System

Abstract

An object of a system according to an embodiment is to reduce a burden on a nursery teacher and to efficiently record growth of a preschooler.SOLUTION: A system includes an input unit, a generation unit, a confirmation unit, and an output unit. The input unit inputs the activity content and the observation result of the kindergarten child by the nursery teacher. The generation unit analyzes the information input by the input unit and generates a sentence. The confirmation unit is used by a nursery teacher to confirm and correct the sentence generated by the generation unit. The output part outputs the sentence corrected by the confirmation part as a final address book.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the problem that it takes a lot of time and effort for nursery teachers to create a communication notebook to record the daily activities and growth of children.

[0005] The system according to the embodiment aims to reduce the burden on nursery teachers and efficiently record the growth of children. [Means for solving the problem]

[0006] The system according to the embodiment includes an input unit, a generation unit, a confirmation unit, and an output unit. The input unit is used by a childcare worker to input details of children's activities and observation results. The generation unit analyzes the information input by the input unit and generates text. The confirmation unit allows the childcare worker to confirm and correct the text generated by the generation unit. The output unit outputs the text corrected by the confirmation unit as the final communication notebook. [Effects of the Invention]

[0007] The system according to the embodiment reduces the burden on nursery teachers and allows them to efficiently record the growth of children. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A communication notebook generation system according to an embodiment of the present invention automatically generates a communication notebook for nursery teachers to record the daily activities and growth of children. In this communication notebook generation system, nursery teachers input details of children's activities and observations, and a generation AI analyzes the input information to generate appropriate sentences. After the nursery teacher confirms and corrects the information, the system outputs the final communication notebook. This reduces the burden on nursery teachers and enables efficient recording of children's growth. For example, nursery teachers input details of children's activities and observations, such as the types of play the children played and the progress they made. This information is then input into the generation AI, which then analyzes the input information. The generation AI then generates appropriate sentences based on the information entered by the nursery teacher. For example, the generation AI generates a sentence such as, "Today, X-chan enjoyed playing with blocks. She tried to create a new shape and succeeded." The generated sentences are then confirmed and corrected by the nursery teacher. The nursery teacher reviews the sentences generated by the generation AI and makes corrections as necessary, for example, adding detailed information about a specific child or changing the wording. Finally, the revised text is output as a communication notebook. The childcare worker provides the final communication notebook to the parents. This reduces the burden on the childcare worker and allows for efficient recording of the children's growth. As a result, the communication notebook generation system allows childcare workers to focus on observing the children, significantly reducing the time required to create communication notebooks. In addition, because the generation AI generates the text, the content of the communication notebook is consistent and easy for parents to understand. For example, detailed records of daily activities and growth make it easier for parents to keep track of their children's growth.

[0029] The communication notebook generation system according to the embodiment includes an input unit, a generation unit, a confirmation unit, and an output unit. The input unit allows a childcare worker to input details of a child's activities and observations. For example, the input unit can include information such as the type of play the child played and the child's progress. The generation unit uses a generation AI to analyze the information input by the input unit and generate appropriate sentences. For example, the generation AI generates a sentence such as, "Today, X-chan enjoyed playing with blocks. She tried to create a new shape and succeeded." based on the information input by the childcare worker. The confirmation unit allows the childcare worker to review and correct the sentences generated by the generation unit. For example, the childcare worker reviews the sentences generated by the generation AI and makes corrections as necessary. The output unit outputs the corrected sentences as the final communication notebook. For example, the corrected sentences can be printed, saved in PDF format, or sent via email. This reduces the burden on childcare workers and enables efficient recording of children's progress. For example, childcare workers can focus on observing children, significantly reducing the time required to create communication notebooks. In addition, because the AI ​​generates the text, the contents of the communication notebook are consistent and easy for parents to understand. For example, detailed records of daily activities and growth are recorded, making it easier for parents to keep track of their child's progress.

[0030] The contact book generation system includes a reception unit that accepts voice input or photo attachments. The reception unit accepts voice input or photo attachments. For example, a childcare worker can vocally input details of a child's activities. A childcare worker can also attach photos of the child taken by the childcare worker. Voice input uses voice recognition technology to convert the voice data into text data. For example, if a childcare worker vocally inputs, "Today, XX-chan was having fun playing with blocks," the voice recognition technology converts the content into text data. For attaching photos, standards such as image format, resolution, and file size are set. For example, a JPEG image file can be attached. This allows voice input and photo attachments, thereby increasing the variety of input methods. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or without AI. For example, the reception unit can input voice data into a generation AI and have the generation AI convert the voice data into text data.

[0031] The address book generation system includes a reference unit that maintains data consistency by referencing past data. The reference unit maintains data consistency by referencing past data. For example, it can reference data from the past year or data from specific events. The reference unit checks the consistency of current data based on past data. For example, it compares the contents of past address books with the contents of current address books to check whether consistency is maintained. The reference unit can also maintain the consistency of current data by referencing past data. For example, it checks the accuracy of current data based on past data. In this way, the consistency of the address book is maintained by referring to past data. Some or all of the above-mentioned processing in the reference unit may be performed using AI, for example, or may be performed without using AI. For example, the reference unit can input past data into the generation AI and have the generation AI check the consistency of the data.

[0032] The contact book generation system includes a history unit that stores the revision history in a database. The history unit stores the revision history in the database. For example, it can store information such as the revision date and time, the revision content, and the person who made the revision. By storing the revision history, the history unit makes it possible to check the content of past revisions. For example, it can check what revisions a childcare worker has made in the past. The history unit can also analyze revision trends based on the revision history. For example, it can analyze the revisions frequently made by a specific childcare worker and find areas for improvement. In this way, by storing the revision history, it is possible to check the content of past revisions. Some or all of the above-mentioned processing in the history unit may be performed using, for example, AI, or may be performed without using AI. For example, the history unit can input the revision history into a generation AI and have the generation AI analyze the content of the revisions.

[0033] The address book generation system includes a providing unit that provides the address book via email or a dedicated app. The providing unit provides the address book via email or a dedicated app. For example, a contact book created by a childcare worker can be sent to a parent via email. The address book can also be provided via a dedicated app. Sending email requires mail server settings and an email template. For example, the contents of the contact book can be embedded in an email template and sent to the parent. Using a dedicated app requires an app installation method and user interface design. For example, parents can install the dedicated app and view the address book. By providing the address book via email or a dedicated app, communication with parents can be made more efficient. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without AI. For example, the providing unit may input the contents of the address book into a generation AI and have the generation AI generate an email and distribute it to the app.

[0034] The communication notebook generation system includes a feedback unit that accepts feedback from parents via an online form. The feedback unit accepts feedback from parents via the online form. For example, parents can enter their opinions or questions about the communication notebook into the online form. The online form is designed with various input field types and submit button layouts. For example, a form with a simple design may be provided to allow parents to easily enter information. The feedback unit stores the accepted feedback in a database so that childcare workers can check it. For example, feedback from parents may be displayed in a list so that childcare workers can respond. In this way, accepting feedback from parents improves communication with parents. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit may input data entered into the online form into a generation AI and have the generation AI analyze the feedback.

[0035] The address book generation system includes a security unit that encrypts data or restricts access. The security unit encrypts data or restricts access. For example, address book data can be protected using encryption technologies such as AES encryption or RSA encryption. It can also restrict access to data by performing user authentication and setting access permissions. For example, when a childcare worker or parent accesses address book data, password authentication is performed. The security unit sets encryption and access restrictions to ensure data security. For example, it encrypts address book data to prevent unauthorized access by third parties. It also sets access permissions so that only specific users can access the data. This improves data security by encrypting data and restricting access. Some or all of the above-described processing in the security unit may be performed using AI, for example, or without AI. For example, the security unit can have the generation AI perform encryption settings and access permission settings.

[0036] The input unit can analyze the childcare worker's past input history and select an input method. The input unit analyzes the childcare worker's past input history and selects the optimal input method. For example, the input unit prioritizes and suggests input methods (voice, text, etc.) that the childcare worker has frequently used in the past. The input unit can also predict and suggest an input method to be used during a specific time period based on the childcare worker's past input history. Furthermore, the input unit can provide an optimal input template based on the content the childcare worker has previously input. In this way, the optimal input method is suggested by analyzing the past input history. Some or all of the above-mentioned processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the childcare worker's past input history data into a generation AI and have the generation AI select the optimal input method.

[0037] The input unit can perform filtering based on the child's current activity status or area of ​​interest. The input unit performs filtering based on the child's current activity status or area of ​​interest. For example, based on the child's current activity, related input items can be preferentially displayed. The input content can also be filtered based on the child's area of ​​interest, allowing appropriate information to be entered. Furthermore, the input content can be customized by referring to the child's past activity history. In this way, appropriate information can be entered by filtering based on the child's current activity status or area of ​​interest. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the child's activity status data to the generation AI and cause the generation AI to perform filtering.

[0038] The input unit can select the optimal input means depending on the input method used by the childcare worker. The input unit selects the optimal input means depending on the input method used by the childcare worker. For example, if the childcare worker uses voice input, voice recognition technology can be used to automatically convert the input content into text. Also, if the childcare worker uses text input, an input support function can be provided to enable efficient information input. Furthermore, if the childcare worker uses images, image recognition technology can be used to automatically analyze the input content. This allows the optimal input means to be selected depending on the childcare worker's input method, thereby making input work more efficient. Some or all of the above-mentioned processing in the input unit may be performed using AI, for example, or may be performed without using AI. For example, the input unit can input the childcare worker's input method data into a generation AI and have the generation AI select the optimal input means.

[0039] The input unit can prioritize input of highly relevant information taking into account the geographical location information of the child. The input unit prioritizes input of highly relevant information taking into account the geographical location information of the child. For example, the input unit prioritizes input of relevant information based on activities performed by the child in a specific location. The input unit can also suggest optimal input items based on the geographical location information of the child. Furthermore, the input content can be customized based on places the child has visited in the past. In this way, highly relevant information is prioritized by taking into account the geographical location information of the child. Some or all of the above-described processing in the input unit may be performed using AI, for example, or may be performed without using AI. For example, the input unit can input the geographical location information data of the child to the generation AI and cause the generation AI to prioritize input of highly relevant information.

[0040] The input unit can analyze the social media activity of the childcare worker and input related information. The input unit analyzes the social media activity of the childcare worker and inputs related information. For example, the input unit suggests related input content based on information shared by the childcare worker on social media. The input unit can also analyze the childcare worker's social media activity and provide appropriate input items. Furthermore, related information can be input by referring to the activity of the childcare worker's friends on social media. In this way, related information is input by analyzing the childcare worker's social media activity. Some or all of the above-mentioned processing in the input unit may be performed using AI, for example, or may be performed without using AI. For example, the input unit can input the childcare worker's social media activity data to the generation AI and cause the generation AI to input related information.

[0041] The input unit can customize the input method by reflecting the childcare worker's past feedback. The input unit customizes the input method by reflecting the childcare worker's past feedback. For example, the input unit suggests an optimal input method based on feedback provided by the childcare worker in the past. The input interface can also be customized by reflecting the childcare worker's past feedback. Furthermore, the input content can be automatically adjusted based on the childcare worker's feedback. In this way, the optimal input method is provided by reflecting the childcare worker's past feedback. Some or all of the above-mentioned processing in the input unit may be performed using AI, for example, or may be performed without using AI. For example, the input unit can input the childcare worker's feedback data into the generation AI and have the generation AI customize the input method.

[0042] The generation unit can adjust the level of detail of the sentences based on the importance of the children's activities. The generation unit adjusts the level of detail of the sentences based on the importance of the children's activities. For example, for important activities, sentences including detailed descriptions can be generated. For everyday activities, sentences including concise descriptions can be generated. For special events, sentences including detailed descriptions and impressions can be generated. In this way, appropriate sentences are generated by adjusting the level of detail of the sentences based on the importance of the children's activities. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the children's activity data into the generation AI and cause the generation AI to adjust the level of detail of the sentences.

[0043] The generation unit can apply different generation algorithms depending on the category of the child. The generation unit applies different generation algorithms depending on the category of the child. For example, different generation algorithms can be applied depending on age to generate appropriate sentences. Different generation algorithms can also be applied depending on the activity content to generate appropriate sentences. Furthermore, different generation algorithms can be applied depending on the characteristics of the child to generate appropriate sentences. In this way, appropriate sentences are generated by applying different generation algorithms depending on the category of the child. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input child category data into the generation AI and cause the generation AI to apply different generation algorithms.

[0044] The generation unit can improve the accuracy of generation by referring to the childcare worker's past generation results. The generation unit improves the accuracy of generation by referring to the childcare worker's past generation results. For example, the generation accuracy can be improved by referring to sentences generated by the childcare worker in the past. The generation unit can also analyze the childcare worker's past generation results and apply the optimal generation algorithm. Furthermore, the generation accuracy can be improved based on the childcare worker's feedback. In this way, the generation accuracy can be improved by referring to the childcare worker's past generation results. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the childcare worker's past generation result data into the generation AI and cause the generation AI to improve the generation accuracy.

