include, for example, facial expression analysis, voice analysis, text analysis, and the like. For example, the facial expression analysis uses a camera to analyze the child's facial expression and estimate the emotion. The voice analysis analyzes the tone and speed of the child's voice and estimates the emotion. The text analysis analyzes the text data entered by the child and estimates the emotion. For example, when the child is nervous, the database unit frequently creates the database and keeps the latest information. In addition, when the child is relaxed, the database unit can also periodically create the database. Furthermore, when the child is in a hurry, the database unit can also prioritize creating only important information in the database. This allows the database unit to create the database at an appropriate frequency according to the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the database unit may be performed, for example, using AI, or may be performed without using AI. For example, the database unit may cause AI to execute a process of estimating the child's emotions and adjusting the frequency of database creation based on the estimated emotions.

[0110] The database unit can weight data based on the time of submission of the consultation content when the data is compiled into a database. The database unit, for example, weights data based on the time of submission of the consultation content when the data is compiled into a database. The submission time includes, for example, a timestamp and a record of the submission date. For example, the database unit weights the consultation content submitted recently highly. The database unit can also weight the consultation content submitted in the past less highly. Furthermore, the database unit can adjust the weighting of data based on the time of submission of the consultation content. This allows the database unit to weight data appropriately according to the time of submission of the consultation content. A part or all of the above-mentioned processing in the database unit may be performed using, for example, AI, or may be performed without using AI. For example, the database unit can cause AI to execute a process of weighting data based on the time of submission of the consultation content.

[0111] The judgment unit can estimate the child's emotions and adjust the judgment criteria for serious cases based on the estimated child's emotions. The judgment unit, for example, estimates the child's emotions and adjusts the judgment criteria for serious cases based on the estimated child's emotions. Methods for estimating the child's emotions include, for example, facial expression analysis, voice analysis, and text analysis. For example, the facial expression analysis uses a camera to analyze the child's facial expression and estimate the emotion. The voice analysis analyzes the tone and speed of the child's voice and estimates the emotion. The text analysis analyzes the text data entered by the child and estimates the emotion. For example, when the child is nervous, the judgment unit applies strict judgment criteria and prioritizes judgment of serious cases. In addition, when the child is relaxed, the judgment unit can also apply flexible judgment criteria and make judgments based on detailed information. Furthermore, when the child is in a hurry, the judgment unit can also apply criteria for making a quick judgment. This allows the judgment unit to apply appropriate judgment criteria according to the child'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 may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit may infer the child's emotions and cause the AI ​​to execute a process of adjusting the judgment criteria for serious cases based on the inferred emotions.

[0112] The judgment unit can improve the accuracy of the judgment by considering the interrelationship of the consultation contents at the time of judgment. The judgment unit, for example, improves the accuracy of the judgment by considering the interrelationship of the consultation contents at the time of judgment. The interrelationship of the consultation contents is evaluated based on criteria such as common keywords and related topics. For example, when the consultation contents are highly related to other consultation contents, the judgment unit makes a judgment by considering the interrelationship. In addition, when the consultation contents are less related to other consultation contents, the judgment unit can make an individual judgment. Furthermore, the judgment unit can improve the accuracy of the judgment based on the interrelationship of the consultation contents. Thereby, the judgment unit can make an appropriate judgment based on the interrelationship of the consultation contents. Part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can cause AI to execute a process of improving the accuracy of the judgment by considering the interrelationship of the consultation contents.

[0113] The judgment unit can make a judgment while considering the attribute information of the person who submitted the consultation content. The judgment unit, for example, makes a judgment while considering the attribute information of the person who submitted the consultation content. The attribute information of the person who submitted the consultation content includes, for example, age, sex, and place of residence. For example, when the person who submitted the consultation content is a child, the judgment unit makes a judgment while considering specific attribute information (age, sex, etc.). In addition, when the person who submitted the consultation content is a guardian, the judgment unit can also make a judgment while considering the attribute information of the guardian. Furthermore, the judgment unit can improve the accuracy of the judgment based on the attribute information of the person who submitted the consultation content. This allows the judgment unit to make an appropriate judgment based on the attribute information of the person who submitted the consultation content. A part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can cause AI to execute a process of making a judgment while considering the attribute information of the person who submitted the consultation content.

