Nursing Support System

Abstract

Provided is a childcare support system suitable for grasping information based on the individuality of a child in care or the like. 【Solution means】 The generation AI server 100 registers activity information regarding the number of contacts between a childcare worker and a child, as well as activity information regarding the activity level of a plurality of children and the number of contacts with others, in the knowledge base 12. Then, a request including a request to generate information about a child is input to the AI model 10, and information output from the AI model 10 is obtained by referring to the activity information in the knowledge base 12 for the request. As a result, information based on the number of contacts of the childcare worker and the activity level and number of contacts of the child can be obtained, so that information based on the individuality, needs, etc. of the child can be grasped as compared with the prior art.

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 individuality of a child in care, etc.

Background Art

[0002] The declining birthrate problem is in a serious situation. For this reason, the government is promoting various measures to address the declining birthrate and aiming to recover the birthrate. In 2023, the "Agency for Children and Families" was established, and in the future, positive measures to address the declining birthrate such as increasing family allowances and improving childcare are planned. Also, the "Universal Nursery System" implemented from fiscal year 2024 is a nursery system that allows parents to send their pre-school children to nursery schools even if they are not working. Currently, basically, only families that have received recognition of the need for childcare due to parents working or having special circumstances such as illness or caregiving can use nurseries. In contrast, the "Universal Nursery System" was formulated so that "anyone" can use nurseries on an hourly basis regardless of whether the parent is employed. In the model project that has been implemented since last year, facilities such as nurseries with available spaces and certified children's gardens are the target facilities. While the need from parents for this system is very high, many opinions from nurseries view the implementation with concern, such as not being able to keep up with the system for securing childcare workers.

[0003] Against this background, DX (Digital Transformation) for nurseries has been developed and put on the market. As DX for nurseries, for example, the technology described in Non-Patent Document 1 is known.

[0004] The technology described in Non-Patent Document 1 has functions such as management of arrival and departure at the nursery, communication with parents, creation of lesson plans and diaries, shift management, billing management, childcare documentation, contact books, calculation of extended childcare fees, temperature checks and infectious disease checks, near misses, growth and health records, emergency communication, questionnaires, photo sharing and sales, management of multiple facilities, security, meal and menu management, bus operation management, etc.

Prior Art Documents

Patent Document

[0005]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] In the commuting kindergarten system where any child can attend, it becomes difficult for nursery teachers to take care of different children every day according to the individuality and needs of each child. For example, when making a daily childcare plan, it is desirable to consider the individuality of the children on that day. However, since different children attend the kindergarten every day, it is difficult to consider the individuality of the children on that day, and an appropriate childcare plan cannot be made. This problem cannot be solved even by the technology described in Non-Patent Document 1.

[0007] Therefore, the present invention has been made by focusing on such unsolved problems of the conventional technology, and an object thereof is to provide a childcare support system suitable for grasping information based on the individuality of the children to be cared for.

Means for Solving the Problems

[0008] 〔Invention 1〕 In order to achieve the above object, the childcare support system of Invention 1 includes a registration means for registering activity information regarding the number of contacts between a childcare worker and a child to be cared for, or activity information regarding the amount of activity of the child to be cared for or the number of contacts with others in a knowledge base that can be referred to by an AI model, an input means for inputting a request including a request for generating information regarding the child to be cared for into the AI model, and an acquisition means for acquiring information output from the AI model by referring to the activity information in the knowledge base in response to the request.

[0009] With such a configuration, activity information is registered in the knowledge base by the registration means. Then, a request including a generation request for information about the child to be cared for is input into the AI model by the input means, and information output from the AI model in response to the request is acquired by the acquisition means. At this time, the activity information in the knowledge base is referred to by the AI model.

[0010] Here, the input means includes, for example, directly inputting a request into the AI model or indirectly inputting it into the AI model via processing, functions, devices, networks, or other means. The same applies to the childcare support system of Invention 2 below.

[0011] Also, the acquisition means includes, 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 to the childcare support system of Invention 2 below.