[0045] The generation unit can determine the generation priority based on the time of submission of the children's activities. The generation unit determines the generation priority based on the time of submission of the children's activities. For example, it prioritizes generating sentences for activities with an approaching submission deadline. It is also possible to postpone generating sentences for activities with a distant submission deadline. It is also possible to generate sentences with special care for activities whose submission deadline has passed. In this way, by determining the generation priority based on the time of submission of the children's activities, appropriate sentences are generated. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input data on the time of submission of the children into the generation AI and have the generation AI determine the generation priority.

[0046] The generation unit can adjust the order of generation based on the relevance of the children. The generation unit adjusts the order of generation based on the relevance of the children. For example, sentences are generated preferentially based on the relevance of the children's activities. The generation order can also be adjusted based on the importance of the children's activities. Furthermore, the generation order can be adjusted based on the frequency of the children's activities. In this way, appropriate sentences are generated by adjusting the order of generation based on the relevance of the children. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input relevance data of the children into the generation AI and cause the generation AI to adjust the order of generation.

[0047] The generation unit can adjust the use of technical terminology in the generation according to the childcare worker's level of expertise. The generation unit adjusts the use of technical terminology in the generation according to the childcare worker's level of expertise. For example, if the childcare worker's level of expertise is high, sentences that use a lot of technical terminology can be generated. Also, if the childcare worker's level of expertise is low, sentences that use simple expressions can be generated. Furthermore, sentences that use appropriate technical terminology can be generated according to the childcare worker's level of expertise. In this way, appropriate sentences are generated by adjusting the use of technical terminology according to the childcare worker's level of expertise. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the childcare worker's level of expertise data into the generation AI and have the generation AI adjust the use of technical terminology.

[0048] The confirmation unit can select the optimal confirmation method by referring to the childcare worker's past confirmation history. The confirmation unit selects the optimal confirmation method by referring to the childcare worker's past confirmation history. For example, the confirmation unit suggests the optimal confirmation method based on confirmation methods used by the childcare worker in the past. The confirmation unit can also analyze the childcare worker's past confirmation history and provide the optimal confirmation method. Furthermore, the confirmation method can be customized based on the childcare worker's feedback. In this way, the optimal confirmation method is provided by referring to the childcare worker's past confirmation history. Some or all of the above-mentioned processing in the confirmation unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation unit can input the childcare worker's confirmation history data into the generation AI and have the generation AI select the optimal confirmation method.

[0049] The confirmation unit can customize the confirmation content based on the child's current situation. The confirmation unit customizes the confirmation content based on the child's current situation. For example, the confirmation content is customized based on the child's current activity status. The confirmation content can also be adjusted by referring to the child's past activity history. Furthermore, the confirmation content can be customized according to the child's characteristics. In this way, appropriate confirmation is performed by customizing the confirmation content based on the child's current situation. Some or all of the above-mentioned processing in the confirmation unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation unit can input the child's current situation data into the generation AI and have the generation AI customize the confirmation content.

[0050] The confirmation unit can improve the confirmation method by reflecting the feedback from the childcare worker. The confirmation unit improves the confirmation method by reflecting the feedback from the childcare worker. For example, the confirmation method is improved based on the feedback from the childcare worker. The confirmation unit can also provide an optimal confirmation method by referring to the childcare worker's past feedback. Furthermore, the confirmation content can be customized by reflecting the feedback from the childcare worker. In this way, the confirmation method is improved by reflecting the feedback from the childcare worker. Some or all of the above-mentioned processing in the confirmation unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation unit can input the feedback data from the childcare worker into the generation AI and have the generation AI improve the confirmation method.

[0051] The confirmation unit can select the optimal confirmation method taking into account the child's geographical location information. The confirmation unit selects the optimal confirmation method taking into account the child's geographical location information. For example, the confirmation unit provides relevant confirmation content based on activities the child has performed in a specific location. The confirmation unit can also suggest the optimal confirmation method based on the child's geographical location information. Furthermore, the confirmation content can be customized based on places the child has visited in the past. In this way, the optimal confirmation method is provided by taking into account the child's geographical location information. Some or all of the above-mentioned processing in the confirmation unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation unit can input the child's geographical location information data into the generation AI and cause the generation AI to select the optimal confirmation method.

[0052] The confirmation unit can analyze the social media activity of the childcare worker and suggest confirmation content. The confirmation unit analyzes the social media activity of the childcare worker and suggest confirmation content. For example, the confirmation unit suggests related confirmation content based on information shared by the childcare worker on social media. The confirmation unit can also analyze the childcare worker's social media activity and provide appropriate confirmation items. Furthermore, the confirmation unit can suggest related confirmation content based on the activity of the childcare worker's friends on social media. In this way, related confirmation content is suggested by analyzing the childcare worker's social media activity. Some or all of the above-mentioned processing in the confirmation unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation unit can input the childcare worker's social media activity data into a generation AI and have the generation AI execute the suggestion of confirmation content.

[0053] The confirmation unit can customize the confirmation method by reflecting the childcare worker's past feedback. The confirmation unit customizes the confirmation method by reflecting the childcare worker's past feedback. For example, the confirmation unit proposes an optimal confirmation method based on feedback provided by the childcare worker in the past. The confirmation interface can also be customized by reflecting the childcare worker's past feedback. Furthermore, the confirmation content can be automatically adjusted based on the childcare worker's feedback. In this way, the optimal confirmation method is provided by reflecting the childcare worker's past feedback. Some or all of the above-mentioned processing in the confirmation unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation unit can input the childcare worker's feedback data into the generation AI and have the generation AI customize the confirmation method.

[0054] The output unit can select the optimal output method by referring to the childcare worker's past output history. The output unit selects the optimal output method by referring to the childcare worker's past output history. For example, the output unit suggests the optimal output method based on output methods used by the childcare worker in the past. The output unit can also analyze the childcare worker's past output history and provide the optimal output method. Furthermore, the output method can be customized based on the childcare worker's feedback. In this way, the optimal output method is provided by referring to the childcare worker's past output history. Some or all of the above-mentioned processing in the output unit may be performed using AI, for example, or may be performed without using AI. For example, the output unit can input the childcare worker's output history data to a generation AI and have the generation AI select the optimal output method.

[0055] The output unit can customize the output content based on the child's current situation. The output unit customizes the output content based on the child's current situation. For example, the output content is customized based on the child's current activity status. The output content can also be adjusted by referring to the child's past activity history. Furthermore, the output content can be customized according to the child's characteristics. In this way, appropriate output is produced by customizing the output content based on the child's current situation. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the child's current situation data to the generation AI and have the generation AI customize the output content.

[0056] The output unit can improve the output method by reflecting the feedback from the childcare worker. The output unit improves the output method by reflecting the feedback from the childcare worker. For example, the output method is improved based on the feedback from the childcare worker. The output unit can also provide the optimal output method by referring to the childcare worker's past feedback. Furthermore, the output content can be customized by reflecting the feedback from the childcare worker. In this way, the output method is improved by reflecting the feedback from the childcare worker. Some or all of the above-mentioned processing in the output unit may be performed using AI, for example, or may be performed without using AI. For example, the output unit can input the feedback data from the childcare worker into the generation AI and have the generation AI improve the output method.

[0057] The output unit can select the optimal output method taking into account the child's geographical location information. The output unit selects the optimal output method taking into account the child's geographical location information. For example, the output unit provides relevant output content based on activities performed by the child in a specific location. The output unit can also suggest the optimal output method based on the child's geographical location information. Furthermore, the output content can be customized based on places the child has visited in the past. In this way, the optimal output method is provided by taking into account the child's geographical location information. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the child's geographical location information data to a generation AI and cause the generation AI to select the optimal output method.

[0058] The output unit can analyze the social media activity of the childcare worker and suggest output content. The output unit analyzes the social media activity of the childcare worker and suggest output content. For example, the output unit suggests related output content based on information shared by the childcare worker on social media. The output unit can also analyze the childcare worker's social media activity and provide appropriate output items. Furthermore, the output unit can suggest related output content by referring to the activity of the childcare worker's friends on social media. In this way, related output content is suggested by analyzing the childcare worker's social media activity. Some or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the childcare worker's social media activity data into a generation AI and have the generation AI suggest output content.

[0059] The output unit can customize the output method by reflecting the childcare worker's past feedback. The output unit customizes the output method by reflecting the childcare worker's past feedback. For example, the output unit suggests an optimal output method based on feedback provided by the childcare worker in the past. The output interface can also be customized by reflecting the childcare worker's past feedback. Furthermore, the output content can be automatically adjusted based on the childcare worker's feedback. In this way, the optimal output method is provided by reflecting the childcare worker's past feedback. Some or all of the above-mentioned processing in the output unit may be performed using AI, for example, or may be performed without using AI. For example, the output unit can input the childcare worker's feedback data into a generation AI and have the generation AI customize the output method.

[0060] The reception unit can select the optimal reception method by referring to the childcare worker's past input history. The reception unit selects the optimal reception method by referring to the childcare worker's past input history. For example, the reception unit suggests the optimal reception method based on the reception methods used by the childcare worker in the past. The reception unit can also analyze the childcare worker's past input history and provide the optimal reception method. Furthermore, the reception method can be customized based on the childcare worker's feedback. In this way, the optimal reception method is provided by referring to the childcare worker's past input history. Some or all of the above-mentioned processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit can input the childcare worker's input history data into the generation AI and have the generation AI select the optimal reception method.

[0061] The reception unit can customize the reception content based on the current situation of the child. The reception unit customizes the reception content based on the current situation of the child. For example, the reception content is customized based on the current activity status of the child. The reception content can also be adjusted by referring to the child's past activity history. Furthermore, the reception content can be customized according to the characteristics of the child. In this way, appropriate reception can be performed by customizing the reception content based on the child's current situation. Some or all of the above-mentioned processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit can input the child's current situation data into the generation AI and have the generation AI customize the reception content.

[0062] The reception unit can select the optimal reception method taking into account the geographical location information of the child. The reception unit selects the optimal reception method taking into account the geographical location information of the child. For example, the reception unit provides relevant reception content based on activities performed by the child in a specific location. The reception unit can also suggest the optimal reception method based on the geographical location information of the child. Furthermore, the reception content can be customized based on places the child has visited in the past. In this way, the optimal reception method is provided by taking into account the geographical location information of the child. Some or all of the above-mentioned processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit can input the geographical location information data of the child into the generation AI and cause the generation AI to select the optimal reception method.

[0063] The reception unit can analyze the social media activity of the childcare worker and suggest the content of the reception. The reception unit analyzes the social media activity of the childcare worker and suggest the content of the reception. For example, the reception unit suggests related content of the reception based on information shared by the childcare worker on social media. The reception unit can also analyze the childcare worker's social media activity and provide appropriate reception items. Furthermore, the reception unit can suggest related content of the reception based on the activity of the childcare worker's friends on social media. In this way, related content of the reception is suggested by analyzing the childcare worker's social media activity. Some or all of the above-mentioned processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit can input the childcare worker's social media activity data into a generation AI and have the generation AI execute the suggestion of content of the reception.

[0064] The reference unit can maintain the consistency of current data by referencing past data. The reference unit maintains the consistency of current data by referencing past data. For example, the reference unit checks the consistency of current data based on past data. The reference unit can also check the consistency of current data by referencing past data. Furthermore, the accuracy of current data can be checked based on past data. In this way, the consistency of current data is maintained by referring to past data. Some or all of the above-mentioned processing in the reference unit may be performed using AI, for example, or may be performed without using AI. For example, the reference unit can input past data into the generation AI and have the generation AI check the consistency of the current data.

[0065] The reference unit can select the optimal reference method by referring to the childcare worker's past reference history. The reference unit selects the optimal reference method by referring to the childcare worker's past reference history. For example, the reference unit can suggest the optimal reference method based on reference methods used by the childcare worker in the past. The reference unit can also analyze the childcare worker's past reference history and provide the optimal reference method. Furthermore, the reference method can be customized based on the childcare worker's feedback. In this way, the optimal reference method is provided by referring to the childcare worker's past reference history. Some or all of the above-mentioned processing in the reference unit may be performed using AI, for example, or may be performed without using AI. For example, the reference unit can input the childcare worker's reference history data into a generation AI and have the generation AI select the optimal reference method.

[0066] The reference unit can weight the reference data based on the time of submission of the children's activities. The reference unit weights the reference data based on the time of submission of the children's activities. For example, for activities with an approaching submission deadline, data can be referenced preferentially. For activities with a distant submission deadline, data can also be referenced later. Furthermore, for activities whose submission deadline has passed, data can be referenced with special care. In this way, by weighting the reference data based on the time of submission of the children's activities, appropriate data can be referenced. Some or all of the above-mentioned processing in the reference unit may be performed using AI, for example, or may be performed without using AI. For example, the reference unit can input data on the time of submission of the children to the generation AI and cause the generation AI to weight the reference data.