[0114] The judgment unit can estimate the child's emotions and adjust the order in which the judgment results are displayed based on the estimated child's emotions. The judgment unit, for example, estimates the child's emotions and adjusts the order in which the judgment results are displayed based on the estimated child's emotions. Methods for estimating the child's emotions include, for example, facial expression analysis, voice analysis, and text analysis. For example, the facial expression analysis uses a camera to analyze the child's facial expression and estimate the emotion. The voice analysis analyzes the tone and speed of the child's voice and estimates the emotion. The text analysis analyzes the text data entered by the child and estimates the emotion. For example, the judgment unit preferentially displays important results when the child is nervous. The judgment unit can also display detailed results when the child is relaxed. Furthermore, the judgment unit can also preferentially display results that highlight the main points when the child is in a hurry. This allows the judgment unit to display the judgment results in an appropriate order according to the child's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be 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 judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit may cause the AI ​​to execute a process of estimating the child's emotion and adjusting the order in which the judgment results are displayed based on the estimated emotion.

[0115] The judgment unit can make a judgment while taking into consideration the geographical distribution of the consultation contents at the time of judgment. The judgment unit makes a judgment while taking into consideration the geographical distribution of the consultation contents at the time of judgment, for example. The geographical distribution includes, for example, GPS data, IP addresses, and the like. For example, when the consultation contents are concentrated in a specific region, the judgment unit makes a judgment while taking into consideration the characteristics of the region. In addition, when the consultation contents are distributed over a wide area, the judgment unit can also make a judgment while taking into consideration the characteristics of each region. Furthermore, the judgment unit can improve the accuracy of the judgment based on the geographical distribution of the consultation contents. This allows the judgment unit to make an appropriate judgment based on the geographical distribution of the consultation contents. A part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can cause AI to execute a process of making a judgment while taking into consideration the geographical distribution of the consultation contents.

[0116] The judgment unit can improve the accuracy of the judgment by referring to related literature of the consultation content at the time of judgment. The judgment unit can improve the accuracy of the judgment by referring to related literature of the consultation content at the time of judgment, for example. The related literature includes, for example, academic papers, past case studies, and the like. For example, the judgment unit can improve the accuracy of the judgment by referring to literature related to the consultation content. The judgment unit can also make a judgment based on research results related to the consultation content. Furthermore, the judgment unit can strengthen the basis of the judgment by referring to related literature of the consultation content. This allows the judgment unit to make an appropriate judgment based on the related literature. A part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can cause AI to execute a process of improving the accuracy of the judgment by referring to related literature of the consultation content.

[0117] The alert unit can estimate the child's emotions and adjust the display method of the alert based on the estimated child's emotions. The alert unit, for example, estimates the child's emotions and adjusts the display method of the alert based on the estimated child's emotions. Methods for estimating the child's emotions include, for example, facial expression analysis, voice analysis, and text analysis. For example, facial expression analysis uses a camera to analyze the child's facial expression and estimate the emotion. Voice analysis analyzes the tone and speed of the child's voice and estimates the emotion. Text analysis analyzes text data entered by the child and estimates the emotion. For example, the alert unit displays a simple and highly visible alert when the child is nervous. In addition, the alert unit can also display a detailed alert when the child is relaxed. Furthermore, the alert unit can display an alert that covers the main points when the child is in a hurry. This allows the alert unit to display an appropriate alert according to the child's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be 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 alert unit may be performed, for example, using AI, or may be performed without using AI. For example, the alert unit may estimate the child's emotion and cause the AI ​​to execute a process of adjusting the display method of the alert based on the estimated emotion.

