Childcare support system

Abstract

A childcare support system suitable for grasping information based on the personality, etc., of a childcare recipient is provided. [Solution] A generation AI server 100 registers activity information related to the number of contacts between childcare workers and children, as well as activity information related to the amount of activity of multiple children and the number of contacts with others, in a knowledge base 12. A request including a request to generate information about children is then input to an AI model 10, and information output from the AI ​​model 10 is obtained in response to the request by referencing the activity information in the knowledge base 12. This makes it possible to obtain information based on the number of contacts between childcare workers and the amount and number of contacts of children, making it possible to grasp information based on the individuality and needs of children more effectively than before.

Description

[Technical Field]

[0001] The present invention relates to a system for supporting childcare, and more particularly to a childcare support system suitable for grasping information based on the personality of a childcare recipient. [Background technology]

[0002] The declining birthrate is a serious problem. For this reason, the government is promoting various measures to address the declining birthrate and restore the birthrate. The "Children and Families Agency" will be established in 2023, and proactive measures such as increased family benefits and improved childcare services are planned. The "Any Child Attends Daycare System," which will be implemented from fiscal year 2024, will allow preschool children to attend daycare centers even if both parents are not working. Currently, daycare centers are generally only available to families certified as needing childcare, such as those with working parents or special circumstances such as illness or caregiving. In contrast, the "Any Child Attends Daycare System" is designed to allow "anyone" to use daycare centers on an hourly basis, regardless of parental employment status. A model project already underway last year targets daycare centers with available spaces and certified childcare centers. While there is strong demand for this system from parents, many daycare centers have expressed concerns about its implementation, citing insufficient resources, such as securing childcare workers.

[0003] Against this background, digital transformation (DX) for childcare centers has been developed and introduced to the market. For example, the technology described in Non-Patent Document 1 is known as DX for childcare centers.

[0004] The technology described in Non-Patent Document 1 has functions such as attendance and entry / exit management, parental contact, lesson plan and diary creation, shift management, billing management, childcare documentation, communication book, extended childcare fee calculation, temperature and infection checks, near misses, growth and health records, emergency contact, surveys, photo sharing and sales, multiple facility management, security, school lunch and menu management, and bus operation management. [Prior art documents] [Patent documents]

[0005] [Non-Patent Document 1] "Childcare ICT System CoDMON | For nurseries and educational facilities | Industry share No. 1", [online], August 9, 2024, CoDMON Co., Ltd., [Searched August 9, 2024], Internet<URL:https: / / www.codmon.com / > Summary of the Invention [Problem to be solved by the invention]

[0006] Under the "Any Child Can Attend" system, childcare workers are responsible for different children each day, making it difficult to provide childcare that suits each child's individuality and needs. For example, when creating a daily childcare plan, it is desirable to take into account the individuality of each child on that day. However, since different children attend each day, it is difficult to take into account the individuality of each child on that day, and an appropriate childcare plan cannot be created. The technology described in Non-Patent Document 1 cannot solve this problem.

[0007] Therefore, the present invention has been made with a focus on the unresolved issues inherent in such conventional technology, and aims to provide a childcare support system that is suitable for grasping information based on the personalities of the children being cared for. [Means for solving the problem]

[0008] [Invention 1] In order to achieve the above object, the childcare support system of Invention 1 comprises a registration means for registering activity information regarding the number of contacts between a caregiver and a care recipient, or activity information regarding the care recipient's activity level or number of contacts with others, in a knowledge base that can be referenced by an AI model; an input means for inputting a request to the AI ​​model, including a request to generate information about the care recipient; and an acquisition means for acquiring information output from the AI ​​model in response to the request by referencing the activity information in the knowledge base.

[0009] With this configuration, the registration means registers activity information in the knowledge base. Then, the input means inputs a request including a request to generate information about a childcare recipient to the AI ​​model, and the acquisition means acquires information output from the AI ​​model in response to the request. At this time, the AI ​​model references the activity information in the knowledge base.

[0010] Here, the input means includes, for example, directly inputting a request to the AI ​​model, or indirectly inputting the request to the AI ​​model via processing, function, device, network, or other means. The same applies hereinafter to the childcare support system of Invention 2.

[0011] The acquisition means may include, for example, directly acquiring the output information of the AI ​​model, or indirectly acquiring the output information of the AI ​​model via processing, functions, devices, networks, or other means. The same applies hereinafter to the childcare support system of Invention 2.

[0012] Furthermore, the activity information relating to the activity amount includes, for example, activity information relating to one or more activity amounts, activity information relating to the activity amount itself, or activity information relating to statistics of the activity amount. Similarly, the activity information relating to the number of contacts includes, for example, activity information relating to one or more number of contacts, activity information relating to the number of contacts itself, or activity information relating to statistics of the number of contacts. The same applies hereinafter to the childcare support system of Invention 2.

[0013] Furthermore, the request to generate information about a childcare recipient includes, for example, a request to generate answer information to a question about the childcare recipient. The same applies to the childcare support system of Invention 2 below.

[0014] Furthermore, generation requests include, for example, explicit requests to generate information about the childcare recipient, and indirect requests to generate information about the childcare recipient. Explicit requests include, for example, a request such as "Please generate information about the childcare recipient." Indirect requests include, for example, a generation request that includes a question about the childcare recipient to request the generation of answer information to a question about the childcare recipient. This is because, in an AI model, answer information is generated when a question about the childcare recipient is entered as a prompt. The same applies below to the childcare support system of Invention 2.

[0015] The activity information and requests can be configured in any format, such as vector data. The same applies to the childcare support system of the second invention.

[0016] Furthermore, the knowledge base stores activity information by any means and at any time, and may store activity information in advance, or may store activity information by external input or the like while the system is operating, without storing activity information in advance.

[0017] Furthermore, this system may be realized as a single device, apparatus, terminal, or other device, or as a network system in which multiple devices, apparatus, terminals, or other devices are communicatively connected. In the latter case, each component may belong to any of the multiple devices as long as they are communicatively connected. The same applies to the childcare support system of Invention 2 below.

[0018] [Invention 2] Furthermore, the childcare support system of Invention 2 comprises an input means for inputting a request to the AI ​​model, which includes activity information regarding the number of contacts between the caregiver and the care recipient, or activity information regarding the care recipient's activity level or number of contacts with others, and a request to generate information about the care recipient, and an acquisition means for acquiring information output from the AI ​​model in response to the request.

[0019] With this configuration, the input means inputs a request to the AI ​​model that includes activity information and a request to generate information about the child, and the acquisition means acquires information output from the AI ​​model in response to the request.

[0020] [Invention 3] Furthermore, in the childcare support system of Invention 3, in the childcare support system of either Invention 1 or 2, the request to generate information about the childcare recipient is a request to generate information about planning, evaluating, or improving collective childcare to be implemented collectively for multiple childcare recipients.

[0021] With this configuration, the input means inputs a request to the AI ​​model, including a request to generate information regarding the planning, evaluation, or improvement of group childcare, and the acquisition means acquires information output from the AI ​​model in response to the request.

[0022] Here, planning, evaluation, or improvement of group childcare includes, for example, planning, evaluation, or improvement of childcare recipients who received group childcare, or planning, evaluation, or improvement of childcare providers who provided group childcare.

[0023] [Invention 4] Furthermore, in the childcare support system of Invention 4, in the childcare support system of either Invention 1 or 2, the request to generate information about the childcare recipient is a request to generate information about the planning, evaluation, or improvement of measures implemented for the development, growth, or growth of the childcare recipient.