[0012] Also, the activity information regarding the activity amount includes, for example, activity information regarding one or more activity amounts, activity information regarding the activity amount itself, or activity information regarding the statistical amount of the activity amount. Similarly, the activity information regarding the contact frequency includes, for example, activity information regarding one or more contact frequencies, activity information regarding the contact frequency itself, or activity information regarding the statistical amount of the contact frequency. The same applies to the childcare support system of Invention 2 below.

[0013] Also, the request for generating information about the child to be cared for includes, for example, a request for generating response information to a question about the child to be cared for. The same applies to the childcare support system of Invention 2 below.

[0014] In addition, generation requirements include, for example, those that explicitly require the generation of information about the child in care, or those that indirectly require the generation of information about the child in care. Explicit requirements include, for example, a requirement such as "Please generate information about the child in care." Indirect requirements include, for example, generating a question about the child in care as a generation requirement in order to require the generation of response information to the question about the child in care. This is because in the AI model, if a question about the child in care is input as a prompt, the response information will be generated. The same applies to the childcare support system of Invention 2 below.

[0015] In addition, the activity information and requests can be configured in any form such as vector data or the like. The same applies to the childcare support system of Invention 2 below.

[0016] In addition, the knowledge base stores activity information by any means and at any time. It may store the activity information in advance, or it may be configured to store the activity information from an external input or the like during the operation of the system without storing the activity information in advance.

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

[0018] 〔Invention 2〕Furthermore, the childcare support system of Invention 2 includes activity information regarding the number of contacts between the childcare worker and the child in care, or activity information regarding the amount of activity of the child in care or the number of contacts with others, and an input means for inputting a request including a request to generate information about the child in care to the AI model, and an acquisition means for acquiring information output from the AI model in response to the request.

[0019] With such a configuration, a request including activity information and a generation request for information regarding the child to be cared for is input to the AI model by the input means, and information output from the AI model in response to the request is acquired by the acquisition means.

[0020] 〔Invention 3〕Furthermore, in the childcare support system of Invention 3, in the childcare support system according to any one of Inventions 1 and 2, the request for generating information regarding the child to be cared for is a request for generating information regarding the plan, evaluation, or improvement of group childcare implemented collectively for a plurality of the children to be cared for.

[0021] With such a configuration, a request including a generation request for information regarding the plan, evaluation, or improvement of group childcare is input to the AI model by the input means, and information output from the AI model in response to the request is acquired by the acquisition means.

[0022] Here, examples of the plan, evaluation, or improvement of group childcare include the plan, evaluation, or improvement of the children who have received group childcare, or the plan, evaluation, or improvement of the childcare workers who have provided group childcare.

[0023] 〔Invention 4〕Furthermore, in the childcare support system of Invention 4, in the childcare support system according to any one of Inventions 1 and 2, the request for generating information regarding the child to be cared for is a request for generating information regarding the plan, evaluation, or improvement of measures implemented for the development, growth, or advancement of the child to be cared for.

[0024] With such a configuration, a request including a generation request for information regarding the plan, evaluation, or improvement of measures is input to the AI model by the input means, and information output from the AI model in response to the request is acquired by the acquisition means.

[0025] Here, examples of the plan, evaluation, or improvement of measures include the plan, evaluation, or improvement of the childcare worker with respect to the measures implemented by the childcare worker, or the plan, evaluation, or improvement of the child to be cared for who has utilized the measures.

[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 for generating information regarding the child in care is a request for generating safety management information regarding the safety management of the child in care.

[0027] With such a configuration, a request including a request for generating safety management information is input to the AI model by the input means, and information output from the AI model in response to the request is acquired by the acquisition means.

Advantages of the Invention

[0028] As described above, according to the childcare support system of Invention 1 or 2, information based on the number of contacts between the childcare worker and the child in care, or the activity level of the child in care or the number of contacts with others can be obtained. Therefore, compared with the prior art, information based on the personality and needs of the child in care can be grasped.

[0029] Furthermore, according to the childcare support system of Invention 3, information regarding the planning, evaluation, or improvement of group childcare can be obtained, so that the planning, evaluation, or improvement of group childcare becomes easy.