[0118] The alert unit can optimize the current alert by referring to past alert data at the time of an alert. The alert unit optimizes the current alert by referring to past alert data, for example, at the time of an alert. The past alert data includes, for example, past alert contents and response results. For example, the alert unit analyzes past alert data and designs an optimal alert display method. The alert unit can also optimize the priority of the alert based on the past alert data. Furthermore, the alert unit can eliminate duplication of alerts by referring to past alert data and perform efficient alert display. This allows the alert unit to perform optimal alerts based on past alert data. Part or all of the above-mentioned processing in the alert unit may be performed, for example, using AI, or may be performed without using AI. For example, the alert unit can cause AI to execute processing to optimize the current alert by referring to past alert data.

[0119] The alert unit can estimate the child's emotion and adjust the importance of the alert based on the estimated child's emotion. The alert unit, for example, estimates the child's emotion and adjusts the importance of the alert based on the estimated child's emotion. Methods for estimating the child's emotion include, for example, facial expression analysis, voice analysis, and text analysis. For example, facial expression analysis uses a camera to analyze the child's facial expression and estimate the emotion. Voice analysis analyzes the tone and speed of the child's voice and estimates the emotion. Text analysis analyzes text data entered by the child and estimates the emotion. For example, the alert unit preferentially displays an alert with a high importance when the child is nervous. In addition, the alert unit can also display a detailed alert when the child is relaxed. Furthermore, the alert unit can also preferentially display an alert that covers the main points when the child is in a hurry. This allows the alert unit to issue an appropriate alert according to the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the alert unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the alert unit may estimate the child's emotion and cause the AI ​​to execute a process of adjusting the importance of the alert based on the estimated emotion.

[0120] The alert unit can determine the priority of the alert based on the submission time of the consultation content at the time of the alert. The alert unit determines the priority of the alert based on the submission time of the consultation content at the time of the alert. The submission time includes, for example, a timestamp, a record of the submission date, and the like. For example, the alert unit preferentially displays an alert when the consultation content has been submitted recently. In addition, the alert unit can also display an alert later when the consultation content has been submitted in the past. Furthermore, the alert unit can adjust the schedule of the alert based on the submission time of the consultation content. This allows the alert unit to perform an appropriate alert according to the submission time of the consultation content. A part or all of the above-mentioned processing in the alert unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the alert unit can cause an AI to execute a process of determining the priority of the alert based on the submission time of the consultation content.

[0121] The alert unit can analyze the alert by referring to market data related to the consultation content at the time of the alert. The alert unit can analyze the alert by referring to market data related to the consultation content at the time of the alert, for example. The related market data includes, for example, market research data, consumer behavior data, and the like. For example, the alert unit can improve the accuracy of the alert by referring to market data related to the consultation content. The alert unit can also display the alert based on market trends related to the consultation content. Furthermore, the alert unit can strengthen the basis of the alert by referring to market data related to the consultation content. This allows the alert unit to issue an appropriate alert based on the related market data. A part or all of the above-mentioned processing in the alert unit may be performed, for example, using AI, or may be performed without using AI. For example, the alert unit can cause AI to execute a process of analyzing the alert by referring to market data related to the consultation content.

[0122] The linking unit can estimate the child's emotion and adjust the linking method based on the estimated child's emotion. The linking unit, for example, estimates the child's emotion and adjusts the linking method based on the estimated child's emotion. Methods for estimating the child's emotion include, for example, facial expression analysis, voice analysis, text analysis, and the like. For example, the facial expression analysis uses a camera to analyze the child's facial expression and estimate the emotion. The voice analysis analyzes the tone and speed of the child's voice and estimates the emotion. The text analysis analyzes the text data entered by the child and estimates the emotion. For example, the linking unit provides a quick and concise linking method when the child is nervous. The linking unit can also provide a detailed linking method when the child is relaxed. Furthermore, the linking unit can also provide a linking method that focuses on the main points when the child is in a hurry. This allows the linking unit to provide an appropriate linking method according to the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be 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 collaboration unit may be performed, for example, using AI, or may be performed without using AI. For example, the collaboration unit may cause the AI ​​to execute processing to estimate the child's emotions and adjust the collaboration method based on the estimated emotions.