[0024] With this configuration, the input means inputs a request to the AI ​​model, including a request to generate information regarding the planning, evaluation, or improvement of a measure, and the acquisition means acquires information output from the AI ​​model in response to the request.

[0025] Here, planning, evaluation or improvement of a policy includes, for example, a plan, evaluation or improvement by a childcare provider of a policy that the childcare provider has implemented, or a plan, evaluation or improvement by a childcare recipient who has used the policy.

[0026] [Invention 5] Furthermore, in the childcare support system of Invention 5, in the childcare support system of either Invention 1 or 2, the request to generate information about the childcare recipient is a request to generate safety management information about the safety management of the childcare recipient.

[0027] With this configuration, the input means inputs a request including a request for generating safety management information to the AI ​​model, and the acquisition means acquires information output from the AI ​​model in response to the request. [Effects of the Invention]

[0028] As explained above, according to the childcare support system of Invention 1 or 2, it is possible to obtain information based on the number of times the caregiver has contact with the care recipient, or the amount of activity of the care recipient or the number of times the care recipient has contact with others, and therefore it is possible to grasp information based on the personality and needs of the care recipient, etc., compared to conventional systems.

[0029] Furthermore, according to the childcare support system of Invention 3, information regarding the planning, evaluation, or improvement of group childcare can be obtained, making it easier to plan, evaluate, or improve group childcare.

[0030] Furthermore, according to the childcare support system of Invention 4, it is possible to obtain information relating to the planning, evaluation or improvement of measures, which makes it easier to plan, evaluate or improve measures.

[0031] Furthermore, according to the childcare support system of Invention 5, safety management information regarding the safety management of the childcare recipients can be obtained, making safety management easier. [Brief explanation of the drawings]

[0032] [Figure 1] FIG. 1 is a diagram showing an outline of a service according to an embodiment of the present invention. [Figure 2] 1 is a block diagram showing a configuration of a network system according to an embodiment of the present invention; [Figure 3] FIG. 2 is a diagram illustrating the hardware configuration of the generation AI server 100. [Figure 4] 10 is a flowchart showing a knowledge data registration process. [Figure 5] FIG. 10 is a diagram showing the data structure of play menu information. [Figure 6] 10 is a flowchart showing an answer information generation process. [Figure 7] A diagram showing the data structure when generating group childcare planning information. [Figure 8] A diagram showing the data structure when generating group childcare planning information. [Figure 9] FIG. 10 is a diagram showing the data structure when generating evaluation information for group childcare. [Figure 10] FIG. 10 is a diagram showing the data structure when generating evaluation information for group childcare. [Figure 11] A diagram showing the data structure when generating improvement information for collective childcare. [Figure 12] FIG. 10 is a diagram showing a data structure when generating plan information for development measures. [Figure 13] FIG. 10 is a diagram showing a data structure when generating evaluation information of development measures. [Figure 14] FIG. 10 is a diagram showing a data structure when generating child safety management information. [Figure 15] FIG. 10 is a diagram showing a data structure when generating health management information for a child. [Figure 16] FIG. 10 is a diagram showing a data structure when generating child diet management information. [Figure 17] FIG. 10 is a diagram showing a data structure when generating emergency response information related to children's health. DETAILED DESCRIPTION OF THE INVENTION

[0033] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will now be described with reference to Figures 1 to 17.

[0034] First, the configuration of this embodiment will be described. [Service Overview] FIG. 1 is a diagram showing an outline of a service according to this embodiment.

[0035] As shown in FIG. 1, the generation AI server 100 is configured to include an AI (Artificial Intelligence) model 10 and a knowledge base 12 that registers data that the AI ​​model 10 refers to for inference.

[0036] When the generation AI server 100 receives basic information, environmental information, qualitative information, quantitative information, or image information from a nursery school terminal 200 installed in the nursery school, a nursery teacher terminal 210 used by a nursery teacher, or a wearable device 220 worn by a child attending the nursery school (hereinafter simply referred to as "child"), the generation AI server 100 registers the received information in a knowledge base 12. Knowledge data such as childcare guidelines are also registered in the knowledge base 12.

[0037] When the generation AI server 100 receives a request including a request to generate information about a child from the childcare worker terminal 210 or the like, it causes the AI ​​model 10 to refer to the data in the knowledge base 12 in response to the received request, and causes the AI ​​model 10 to generate answer information related to the generation request.The generated answer information is then sent to the childcare worker terminal 210 or the like.

[0038] On the childcare worker terminal 210, etc., the childcare worker can ask questions via a UI (User Interface) or voice. The childcare worker terminal 210, etc., sends a request to the generation AI server 100, including a request to generate answer information for the question input via the UI or voice. Then, when answer information is received in response to the request, the received answer information is displayed.

[0039] The generation AI server 100 performs a predetermined process to have the AI ​​model 10 refer to the data in the knowledge base 12 and generate information about the child. Then, based on the generated information, the generation AI server 10 sends breaking news, signals, alerts, and other notifications to the childcare worker terminal 210, etc.

[0040] When the childcare worker terminal 210 etc. receives a breaking news report, a signal, an alert, or other notification, it displays the received notification.

[0041] [Network System] Next, the configuration of the network system according to this embodiment will be described.

[0042] FIG. 2 is a block diagram showing the configuration of a network system according to this embodiment. As shown in Fig. 2, the Internet 199 is connected to a generation AI server 100, one or more nursery school terminals 200, one or more childcare worker terminals 210, and one or more wearable devices 220. As for allocation, for example, a nursery school terminal 200 is assigned to each nursery school, a childcare worker terminal 210 is assigned to each childcare worker, and a wearable device 220 is assigned to each childcare worker and each child.

[0043] [Generation AI Server 100] Next, the configuration of the generation AI server 100 will be described. FIG. 3 is a diagram showing the hardware configuration of the generation AI server 100. As shown in FIG.

[0044] As shown in Figure 3, the generation AI server 100 is composed of a CPU (Central Processing Unit) 30 that controls calculations and the entire system based on a control program, a ROM (Read Only Memory) 32 that stores the control program, etc. of the CPU 30 in a predetermined area, a RAM (Random Access Memory) 34 that stores data read from the ROM 32, etc. and the calculation results required in the calculation process of the CPU 30, and an I / F (Interface) 38 that mediates the input and output of data to external devices.These are connected to each other and capable of sending and receiving data via a bus 39, which is a signal line for transferring data.

[0045] The I / F 38 is connected to external devices such as an input device 40 consisting of a keyboard, mouse, etc. that can input data as a human interface, a memory device 42 that stores data, tables, etc. as files, a display device 44 that displays a screen based on an image signal, and a signal line for connecting to the Internet 199.

[0046] The storage device 42 stores the AI ​​model 10 and the knowledge base 12 . The AI ​​model 10 is an AI model trained on a large data set and is a highly versatile model capable of performing a variety of tasks. For example, a large language model can be used as the AI ​​model 10. A large language model is a deep learning model that pre-trains a language model, which models human spoken language based on its occurrence probability, from a massive amount of data. When a prompt is input, the large language model statistically infers the probability of generating the next word from the sentence included in the input prompt and outputs the inference result. For example, known technologies described on the internet sites "https: / / chatgpt-lab.com / n / n418d3aa56f0b" and "https: / / agirobots.com / chatgpt-mechanism-and-problem / " can be used as the large language model. More specifically, for example, Titan Text G1 - Express, Titan Text G1 - Lite, Titan Image Generator G1, Titan Embeddings G1 - Text, Titan Embeddings Text V2, Titan Multimodal Embeddings G1, Claude, Claude Instant, Claude 3 Sonnet, Claude 3 Haiku, Claude 3 Opus, Jurassic-2 Mid, Jurassic-2 Ultra, Command, Command Light, Command R, Command R+, Embed English, Embed Multilingual, Llama 2 Chat 13B, Llama 2 Chat 70B, Llama 2 13B, Llama 2 70B, Llama 3 8b Instruct, Llama 3 70b Instruct, Mistral 7B Instruct, Mixtral 8X7B Instruct, Mistral Large, and Stable Diffusion XL can be adopted.