[0067] The reference unit can adjust the reference method by reflecting the feedback from the childcare worker. The reference unit adjusts the reference method by reflecting the feedback from the childcare worker. For example, the reference method is improved based on the feedback from the childcare worker. The reference unit can also provide an optimal reference method by referring to the childcare worker's past feedback. Furthermore, the reference content can be customized by reflecting the feedback from the childcare worker. In this way, the reference method is adjusted by reflecting the feedback from the childcare worker. Some or all of the above-mentioned processing in the reference unit may be performed using AI, for example, or may be performed without using AI. For example, the reference unit can input the feedback data from the childcare worker into the generation AI and have the generation AI adjust the reference method.

[0068] The history unit can select the optimal storage method by referring to the childcare worker's past revision history. The history unit selects the optimal storage method by referring to the childcare worker's past revision history. For example, the history unit suggests the optimal storage method based on the storage methods used by the childcare worker in the past. The history unit can also analyze the childcare worker's past revision history and provide the optimal storage method. Furthermore, the storage method can be customized based on the childcare worker's feedback. In this way, the optimal storage method is provided by referring to the childcare worker's past revision history. Some or all of the above-mentioned processing in the history unit may be performed using AI, for example, or may be performed without using AI. For example, the history unit can input the childcare worker's revision history data into the generation AI and have the generation AI select the optimal storage method.

[0069] The history unit can customize the stored content based on the child's current situation. The history unit customizes the stored content based on the child's current situation. For example, the stored content is customized based on the child's current activity status. The stored content can also be adjusted by referring to the child's past activity history. Furthermore, the stored content can be customized according to the child's characteristics. In this way, appropriate storage is performed by customizing the stored content based on the child's current situation. Some or all of the above-mentioned processing in the history unit may be performed using AI, for example, or may be performed without using AI. For example, the history unit can input the child's current situation data into the generation AI and have the generation AI customize the stored content.

[0070] The history unit can select the optimal storage method taking into account the child's geographical location information. The history unit selects the optimal storage method taking into account the child's geographical location information. For example, the history unit stores related history based on activities performed by the child in a specific location. The history unit can also suggest the optimal storage method based on the child's geographical location information. Furthermore, the storage content can be customized based on places the child has visited in the past. In this way, the optimal storage method is provided by taking into account the child's geographical location information. Some or all of the above-described processing in the history unit may be performed using AI, for example, or may be performed without using AI. For example, the history unit can input the child's geographical location information data into the generation AI and cause the generation AI to select the optimal storage method.

[0071] The history unit can analyze the childcare worker's social media activity and suggest content to be saved. The history unit can analyze the childcare worker's social media activity and suggest content to be saved. For example, the history unit saves related history based on information shared by the childcare worker on social media. The history unit can also analyze the childcare worker's social media activity and suggest appropriate saved items. Furthermore, the history unit can save related history by referring to the activity of the childcare worker's friends on social media. In this way, related saved content is suggested by analyzing the childcare worker's social media activity. Some or all of the above-mentioned processing in the history unit may be performed using, for example, AI, or may be performed without using AI. For example, the history unit can input the childcare worker's social media activity data into a generation AI and have the generation AI suggest saved content.

[0072] The provision unit can select the optimal provision method by referring to the childcare worker's past provision history. The provision unit selects the optimal provision method by referring to the childcare worker's past provision history. For example, the optimal provision method is suggested based on provision methods used by the childcare worker in the past. The provision unit can also analyze the childcare worker's past provision history and provide the optimal provision method. Furthermore, the provision method can be customized based on the childcare worker's feedback. In this way, the optimal provision method is provided by referring to the childcare worker's past provision history. Some or all of the above-mentioned processing in the provision unit may be performed using AI, for example, or may be performed without using AI. For example, the provision unit can input the childcare worker's provision history data into the generation AI and cause the generation AI to select the optimal provision method.

[0073] The providing unit can customize the content to be provided based on the current situation of the child. The providing unit customizes the content to be provided based on the current situation of the child. For example, the providing unit customizes the content to be provided based on the current activity status of the child. The providing unit can also adjust the content to be provided by referring to the child's past activity history. Furthermore, the providing unit can customize the content to be provided according to the characteristics of the child. In this way, by customizing the content to be provided based on the current situation of the child, appropriate content is provided. Some or all of the above-mentioned processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input the current situation data of the child into the generating AI and cause the generating AI to customize the content to be provided.

[0074] The provision unit can improve the provision method by reflecting the feedback from the childcare worker. The provision unit improves the provision method by reflecting the feedback from the childcare worker. For example, the provision method is improved based on the feedback from the childcare worker. The optimal provision method can also be provided by referring to the childcare worker's past feedback. Furthermore, the provision content can be customized by reflecting the feedback from the childcare worker. In this way, the provision method is improved by reflecting the feedback from the childcare worker. Some or all of the above-mentioned processing in the provision unit may be performed using AI, for example, or may be performed without using AI. For example, the provision unit can input the feedback data from the childcare worker into the generation AI and cause the generation AI to improve the provision method.

[0075] The provision unit can select the optimal provision method by taking into account the geographical location information of the child. The provision unit selects the optimal provision method by taking into account the geographical location information of the child. For example, related provision content is provided based on activities performed by the child in a specific location. The optimal provision method can also be suggested based on the geographical location information of the child. Furthermore, the provision content can be customized based on places the child has visited in the past. In this way, the optimal provision method is provided by taking into account the geographical location information of the child. Some or all of the above-mentioned processing in the provision unit may be performed using AI, for example, or may be performed without using AI. For example, the provision unit can input the geographical location information data of the child into the generation AI and cause the generation AI to select the optimal provision method.

[0076] The provision unit can analyze the social media activity of the childcare worker and suggest content to be provided. The provision unit analyzes the social media activity of the childcare worker and suggest content to be provided. For example, the provision unit suggests related content to be provided based on information shared by the childcare worker on social media. The provision unit can also analyze the childcare worker's social media activity and provide appropriate content to be provided. Furthermore, the provision unit can also suggest related content to be provided by referring to the activity of the childcare worker's friends on social media. In this way, related content to be provided is suggested by analyzing the childcare worker's social media activity. Some or all of the above-mentioned processing in the provision unit may be performed using AI, for example, or may be performed without using AI. For example, the provision unit can input the childcare worker's social media activity data into a generation AI and have the generation AI execute the suggestion of content to be provided.

[0077] The provision unit can customize the provision method by reflecting the childcare worker's past feedback. The provision unit customizes the provision method by reflecting the childcare worker's past feedback. For example, the provision unit proposes an optimal provision method based on feedback provided by the childcare worker in the past. The provision interface can also be customized by reflecting the childcare worker's past feedback. Furthermore, the provision content can be automatically adjusted based on the childcare worker's feedback. In this way, the optimal provision method is provided by reflecting the childcare worker's past feedback. Some or all of the above-mentioned processing in the provision unit may be performed using AI, for example, or may be performed without using AI. For example, the provision unit can input the childcare worker's feedback data into the generation AI and cause the generation AI to customize the provision method.

[0078] The feedback unit can select the optimal reception method by referring to the parent's past feedback history. The feedback unit selects the optimal reception method by referring to the parent's past feedback history. For example, the feedback unit may suggest the optimal reception method based on feedback reception methods used by the parent in the past. The feedback unit may also analyze the parent's past feedback history and provide the optimal reception method. Furthermore, the reception method may be customized based on the parent's feedback. In this way, the optimal reception method is provided by referring to the parent's past feedback history. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit may input the parent's feedback history data into the generation AI and cause the generation AI to select the optimal reception method.

[0079] The feedback unit can customize the acceptance content based on the current situation of the child. The feedback unit customizes the acceptance content based on the current situation of the child. For example, the acceptance content is customized based on the current activity status of the child. The acceptance content can also be adjusted by referring to the child's past activity history. Furthermore, the acceptance content can also be customized according to the characteristics of the child. In this way, appropriate acceptance is performed by customizing the acceptance content based on the child's current situation. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input the child's current situation data into the generation AI and cause the generation AI to customize the acceptance content.

[0080] The feedback unit can select the optimal reception method by taking into account the geographical location information of the guardian. The feedback unit selects the optimal reception method by taking into account the geographical location information of the guardian. For example, the feedback unit receives related feedback content based on activities performed by the guardian in a specific location. The optimal reception method can also be suggested based on the geographical location information of the guardian. Furthermore, the reception content can be customized based on places the guardian has visited in the past. In this way, the optimal reception method is provided by taking into account the geographical location information of the guardian. Some or all of the above-described processing in the feedback unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback unit can input the geographical location information data of the guardian into the generation AI and cause the generation AI to select the optimal reception method.

[0081] The feedback unit can analyze the parent's social media activity to suggest acceptance content. The feedback unit analyzes the parent's social media activity to suggest acceptance content. For example, the feedback unit suggests relevant feedback content based on information shared by the parent on social media. The feedback unit can also analyze the parent's social media activity to provide appropriate feedback items. Furthermore, the feedback unit can suggest relevant feedback content by referring to the activity of the parent's friends on social media. In this way, relevant acceptance content is suggested by analyzing the parent's social media activity. Some or all of the above-mentioned processing in the feedback unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback unit can input the parent's social media activity data into a generation AI and cause the generation AI to suggest acceptance content.

[0082] The security unit can select the optimal setting method by referring to the childcare worker's past security history. The security unit selects the optimal setting method by referring to the childcare worker's past security history. For example, the security unit can suggest the optimal setting method based on security settings used by the childcare worker in the past. The security unit can also analyze the childcare worker's past security history and provide the optimal setting method. Furthermore, the security settings can be customized based on the childcare worker's feedback. In this way, the optimal setting method is provided by referring to the childcare worker's past security history. Some or all of the above-mentioned processing in the security unit may be performed using AI, for example, or may be performed without using AI. For example, the security unit can input the childcare worker's security history data into a generation AI and have the generation AI select the optimal setting method.

[0083] The security unit can customize the settings based on the current situation of the child. The security unit customizes the settings based on the current situation of the child. For example, the security settings are customized based on the current activity status of the child. The security settings can also be adjusted by referring to the child's past activity history. Furthermore, the security settings can be customized according to the characteristics of the child. In this way, appropriate security settings are set by customizing the settings based on the current situation of the child. Some or all of the above-mentioned processing in the security unit may be performed using, for example, AI, or may be performed without using AI. For example, the security unit can input the child's current situation data into a generation AI and have the generation AI customize the settings.

[0084] The security unit can select the optimal setting method by taking into account the geographical location information of the child. The security unit selects the optimal setting method by taking into account the geographical location information of the child. For example, relevant security settings can be provided based on activities performed by the child in a specific location. The security unit can also suggest optimal security settings based on the geographical location information of the child. Furthermore, security settings can be customized based on places the child has visited in the past. In this way, the optimal setting method is provided by taking into account the geographical location information of the child. Some or all of the above-mentioned processing in the security unit may be performed using AI, for example, or may be performed without using AI. For example, the security unit can input the geographical location information data of the child into a generation AI and have the generation AI select the optimal setting method.

[0085] The security unit can analyze the social media activity of the childcare worker and suggest settings. The security unit can analyze the social media activity of the childcare worker and suggest settings. For example, the security unit can suggest relevant security settings based on information shared by the childcare worker on social media. The security unit can also analyze the childcare worker's social media activity and provide appropriate security settings. Furthermore, the security unit can suggest relevant security settings based on the activity of the childcare worker's friends on social media. In this way, relevant settings are suggested by analyzing the childcare worker's social media activity. Some or all of the above-mentioned processing in the security unit may be performed using AI, for example, or may be performed without using AI. For example, the security unit can input the childcare worker's social media activity data into a generation AI and have the generation AI suggest settings.

[0086] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0087] The contact notebook generation system can analyze the childcare worker's past input history and customize the input method. For example, it can prioritize and suggest input methods (voice, text, etc.) that the childcare worker has frequently used in the past. It can also predict and suggest the input method to be used during a specific time period based on the childcare worker's past input history. It can also provide an optimal input template based on the content the childcare worker has previously entered. In this way, the optimal input method is suggested by analyzing the past input history. Some or all of the above-mentioned processing in the input unit may be performed using AI, or may be performed without using AI. For example, the input unit can input the childcare worker's past input history data into the generation AI and have the generation AI select the optimal input method.

[0088] The communication notebook generation system can customize the input method by reflecting the childcare worker's past feedback. For example, the optimal input method is suggested based on feedback provided by the childcare worker in the past. The input interface can also be customized by reflecting the childcare worker's past feedback. Furthermore, the input content can be automatically adjusted based on the childcare worker's feedback. In this way, the optimal input method is provided by reflecting the childcare worker's past feedback. Some or all of the above-mentioned processing in the input unit may be performed using AI, or may be performed without using AI. For example, the input unit can input the childcare worker's feedback data into the generation AI and have the generation AI customize the input method.