[0123] The coordination unit can optimize the coordination algorithm by referring to past coordination data at the time of coordination. For example, the coordination unit optimizes the coordination algorithm by referring to past coordination data at the time of coordination. The past coordination data includes, for example, past coordination contents, response results, and the like. For example, the coordination unit analyzes the past coordination data and designs an optimal coordination method. The coordination unit can also optimize the priority order of coordination based on the past coordination data. Furthermore, the coordination unit can eliminate duplication of coordination by referring to the past coordination data and perform efficient coordination. This allows the coordination unit to perform optimal coordination based on the past coordination data. A part or all of the above-mentioned processing in the coordination unit may be performed using, for example, AI, or may be performed without using AI. For example, the coordination unit can cause AI to execute a process of optimizing the coordination algorithm by referring to the past coordination data.

[0124] The linking unit can estimate the child's emotions and adjust the frequency of linking based on the estimated child's emotions. The linking unit, for example, estimates the child's emotions and adjusts the frequency of linking based on the estimated child's emotions. Methods for estimating the child's emotions include, for example, facial expression analysis, voice analysis, and text analysis. For example, the facial expression analysis uses a camera to analyze the child's facial expression and estimate the emotion. The voice analysis analyzes the tone and speed of the child's voice and estimates the emotion. The text analysis analyzes the text data entered by the child and estimates the emotion. For example, when the child is nervous, the linking unit frequently links and keeps the latest information. In addition, when the child is relaxed, the linking unit can also periodically link. Furthermore, when the child is in a hurry, the linking unit can prioritize linking only important information. This allows the linking unit to link at an appropriate frequency according to the child's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be 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 collaboration unit may be performed, for example, using AI, or may be performed without using AI. For example, the collaboration unit may cause the AI ​​to execute a process of estimating the child's emotions and adjusting the frequency of collaboration based on the estimated emotions.

[0125] The linking unit can weight the linked data based on the time of submission of the consultation content at the time of linking. For example, the linking unit weights the linked data based on the time of submission of the consultation content at the time of linking. The submission time includes, for example, a timestamp and a record of the submission date. For example, the linking unit weights the consultation content submitted recently highly. The linking unit can also weight the consultation content submitted in the past less highly. Furthermore, the linking unit can adjust the weighting of the linked data based on the time of submission of the consultation content. This allows the linking unit to perform appropriate weighting according to the time of submission of the consultation content. A part or all of the above-mentioned processing in the linking unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the linking unit can cause an AI to execute a process of weighting the linked data based on the time of submission of the consultation content.

[0126] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0127] When the child inputs the content of the consultation, the reception unit can provide a template according to the category of the content of the consultation. For example, in the case of a consultation about bullying, a template for inputting the specific circumstances and frequency of the bullying can be provided. In addition, in the case of a consultation about family problems, a template for inputting specific problems within the family and information on the people involved can also be provided. Furthermore, in the case of a consultation about academic worries, a template for inputting specific academic problems and the status of grades can also be provided. In this way, the reception unit allows the child to input the content of the consultation more specifically.

[0128] When analyzing the contents of a child's consultation, the analysis unit can apply an analysis algorithm according to the category of the consultation. For example, in the case of a consultation about bullying, an algorithm for analyzing the pattern and frequency of bullying can be applied. In addition, in the case of a consultation about family problems, an algorithm for analyzing the relationships within the family and the seriousness of the problem can be applied. Furthermore, in the case of a consultation about academic worries, an algorithm for analyzing academic performance and the learning environment can be applied. This allows the analysis unit to perform an appropriate analysis according to the contents of the consultation.

[0129] When a child inputs the details of a consultation, the providing unit can provide advice according to the category of the consultation. For example, in the case of a consultation about bullying, the providing unit can provide ways to deal with bullying and advice providers. In addition, in the case of a consultation about family problems, the providing unit can provide advice for resolving problems within the family and information on support organizations. Furthermore, in the case of a consultation about worries about schoolwork, the providing unit can provide information on ways to improve schoolwork and learning support. This allows the providing unit to provide the child with specific advice according to the details of the consultation.