[0047] The knowledge base 12 can register information received from the nursery school terminal 200, the nursery teacher terminal 210, or the wearable device 220. The knowledge base 12 also stores, as knowledge data such as childcare guidelines, (1) information related to the nursery school's childcare guidelines, (2) information related to laws and other rules or standards related to childcare, (3) manual information related to childcare, or (4) emergency response information. The emergency response information includes, for example, (1) health-related emergency response information (e.g., sudden illness, allergy information, injury, difficulty breathing), (2) environmental emergency response information (e.g., fire, earthquake or natural disaster, power outage, gas leak), (3) security-related emergency response information (e.g., intrusion by a suspicious person, kidnapping, missing person), or (4) other emergency response information (e.g., mass infection, sudden illness or shortage of staff).

[0048] [Nursery school terminal 200 and nursery teacher terminal 210] Next, the configurations of the nursery school terminal 200 and the nursery teacher terminal 210 will be described.

[0049] The nursery school terminal 200 and the nursery teacher terminal 210 are configured to have the same hardware configuration as the generation AI server 100. The nursery school terminal 200 and the nursery teacher terminal 210 can be configured as a smartphone or a tablet terminal.

[0050] [Wearable Device 220] Next, the configuration of the wearable device 220 will be described.

[0051] Wearable device 220 is a device that can be worn on the wrist, arm, neck, or other part of the body of a childcare worker or child, and is configured with the same functions as a general computer with a CPU, ROM, RAM, I / F, etc. connected via a bus.

[0052] The wearable device 220 is equipped with a vital sensor and an acceleration sensor, and calculates the wearer's activity level (e.g., number of steps, distance traveled, calories burned, heart rate) based on the detection results of the vital sensor and acceleration sensor, and transmits activity information including the calculated activity level to the generation AI server 100.

[0053] Wearable device 220 is equipped with an RFID (Radio Frequency Identification) tag and reader, and uses the RFID reader to read the RFID tags of other wearable devices 220 present within a predetermined range (for example, within a close distance or personal distance range), calculates the number of contacts between the wearer and other wearers (hereinafter simply referred to as "number of contacts") based on the detection results of the RFID reader, and transmits activity information including the calculated number of contacts to generation AI server 100. The number of contacts with others is an indicator of a child's social interactions (how much they have interacted with other children and caregivers).

[0054] The wearable device 220 is equipped with a radio wave intensity sensor, and based on the detection result of the radio wave intensity sensor, transmits activity information to the generation AI server 100, including the intensity of radio waves used in BLE (Bluetooth Low Energy) communication with a specific wearable device 220 (hereinafter referred to as "BLE intensity"). For example, if a wearable device 220 worn by a childcare worker who is caring for a child is set as a specific wearable device 220, activity information including the BLE intensity for the wearable device 220 worn by the childcare worker can be transmitted to the generation AI server 100. This activity information indicates how far away a child is from the childcare worker and how far the child is from the childcare worker.

[0055] Next, the operation of this embodiment will be described. [Knowledge data registration] First, the case where the generation AI server 100 registers knowledge data will be described.

[0056] FIG. 4 is a flowchart showing the knowledge data registration process. The CPU 30 is comprised of an MPU (Micro-Processing Unit) or the like, and starts a predetermined program stored in a predetermined area of ​​the ROM 32, and executes the knowledge data registration process shown in the flowchart of Fig. 4 in accordance with the program. The knowledge data registration process is executed when a request including a registration request to register knowledge data (hereinafter simply referred to as a "registration request") is received, and when executed by the CPU 30, the process first proceeds to step S100 as shown in Fig. 4.

[0057] In step S100, activity information and other information to be registered are received, and the process proceeds to step S102, where the received activity information and other information are stored in the storage device 42, and the process proceeds to step S104.

[0058] In step S104, the received activity information, etc. is converted into vector data that can be referenced by the AI ​​model 10. The vector data can be generated by a technology (embedding) that converts data including characters, images, sounds, etc. into a numerical vector.

[0059] Next, the process proceeds to step S106, where the converted vector data is registered in the knowledge base 12. At this time, the vector data is registered in association with identification information so that the AI ​​model 10 can refer to specific data in the knowledge base 12. A request to refer to the knowledge base 12 and the identification information can be included in the request, and the AI ​​model 10 can refer to the data in the knowledge base 12 that corresponds to the identification information.

[0060] Examples of identification information include: (1) identification information for identifying a nursery school or a group thereof; (2) identification information for identifying a nursery teacher or a group thereof; (3) identification information for identifying a child or a group thereof; (4) identification information for identifying basic information, environmental information, qualitative information, quantitative information, image information, or other information; (5) identification information for identifying childcare provided to multiple children at once (hereinafter referred to as "group childcare"); (6) identification information for identifying the date, time, period, location, or other information related to the group childcare provided; (7) identification information for identifying a child or group of children who received group childcare; or (8) identification information for identifying measures implemented for the development, growth, or growth of one or more children (e.g., creation of a childcare curriculum, changes to the outdoor or indoor layout of a nursery school) (hereinafter referred to as "developmental measures"). This allows the AI ​​model 10 to reference, using identification information, data from the knowledge base 12, such as (1) data corresponding to a nursery school or a group thereof, (2) data corresponding to a nursery teacher or a group thereof, (3) data corresponding to a child or a group thereof, (4) data corresponding to basic information, environmental information, qualitative information, quantitative information, image information, or other information, (5) data corresponding to group childcare, (6) data corresponding to the date, time, location, or other information related to the implementation of group childcare, (7) data corresponding to a child or a group thereof who received group childcare, or (8) data corresponding to developmental measures.

[0061] When the process of step S106 is completed, the series of processes ends. [Activity information registration] The wearable device 220 transmits a request including activity information on the wearer's activity level, number of contacts, and BLE intensity, as well as a registration request, to the generation AI server 100 at predetermined intervals (e.g., 10 minutes) or at predetermined or arbitrary timing, and the activity information is registered in the knowledge base 12. The activity information is registered in association with the identification information of the childcare worker or child related to the activity information, date and time information when the activity information was acquired, or location information when the activity information was acquired, etc. In this way, activity information of multiple children is registered as knowledge data.

[0062] [Registration of basic information, etc.] The nursery school terminal 200 or the nursery teacher terminal 210 (hereinafter referred to as "nursery teacher terminal 210, etc.") sends a request including basic information, environmental information, qualitative information, quantitative information, image information or other information and a registration request to the generation AI server 100 at predetermined time intervals (for example, every 10 minutes) or at predetermined or arbitrary timing, and the basic information, etc. is registered in the knowledge base 12. The basic information, etc. is registered in association with the identification information of the nursery school, nursery teacher or child related to the basic information, etc., the date and time information when the basic information, etc. was acquired, or the location information when the basic information, etc. was acquired, etc.