[0089] The communication notebook generation system can improve the accuracy of generation by referring to the childcare worker's past generation results. For example, the generation accuracy can be improved by referring to sentences generated by the childcare worker in the past. The childcare worker's past generation results can also be analyzed and the optimal generation algorithm can be applied. Furthermore, the generation accuracy can be improved based on the childcare worker's feedback. In this way, the generation accuracy can be improved by referring to the childcare worker's past generation results. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the childcare worker's past generation result data into the generation AI and have the generation AI improve the generation accuracy.

[0090] The communication notebook generation system can select the optimal verification method by referring to the childcare worker's past verification history. For example, it can suggest the optimal verification method based on the verification methods used by the childcare worker in the past. It can also analyze the childcare worker's past verification history and provide the optimal verification method. It can also customize the verification method based on the childcare worker's feedback. In this way, the optimal verification method is provided by referring to the childcare worker's past verification history. Some or all of the above-mentioned processing in the verification unit may be performed using AI, or may be performed without using AI. For example, the verification unit can input the childcare worker's verification history data into the generation AI and have the generation AI select the optimal verification method.

[0091] The communication notebook generation system can select the optimal output method by referring to the childcare worker's past output history. For example, it can suggest the optimal output method based on the output methods used by the childcare worker in the past. It can also analyze the childcare worker's past output history and provide the optimal output method. It can also customize the output method based on the childcare worker's feedback. In this way, the optimal output method is provided by referring to the childcare worker's past output history. Some or all of the above-mentioned processing in the output unit may be performed using AI, or may be performed without using AI. For example, the output unit can input the childcare worker's output history data into the generation AI and have the generation AI select the optimal output method.

[0092] The processing flow of the first embodiment will be briefly explained below.

[0093] Step 1: In the input section, the nursery teacher inputs the details of the children's activities and observations. For example, they can input information such as what kind of play the children did and how they grew. Step 2: The generation unit uses the generation AI to analyze the information input by the input unit and generate appropriate sentences. For example, based on the information input by the nursery teacher, the generation AI generates a sentence such as, "Today, X-chan enjoyed playing with blocks. She tried to create a new shape and succeeded." Step 3: In the confirmation unit, a childcare worker confirms and corrects the sentences generated by the generation unit. For example, a childcare worker confirms the sentences generated by the generation AI and makes corrections as necessary. Step 4: The output unit outputs the text corrected by the confirmation unit as the final contact list. For example, the corrected text can be printed, saved in PDF format, or sent by email.

[0094] (Example 2) A communication notebook generation system according to an embodiment of the present invention automatically generates a communication notebook for nursery teachers to record the daily activities and growth of children. In this communication notebook generation system, nursery teachers input details of children's activities and observations, and a generation AI analyzes the input information to generate appropriate sentences. After the nursery teacher confirms and corrects the information, the system outputs the final communication notebook. This reduces the burden on nursery teachers and enables efficient recording of children's growth. For example, nursery teachers input details of children's activities and observations, such as the types of play the children played and the progress they made. This information is then input into the generation AI, which then analyzes the input information. The generation AI then generates appropriate sentences based on the information entered by the nursery teacher. For example, the generation AI generates a sentence such as, "Today, X-chan enjoyed playing with blocks. She tried to create a new shape and succeeded." The generated sentences are then confirmed and corrected by the nursery teacher. The nursery teacher reviews the sentences generated by the generation AI and makes corrections as necessary, for example, adding detailed information about a specific child or changing the wording. Finally, the revised text is output as a communication notebook. The childcare worker provides the final communication notebook to the parents. This reduces the burden on the childcare worker and allows for efficient recording of the children's growth. As a result, the communication notebook generation system allows childcare workers to focus on observing the children, significantly reducing the time required to create communication notebooks. In addition, because the generation AI generates the text, the content of the communication notebook is consistent and easy for parents to understand. For example, detailed records of daily activities and growth make it easier for parents to keep track of their children's growth.

[0095] The communication notebook generation system according to the embodiment includes an input unit, a generation unit, a confirmation unit, and an output unit. The input unit allows a childcare worker to input details of a child's activities and observations. For example, the input unit can include information such as the type of play the child played and the child's progress. The generation unit uses a generation AI to analyze the information input by the input unit and generate appropriate sentences. For example, the generation AI generates a sentence such as, "Today, X-chan enjoyed playing with blocks. She tried to create a new shape and succeeded." based on the information input by the childcare worker. The confirmation unit allows the childcare worker to review and correct the sentences generated by the generation unit. For example, the childcare worker reviews the sentences generated by the generation AI and makes corrections as necessary. The output unit outputs the corrected sentences as the final communication notebook. For example, the corrected sentences can be printed, saved in PDF format, or sent via email. This reduces the burden on childcare workers and enables efficient recording of children's progress. For example, childcare workers can focus on observing children, significantly reducing the time required to create communication notebooks. In addition, because the AI ​​generates the text, the contents of the communication notebook are consistent and easy for parents to understand. For example, detailed records of daily activities and growth are recorded, making it easier for parents to keep track of their child's progress.

[0096] The contact book generation system includes a reception unit that accepts voice input or photo attachments. The reception unit accepts voice input or photo attachments. For example, a childcare worker can vocally input details of a child's activities. A childcare worker can also attach photos of the child taken by the childcare worker. Voice input uses voice recognition technology to convert the voice data into text data. For example, if a childcare worker vocally inputs, "Today, XX-chan was having fun playing with blocks," the voice recognition technology converts the content into text data. For attaching photos, standards such as image format, resolution, and file size are set. For example, a JPEG image file can be attached. This allows voice input and photo attachments, thereby increasing the variety of input methods. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or without AI. For example, the reception unit can input voice data into a generation AI and have the generation AI convert the voice data into text data.

[0097] The address book generation system includes a reference unit that maintains data consistency by referencing past data. The reference unit maintains data consistency by referencing past data. For example, it can reference data from the past year or data from specific events. The reference unit checks the consistency of current data based on past data. For example, it compares the contents of past address books with the contents of current address books to check whether consistency is maintained. The reference unit can also maintain the consistency of current data by referencing past data. For example, it checks the accuracy of current data based on past data. In this way, the consistency of the address book is maintained by referring to past data. Some or all of the above-mentioned processing in the reference unit may be performed using AI, for example, or may be performed without using AI. For example, the reference unit can input past data into the generation AI and have the generation AI check the consistency of the data.

[0098] The contact book generation system includes a history unit that stores the revision history in a database. The history unit stores the revision history in the database. For example, it can store information such as the revision date and time, the revision content, and the person who made the revision. By storing the revision history, the history unit makes it possible to check the content of past revisions. For example, it can check what revisions a childcare worker has made in the past. The history unit can also analyze revision trends based on the revision history. For example, it can analyze the revisions frequently made by a specific childcare worker and find areas for improvement. In this way, by storing the revision history, it is possible to check the content of past revisions. Some or all of the above-mentioned processing in the history unit may be performed using, for example, AI, or may be performed without using AI. For example, the history unit can input the revision history into a generation AI and have the generation AI analyze the content of the revisions.

[0099] The address book generation system includes a providing unit that provides the address book via email or a dedicated app. The providing unit provides the address book via email or a dedicated app. For example, a contact book created by a childcare worker can be sent to a parent via email. The address book can also be provided via a dedicated app. Sending email requires mail server settings and an email template. For example, the contents of the contact book can be embedded in an email template and sent to the parent. Using a dedicated app requires an app installation method and user interface design. For example, parents can install the dedicated app and view the address book. By providing the address book via email or a dedicated app, communication with parents can be made more efficient. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without AI. For example, the providing unit may input the contents of the address book into a generation AI and have the generation AI generate an email and distribute it to the app.

[0100] The communication notebook generation system includes a feedback unit that accepts feedback from parents via an online form. The feedback unit accepts feedback from parents via the online form. For example, parents can enter their opinions or questions about the communication notebook into the online form. The online form is designed with various input field types and submit button layouts. For example, a form with a simple design may be provided to allow parents to easily enter information. The feedback unit stores the accepted feedback in a database so that childcare workers can check it. For example, feedback from parents may be displayed in a list so that childcare workers can respond. In this way, accepting feedback from parents improves communication with parents. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit may input data entered into the online form into a generation AI and have the generation AI analyze the feedback.

[0101] The address book generation system includes a security unit that encrypts data or restricts access. The security unit encrypts data or restricts access. For example, address book data can be protected using encryption technologies such as AES encryption or RSA encryption. It can also restrict access to data by performing user authentication and setting access permissions. For example, when a childcare worker or parent accesses address book data, password authentication is performed. The security unit sets encryption and access restrictions to ensure data security. For example, it encrypts address book data to prevent unauthorized access by third parties. It also sets access permissions so that only specific users can access the data. This improves data security by encrypting data and restricting access. Some or all of the above-described processing in the security unit may be performed using AI, for example, or without AI. For example, the security unit can have the generation AI perform encryption settings and access permission settings.

[0102] The input unit can estimate the emotions of the childcare worker using a machine learning algorithm and adjust the timing of input based on the estimated emotions of the childcare worker. The input unit can estimate the emotions of the childcare worker and adjust the timing of input based on the estimated emotions of the childcare worker. For example, if the childcare worker is stressed, the timing of input can be delayed to provide time for relaxation. Also, if the childcare worker is relaxed, the timing of input can be accelerated to allow the childcare worker to input information efficiently. Also, if the childcare worker is tired, the timing of input can be adjusted to allow the childcare worker to complete input in a short time. This improves the efficiency of input work by adjusting the timing of input according to the childcare worker's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 input unit can be performed using, for example, AI, or without AI. For example, the input unit can input the emotion data of the childcare worker into the generation AI and have the generation AI perform emotion estimation.

[0103] The input unit can analyze the childcare worker's past input history and select an input method. The input unit analyzes the childcare worker's past input history and selects the optimal input method. For example, the input unit prioritizes and suggests input methods (voice, text, etc.) that the childcare worker has frequently used in the past. The input unit can also predict and suggest an input method to be used during a specific time period based on the childcare worker's past input history. Furthermore, the input unit can provide an optimal input template based on the content the childcare worker has previously input. In this way, the optimal input method is suggested by analyzing the past input history. Some or all of the above-mentioned processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the childcare worker's past input history data into a generation AI and have the generation AI select the optimal input method.

[0104] The input unit can perform filtering based on the child's current activity status or area of ​​interest. The input unit performs filtering based on the child's current activity status or area of ​​interest. For example, based on the child's current activity, related input items can be preferentially displayed. The input content can also be filtered based on the child's area of ​​interest, allowing appropriate information to be entered. Furthermore, the input content can be customized by referring to the child's past activity history. In this way, appropriate information can be entered by filtering based on the child's current activity status or area of ​​interest. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the child's activity status data to the generation AI and cause the generation AI to perform filtering.

[0105] The input unit can select the optimal input means depending on the input method used by the childcare worker. The input unit selects the optimal input means depending on the input method used by the childcare worker. For example, if the childcare worker uses voice input, voice recognition technology can be used to automatically convert the input content into text. Also, if the childcare worker uses text input, an input support function can be provided to enable efficient information input. Furthermore, if the childcare worker uses images, image recognition technology can be used to automatically analyze the input content. This allows the optimal input means to be selected depending on the childcare worker's input method, thereby making input work more efficient. Some or all of the above-mentioned processing in the input unit may be performed using AI, for example, or may be performed without using AI. For example, the input unit can input the childcare worker's input method data into a generation AI and have the generation AI select the optimal input means.

[0106] The input unit can estimate the emotions of the childcare worker and adjust the design of the input interface based on the estimated emotions of the childcare worker. The input unit can estimate the emotions of the childcare worker and adjust the design of the input interface based on the estimated emotions of the childcare worker. For example, if the childcare worker is nervous, a calm-colored interface can be provided to reduce visual stress. If the childcare worker is having fun, a bright-colored interface can be provided to make input work more enjoyable. Furthermore, if the childcare worker is tired, a simple, highly visible interface can be provided to make input work easier. This makes input work more comfortable by adjusting the design of the input interface according to the childcare worker's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 input unit can be performed using AI, for example, or without AI. For example, the input unit can input the emotion data of the childcare worker into the generation AI and have the generation AI adjust the interface design.

[0107] The input unit can prioritize input of highly relevant information taking into account the geographical location information of the child. The input unit prioritizes input of highly relevant information taking into account the geographical location information of the child. For example, the input unit prioritizes input of relevant information based on activities performed by the child in a specific location. The input unit can also suggest optimal input items based on the geographical location information of the child. Furthermore, the input content can be customized based on places the child has visited in the past. In this way, highly relevant information is prioritized by taking into account the geographical location information of the child. Some or all of the above-described processing in the input unit may be performed using AI, for example, or may be performed without using AI. For example, the input unit can input the geographical location information data of the child to the generation AI and cause the generation AI to prioritize input of highly relevant information.