[0130] When creating a database of the child's consultation content, the database unit can design a database structure according to the category of the consultation content. For example, in the case of a consultation about bullying, a database structure for recording the pattern and frequency of bullying can be designed. In addition, in the case of a consultation about family problems, a database structure for recording the relationships within the family and the seriousness of the problem can be designed. Furthermore, in the case of a consultation about academic worries, a database structure for recording academic results and the learning environment can be designed. In this way, the database unit can create an appropriate database according to the consultation content.

[0131] When judging the contents of the child's consultation, the judgment unit can apply judgment criteria according to the category of the consultation contents. For example, in the case of a consultation about bullying, the seriousness can be judged based on the pattern and frequency of bullying. In addition, in the case of a consultation about a family problem, the seriousness can be judged based on the relationships within the family and the seriousness of the problem. Furthermore, in the case of a consultation about academic worries, the seriousness can be judged based on academic performance and the learning environment. This allows the judgment unit to make an appropriate judgment according to the contents of the consultation.

[0132] The reception unit can estimate the child's emotions and adjust the input method of the consultation content based on the estimated emotions. For example, if the child is nervous, a simple and intuitive interface can be provided to minimize the input steps. Also, if the child is relaxed, detailed input options can be provided and a customizable input method can be suggested. Furthermore, if the child is in a hurry, voice input can be prioritized to allow the consultation content to be input quickly. In this way, the reception unit can provide an appropriate input method according to the child's emotions.

[0133] The analysis unit can estimate the child's emotions and adjust the way the analysis is presented based on the estimated emotions. For example, if the child is nervous, a simple, highly visible analysis result can be provided. If the child is relaxed, a detailed analysis result can be provided. Furthermore, if the child is in a hurry, an analysis result that focuses on the main points can be provided. This allows the analysis unit to provide appropriate analysis results according to the child's emotions.

[0134] The providing unit can estimate the child's emotions and adjust the way in which advice is expressed based on the estimated emotions. For example, if the child is nervous, simple, highly visible advice can be provided. If the child is relaxed, detailed advice can be provided. Furthermore, if the child is in a hurry, advice that focuses on the main points can be provided. This allows the providing unit to provide appropriate advice according to the child's emotions.

[0135] The judgment unit can estimate the child's emotions and adjust the judgment criteria for serious cases based on the estimated emotions. For example, if the child is nervous, strict judgment criteria can be applied and serious cases can be judged as a priority. If the child is relaxed, flexible judgment criteria can be applied and judgment can be made based on detailed information. Furthermore, if the child is in a hurry, criteria for making a quick judgment can be applied. This allows the judgment unit to apply appropriate judgment criteria according to the child's emotions.

[0136] The alert unit can estimate the child's emotions and adjust the way the alert is displayed based on the estimated emotions. For example, if the child is nervous, a simple, highly visible alert can be displayed. If the child is relaxed, a detailed alert can be displayed. Furthermore, if the child is in a hurry, an alert that focuses on the main points can be displayed. This allows the alert unit to display an appropriate alert according to the child's emotions.

[0137] The process flow of the second embodiment will be briefly described below.