[0063] Basic information includes, for example, (1) the name, address, number of staff, number of children, and other information about the attributes of the nursery school; (2) the name, age, sex, and other information about the staff member's nursery school; (3) the name, age, sex, height, weight, temperature, allergy information, vaccination history, medical history, and other information about the staff member's nursery school; (4) information about comments from staff or parents about the child; or (5) information about a child's emergency.

[0064] Examples of environmental information include (1) information about the temperature, humidity, air pressure, wind direction, wind speed, light intensity, noise, sunlight (e.g., ultraviolet light), electromagnetic wave intensity, carbon dioxide concentration, weather, or smell in the nursery school or other environment where childcare is provided, or (2) information about developmental measures. These are obtained by installing temperature sensors or the like in the nursery school or other environment where childcare is provided, and the results of detection by the temperature sensors or the like are acquired on the childcare worker terminal 210 or the like, and a request including the acquired detection results as environmental information is sent to the generation AI server 100.

[0065] Examples of qualitative information (information that is difficult to quantify) include (1) information about behavior (e.g., how to play, how to interact with friends, behavioral characteristics), (2) information about emotions (e.g., expressions of joy, anger, sadness, happiness, etc., expressions of accomplishment, expressions at the time of failure, emotional stability), (3) information about thinking (e.g., problem-solving methods, curiosity, imagination), (4) information about language (e.g., vocabulary, speaking style, comprehension), and (5) information about sociality (e.g., cooperation, consideration, awareness of rules). Note that information that partially overlaps with basic information may be considered qualitative information, or information that does not overlap with basic information may be considered qualitative information.

[0066] Examples of quantitative information (information that can be quantified) include (1) information about development, growth, or development (e.g., height, weight, vocabulary size, and motor skills such as walking, running, and jumping), (2) information about lifestyle habits (e.g., dietary content, dietary intake, sleep time, and play time), (3) information about learning (e.g., number of correct and incorrect answers to questions, number of books read), and (4) information about health (e.g., body temperature, number of visits to medical institutions, medication status, and allergy information). Quantitative information may include information that partially overlaps with activity information, basic information, and environmental information, or information that does not overlap with activity information, basic information, and environmental information.

[0067] FIG. 5 is a diagram showing the data structure of the play menu information. The quantitative information further includes play menu information relating to children's play and their activity levels. The play menu information is configured as a table structure in which one record is registered for each play, as shown in FIG. 5, for example. Each record includes fields for registering the name of the play, a summary of the play, activity elements, play variations, and activity level (for example, an estimated value for the activity level (e.g., number of steps) over 20 minutes). In the example of FIG. 5, seven play menus are registered as play activities for children in the park.

[0068] Image information includes, for example, image information related to behavior, image information related to emotions, image information related to thoughts, image information related to language, image information related to sociality, image information related to development, growth or development, image information related to lifestyle habits, image information related to learning, and image information related to health, corresponding to the above examples of qualitative information and quantitative information.

[0069] [Answer information generation] Next, a case where the generation AI server 100 generates answer information using the AI ​​model 10 will be described.

[0070] FIG. 6 is a flowchart showing the response information generating process. The CPU 30 starts a predetermined program stored in a predetermined area of ​​the ROM 32, and in accordance with the program, executes the answer information generation process shown in the flowchart of Fig. 6. The answer information generation process is executed when a request to generate information about a child is received, and when executed by the CPU 30, the process first proceeds to step S200 as shown in Fig. 6.

[0071] In step S200, a request for generating answer information is received. The request includes a request for generating answer information and parameters. The generation request includes, for example, a request for generating answer information to a question about children, or a request for generating other information about children. The parameters include, for example, a reference request to reference all data or specific data in the knowledge base 12, and in the case of a reference request to reference specific data, identification information for identifying the data.

[0072] Next, the process proceeds to step S202, where a prompt is generated based on the generation request included in the received request to instruct the AI ​​model 10. If the generation request is in the form of a prompt, the generation request is obtained from the received request, and the obtained generation request is used as the prompt.

[0073] Next, the process proceeds to step S204, where the generated prompt is input to the AI ​​model 10. Here, if the received request includes a reference request, the reference request is input to the AI ​​model 10; if the received request includes a reference request and identification information, the reference request and identification information are input to the AI ​​model 10.

[0074] When a prompt is input, the AI ​​model 10 infers answer information from the input prompt, thereby obtaining answer information that matches the learning data and generation request of the AI ​​model 10 as the inference result of the AI ​​model 10.

[0075] When a prompt and a reference request are input, the AI ​​model 10 references all data in the knowledge base 12 based on the input reference request and infers answer information from the input prompt. As a result, the AI ​​model 10 obtains, as an inference result, answer information that matches the learning data of the AI ​​model 10, all data in the knowledge base 12, and the generation request.

[0076] When a prompt, a reference request, and identification information are input, the AI ​​model 10 refers to specific data in the knowledge base 12 based on the input reference request and identification information, and infers answer information from the input prompt. As a result, answer information that matches the learning data of the AI ​​model 10, the specific data in the knowledge base 12, and the generation request is obtained as the inference result of the AI ​​model 10.

[0077] Next, the process proceeds to step S206, where the inference result of the AI ​​model 10 is acquired, and then the process proceeds to step S208, where answer information including the acquired inference result is sent to the terminal that made the request, and the series of processes is terminated.

[0078] [1. Generating planning information for group childcare] 7 and 8 are diagrams showing the data structure when generating group childcare planning information. Figure 7(a) shows the data structure of the request, Figure 7(b) shows the data structure of the information in the knowledge base 12 referenced by the AI ​​model 10, and Figure 7(c) shows the data structure of the response information from the generation AI server 100.

[0079] The first example is an example in which afternoon group childcare plan information is generated from morning information. When a childcare worker wishes to obtain plan information for a group childcare plan, the plan is based on the number of contacts between the childcare worker and the child's activity level and number of contacts. The childcare worker inputs a request for generating plan information on the childcare worker terminal 210 or the like. When the request for generating plan information is input, the childcare worker terminal 210 or the like transmits a request including the input generation request and parameters to the generation AI server 100. For example, as shown in FIG. 7(a), the request includes a generation request "Morning data...Please consider measures" and parameters including a reference request and identification information "Nursery school: Midori-no-oka Nursery School...Information on the nursery school's childcare guidelines." Among these parameters, "Reference Information 1" indicates that the AI ​​model 10 is to reference information from the knowledge base 12 regarding the child's morning attendance at the nursery school, including (1) the child's identification information, (2) the child's name, (3) activity information 1 indicating measurements taken during one hour of free play in the park in the morning, (4) activity information 2 indicating measurements taken during one hour of reading aloud in the nursery school in the morning, and (5) visual inspection comments. Activity information 1 is information about the child's activity level (e.g., number of steps), the number of contacts between the childcare worker and the child. The same is true for activity information 2. Therefore, the information in knowledge base 12 referenced by AI model 10 is configured, for example, as shown in Figure 7(b). Furthermore, "reference information 2" indicates that AI model 10 is to refer to information in knowledge base 12 about the childcare guidelines of the nursery school.

[0080] In response to this request, plan information is obtained from the generation AI server 100. The plan information is configured as shown in FIG. 7(c).

[0081] The second example is an example in which, when free play in the park is performed for 20 minutes, plan information for collective childcare for the remaining 40 minutes is generated.