[0030] Furthermore, according to the childcare support system of Invention 4, information regarding the planning, evaluation, or improvement of measures can be obtained, so that the planning, evaluation, or improvement of measures becomes easy.

[0031] Furthermore, according to the childcare support system of Invention 5, safety management information regarding the safety management of the child in care can be obtained, so that safety management becomes easy.

Brief Description of the Drawings

[0032]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Embodiments for Carrying Out the Invention

[0033] Hereinafter, embodiments of the present invention will be described. FIGS. 1 to 17 are diagrams showing this embodiment.

[0034] First, the configuration of this embodiment will be described. 〔Service Outline〕 FIG. 1 is a diagram showing an overview of the service according to the present 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 for registering 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 terminal 200 installed in a nursery, a nursery teacher terminal 210 used by a nursery teacher, or a wearable device 220 worn by a child (hereinafter simply referred to as "child") who attends the nursery, the received information is registered in the knowledge base 12. Knowledge data such as nursery guidelines is 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 nursery teacher terminal 210 or the like, in response to the received request, the data in the knowledge base 12 is referred to by the AI model 10, and the AI model 10 is caused to generate response information related to the generation request. Then, the generated response information is transmitted to the nursery teacher terminal 210 or the like.

[0038] On the nursery teacher terminal 210 or the like, the nursery teacher can ask questions by UI (User Interface) or voice. The nursery teacher terminal 210 or the like transmits a request including a request to generate response information for a question input by UI or voice to the generation AI server 100. Then, when receiving response information for the request, the received response information is displayed.

[0039] The generation AI server 100 causes the AI model 10 to refer to the data in the knowledge base 12 by a predetermined process and causes the AI model 10 to generate information about the child. Then, based on the generated information, a flash report, a signal, an alert, or other notifications are transmitted to the nursery teacher terminal 210 or the like.

[0040] When the caregiver terminal 210 or the like receives a quick report, a signal, an alert, or other notifications, it displays the received notifications.

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

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

[0044] As shown in FIG. 3, the generation AI server 100 includes a CPU (Central Processing Unit) 30 that controls operations and the entire system based on a control program, a ROM (Read Only Memory) 32 that stores the control program of the CPU 30 and the like in a predetermined area in advance, a RAM (Random Access Memory) 34 that stores data read from the ROM 32 and the like and calculation results necessary in the calculation process of the CPU 30, and an I / F (InterFace) 38 that mediates data input / output to and from external devices. These are connected to each other via a bus 39, which is a signal line for transferring data, so that data can be exchanged.

[0045] Connected to I / F 38 as external devices are an input device 40 consisting of a keyboard, a mouse, etc. capable of inputting data as a human interface, a storage device 42 for storing data, tables, etc. as files, a display device 44 for displaying 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 dataset and is a highly versatile model capable of performing various tasks. As the AI model 10, for example, a Large Language Model can be adopted. A Large Language Model is a deep learning model that pre-learns from a vast amount of data a language model called a model that models human spoken language by its occurrence probability. When a prompt is input, the Large Language Model statistically infers the generation probability of the next word from the text contained in the input prompt and outputs the inference result. As the Large Language Model, 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 adopted. 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, Stable Diffusion XL can be adopted.

[0047] The knowledge base 12 can register the information received from the nursery terminal 200, the nursery teacher terminal 210, or the wearable device 220. Also, in the knowledge base 12, as knowledge data such as nursery guidelines, (1) information regarding the nursery guidelines of the nursery, (2) information regarding laws and other rules or standards related to childcare, (3) manual information related to childcare, or (4) emergency response information is registered. As the emergency response information, for example, (1) emergency response information related to health (e.g., acute illness, allergy information, injury, dyspnea), (2) emergency response information related to the environment (e.g., fire, earthquake or natural disaster, power outage, gas leak), (3) emergency response information related to security (e.g., intrusion of a suspicious person, abduction or disappearance), or (4) other emergency response information (e.g., mass infection, acute illness or shortage of staff) is included.