[0108] The input unit can analyze the social media activity of the childcare worker and input related information. The input unit analyzes the social media activity of the childcare worker and inputs related information. For example, the input unit suggests related input content based on information shared by the childcare worker on social media. The input unit can also analyze the childcare worker's social media activity and provide appropriate input items. Furthermore, related information can be input by referring to the activity of the childcare worker's friends on social media. In this way, related information is input by analyzing the childcare worker's social media activity. Some or all of the above-mentioned processing in the input unit may be performed using AI, for example, or may be performed without using AI. For example, the input unit can input the childcare worker's social media activity data to the generation AI and cause the generation AI to input related information.

[0109] The input unit can customize the input method by reflecting the childcare worker's past feedback. The input unit customizes the input method by reflecting the childcare worker's past feedback. For example, the input unit suggests an optimal input method based on feedback provided by the childcare worker in the past. The input interface can also be customized by reflecting the childcare worker's past feedback. Furthermore, the input content can be automatically adjusted based on the childcare worker's feedback. In this way, the optimal input method is provided by reflecting the childcare worker's past feedback. Some or all of the above-mentioned processing in the input unit may be performed using AI, for example, or may be performed without using AI. For example, the input unit can input the childcare worker's feedback data into the generation AI and have the generation AI customize the input method.

[0110] The generation unit can estimate the emotions of the childcare worker and adjust the expression style of the generated sentences based on the estimated emotions of the childcare worker. The generation unit can estimate the emotions of the childcare worker and adjust the expression style of the generated sentences based on the estimated emotions of the childcare worker. For example, if the childcare worker is relaxed, the generation unit can generate sentences using gentle expressions. If the childcare worker is in a hurry, the generation unit can generate sentences that are concise and to the point. Furthermore, if the childcare worker is excited, the generation unit can generate sentences using emotional expressions. In this way, appropriate sentences are generated by adjusting the expression style of the sentences according to the emotions of the childcare worker. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the generation unit can be performed using AI, for example, or without AI. For example, the generation unit can input the emotion data of the childcare worker into the generation AI and cause the generation AI to adjust the expression style of the sentences.

[0111] The generation unit can adjust the level of detail of the sentences based on the importance of the children's activities. The generation unit adjusts the level of detail of the sentences based on the importance of the children's activities. For example, for important activities, sentences including detailed descriptions can be generated. For everyday activities, sentences including concise descriptions can be generated. For special events, sentences including detailed descriptions and impressions can be generated. In this way, appropriate sentences are generated by adjusting the level of detail of the sentences based on the importance of the children's activities. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the children's activity data into the generation AI and cause the generation AI to adjust the level of detail of the sentences.

[0112] The generation unit can apply different generation algorithms depending on the category of the child. The generation unit applies different generation algorithms depending on the category of the child. For example, different generation algorithms can be applied depending on age to generate appropriate sentences. Different generation algorithms can also be applied depending on the activity content to generate appropriate sentences. Furthermore, different generation algorithms can be applied depending on the characteristics of the child to generate appropriate sentences. In this way, appropriate sentences are generated by applying different generation algorithms depending on the category of the child. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input child category data into the generation AI and cause the generation AI to apply different generation algorithms.

[0113] The generation unit can improve the accuracy of generation by referring to the childcare worker's past generation results. The generation unit improves the accuracy of generation by referring to the childcare worker's past generation results. For example, the generation accuracy can be improved by referring to sentences generated by the childcare worker in the past. The generation unit can also analyze the childcare worker's past generation results and apply the optimal generation algorithm. Furthermore, the generation accuracy can be improved based on the childcare worker's feedback. In this way, the generation accuracy can be improved by referring to the childcare worker's past generation results. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the childcare worker's past generation result data into the generation AI and cause the generation AI to improve the generation accuracy.

[0114] The generation unit can estimate the emotions of the childcare worker and adjust the length of the sentences to be generated based on the estimated emotions of the childcare worker. The generation unit can estimate the emotions of the childcare worker and adjust the length of the sentences to be generated based on the estimated emotions of the childcare worker. For example, if the childcare worker is relaxed, the generation unit can generate longer sentences with detailed explanations. If the childcare worker is in a hurry, the generation unit can generate short sentences that are concise and to the point. Furthermore, if the childcare worker is excited, the generation unit can generate sentences using emotional expressions. In this way, appropriate sentences can be generated by adjusting the length of the sentences according to the emotions of the childcare worker. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, the generation AI. For example, the generation unit can input the emotion data of the childcare worker into the generation AI and have the generation AI adjust the length of the sentences.

[0115] The generation unit can determine the generation priority based on the time of submission of the children's activities. The generation unit determines the generation priority based on the time of submission of the children's activities. For example, it prioritizes generating sentences for activities with an approaching submission deadline. It is also possible to postpone generating sentences for activities with a distant submission deadline. It is also possible to generate sentences with special care for activities whose submission deadline has passed. In this way, by determining the generation priority based on the time of submission of the children's activities, appropriate sentences are generated. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input data on the time of submission of the children into the generation AI and have the generation AI determine the generation priority.

[0116] The generation unit can adjust the order of generation based on the relevance of the children. The generation unit adjusts the order of generation based on the relevance of the children. For example, sentences are generated preferentially based on the relevance of the children's activities. The generation order can also be adjusted based on the importance of the children's activities. Furthermore, the generation order can be adjusted based on the frequency of the children's activities. In this way, appropriate sentences are generated by adjusting the order of generation based on the relevance of the children. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input relevance data of the children into the generation AI and cause the generation AI to adjust the order of generation.

[0117] The generation unit can adjust the use of technical terminology in the generation according to the childcare worker's level of expertise. The generation unit adjusts the use of technical terminology in the generation according to the childcare worker's level of expertise. For example, if the childcare worker's level of expertise is high, sentences that use a lot of technical terminology can be generated. Also, if the childcare worker's level of expertise is low, sentences that use simple expressions can be generated. Furthermore, sentences that use appropriate technical terminology can be generated according to the childcare worker's level of expertise. In this way, appropriate sentences are generated by adjusting the use of technical terminology according to the childcare worker's level of expertise. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the childcare worker's level of expertise data into the generation AI and have the generation AI adjust the use of technical terminology.

[0118] The confirmation unit can estimate the childcare worker's emotions and adjust the confirmation method based on the estimated childcare worker's emotions. The confirmation unit can estimate the childcare worker's emotions and adjust the confirmation method based on the estimated childcare worker's emotions. For example, if the childcare worker is relaxed, a detailed confirmation method can be provided. If the childcare worker is in a hurry, a simple confirmation method can be provided. Furthermore, if the childcare worker is excited, a confirmation method using expressive expressions can be provided. This adjusts the confirmation method according to the childcare worker's emotions, thereby improving the efficiency of the confirmation work. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 confirmation unit can be performed using AI, for example, or without AI. For example, the confirmation unit can input the childcare worker's emotion data into the generation AI and have the generation AI adjust the confirmation method.

[0119] The confirmation unit can select the optimal confirmation method by referring to the childcare worker's past confirmation history. The confirmation unit selects the optimal confirmation method by referring to the childcare worker's past confirmation history. For example, the confirmation unit suggests the optimal confirmation method based on confirmation methods used by the childcare worker in the past. The confirmation unit can also analyze the childcare worker's past confirmation history and provide the optimal confirmation method. Furthermore, the confirmation method can be customized based on the childcare worker's feedback. In this way, the optimal confirmation method is provided by referring to the childcare worker's past confirmation history. Some or all of the above-mentioned processing in the confirmation unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation unit can input the childcare worker's confirmation history data into the generation AI and have the generation AI select the optimal confirmation method.

[0120] The confirmation unit can customize the confirmation content based on the child's current situation. The confirmation unit customizes the confirmation content based on the child's current situation. For example, the confirmation content is customized based on the child's current activity status. The confirmation content can also be adjusted by referring to the child's past activity history. Furthermore, the confirmation content can be customized according to the child's characteristics. In this way, appropriate confirmation is performed by customizing the confirmation content based on the child's current situation. Some or all of the above-mentioned processing in the confirmation unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation unit can input the child's current situation data into the generation AI and have the generation AI customize the confirmation content.

[0121] The confirmation unit can improve the confirmation method by reflecting the feedback from the childcare worker. The confirmation unit improves the confirmation method by reflecting the feedback from the childcare worker. For example, the confirmation method is improved based on the feedback from the childcare worker. The confirmation unit can also provide an optimal confirmation method by referring to the childcare worker's past feedback. Furthermore, the confirmation content can be customized by reflecting the feedback from the childcare worker. In this way, the confirmation method is improved by reflecting the feedback from the childcare worker. Some or all of the above-mentioned processing in the confirmation unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation unit can input the feedback data from the childcare worker into the generation AI and have the generation AI improve the confirmation method.

[0122] The confirmation unit can estimate the emotions of the childcare worker and determine the priority of confirmation based on the estimated emotions of the childcare worker. The confirmation unit can estimate the emotions of the childcare worker and determine the priority of confirmation based on the estimated emotions of the childcare worker. For example, if the childcare worker is relaxed, detailed confirmation can be prioritized. Also, if the childcare worker is in a hurry, important confirmation items can be prioritized. Furthermore, if the childcare worker is tired, simple confirmation can be prioritized. This makes confirmation work more efficient by determining the priority of confirmation based on the emotions of the childcare worker. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 confirmation unit can be performed using AI, for example, or without AI. For example, the confirmation unit can input the emotion data of the childcare worker into the generation AI and have the generation AI determine the priority of confirmation.

[0123] The confirmation unit can select the optimal confirmation method taking into account the child's geographical location information. The confirmation unit selects the optimal confirmation method taking into account the child's geographical location information. For example, the confirmation unit provides relevant confirmation content based on activities the child has performed in a specific location. The confirmation unit can also suggest the optimal confirmation method based on the child's geographical location information. Furthermore, the confirmation content can be customized based on places the child has visited in the past. In this way, the optimal confirmation method is provided by taking into account the child's geographical location information. Some or all of the above-mentioned processing in the confirmation unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation unit can input the child's geographical location information data into the generation AI and cause the generation AI to select the optimal confirmation method.

[0124] The confirmation unit can analyze the social media activity of the childcare worker and suggest confirmation content. The confirmation unit analyzes the social media activity of the childcare worker and suggest confirmation content. For example, the confirmation unit suggests related confirmation content based on information shared by the childcare worker on social media. The confirmation unit can also analyze the childcare worker's social media activity and provide appropriate confirmation items. Furthermore, the confirmation unit can suggest related confirmation content based on the activity of the childcare worker's friends on social media. In this way, related confirmation content is suggested by analyzing the childcare worker's social media activity. Some or all of the above-mentioned processing in the confirmation unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation unit can input the childcare worker's social media activity data into a generation AI and have the generation AI execute the suggestion of confirmation content.

[0125] The confirmation unit can customize the confirmation method by reflecting the childcare worker's past feedback. The confirmation unit customizes the confirmation method by reflecting the childcare worker's past feedback. For example, the confirmation unit proposes an optimal confirmation method based on feedback provided by the childcare worker in the past. The confirmation interface can also be customized by reflecting the childcare worker's past feedback. Furthermore, the confirmation content can be automatically adjusted based on the childcare worker's feedback. In this way, the optimal confirmation method is provided by reflecting the childcare worker's past feedback. Some or all of the above-mentioned processing in the confirmation unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation unit can input the childcare worker's feedback data into the generation AI and have the generation AI customize the confirmation method.

[0126] The output unit can estimate the emotions of the childcare worker and adjust the output method based on the estimated emotions of the childcare worker. The output unit can estimate the emotions of the childcare worker and adjust the output method based on the estimated emotions of the childcare worker. For example, if the childcare worker is relaxed, a detailed output method can be provided. If the childcare worker is in a hurry, a concise output method can be provided. Furthermore, if the childcare worker is excited, an output method using expressive expressions can be provided. This adjusts the output method according to the emotions of the childcare worker, thereby improving the efficiency of the output work. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 output unit can be performed using AI, for example, or without AI. For example, the output unit can input the emotion data of the childcare worker to the generation AI and have the generation AI adjust the output method.

[0127] The output unit can select the optimal output method by referring to the childcare worker's past output history. The output unit selects the optimal output method by referring to the childcare worker's past output history. For example, the output unit suggests the optimal output method based on output methods used by the childcare worker in the past. The output unit can also analyze the childcare worker's past output history and provide the optimal output method. Furthermore, the output method can be customized based on the childcare worker's feedback. In this way, the optimal output method is provided by referring to the childcare worker's past output history. Some or all of the above-mentioned processing in the output unit may be performed using AI, for example, or may be performed without using AI. For example, the output unit can input the childcare worker's output history data to a generation AI and have the generation AI select the optimal output method.