[0082] When a request for generating plan information is input to the childcare worker terminal 210 or the like, a request including the input generation request and parameters is sent to the generation AI server 100. For example, as shown in FIG. 8(a), the request includes a generation request such as "Regarding one hour of play in the park...please also provide a reason" and parameters such as a reference request and identification information such as "Nursery school: Midori-no-oka Nursery School...play menu information." Among these parameters, "Reference Information 1" refers to information from the knowledge base 12 about free play in the park as a walk out, including (1) the child's identification information, (2) the child's name, (3) activity information 1 indicating the measured values ​​for the first 20 minutes of free play in the park, (4) activity information 2 indicating the actual values ​​for the first 20 minutes of free play in the park in the past, and (5) BLE intensity. Activity information 1 is information about the child's activity level (e.g., number of steps) and the child's number of contacts. Activity information 2 is similar. Therefore, the information in the knowledge base 12 that the AI ​​model 10 refers to is configured, for example, as shown in Figure 8(b). Also, "Reference information 2" indicates that the AI ​​model 10 refers to play menu information among the information in the knowledge base 12.

[0083] In response to this request, plan information is obtained from the generation AI server 100. The plan information is configured as shown in FIG. 8(c).

[0084] [2. Generating evaluation information for bulk childcare] 9 and 10 are diagrams showing the data structures when generating evaluation information for group childcare. Figure 9(a) shows the data structure of the request, Figure 9(b) shows the data structure of the information in the knowledge base 12 referenced by the AI ​​model 10, and Figure 9(c) shows the data structure of the response information from the generation AI server 100.

[0085] The first example is an example of generating collective childcare evaluation information when "tag" is played after 20 minutes of free play in the park.

[0086] When a childcare worker wishes to obtain evaluation information related to a collective childcare evaluation, which is based on the number of contacts between the childcare worker and the child's activity level, the childcare worker inputs a request for generating evaluation information on the childcare worker terminal 210 or the like. When the request for generating evaluation information is input, the childcare worker terminal 210 or the like transmits a request including the input generation request and parameters to the generation AI server 100. For example, as shown in FIG. 9(a), the request includes a generation request such as "20 minutes into the event...please rate" and parameters such as a reference request and identification information such as "Nursery school: Midori-no-oka Nursery School...information about the nursery school's childcare guidelines." Among these parameters, "Reference Information 1" indicates that the AI ​​model 10 is to reference information from the knowledge base 12 about free play in the park as a walk, including (1) the child's identification information, (2) the child's name, (3) activity information 1 indicating measurements taken during the first 20 minutes of free play in the park, (4) activity information 2 indicating measurements taken during the first 60 minutes of free play in the park, and (5) comments from the childcare worker. Activity information 1 is information about the child's activity level (e.g., number of steps) and the number of contacts with the childcare worker. The same is true for activity information 2. Therefore, the information in the knowledge base 12 referenced by the AI ​​model 10 is configured, for example, as shown in Figure 9(b). Furthermore, "reference information 2" indicates that the AI ​​model 10 is to refer to information in the knowledge base 12 that relates to the childcare guidelines of the nursery school.

[0087] In response to this request, evaluation information is obtained from the generation AI server 100. The evaluation information is configured as shown in FIG. 9(c).

[0088] The second example is an example of generating evaluation information regarding evaluations of group childcare conducted continuously for a certain period of time for a specific child.

[0089] When a childcare worker wishes to obtain evaluation information related to a collective childcare evaluation, the evaluation is based on the number of contacts between the childcare worker and the child's activity level and the number of contacts. The childcare worker inputs a request for generating evaluation information on the childcare worker terminal 210 or the like. When the request for generating evaluation information is input, the childcare worker terminal 210 or the like transmits a request including the input generation request and parameters to the generation AI server 100. For example, as shown in FIG. 10(a), the request includes a generation request "Please evaluate the childcare guidelines of the childcare center." The request also includes a reference request and identification information as parameters, such as "Childcare center: Midori-no-oka Nursery School...information related to the childcare guidelines of the childcare center." Among these parameters, "Reference Information 1" indicates that the AI ​​model 10 is to reference information from the knowledge base 12 about free play in the park and reading aloud within the nursery. The information includes (1) the child's identification information, (2) the child's name, (3) the child's age (in months), (4) activity information 1 indicating measurements taken during one hour of free play in the park, and (5) activity information 2 indicating measurements taken during one hour of reading aloud within the nursery. Activity information 1 is information about the child's activity level (e.g., number of steps), the number of contacts with the childcare worker, the number of contacts with the child, and the childcare worker's comments. The same is true for activity information 2. Therefore, the information in knowledge base 12 referenced by AI model 10 is configured, for example, as shown in Figure 10(b). Furthermore, "reference information 2" indicates that AI model 10 refers to information in knowledge base 12 related to the childcare guidelines of the nursery school.

[0090] In response to this request, evaluation information is obtained from the generation AI server 100. The evaluation information is configured as shown in FIG.

[0091] [3. Generating information to improve childcare services] 11 shows the data structure when generating improvement information for batch childcare. (a) shows the data structure of the request, (b) shows the data structure of the information in the knowledge base 12 referenced by the AI ​​model 10, and (c) shows the data structure of the response information from the generation AI server 100.

[0092] When a childcare worker wishes to obtain improvement information related to improvements to childcare services, based on the number of contacts between the childcare worker and the child's activity level, the childcare worker inputs a request for generating improvement information on the childcare worker terminal 210 or the like. When the request for generating improvement information is input, the childcare worker terminal 210 or the like transmits a request including the input generation request and parameters to the generation AI server 100. For example, as shown in FIG. 11(a), the request includes a generation request such as "Please provide the measurement values ​​indicating the results of the execution Do and..." and parameters such as a reference request and identification information such as "Childcare center: Midori-no-oka Nursery School...play menu information." Among these parameters, "Reference Information 1" indicates that the AI ​​model 10 is to reference information from the knowledge base 12 about free play in the park as a walk, including (1) the child's identification information, (2) the child's name, (3) activity information 1 indicating the measurement values ​​for the first 20 minutes of free play in the park, (4) activity information 2 indicating the measurement values ​​for the first 60 minutes of free play in the park, and (5) comments from the childcare worker. Activity information 1 is information about the child's activity level (e.g., number of steps) and the number of contacts with the childcare worker. The same is true for activity information 2. Therefore, the information in knowledge base 12 referenced by AI model 10 is configured, for example, as shown in Figure 11(b). Furthermore, "reference information 2" indicates that AI model 10 refers to information in knowledge base 12 related to the childcare guidelines of the nursery school.

[0093] In response to this request, improvement information is obtained from the generation AI server 100. The improvement information is configured as shown in FIG.

[0094] [4. Generation of development policy planning information] 12A and 12B are diagrams showing data structures when generating planning information for developmental measures: (a) shows the data structure of a request, (b) shows the data structure of information in the knowledge base 12 referenced by the AI ​​model 10, and (c) shows the data structure of response information from the generation AI server 100.

[0095] When a childcare worker wishes to obtain plan information for a developmental program, the plan is based on the number of contacts between the childcare worker and the child's activity level and the number of contacts. The childcare worker inputs a request for generating plan information on the childcare worker terminal 210 or the like. When the request for generating plan information is input, the childcare worker terminal 210 or the like transmits a request including the input generation request and parameters to the generation AI server 100. For example, as shown in FIG. 12(a), the request includes a generation request "Please propose the introduction of an atelier..." and parameters including a reference request and identification information "Nursery school: Midori-no-oka Nursery School...information regarding the nursery school's childcare guidelines." Among these parameters, "Reference Information 1" indicates that the AI ​​model 10 is to reference information from the knowledge base 12 regarding in-school activities, including (1) the child's identification information, (2) the child's name, and (3) activity information indicating measurements from in-school activities before the introduction of the atelier. The activity information includes information regarding the child's activity level (e.g., number of steps), the number of contacts between the childcare worker, and the number of contacts between the child and the child. Therefore, the information in the knowledge base 12 referenced by the AI ​​model 10 is configured, for example, as shown in Figure 12(b). Also, "Reference information 2" indicates that the AI ​​model 10 is to refer to information in the knowledge base 12 that relates to the childcare guidelines of the nursery school.