[0138] Step 1: The reception desk consults with children about their concerns. Children's concerns may include bullying, family problems, and academic worries. The reception desk is equipped with interfaces such as voice input and a touch panel. The voice input uses voice recognition technology to convert the child's voice into text data, and the touch panel uses technologies such as capacitive and resistive membrane to allow the child to input directly. Step 2: The analysis unit analyzes the information received by the reception unit. The analysis is performed by methods such as text analysis, sentiment analysis, and pattern recognition. Text analysis analyzes the input text data using natural language processing technology, sentiment analysis estimates emotions from the input text data, and pattern recognition analyzes the patterns of the input data to find specific trends. Step 3: The provision unit provides initial countermeasures based on the information analyzed by the analysis unit. The initial countermeasures include suggesting counseling, providing emergency contact information, etc., and providing specific advice that the child can take immediately. Step 4: The Database Department will compile the information provided by the Service Department into a database. Database compilation will be carried out in accordance with standards for data format, storage method, access rights, etc., and the contents of consultations will be compiled into a database that can be viewed by instructors and staff nationwide. Step 5: The judgment unit judges whether a case is serious based on the information stored in the database by the database unit. A serious case is judged based on criteria such as the frequency of occurrence of specific keywords and emotion scores, and a case containing specific keywords or phrases is judged to be serious. Step 6: The Alerting Department raises an alert for cases that are judged to be serious by the Judgment Department. Alerts are issued according to criteria such as the notification method, notification recipient, and level of urgency, and raises an alert for serious cases and notifies the specialized team. Step 7: The Coordination Unit will respond with a specialized unit based on the information notified by the Alert Unit. The specialized unit will be composed of psychological counselors, police, school personnel, etc., and will respond in coordination with the school and police.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] Each of the multiple elements including the above-mentioned reception unit, analysis unit, provision unit, database unit, judgment unit, alert unit, and linkage unit is realized, for example, in at least one of the smart device 14 and the data processing device 12. For example, the reception unit accepts the child's worries using voice input or a touch panel of the smart device 14. The analysis unit analyzes the accepted information by the specific processing unit 290 of the data processing device 12. The provision unit provides an initial countermeasure based on the analysis result by the specific processing unit 290 of the data processing device 12. The database unit stores information in the database 24 of the data processing device 12. The judgment unit judges a serious case by the specific processing unit 290 of the data processing device 12. The alert unit raises an alert for a serious case by the specific processing unit 290 of the data processing device 12. The linkage unit responds in cooperation with a specialized unit by the specific processing unit 290 of the data processing device 12. The correspondence relationship between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0143] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] Each of the multiple elements including the reception unit, analysis unit, provision unit, database unit, judgment unit, alert unit, and linkage unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit accepts the child's worries using voice input or a touch panel of the smart glasses 214. The analysis unit analyzes the accepted information by the specific processing unit 290 of the data processing device 12. The provision unit provides an initial response based on the analysis result by the specific processing unit 290 of the data processing device 12. The database unit stores information in the database 24 of the data processing device 12. The judgment unit judges a serious case by the specific processing unit 290 of the data processing device 12. The alert unit raises an alert for a serious case by the specific processing unit 290 of the data processing device 12. The linkage unit responds in cooperation with a specialized unit by the specific processing unit 290 of the data processing device 12. The correspondence relationship between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0159] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] Each of the multiple elements including the above-mentioned reception unit, analysis unit, provision unit, database unit, judgment unit, alert unit, and linkage unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit accepts the child's worries using voice input or a touch panel of the headset type terminal 314. The analysis unit analyzes the accepted information by the specific processing unit 290 of the data processing device 12. The provision unit provides an initial response based on the analysis result by the specific processing unit 290 of the data processing device 12. The database unit stores information in the database 24 of the data processing device 12. The judgment unit judges a serious case by the specific processing unit 290 of the data processing device 12. The alert unit issues an alert for a serious case by the specific processing unit 290 of the data processing device 12. The linkage unit responds in cooperation with a specialized unit by the specific processing unit 290 of the data processing device 12. The correspondence relationship between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0175] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0176] 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.

[0177] 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.

[0178] 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. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0179] 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.

[0180] 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).

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] Each of the multiple elements including the above-mentioned reception unit, analysis unit, provision unit, database unit, judgment unit, alert unit, and collaboration unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit accepts the child's worries using the voice input or touch panel of the robot 414. The analysis unit analyzes the accepted information by the specific processing unit 290 of the data processing device 12. The provision unit provides an initial countermeasure based on the analysis result by the specific processing unit 290 of the data processing device 12. The database unit stores information in the database 24 of the data processing device 12. The judgment unit judges a serious case by the specific processing unit 290 of the data processing device 12. The alert unit issues an alert for a serious case by the specific processing unit 290 of the data processing device 12. The collaboration unit responds in cooperation with a specialized unit by the specific processing unit 290 of the data processing device 12. The correspondence relationship between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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).