[0128] The output unit can customize the output content based on the child's current situation. The output unit customizes the output content based on the child's current situation. For example, the output content is customized based on the child's current activity status. The output content can also be adjusted by referring to the child's past activity history. Furthermore, the output content can be customized according to the child's characteristics. In this way, appropriate output is produced by customizing the output content based on the child's current situation. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the child's current situation data to the generation AI and have the generation AI customize the output content.

[0129] The output unit can improve the output method by reflecting the feedback from the childcare worker. The output unit improves the output method by reflecting the feedback from the childcare worker. For example, the output method is improved based on the feedback from the childcare worker. The output unit can also provide the optimal output method by referring to the childcare worker's past feedback. Furthermore, the output content can be customized by reflecting the feedback from the childcare worker. In this way, the output method is improved by reflecting the feedback from the childcare worker. Some or all of the above-mentioned processing in the output unit may be performed using AI, for example, or may be performed without using AI. For example, the output unit can input the feedback data from the childcare worker into the generation AI and have the generation AI improve the output method.

[0130] The output unit can estimate the emotions of the childcare worker and determine output priorities based on the estimated emotions of the childcare worker. The output unit can estimate the emotions of the childcare worker and determine output priorities based on the estimated emotions of the childcare worker. For example, if the childcare worker is relaxed, detailed output can be prioritized. Also, if the childcare worker is in a hurry, important output items can be prioritized. Furthermore, if the childcare worker is tired, concise output can be prioritized. This allows output work to be performed more efficiently by determining output priorities based on the emotions of the childcare worker. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the output unit can be performed using, for example, an AI, or without an AI. For example, the output unit can input the emotion data of the childcare worker to the generation AI and have the generation AI determine the output priorities.

[0131] The output unit can select the optimal output method taking into account the child's geographical location information. The output unit selects the optimal output method taking into account the child's geographical location information. For example, the output unit provides relevant output content based on activities performed by the child in a specific location. The output unit can also suggest the optimal output method based on the child's geographical location information. Furthermore, the output content can be customized based on places the child has visited in the past. In this way, the optimal output method is provided by taking into account the child's geographical location information. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the child's geographical location information data to a generation AI and cause the generation AI to select the optimal output method.

[0132] The output unit can analyze the social media activity of the childcare worker and suggest output content. The output unit analyzes the social media activity of the childcare worker and suggest output content. For example, the output unit suggests related output content based on information shared by the childcare worker on social media. The output unit can also analyze the childcare worker's social media activity and provide appropriate output items. Furthermore, the output unit can suggest related output content by referring to the activity of the childcare worker's friends on social media. In this way, related output content is suggested by analyzing the childcare worker's social media activity. Some or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the childcare worker's social media activity data into a generation AI and have the generation AI suggest output content.

[0133] The output unit can customize the output method by reflecting the childcare worker's past feedback. The output unit customizes the output method by reflecting the childcare worker's past feedback. For example, the output unit suggests an optimal output method based on feedback provided by the childcare worker in the past. The output interface can also be customized by reflecting the childcare worker's past feedback. Furthermore, the output content can be automatically adjusted based on the childcare worker's feedback. In this way, the optimal output method is provided by reflecting the childcare worker's past feedback. Some or all of the above-mentioned processing in the output unit may be performed using AI, for example, or may be performed without using AI. For example, the output unit can input the childcare worker's feedback data into a generation AI and have the generation AI customize the output method.

[0134] The reception unit can estimate the emotions of the childcare worker and adjust the voice input and photo attachment methods based on the estimated emotions of the childcare worker. The reception unit can estimate the emotions of the childcare worker and adjust the voice input and photo attachment methods based on the estimated emotions of the childcare worker. For example, if the childcare worker is relaxed, detailed voice input and photo attachment methods can be provided. If the childcare worker is in a hurry, concise voice input and photo attachment methods can be provided. Furthermore, if the childcare worker is excited, voice input and photo attachment methods using expressive voice input and photo attachment methods can be provided. This improves the efficiency of input work by adjusting the voice input and photo attachment methods according to the emotions of the childcare worker. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the reception unit can be performed, for example, using AI or without AI. For example, the reception unit can input the emotional data of the childcare worker into the generation AI and have the generation AI adjust the voice input and photo attachment method.

[0135] The reception unit can select the optimal reception method by referring to the childcare worker's past input history. The reception unit selects the optimal reception method by referring to the childcare worker's past input history. For example, the reception unit suggests the optimal reception method based on the reception methods used by the childcare worker in the past. The reception unit can also analyze the childcare worker's past input history and provide the optimal reception method. Furthermore, the reception method can be customized based on the childcare worker's feedback. In this way, the optimal reception method is provided by referring to the childcare worker's past input history. Some or all of the above-mentioned processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit can input the childcare worker's input history data into the generation AI and have the generation AI select the optimal reception method.

[0136] The reception unit can customize the reception content based on the current situation of the child. The reception unit customizes the reception content based on the current situation of the child. For example, the reception content is customized based on the current activity status of the child. The reception content can also be adjusted by referring to the child's past activity history. Furthermore, the reception content can be customized according to the characteristics of the child. In this way, appropriate reception can be performed by customizing the reception content based on the child's current situation. Some or all of the above-mentioned processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit can input the child's current situation data into the generation AI and have the generation AI customize the reception content.

[0137] The reception unit can estimate the emotions of the childcare worker and determine the priority of reception based on the estimated emotions of the childcare worker. The reception unit can estimate the emotions of the childcare worker and determine the priority of reception based on the estimated emotions of the childcare worker. For example, if the childcare worker is relaxed, detailed reception can be prioritized. Also, if the childcare worker is in a hurry, important reception items can be prioritized. Furthermore, if the childcare worker is tired, brief reception can be prioritized. This allows reception work to be made more efficient by determining the priority of reception based on the emotions of the childcare worker. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 can be performed using, for example, AI, or without AI. For example, the reception unit can input the emotion data of the childcare worker into the generation AI and have the generation AI determine the priority of reception.

[0138] The reception unit can select the optimal reception method taking into account the geographical location information of the child. The reception unit selects the optimal reception method taking into account the geographical location information of the child. For example, the reception unit provides relevant reception content based on activities performed by the child in a specific location. The reception unit can also suggest the optimal reception method based on the geographical location information of the child. Furthermore, the reception content can be customized based on places the child has visited in the past. In this way, the optimal reception method is provided by taking into account the geographical location information of the child. Some or all of the above-mentioned processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit can input the geographical location information data of the child into the generation AI and cause the generation AI to select the optimal reception method.

[0139] The reception unit can analyze the social media activity of the childcare worker and suggest the content of the reception. The reception unit analyzes the social media activity of the childcare worker and suggest the content of the reception. For example, the reception unit suggests related content of the reception based on information shared by the childcare worker on social media. The reception unit can also analyze the childcare worker's social media activity and provide appropriate reception items. Furthermore, the reception unit can suggest related content of the reception based on the activity of the childcare worker's friends on social media. In this way, related content of the reception is suggested by analyzing the childcare worker's social media activity. Some or all of the above-mentioned processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit can input the childcare worker's social media activity data into a generation AI and have the generation AI execute the suggestion of content of the reception.

[0140] The reference unit can estimate the emotions of the childcare worker and select data to reference based on the estimated emotions of the childcare worker. The reference unit can estimate the emotions of the childcare worker and select data to reference based on the estimated emotions of the childcare worker. For example, if the childcare worker is relaxed, detailed data can be referenced. If the childcare worker is in a hurry, concise data can be referenced. Furthermore, if the childcare worker is excited, emotionally rich data can be referenced. In this way, appropriate data can be referenced by selecting data to reference based on the emotions of the childcare worker. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can 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 reference unit can be performed using AI, for example, or without AI. For example, the reference unit can input the emotion data of the childcare worker to the generation AI and have the generation AI select the data to reference.

[0141] The reference unit can maintain the consistency of current data by referencing past data. The reference unit maintains the consistency of current data by referencing past data. For example, the reference unit checks the consistency of current data based on past data. The reference unit can also check the consistency of current data by referencing past data. Furthermore, the accuracy of current data can be checked based on past data. In this way, the consistency of current data is maintained by referring to past data. Some or all of the above-mentioned processing in the reference unit may be performed using AI, for example, or may be performed without using AI. For example, the reference unit can input past data into the generation AI and have the generation AI check the consistency of the current data.

[0142] The reference unit can select the optimal reference method by referring to the childcare worker's past reference history. The reference unit selects the optimal reference method by referring to the childcare worker's past reference history. For example, the reference unit can suggest the optimal reference method based on reference methods used by the childcare worker in the past. The reference unit can also analyze the childcare worker's past reference history and provide the optimal reference method. Furthermore, the reference method can be customized based on the childcare worker's feedback. In this way, the optimal reference method is provided by referring to the childcare worker's past reference history. Some or all of the above-mentioned processing in the reference unit may be performed using AI, for example, or may be performed without using AI. For example, the reference unit can input the childcare worker's reference history data into a generation AI and have the generation AI select the optimal reference method.

[0143] The reference unit can estimate the emotions of the childcare worker and adjust the frequency of reference based on the estimated emotions of the childcare worker. The reference unit can estimate the emotions of the childcare worker and adjust the frequency of reference based on the estimated emotions of the childcare worker. For example, if the childcare worker is relaxed, the reference unit can frequently reference data. If the childcare worker is in a hurry, the reference unit can also reference the minimum amount of data necessary. Furthermore, if the childcare worker is excited, the reference unit can frequently reference emotional data. In this way, by adjusting the frequency of reference according to the emotions of the childcare worker, data can be referenced at an appropriate frequency. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 reference unit can be performed using, for example, AI, or without AI. For example, the reference unit can input the emotion data of the childcare worker to the generation AI and have the generation AI adjust the frequency of reference.

[0144] The reference unit can weight the reference data based on the time of submission of the children's activities. The reference unit weights the reference data based on the time of submission of the children's activities. For example, for activities with an approaching submission deadline, data can be referenced preferentially. For activities with a distant submission deadline, data can also be referenced later. Furthermore, for activities whose submission deadline has passed, data can be referenced with special care. In this way, by weighting the reference data based on the time of submission of the children's activities, appropriate data can be referenced. Some or all of the above-mentioned processing in the reference unit may be performed using AI, for example, or may be performed without using AI. For example, the reference unit can input data on the time of submission of the children to the generation AI and cause the generation AI to weight the reference data.

[0145] The reference unit can adjust the reference method by reflecting the feedback from the childcare worker. The reference unit adjusts the reference method by reflecting the feedback from the childcare worker. For example, the reference method is improved based on the feedback from the childcare worker. The reference unit can also provide an optimal reference method by referring to the childcare worker's past feedback. Furthermore, the reference content can be customized by reflecting the feedback from the childcare worker. In this way, the reference method is adjusted by reflecting the feedback from the childcare worker. Some or all of the above-mentioned processing in the reference unit may be performed using AI, for example, or may be performed without using AI. For example, the reference unit can input the feedback data from the childcare worker into the generation AI and have the generation AI adjust the reference method.

[0146] The history unit can estimate the emotions of the childcare worker and adjust the method for saving the revision history based on the estimated emotions of the childcare worker. The history unit can estimate the emotions of the childcare worker and adjust the method for saving the revision history based on the estimated emotions of the childcare worker. For example, if the childcare worker is relaxed, a detailed revision history can be saved. If the childcare worker is in a hurry, a concise revision history can be saved. Furthermore, if the childcare worker is excited, an emotional revision history can be saved. This allows appropriate saving by adjusting the method for saving the revision history according to the emotions of the childcare worker. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can 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 history unit can be performed using, for example, an AI, or without an AI. For example, the history unit can input the emotion data of the childcare worker into the generation AI and cause the generation AI to adjust the method for saving the revision history.

[0147] The history unit can select the optimal storage method by referring to the childcare worker's past revision history. The history unit selects the optimal storage method by referring to the childcare worker's past revision history. For example, the history unit suggests the optimal storage method based on the storage methods used by the childcare worker in the past. The history unit can also analyze the childcare worker's past revision history and provide the optimal storage method. Furthermore, the storage method can be customized based on the childcare worker's feedback. In this way, the optimal storage method is provided by referring to the childcare worker's past revision history. Some or all of the above-mentioned processing in the history unit may be performed using AI, for example, or may be performed without using AI. For example, the history unit can input the childcare worker's revision history data into the generation AI and have the generation AI select the optimal storage method.