[0096] In response to this request, plan information is obtained from the generation AI server 100. The plan information is configured as shown in FIG.

[0097] [5. Generating evaluation information for developmental policies] 13A and 13B are diagrams showing data structures when generating evaluation information for developmental measures: (a) shows the data structure of a request, (b) shows the data structure of information in the knowledge base 12 referenced by the AI ​​model 10, and (c) shows the data structure of response information from the generation AI server 100.

[0098] When a childcare worker wishes to obtain evaluation information related to the evaluation of developmental programs, the evaluation is based on the number of contacts between the childcare worker and the child's activity level and number of contacts. The childcare worker inputs a request for generating evaluation information into the childcare worker terminal 210 or the like. When the request for generating evaluation information is input into the childcare worker terminal 210 or the like, a request including the input generation request and parameters is sent to the generation AI server 100. For example, as shown in FIG. 13(a), the request includes a generation request "Please rate Atelier..." and parameters including a reference request and identification information "Nursery school: Midori-no-oka Nursery School...information regarding the nursery school's childcare guidelines." Among these parameters, "Reference Information 1" indicates that the AI ​​model 10 is to reference information from the knowledge base 12 regarding in-school activities, including (1) the child's identification information, (2) the child's name, (3) activity information 1 indicating measurements taken during in-school activities before the introduction of Atelier, (4) activity information 2 indicating measurements taken during in-school activities after the introduction of Atelier, and (5) comments from the childcare worker. Activity information 1 is information about the child's activity level (e.g., number of steps), the number of contacts between the childcare worker and the child. The same is true for activity information 2. Therefore, the information in knowledge base 12 referenced by AI model 10 is configured, for example, as shown in Figure 13(b). Furthermore, "reference information 2" indicates that AI model 10 is to refer to information in knowledge base 12 about the childcare guidelines of the nursery school.

[0099] In response to this request, evaluation information is obtained from the generation AI server 100. The evaluation information is configured as shown in FIG.

[0100] [6. Generating information to improve development policies] When a childcare worker wishes to obtain improvement information related to the improvement of developmental measures, which is based on the number of contacts between the childcare worker and the amount of activity and number of contacts between the childcare worker, the childcare worker inputs a request to generate improvement information on the childcare worker terminal 210. Here, the request, the information in the knowledge base 12 to be referenced, and the response information from the generation AI server 100 can be configured as a data structure similar to that shown in FIG.

[0101] [7. Creation of safety management information] 14 shows the data structure when generating child safety management information: (a) shows the data structure of the request, (b) shows the data structure of the information in the knowledge base 12 referenced by the AI ​​model 10, and (c) shows the data structure of the response information from the generation AI server 100.

[0102] When a childcare worker wishes to obtain safety management information for one or more children, the safety management information is based on the number of contacts between the childcare worker and the child's activity level and number of contacts. The childcare worker inputs a safety management information generation request into the childcare worker terminal 210 or the like. When the safety management information generation request is input into the childcare worker terminal 210 or the like, a request including the input generation request and parameters is sent to the generation AI server 100. For example, as shown in FIG. 14(a), the request includes a generation request such as "Child risk occurs...Please compare and comment." The parameter is a reference request and identification information such as "Childcare center: Midori-no-oka Nursery School...BLE intensity." The "reference information" parameter indicates that the AI ​​model 10 is to reference information from the knowledge base 12 about free play in the park as a walk, including (1) the child's identification information, (2) the child's name, (3) activity information 1 indicating measurements taken during free play in the park, (4) activity information 2 indicating actual values ​​from past free play in the park, and (5) BLE intensity. Activity information 1 is information about the amount of activity of the child (e.g., the number of steps), the number of contacts between the childcare worker and the child. The same is true for activity information 2. Therefore, the information in the knowledge base 12 referenced by the AI ​​model 10 is configured, for example, as shown in FIG. 14(b).

[0103] In response to this request, safety management information is obtained from the generation AI server 100. The safety management information is configured as shown in FIG.

[0104] 8. Generation of Health Management Information 15 shows the data structure when generating child health management information: (a) shows the data structure of a request, (b) shows the data structure of information in the knowledge base 12 referenced by the AI ​​model 10, and (c) shows the data structure of response information from the generation AI server 100.

[0105] When a childcare worker wishes to obtain health management information for one or more children, the childcare worker inputs a request for generating health management information on the childcare worker terminal 210 or the like. When the request for generating health management information is input, the childcare worker terminal 210 or the like transmits a request including the input generation request and parameters to the generation AI server 100. For example, as shown in FIG. 15(a), the request is composed of a generation request "Please tell me about health management precautions" and parameters including a reference request and identification information "Nursery school: Midori-no-oka Nursery School...visual examination and parental comments." Among these parameters, the "reference information" indicates that the AI ​​model 10 is to reference information from the knowledge base 12 at the time of arrival, including (1) the child's identification information, (2) the child's name, (3) the child's temperature, and (4) the visual examination and parental comments. Therefore, the information from the knowledge base 12 referenced by the AI ​​model 10 is configured, for example, as shown in FIG. 15(b).

[0106] In response to this request, health management information is obtained from the generation AI server 100. The health management information is configured as shown in FIG.

[0107] Health management information includes information about children's medication administration. For example, if a child is prescribed medication by a doctor three times a day, a childcare worker administers the one dose of medication to the child after lunch. Childcare workers must pay close attention to not forgetting to administer the medication, not giving the wrong medication to other children, giving the wrong medication, and not missing the timing of administration. However, since different children attend daycare every day, it is difficult to keep track of each child's medication status on each day, making appropriate health management difficult. Therefore, by generating information about the medication administration of one or more children using AI model 10, childcare workers can understand the medication administration status of each child. For example, as shown in Figure 15(b), if the visual examination and parental comment is "Administer medication after lunch (medication request form available)," as shown in Figure 15(c), the information about child medication administration can be obtained as "Ayaka-chan (administer medication after lunch): It is important to administer medication at the correct time. After administering the medication, carefully monitor the child's condition for any changes and keep a record."

[0108] [9. Dietary Management Information] 16 shows the data structure when generating child dietary management information: (a) shows the data structure of a request, (b) shows the data structure of information in the knowledge base 12 referenced by the AI ​​model 10, and (c) shows the data structure of response information from the generation AI server 100.

[0109] When a childcare worker wishes to obtain dietary management information for one or more children, the childcare worker inputs a request for generating dietary management information and image information of the school lunch menu into the childcare worker terminal 210 or the like. When the childcare worker terminal 210 or the like inputs the request for generating dietary management information and image information, a request including the input generation request, parameters, and image information is sent to the generation AI server 100. For example, as shown in FIG. 16(a), the request is composed of a generation request "Is there a risk to my child...? Is there a risk?", a reference request and identification information "Nursery school: Midori-no-oka Nursery School...Allergy information" as parameters, and image information (not shown). Among these parameters, the "reference information" is information about lunchtime in the knowledge base 12, and indicates that the AI ​​model 10 is to reference (1) the child's identification information, (2) the child's name, (3) visual examination and parental comments, and (4) the child's allergy information. Therefore, the information in the knowledge base 12 referenced by the AI ​​model 10 is configured, for example, as shown in FIG. 16(b).