[0196] 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.

[0197] 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."

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] (Appendix 1) A reception desk where children can ask for advice on their problems, an analysis unit that analyzes the information received by the reception unit; a provision unit that provides an initial countermeasure based on the information analyzed by the analysis unit; a database unit that compiles the information provided by the providing unit into a database; A judgment unit for judging serious cases based on the information stored in the database by the database unit; an alert unit that issues an alert for a case that is determined to be serious by the determination unit; A coordination unit in which a specialized team responds based on the information notified by the alert unit. A system characterized by: (Appendix 2) The reception department is Equipped with at least one interface of voice input or touch panel 2. The system of claim 1, (Appendix 3) The provision department Provide concrete advice that children can put into practice immediately 2. The system of claim 1, (Appendix 4) The database section is The contents of consultations will be compiled into a database and made available to at least one of the instructors or staff nationwide. 2. The system of claim 1, (Appendix 5) The judgment section is Critical cases are identified if the page contains at least one specific keyword or phrase 2. The system of claim 1, (Appendix 6) The alert section is Raise alerts for serious cases and notify specialized units 2. The system of claim 1, (Appendix 7) The Collaboration Department is Specialized units will respond in cooperation with schools and police 2. The system of claim 1, (Appendix 8) The reception unit is Estimate the child's emotions and adjust the method of inputting the consultation content based on the estimated child's emotions 2. The system of claim 1, (Appendix 9) The reception unit is Analyze the child's past consultation history and select the optimal input interface 2. The system of claim 1, (Appendix 10) The reception unit is When receiving consultations, they are filtered based on the child's current living situation and areas of interest. 2. The system of claim 1, (Appendix 11) The reception unit is Estimate the child's emotions and determine the priority of the consultation content to be accepted based on the estimated child's emotions 2. The system of claim 1, (Appendix 12) The reception unit is When accepting consultation requests, the child's geographic location information is taken into consideration to give priority to relevant requests. 2. The system of claim 1, (Appendix 13) The reception unit is When receiving a consultation, analyze the child's social media activity and receive related information. 2. The system of claim 1, (Appendix 14) The analysis unit is Infer the child's emotions and adjust the way the analysis is expressed based on the estimated child's emotions 2. The system of claim 1, (Appendix 15) The analysis unit is During analysis, adjust the level of detail based on the importance of the consultation content 2. The system of claim 1, (Appendix 16) The analysis unit is During analysis, different analysis algorithms are applied depending on the category of the consultation content. 2. The system of claim 1, (Appendix 17) The analysis unit is Inferring the child's emotions and adjusting the length of the analysis based on the estimated child's emotions 2. The system of claim 1, (Appendix 18) The analysis unit is During the analysis, the analysis priority will be determined based on the time of submission of the consultation. 2. The system of claim 1, (Appendix 19) The analysis unit is During analysis, adjust the order of analysis based on the relevance of the consultation content 2. The system of claim 1, (Appendix 20) The providing unit is Inferring the child's emotions and adjusting the way advice is expressed based on the estimated child's emotions 2. The system of claim 1, (Appendix 21) The providing unit is When providing advice, adjust the level of detail based on the importance of the consultation content 2. The system of claim 1, (Appendix 22) The providing unit is When providing advice, different advice algorithms are applied depending on the category of the consultation. 2. The system of claim 1, (Appendix 23) The providing unit is Estimate the child's emotions and adjust the length of the advice based on the estimated child's emotions 2. The system of claim 1, (Appendix 24) The providing unit is When providing advice, prioritize the advice based on when it was submitted 2. The system of claim 1, (Appendix 25) The providing unit is When providing advice, adjust the order of advice based on the relevance of the consultation 2. The system of claim 1, (Appendix 26) The database unit includes: Infer the child's emotions and select information to be included in the database based on the inferred child's emotions. 