[0148] The history unit can customize the stored content based on the child's current situation. The history unit customizes the stored content based on the child's current situation. For example, the stored content is customized based on the child's current activity status. The stored content can also be adjusted by referring to the child's past activity history. Furthermore, the stored content can be customized according to the child's characteristics. In this way, appropriate storage is performed by customizing the stored content based on the child's current situation. Some or all of the above-mentioned processing in the history unit may be performed using AI, for example, or may be performed without using AI. For example, the history unit can input the child's current situation data into the generation AI and have the generation AI customize the stored content.

[0149] The history unit can estimate the emotions of the childcare worker and determine the priority of history storage based on the estimated emotions of the childcare worker. The history unit can estimate the emotions of the childcare worker and determine the priority of history storage based on the estimated emotions of the childcare worker. For example, if the childcare worker is relaxed, detailed history storage can be prioritized. Also, if the childcare worker is in a hurry, important history storage can be prioritized. Furthermore, if the childcare worker is tired, brief history storage can be prioritized. This allows the efficiency of history storage work by determining the priority of history storage based on the emotions of the childcare worker. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 history unit can be performed using AI, for example, or without AI. For example, the history unit can input the emotion data of the childcare worker into the generation AI and have the generation AI determine the priority of history storage.

[0150] The history unit can select the optimal storage method taking into account the child's geographical location information. The history unit selects the optimal storage method taking into account the child's geographical location information. For example, the history unit stores related history based on activities performed by the child in a specific location. The history unit can also suggest the optimal storage method based on the child's geographical location information. Furthermore, the storage content can be customized based on places the child has visited in the past. In this way, the optimal storage method is provided by taking into account the child's geographical location information. Some or all of the above-described processing in the history unit may be performed using AI, for example, or may be performed without using AI. For example, the history unit can input the child's geographical location information data into the generation AI and cause the generation AI to select the optimal storage method.

[0151] The history unit can analyze the childcare worker's social media activity and suggest content to be saved. The history unit can analyze the childcare worker's social media activity and suggest content to be saved. For example, the history unit saves related history based on information shared by the childcare worker on social media. The history unit can also analyze the childcare worker's social media activity and suggest appropriate saved items. Furthermore, the history unit can save related history by referring to the activity of the childcare worker's friends on social media. In this way, related saved content is suggested by analyzing the childcare worker's social media activity. Some or all of the above-mentioned processing in the history unit may be performed using, for example, AI, or may be performed without using AI. For example, the history unit can input the childcare worker's social media activity data into a generation AI and have the generation AI suggest saved content.

[0152] The providing unit can estimate the childcare worker's emotions and adjust the method of providing the communication notebook based on the estimated childcare worker's emotions. The providing unit can estimate the childcare worker's emotions and adjust the method of providing the communication notebook based on the estimated childcare worker's emotions. For example, if the childcare worker is relaxed, a detailed communication notebook can be provided. If the childcare worker is in a hurry, a concise communication notebook can be provided. Furthermore, if the childcare worker is excited, a communication notebook using expressive expressions can be provided. This adjusts the method of providing the communication notebook according to the childcare worker's emotions, thereby improving the efficiency of the providing work. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the providing unit can be performed using AI, for example, or without AI. For example, the providing unit can input the childcare worker's emotion data into the generation AI and cause the generation AI to adjust the method of providing the communication notebook.

[0153] The provision unit can select the optimal provision method by referring to the childcare worker's past provision history. The provision unit selects the optimal provision method by referring to the childcare worker's past provision history. For example, the optimal provision method is suggested based on provision methods used by the childcare worker in the past. The provision unit can also analyze the childcare worker's past provision history and provide the optimal provision method. Furthermore, the provision method can be customized based on the childcare worker's feedback. In this way, the optimal provision method is provided by referring to the childcare worker's past provision history. Some or all of the above-mentioned processing in the provision unit may be performed using AI, for example, or may be performed without using AI. For example, the provision unit can input the childcare worker's provision history data into the generation AI and cause the generation AI to select the optimal provision method.

[0154] The providing unit can customize the content to be provided based on the current situation of the child. The providing unit customizes the content to be provided based on the current situation of the child. For example, the providing unit customizes the content to be provided based on the current activity status of the child. The providing unit can also adjust the content to be provided by referring to the child's past activity history. Furthermore, the providing unit can customize the content to be provided according to the characteristics of the child. In this way, by customizing the content to be provided based on the current situation of the child, appropriate content is provided. Some or all of the above-mentioned processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input the current situation data of the child into the generating AI and cause the generating AI to customize the content to be provided.

[0155] The provision unit can improve the provision method by reflecting the feedback from the childcare worker. The provision unit improves the provision method by reflecting the feedback from the childcare worker. For example, the provision method is improved based on the feedback from the childcare worker. The optimal provision method can also be provided by referring to the childcare worker's past feedback. Furthermore, the provision content can be customized by reflecting the feedback from the childcare worker. In this way, the provision method is improved by reflecting the feedback from the childcare worker. Some or all of the above-mentioned processing in the provision unit may be performed using AI, for example, or may be performed without using AI. For example, the provision unit can input the feedback data from the childcare worker into the generation AI and cause the generation AI to improve the provision method.

[0156] The providing unit can estimate the emotions of the childcare worker and determine the priority of provision based on the estimated emotions of the childcare worker. The providing unit can estimate the emotions of the childcare worker and determine the priority of provision based on the estimated emotions of the childcare worker. For example, if the childcare worker is relaxed, detailed provision can be prioritized. Also, if the childcare worker is in a hurry, important provision items can be prioritized. Furthermore, if the childcare worker is tired, concise provision can be prioritized. This allows the provision work to be performed more efficiently by determining the priority of provision based on the emotions of the childcare worker. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 can be performed using, for example, AI, or without AI. For example, the providing unit can input the emotion data of the childcare worker into the generation AI and have the generation AI determine the priority of provision.

[0157] The provision unit can select the optimal provision method by taking into account the geographical location information of the child. The provision unit selects the optimal provision method by taking into account the geographical location information of the child. For example, related provision content is provided based on activities performed by the child in a specific location. The optimal provision method can also be suggested based on the geographical location information of the child. Furthermore, the provision content can be customized based on places the child has visited in the past. In this way, the optimal provision method is provided by taking into account the geographical location information of the child. Some or all of the above-mentioned processing in the provision unit may be performed using AI, for example, or may be performed without using AI. For example, the provision unit can input the geographical location information data of the child into the generation AI and cause the generation AI to select the optimal provision method.

[0158] The provision unit can analyze the social media activity of the childcare worker and suggest content to be provided. The provision unit analyzes the social media activity of the childcare worker and suggest content to be provided. For example, the provision unit suggests related content to be provided based on information shared by the childcare worker on social media. The provision unit can also analyze the childcare worker's social media activity and provide appropriate content to be provided. Furthermore, the provision unit can also suggest related content to be provided by referring to the activity of the childcare worker's friends on social media. In this way, related content to be provided is suggested by analyzing the childcare worker's social media activity. Some or all of the above-mentioned processing in the provision unit may be performed using AI, for example, or may be performed without using AI. For example, the provision unit can input the childcare worker's social media activity data into a generation AI and have the generation AI execute the suggestion of content to be provided.

[0159] The provision unit can customize the provision method by reflecting the childcare worker's past feedback. The provision unit customizes the provision method by reflecting the childcare worker's past feedback. For example, the provision unit proposes an optimal provision method based on feedback provided by the childcare worker in the past. The provision interface can also be customized by reflecting the childcare worker's past feedback. Furthermore, the provision content can be automatically adjusted based on the childcare worker's feedback. In this way, the optimal provision method is provided by reflecting the childcare worker's past feedback. Some or all of the above-mentioned processing in the provision unit may be performed using AI, for example, or may be performed without using AI. For example, the provision unit can input the childcare worker's feedback data into the generation AI and cause the generation AI to customize the provision method.

[0160] The feedback unit can estimate the parent's emotion and adjust the feedback acceptance method based on the estimated parent's emotion. The feedback unit can estimate the parent's emotion and adjust the feedback acceptance method based on the estimated parent's emotion. For example, if the parent is relaxed, a detailed feedback acceptance method can be provided. If the parent is in a hurry, a concise feedback acceptance method can be provided. Furthermore, if the parent is excited, a feedback acceptance method using expressive expressions can be provided. This adjusts the feedback acceptance method according to the parent's emotion, thereby improving the efficiency of the feedback acceptance process. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 feedback unit can be performed using AI, for example, or without AI. For example, the feedback unit can input parent's emotion data into the generation AI and cause the generation AI to adjust the feedback acceptance method.

[0161] The feedback unit can select the optimal reception method by referring to the parent's past feedback history. The feedback unit selects the optimal reception method by referring to the parent's past feedback history. For example, the feedback unit may suggest the optimal reception method based on feedback reception methods used by the parent in the past. The feedback unit may also analyze the parent's past feedback history and provide the optimal reception method. Furthermore, the reception method may be customized based on the parent's feedback. In this way, the optimal reception method is provided by referring to the parent's past feedback history. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit may input the parent's feedback history data into the generation AI and cause the generation AI to select the optimal reception method.

[0162] The feedback unit can customize the acceptance content based on the current situation of the child. The feedback unit customizes the acceptance content based on the current situation of the child. For example, the acceptance content is customized based on the current activity status of the child. The acceptance content can also be adjusted by referring to the child's past activity history. Furthermore, the acceptance content can also be customized according to the characteristics of the child. In this way, appropriate acceptance is performed by customizing the acceptance content based on the child's current situation. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input the child's current situation data into the generation AI and cause the generation AI to customize the acceptance content.

[0163] The feedback unit can estimate the parent's emotions and determine the priority of feedback based on the estimated parent's emotions. The feedback unit can estimate the parent's emotions and determine the priority of feedback based on the estimated parent's emotions. For example, if the parent is relaxed, detailed feedback can be given priority. Also, if the parent is in a hurry, important feedback items can be given priority. Furthermore, if the parent is tired, brief feedback can be given priority. This allows the priority of feedback to be determined according to the parent's emotions, thereby streamlining the feedback process. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the feedback unit can be performed using AI, for example, or without AI. For example, the feedback unit can input parent's emotion data into the generation AI and have the generation AI determine the priority of feedback.

[0164] The feedback unit can select the optimal reception method by taking into account the geographical location information of the guardian. The feedback unit selects the optimal reception method by taking into account the geographical location information of the guardian. For example, the feedback unit receives related feedback content based on activities performed by the guardian in a specific location. The optimal reception method can also be suggested based on the geographical location information of the guardian. Furthermore, the reception content can be customized based on places the guardian has visited in the past. In this way, the optimal reception method is provided by taking into account the geographical location information of the guardian. Some or all of the above-described processing in the feedback unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback unit can input the geographical location information data of the guardian into the generation AI and cause the generation AI to select the optimal reception method.

[0165] The feedback unit can analyze the parent's social media activity to suggest acceptance content. The feedback unit analyzes the parent's social media activity to suggest acceptance content. For example, the feedback unit suggests relevant feedback content based on information shared by the parent on social media. The feedback unit can also analyze the parent's social media activity to provide appropriate feedback items. Furthermore, the feedback unit can suggest relevant feedback content by referring to the activity of the parent's friends on social media. In this way, relevant acceptance content is suggested by analyzing the parent's social media activity. Some or all of the above-mentioned processing in the feedback unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback unit can input the parent's social media activity data into a generation AI and cause the generation AI to suggest acceptance content.

[0166] The security unit can estimate the emotions of the childcare worker and adjust the data encryption method based on the estimated emotions of the childcare worker. The security unit can estimate the emotions of the childcare worker and adjust the data encryption method based on the estimated emotions of the childcare worker. For example, if the childcare worker is relaxed, a detailed encryption method can be provided. If the childcare worker is in a hurry, a simple encryption method can be provided. Furthermore, if the childcare worker is excited, an encryption method using expressive expressions can be provided. This improves data security by adjusting the data encryption method according to the emotions of the childcare worker. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 security unit can be performed using AI, for example, or without AI. For example, the security unit can input the emotion data of the childcare worker into the generation AI and have the generation AI adjust the data encryption method.

[0167] The security unit can select the optimal setting method by referring to the childcare worker's past security history. The security unit selects the optimal setting method by referring to the childcare worker's past security history. For example, the security unit can suggest the optimal setting method based on security settings used by the childcare worker in the past. The security unit can also analyze the childcare worker's past security history and provide the optimal setting method. Furthermore, the security settings can be customized based on the childcare worker's feedback. In this way, the optimal setting method is provided by referring to the childcare worker's past security history. Some or all of the above-mentioned processing in the security unit may be performed using AI, for example, or may be performed without using AI. For example, the security unit can input the childcare worker's security history data into a generation AI and have the generation AI select the optimal setting method.

[0168] The security unit can customize the settings based on the current situation of the child. The security unit customizes the settings based on the current situation of the child. For example, the security settings are customized based on the current activity status of the child. The security settings can also be adjusted by referring to the child's past activity history. Furthermore, the security settings can be customized according to the characteristics of the child. In this way, appropriate security settings are set by customizing the settings based on the current situation of the child. Some or all of the above-mentioned processing in the security unit may be performed using, for example, AI, or may be performed without using AI. For example, the security unit can input the child's current situation data into a generation AI and have the generation AI customize the settings.