[0110] In response to this request, diet management information is obtained from the generation AI server 100. The diet management information is configured as shown in FIG.

[0111] [10. Generation of emergency response information] 17 shows the data structure when generating emergency response information related to a child's health. Figure 17(a) shows the data structure of a request, Figure 17(b) shows the data structure of information in the knowledge base 12 referenced by the AI ​​model 10, and Figure 17(c) shows the data structure of response information from the generation AI server 100.

[0112] When a childcare worker wishes to obtain emergency response information related to the health of one or more children, the childcare worker inputs a request for generating emergency response information on the childcare worker terminal 210 or the like. When the request for generating emergency response information is input, the childcare worker terminal 210 or the like transmits a request including the input generation request and parameters to the generation AI server 100. For example, as shown in FIG. 17(a), the request includes a generation request such as "Please explain what is happening based on the details of the incident... Share this information." The request also includes a reference request and identification information as parameters, such as "Childcare center: Midori-no-oka Nursery School...Health emergency response information." Among these parameters, "Reference Information 1" indicates that the AI ​​model 10 is to reference information from the knowledge base 12 when an emergency occurs during lunchtime, including (1) the child's identification information, (2) the child's name, (3) the details of the emergency, (4) the child's temperature, (5) visual examination and parental comments, (6) the child's allergy information, and (6) vaccination history. Therefore, the information from the knowledge base 12 referenced by the AI ​​model 10 is configured, for example, as shown in FIG. 17(b). In addition, "Reference Information 2" indicates that the AI ​​model 10 is to refer to health-related emergency response information from the knowledge base 12.

[0113] In response to this request, emergency response information is obtained from the generation AI server 100. The emergency response information is configured as shown in FIG. 17(c).

[0114] Similarly, other emergency response information may include (1) environmental emergency response information, (2) security emergency response information, or (3) other emergency response information.

[0115] [Notification information generation process] Next, a case where the generation AI server 100 generates notification information using the AI ​​model 10 will be described.

[0116] Any of the following configurations can be used to send breaking news, signals, alerts, and other notifications to the childcare worker terminal 210, etc.

[0117] In the first configuration, when a predetermined condition is met, a predetermined prompt and a necessary reference request are input to the AI ​​model 10. Here, the necessary reference request means that a reference request or a reference request and identification information are input when necessary, but not when unnecessary. This is similar to the second to fourth configurations. Then, the inference result of the AI ​​model 10 is acquired, and notification information including the acquired inference result is sent to the childcare worker terminal 210, etc. As the prompt, for example, a prompt corresponding to the request exemplified in the answer information generation process of FIG. 6 (a prompt generated based on the generation request included in the request) can be adopted. As the condition, for example, (1) whether the current date, time, or day of the week is a predetermined date, time, or day; (2) whether the location where the childcare to be provided, the childcare currently being provided, or the childcare that has been completed (hereinafter simply referred to as "childcare") is provided is a predetermined location; (3) whether the childcare worker providing the childcare is a predetermined person or group; (4) whether the childcare has a predetermined content; and (5) whether the child's activity level, number of contacts, or BLE intensity is above or below a predetermined level.

[0118] In the second configuration, a table in which conditions, prompts, and necessary reference requests are associated and registered is stored in the storage device 42, and when a condition in the table is met, the corresponding prompt and necessary reference request are obtained from the table and the obtained prompt and necessary reference request are input to the AI ​​model 10. Then, the inference result of the AI ​​model 10 is obtained, and notification information including the obtained inference result is sent to the childcare worker terminal 210, etc.

[0119] The third configuration inputs a predetermined prompt and a necessary reference request into the AI ​​model 10, and obtains the inference result of the AI ​​model 10. Then, if the inference result satisfies a predetermined condition, notification information including the inference result is sent to the childcare worker terminal 210, etc.

[0120] In the fourth configuration, a table in which conditions, prompts, and necessary reference requests are associated and registered is stored in the storage device 42, the prompts and necessary reference requests are obtained from the table, the obtained prompts and necessary reference requests are input into the AI ​​model 10, and the inference result of the AI ​​model 10 is obtained. Then, if the inference result satisfies the corresponding condition in the table, notification information including the inference result is sent to the childcare worker terminal 210, etc.

[0121] Next, the effects of this embodiment will be described. In this embodiment, activity information regarding the number of contacts by childcare workers and activity information regarding the child's activity level and number of contacts are registered in knowledge base 12, a request including a request to generate information about the child is input to AI model 10, and information output from AI model 10 is obtained in response to the request by referring to the activity information in knowledge base 12.

[0122] This allows us to obtain information based on the number of contacts between childcare workers and the child's activity level and number of contacts, making it possible to grasp information based on the child's personality, needs, etc., more than was previously possible.

[0123] Furthermore, in this embodiment, activity information of a plurality of children is registered in the knowledge base 12.

[0124] This makes it possible to obtain information based on the activity levels and number of contacts of multiple children, making it possible to grasp information based on the personalities of the children when providing childcare for multiple children.

[0125] Furthermore, in this embodiment, the request to generate information about children is a request to generate information about planning, evaluating, or improving group childcare.

[0126] This allows information to be obtained on the planning, evaluation or improvement of group childcare, making it easier to plan, evaluate or improve group childcare.

[0127] Furthermore, in this embodiment, the request to generate information about a child is a request to generate evaluation information about the evaluation of development measures.

[0128] This makes it possible to obtain evaluation information regarding the evaluation of the policy or the evaluation of the policy by childcare workers, making it easier to evaluate the policy or the evaluation of the policy by childcare workers.

[0129] Furthermore, in this embodiment, the request to generate information about children is a request to generate safety management information related to safety management of children.

[0130] This allows safety management information regarding the safety management of children to be obtained, making safety management easier.

[0131] In this embodiment, step S106 corresponds to the registration means of invention 1, step S204 corresponds to the input means of invention 1, and step S206 corresponds to the acquisition means of invention 1.

[0132] [Modification] In the above embodiment and its modifications, the AI ​​model 10 refers to information in the knowledge base 12, but the present invention is not limited to this. Information to be referred to in the knowledge base 12 (for example, activity information, basic information, environmental information, qualitative information, quantitative information, image information, or knowledge data such as childcare guidelines) can be included in the request. This makes the present invention applicable even to a configuration that does not include the knowledge base 12.

[0133] Furthermore, in the above-described embodiment and its variations, the activity information is configured as information regarding the amount of activity, the number of contacts, and the BLE intensity, but is not limited thereto, and can be configured as information regarding one or two elements of the amount of activity, the number of contacts, and the BLE intensity.

[0134] In the above-described embodiment and its modified examples, the AI ​​model 10 is made to refer to activity information relating to the number of contacts of the childcare worker, as in the cases of Figures 7 and 9 to 14, but this is not limiting, and it is also possible not to refer to activity information relating to the number of contacts of the childcare worker. In addition, the AI ​​model 10 is not made to refer to activity information relating to the number of contacts of the childcare worker, as in the cases of Figures 8 and 15 to 17, but it is also possible to refer to activity information relating to the number of contacts of the childcare worker.