2. The system of claim 1, (Appendix 27) The database unit includes: When creating a database, optimize the database algorithm by referencing past data. 2. The system of claim 1, (Appendix 28) The database unit includes: The child's emotions are estimated, and the frequency of database creation is adjusted based on the estimated child's emotions. 2. The system of claim 1, (Appendix 29) The database unit includes: When compiling the database, the data is weighted based on the time when the consultation was submitted. 2. The system of claim 1, (Appendix 30) The determination unit is Estimate the child's emotions and adjust the criteria for serious cases based on the estimated child's emotions 2. The system of claim 1, (Appendix 31) The determination unit is When making a decision, improve the accuracy of the decision by taking into account the interrelationships between the consultation contents. 2. The system of claim 1, (Appendix 32) The determination unit is When making a decision, the attribute information of the person submitting the consultation will be taken into consideration. 2. The system of claim 1, (Appendix 33) The determination unit is Infer the child's emotions and adjust the order in which the results of judgments are displayed based on the estimated child's emotions. 2. The system of claim 1, (Appendix 34) The determination unit is When making a decision, the geographical distribution of the consultation content will be taken into consideration. 2. The system of claim 1, (Appendix 35) The determination unit is When making a decision, refer to literature related to the consultation content to improve the accuracy of the decision. 2. The system of claim 1, (Appendix 36) The alert unit is Infer a child's emotions and adjust how alerts are displayed based on the estimated child's emotions 2. The system of claim 1, (Appendix 37) The alert unit is At the time of alert, refer to past alert data to optimize the current alert 2. The system of claim 1, (Appendix 38) The alert unit is Infer a child's emotions and adjust the importance of the alert based on the estimated child's emotions 2. The system of claim 1, (Appendix 39) The alert unit is At the time of alert, prioritize alerts based on when the consultation was submitted 2. The system of claim 1, (Appendix 40) The alert unit is When an alert occurs, analyze the alert by referencing market data related to the consultation content 2. The system of claim 1, (Appendix 41) The linking portion is Infer the child's emotions and adjust the way you interact with them based on the inferred emotions 2. The system of claim 1, (Appendix 42) The linking portion is When linking, the linking algorithm is optimized by referencing past linking data. 2. The system of claim 1, (Appendix 43) The linking portion is Estimate the child's emotions and adjust the frequency of interactions based on the estimated child's emotions 2. The system of claim 1, (Appendix 44) The linking portion is When linking, the linked data is weighted based on the time of submission of the consultation. 2. The system of claim 1, [Explanation of symbols]

[0211] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception desk where children can ask for advice on their problems, an analysis unit that analyzes the information received by the reception unit; a provision unit that provides an initial countermeasure based on the information analyzed by the analysis unit; a database unit that compiles the information provided by the providing unit into a database; A judgment unit for judging serious cases based on the information stored in the database by the database unit; an alert unit that issues an alert for a case that is determined to be serious by the determination unit; A coordination unit in which a specialized team responds based on the information notified by the alert unit. A system characterized by:

2. The reception unit is Equipped with at least one interface of voice input or touch panel 2. The system of claim 1 .

3. The providing unit is Provide concrete advice that children can put into practice immediately 2. The system of claim 1 .

4. The database unit includes: The contents of consultations will be compiled into a database and made available to at least one of the instructors or staff nationwide.

2. The system of claim 1 .

5. The determination unit is Critical cases are identified if the page contains at least one specific keyword or phrase 2. The system of claim 1 .

6. The alert unit is Raise alerts for serious cases and notify specialized units 2. The system of claim 1 .

7. The linking portion is Specialized units will respond in cooperation with schools and police 2. The system of claim 1 .

8. The reception unit is Estimate the child's emotions and adjust the method of inputting the consultation content based on the estimated child's emotions 2. The system of claim 1 .

Images