[0169] The security unit can estimate the emotions of the childcare worker and prioritize security settings based on the estimated emotions of the childcare worker. The security unit can estimate the emotions of the childcare worker and prioritize security settings based on the estimated emotions of the childcare worker. For example, if the childcare worker is relaxed, detailed security settings can be prioritized. Also, if the childcare worker is in a hurry, important security settings can be prioritized. Furthermore, if the childcare worker is tired, simple security settings can be prioritized. This makes the security settings work more efficient by prioritizing security settings based on the emotions of the childcare worker. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 security unit can be performed using AI, for example, or without AI. For example, the security unit can input the emotion data of the childcare worker into the generation AI and have the generation AI determine the priority of security settings.

[0170] The security unit can select the optimal setting method by taking into account the geographical location information of the child. The security unit selects the optimal setting method by taking into account the geographical location information of the child. For example, relevant security settings can be provided based on activities performed by the child in a specific location. The security unit can also suggest optimal security settings based on the geographical location information of the child. Furthermore, security settings can be customized based on places the child has visited in the past. In this way, the optimal setting method is provided by taking into account the geographical location information of the child. Some or all of the above-mentioned processing in the security unit may be performed using AI, for example, or may be performed without using AI. For example, the security unit can input the geographical location information data of the child into a generation AI and have the generation AI select the optimal setting method.

[0171] The security unit can analyze the social media activity of the childcare worker and suggest settings. The security unit can analyze the social media activity of the childcare worker and suggest settings. For example, the security unit can suggest relevant security settings based on information shared by the childcare worker on social media. The security unit can also analyze the childcare worker's social media activity and provide appropriate security settings. Furthermore, the security unit can suggest relevant security settings based on the activity of the childcare worker's friends on social media. In this way, relevant settings are suggested by analyzing the childcare worker's social media activity. Some or all of the above-mentioned processing in the security unit may be performed using AI, for example, or may be performed without using AI. For example, the security unit can input the childcare worker's social media activity data into a generation AI and have the generation AI suggest settings. === Hard Collateral 1-1 === Each of the multiple elements including the input unit, generation unit, confirmation unit, and output unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the input unit allows a childcare worker to input details of children's activities and observation results using the reception device 38 of the smart device 14. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and a generation AI analyzes the input information and generates appropriate sentences. The confirmation unit is realized by the control unit 46A of the smart device 14, and the childcare worker confirms and corrects the generated sentences. The output unit provides the final communication notebook to the parent / guardian using the output device 40 of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements including the input unit, generation unit, confirmation unit, and output unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the input unit allows a childcare worker to voice-input details of a child's activities and observations using the microphone 238 of the smart glasses 214. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and a generation AI analyzes the input information and generates appropriate sentences. The confirmation unit is realized by the control unit 46A of the smart glasses 214, and the childcare worker confirms and corrects the generated sentences. The output unit provides the final communication notebook to the guardian using the speaker 240 of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the input unit, generation unit, confirmation unit, and output unit described above is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the input unit allows a childcare worker to voice-input details of a child's activities and observations using the microphone 238 of the headset terminal 314. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and a generation AI analyzes the input information and generates appropriate sentences. The confirmation unit is realized by the control unit 46A of the headset terminal 314, and the childcare worker confirms and corrects the generated sentences. The output unit provides the final communication notebook to the parent / guardian using the display 343 of the headset terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the input unit, generation unit, confirmation unit, and output unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the input unit allows a nursery teacher to voice-input details of a child's activities and observations using the microphone 238 of the robot 414. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and a generation AI analyzes the input information and generates appropriate sentences. The confirmation unit is realized by the control unit 46A of the robot 414, and the nursery teacher confirms and corrects the generated sentences. The output unit provides the final communication notebook to the guardian using the speaker 240 of the robot 414.

[0172] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0173] The communication notebook generation system can estimate the emotions of the childcare worker and adjust the tone of the generated text based on the estimated emotions. For example, if the childcare worker is relaxed, the system can generate text with a soft tone. If the childcare worker is in a hurry, the system can generate text with a concise and to-the-point tone. Furthermore, if the childcare worker is excited, the system can generate text with an emotional tone. This allows appropriate text to be generated by adjusting the tone of the text according to the childcare worker's emotions. Emotion estimation is achieved using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using AI or without AI. For example, the generation unit may input the childcare worker's emotional data into the generation AI and have the generation AI adjust the tone of the text.

[0174] The contact notebook generation system can analyze the childcare worker's past input history and customize the input method. For example, it can prioritize and suggest input methods (voice, text, etc.) that the childcare worker has frequently used in the past. It can also predict and suggest the input method to be used during a specific time period based on the childcare worker's past input history. It can also provide an optimal input template based on the content the childcare worker has previously entered. In this way, the optimal input method is suggested by analyzing the past input history. Some or all of the above-mentioned processing in the input unit may be performed using AI, or may be performed without using AI. For example, the input unit can input the childcare worker's past input history data into the generation AI and have the generation AI select the optimal input method.

[0175] The communication notebook generation system can estimate the emotions of a childcare worker and adjust the design of the input interface based on the estimated emotions. For example, if the childcare worker is nervous, a calm-colored interface can be provided to reduce visual stress. If the childcare worker is having fun, a bright-colored interface can be provided to make input work more enjoyable. Furthermore, if the childcare worker is tired, a simple, highly visible interface can be provided to make input work easier. This makes input work more comfortable by adjusting the design of the input interface according to the childcare worker's emotions. Emotion estimation is achieved using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI or a multimodal generation AI. Some or all of the above-described processing in the input unit can be performed using AI or without AI. For example, the input unit can input the childcare worker's emotional data into a generation AI and have the generation AI adjust the interface design.

[0176] The communication notebook generation system can customize the input method by reflecting the childcare worker's past feedback. For example, the optimal input method is suggested based on feedback provided by the childcare worker in the past. The input interface can also be customized by reflecting the childcare worker's past feedback. Furthermore, the input content can be automatically adjusted based on the childcare worker's feedback. In this way, the optimal input method is provided by reflecting the childcare worker's past feedback. Some or all of the above-mentioned processing in the input unit may be performed using AI, or may be performed without using AI. For example, the input unit can input the childcare worker's feedback data into the generation AI and have the generation AI customize the input method.

[0177] The communication notebook generation system can estimate the emotions of the childcare worker and adjust the length of the generated sentences based on the estimated emotions. For example, if the childcare worker is relaxed, it can generate longer sentences with detailed explanations. If the childcare worker is in a hurry, it can generate short, concise sentences that get to the point. Furthermore, if the childcare worker is excited, it can generate sentences using expressive expressions. This allows appropriate sentences to be generated by adjusting the length of the sentences according to the childcare worker's emotions. Emotion estimation is achieved using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI or a multimodal generation AI. Some or all of the above-described processing in the generation unit can be performed using AI or without AI. For example, the generation unit can input the childcare worker's emotion data into the generation AI and have the generation AI adjust the length of the sentences.

[0178] The communication notebook generation system can improve the accuracy of generation by referring to the childcare worker's past generation results. For example, the generation accuracy can be improved by referring to sentences generated by the childcare worker in the past. The childcare worker's past generation results can also be analyzed and the optimal generation algorithm can be applied. Furthermore, the generation accuracy can be improved based on the childcare worker's feedback. In this way, the generation accuracy can be improved by referring to the childcare worker's past generation results. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the childcare worker's past generation result data into the generation AI and have the generation AI improve the generation accuracy.

[0179] The communication notebook generation system can estimate the emotions of the childcare worker and adjust the confirmation method based on the estimated emotions. For example, if the childcare worker is relaxed, a detailed confirmation method can be provided. If the childcare worker is in a hurry, a simple confirmation method can be provided. Furthermore, if the childcare worker is excited, a confirmation method using expressive expressions can be provided. This allows the confirmation method to be adjusted according to the childcare worker's emotions, making the confirmation process more efficient. Emotion estimation is achieved using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI or a multimodal generation AI. Some or all of the above-mentioned processing in the confirmation unit can be performed using AI or without AI. For example, the confirmation unit can input the childcare worker's emotion data into the generation AI and have the generation AI adjust the confirmation method.

[0180] The communication notebook generation system can select the optimal verification method by referring to the childcare worker's past verification history. For example, it can suggest the optimal verification method based on the verification methods used by the childcare worker in the past. It can also analyze the childcare worker's past verification history and provide the optimal verification method. It can also customize the verification method based on the childcare worker's feedback. In this way, the optimal verification method is provided by referring to the childcare worker's past verification history. Some or all of the above-mentioned processing in the verification unit may be performed using AI, or may be performed without using AI. For example, the verification unit can input the childcare worker's verification history data into the generation AI and have the generation AI select the optimal verification method.

[0181] The communication notebook generation system can estimate the emotions of the childcare worker and adjust the output method based on the estimated emotions. For example, if the childcare worker is relaxed, a detailed output method can be provided. If the childcare worker is in a hurry, a concise output method can be provided. Furthermore, if the childcare worker is excited, an output method using expressive expressions can be provided. This allows the output method to be adjusted according to the childcare worker's emotions, thereby improving the efficiency of the output work. Emotion estimation is achieved using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI or a multimodal generation AI. Some or all of the above-mentioned processing in the output unit can be performed using AI or without AI. For example, the output unit can input the childcare worker's emotion data into the generation AI and have the generation AI adjust the output method.

[0182] The communication notebook generation system can select the optimal output method by referring to the childcare worker's past output history. For example, it can suggest the optimal output method based on the output methods used by the childcare worker in the past. It can also analyze the childcare worker's past output history and provide the optimal output method. It can also customize the output method based on the childcare worker's feedback. In this way, the optimal output method is provided by referring to the childcare worker's past output history. Some or all of the above-mentioned processing in the output unit may be performed using AI, or may be performed without using AI. For example, the output unit can input the childcare worker's output history data into the generation AI and have the generation AI select the optimal output method.

[0183] The processing flow of the second embodiment will be briefly explained below.

[0184] Step 1: In the input section, the nursery teacher inputs the details of the children's activities and observations. For example, they can input information such as what kind of play the children did and how they grew. Step 2: The generation unit uses the generation AI to analyze the information input by the input unit and generate appropriate sentences. For example, based on the information input by the nursery teacher, the generation AI generates a sentence such as, "Today, X-chan enjoyed playing with blocks. She tried to create a new shape and succeeded." Step 3: In the confirmation unit, a childcare worker confirms and corrects the sentences generated by the generation unit. For example, a childcare worker confirms the sentences generated by the generation AI and makes corrections as necessary. Step 4: The output unit outputs the text corrected by the confirmation unit as the final contact list. For example, the corrected text can be printed, saved in PDF format, or sent by email.

[0185] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0186] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0187] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0188] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0189] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0190] 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.

[0191] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0192] 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.

[0193] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0194] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0195] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0196] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0197] 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.

[0198] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0199] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0200] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0201] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0202] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0203] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0204] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0205] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0206] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0207] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0208] 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.

[0209] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0210] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0211] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0212] 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.

[0213] 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.

[0214] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0215] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0216] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0217] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0218] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0219] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0220] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0221] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0222] 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.

[0223] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0224] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0225] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0226] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0227] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0228] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0229] 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.

[0230] 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.

[0231] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0232] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0233] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0234] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0235] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0236] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0237] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0238] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0239] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0240] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0241] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0242] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0243] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0244] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0245] 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.

[0246] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0247] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0248] 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.

[0249] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0250] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0251] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0252] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0253] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0254] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0255] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0256] [Explanation of symbols]

[0257] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. An input section where nursery teachers input the details of the children's activities and observation results; a generation unit that analyzes the information input by the input unit and generates a sentence; a confirmation unit in which a childcare worker confirms and corrects the sentences generated by the generation unit; an output unit that outputs the sentence corrected by the confirmation unit as a final contact book. A system characterized by:

2. Equipped with a reception section that accepts voice input or photo attachments 2. The system of claim 1.

3. It has a reference section that references past data to maintain data consistency.

2. The system of claim 1.

4. Equipped with a history section that stores revision history in a database 2. The system of claim 1.

5. Equipped with a provision unit that provides contacts via email or a dedicated app 2. The system of claim 1.

6. Provides a feedback section that accepts feedback from parents via an online form 2. The system of claim 1.

7. Equipped with a security unit that encrypts data or restricts access 2. The system of claim 1.

8. The input unit The emotions of the childcare worker are estimated using a machine learning algorithm, and the timing of input is adjusted based on the estimated emotions of the childcare worker.

2. The system of claim 1.

9. The input unit Analyze the childcare worker's past input history and select the input method 2. The system of claim 1.

Images