[0135] Furthermore, in the above embodiment and its variants, the AI ​​model 10 does not refer to activity information regarding the activity level of the childcare worker, as in the case of Figures 7 to 15, but this is not limited to this, and the AI ​​model 10 can be made to refer to activity information regarding the activity level of the childcare worker.

[0136] In the above-described embodiment and its modifications, the AI ​​model 10 is made to refer to activity information relating to the number of contacts with the child as in the cases of Figures 7, 8, and 11 to 14, but this is not limiting and the AI ​​model 10 may not be made to refer to activity information relating to the number of contacts with the child. In addition, the AI ​​model 10 is not made to refer to activity information relating to the number of contacts with the child as in the cases of Figures 9, 10, and 15 to 17, but this is not limiting and the AI ​​model 10 may be made to refer to activity information relating to the number of contacts with the child.

[0137] In the above-described embodiment and its modified examples, the AI ​​model 10 is made to refer to activity information related to the amount of activity of the child as in the cases of Figures 7 to 14, but this is not limiting and the AI ​​model 10 may not be made to refer to activity information related to the amount of activity of the child. In addition, in the cases of Figures 15 to 17, the AI ​​model 10 is not made to refer to activity information related to the amount of activity of the child, but this is not limiting and the AI ​​model 10 may be made to refer to activity information related to the amount of activity of the child.

[0138] 7 to 14, the AI ​​model 10 references activity information related to the amount of activity or the number of contacts acquired at two different times or places. However, the present invention is not limited to this. The AI ​​model 10 may reference activity information related to the difference, sum, variance, standard error, standard deviation, deviation value, mean, median, mode, kurtosis, skewness, minimum value, maximum value, or other statistical quantities of the amount of activity or the number of contacts. Furthermore, the AI ​​model 10 may reference activity information related to the amount of activity or the number of contacts acquired at one time or place, or at three or more time points or places, instead of two different times or places.

[0139] In the above embodiment and its modifications, information regarding the planning, evaluation, or improvement of developmental measures is generated as in the case of Fig. 13, but this is not limiting. Information regarding the planning, evaluation, or improvement of a childcare worker or a group of childcare workers with respect to developmental measures proposed or implemented by the childcare worker or a group of childcare workers can also be generated. This makes it possible to plan, evaluate, or improve a childcare worker or a group of childcare workers who have proposed or implemented developmental measures.

[0140] In the above embodiment and its modifications, information regarding the planning, evaluation, or improvement of developmental measures is generated as in the case of Fig. 13, but this is not limiting. Information regarding the planning, evaluation, or improvement of a child or a group of children who have used developmental measures can also be generated. This makes it possible to plan, evaluate, or improve a child or a group of children who have used developmental measures.

[0141] In the above embodiment and its modifications, information about multiple children is generated as in Figures 7 to 10 and 12 to 17, but this is not limiting and information about one child can also be generated. Also, in the case of Figure 11, information about one child is generated as in Figure 11, but this is not limiting and information about multiple children can also be generated.

[0142] Furthermore, in the above-described embodiment and its variations, information about one or more children is generated as in the cases of Figures 7 to 17, but it is not limited to this, or in addition, it is also possible to generate information about one or more childcare workers involved in the group childcare, developmental measures, and other events of Figures 7 to 17.

[0143] Furthermore, in the above embodiment and its modifications, the configurations of FIGS. 15 to 17 have been described as independent configurations, but the present invention is not limited to this and may be an additional configuration to the configurations of FIGS.

[0144] In the above embodiment and its variations, a request including a generation request and a reference request and identification information as parameters is transmitted, but this is not limiting. (1) a request including a generation request, or (2) a request including a generation request and a reference request as parameters can be transmitted. In other words, the AI ​​model 10 can be made to (1) perform inference without referencing data in the knowledge base 12, or (2) perform inference by referencing all data in the knowledge base 12.

[0145] In the above embodiment and its modifications, vector data is associated with identification information and registered in the knowledge base 12, but this is not limiting, and vector data can be registered without being associated with identification information. Furthermore, data in any format can be used, not just vector data.

[0146] Furthermore, in the above embodiment and its variations, the distance between the caregiver and the child is measured by BLE strength, but this is not limited to this. The wearable device 220 worn by the caregiver and the child can be equipped with a location information sensor such as GPS, and the distance between the caregiver and the child can be calculated based on the detection results of the location information sensor.

[0147] Furthermore, in the above embodiment and its modifications, the wearable device 220 is used, but this is not limiting and any device that can acquire activity information can be used. For example, an acceleration triggered multi-advertise BLE beacon can be used.

[0148] Furthermore, in the above embodiment and its variations, the generation AI server 100 is configured as an integrated unit of the functions consisting of the AI ​​model 10, knowledge base 12, and processing of steps S100 to S106 and S200 to S208, but this is not limited to this, and some functions can be configured on a separate server, etc.

[0149] Furthermore, in the above embodiment and its modifications, the system is realized as a network system, but the present invention is not limited to this and can be realized as a single device or application.

[0150] Furthermore, in the above embodiment and its modifications, the case where the present invention is applied to a network system consisting of the Internet 199 has been described, but the present invention is not limited to this, and may be applied, for example, to a so-called intranet that communicates using the same method as the Internet 199. Of course, the present invention is not limited to a network that communicates using the same method as the Internet 199, and may be applied to a network of any communication method.

[0151] Furthermore, in the above-described embodiment and its variations, the processes shown in the flowcharts of Figures 4 and 6 are executed by executing a program that is pre-stored in ROM 32. However, this is not limiting, and the program showing these procedures may be read from a storage medium on which the program is stored, into RAM 34, and executed.

[0152] Furthermore, the above-described embodiments and their modifications can be applied to each other. In the above embodiment and its modifications, the present invention is applied to a case where a childcare worker provides care for children, but it is not limited to this and can be applied to other cases within the scope of the gist of the present invention. For example, the present invention can be applied to a case where a childcare worker other than a childcare worker provides care for people other than children. [Explanation of symbols]

[0153] 100...Generation AI server, 10...AI model, 12...Knowledge base, 30...CPU, 32...ROM, 38...I / F, 39...Bus, 40...Input device, 42...Storage device, 44...Display device, 200...Nursery school terminal, 210...Nursery teacher terminal, 220...Wearable device, 199...Internet

Claims

1. A registration means for registering activity information relating to the number of contacts between the caregiver and the care recipient, or activity information relating to the amount of activity of the care recipient or the number of contacts with others, in a knowledge base that can be referenced by the AI ​​model; an input means for inputting a request including a request to generate information about the child to the AI ​​model; A childcare support system characterized by comprising an acquisition means for acquiring information output from the AI ​​model in response to the request by referring to activity information in the knowledge base.

2. An input means for inputting a request to the AI ​​model, the request including activity information regarding the number of contacts between the caregiver and the care recipient, or activity information regarding the care recipient's activity level or the number of contacts with others, and a request to generate information regarding the care recipient; A childcare support system characterized by comprising an acquisition means for acquiring information output from the AI ​​model in response to the request.

3. In any one of claims 1 and 2, A childcare support system characterized in that the request to generate information about the childcare recipient is a request to generate information about planning, evaluating, or improving group childcare to be implemented collectively for multiple childcare recipients.

4. In any one of claims 1 and 2, A childcare support system characterized in that the request to generate information about the child is a request to generate information regarding the planning, evaluation, or improvement of measures implemented for the development, growth, or growth of the child.

5. In any one of claims 1 and 2, A childcare support system characterized in that the request to generate information about the child is a request to generate safety management information regarding safety management of the child.

Images