[0048] 〔Nursery Terminal 200 and Nursery Teacher Terminal 210〕 Next, the configurations of the nursery terminal 200 and the nursery teacher terminal 210 will be described.

[0049] The nursery terminal 200 and the nursery teacher terminal 210 are configured to have the same hardware configuration as the generation AI server 100. The nursery 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] The wearable device 220 is a device that can be worn on the wrist, arm, neck, or other parts of a nursery teacher or a child, and is configured to have the same functions as a general computer with a CPU, ROM, RAM, and I / F connected by a bus.

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

[0053] The wearable device 220 is equipped with an RFID (Radio Frequency Identification) tag and a reader, reads the RFID tag of another wearable device 220 existing within a predetermined range (e.g., the range of close distance or personal distance) with the RFID reader, calculates the number of contacts between the wearer and other wearers (hereinafter simply referred to as "number of contacts") based on the detection result of the RFID reader, and transmits activity information including the calculated number of contacts to the generation AI server 100. The number of contacts with others is an indicator showing the social interaction of children (how much they interact 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 including the intensity of the radio wave (hereinafter referred to as "BLE intensity") used in BLE (Bluetooth Low Energy) communication with a specific wearable device 220 to the generation AI server 100. For example, if the wearable device 220 worn by a caregiver who takes care of children is set as a specific wearable device 220, activity information including the BLE intensity for the wearable device 220 worn by the caregiver can be transmitted to the generation AI server 100. From this activity information, it is possible to know where the child is active away from the caregiver.

[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] Figure 4 is a flowchart showing the knowledge data registration process. The CPU 30 consists of an MPU (Micro-Processing Unit) or the like, activates 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 according to the program. The knowledge data registration process is a process executed when a request including a registration request (hereinafter simply referred to as "registration request") for registering knowledge data is received. When executed in the CPU 30, as shown in FIG. 4, first, it proceeds to step S100.

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

[0058] In step S104, the received activity information and the like are converted into vector data that can be referred to by the AI model 10. The vector data can be generated by a technique (embedding) that converts data including characters, images, voices, etc. into numerical vectors.

[0059] Next, it proceeds to step S106, where the converted vector data is registered in the knowledge base 12. At this time, in order to allow the AI model 10 to refer to specific data in the knowledge base 12, the vector data is registered in association with identification information. By including the reference request and identification information of the knowledge base 12 in the request, the AI model 10 can be made to refer to the data corresponding to the identification information of the knowledge base 12.

[0060] As identification information, for example, (1) identification information for identifying a nursery or its group, (2) identification information for identifying a nursery teacher or its group, (3) identification information for identifying a child or its group, (4) identification information for identifying basic information, environmental information, qualitative information, quantitative information, image information, or other information, (5) identification information for identifying group care (hereinafter referred to as "group care") implemented for a plurality of children at once, (6) identification information for identifying the date and time, period, location, or other information related to the implementation of group care, (7) identification information for identifying the children who received group care or their group, or (8) identification information for identifying measures implemented for the development, growth, or advancement of one or more children (for example, creation of a childcare curriculum, change in the layout of the outdoor or indoor area of the nursery) (hereinafter referred to as "development measures") is included. Thereby, among the data in the knowledge base 12, for example, (1) data corresponding to a nursery or its group, (2) data corresponding to a nursery teacher or its group, (3) data corresponding to a child or its group, (4) data corresponding to basic information, environmental information, qualitative information, quantitative information, image information, or other information, (5) data corresponding to group care, (6) data corresponding to the date and time, location, or other information related to the implementation of group care, (7) data corresponding to the children who received group care or their group, or (8) data corresponding to development measures can be specified by the identification information and referred to the AI model 10.

[0061] When the process of step S106 ends, the series of processes ends. 〔Registration of Activity Information〕 In the wearable device 220, at predetermined intervals (for example, every 10 minutes) or at a predetermined or arbitrary timing, activity information regarding the wearer's activity level, contact frequency, and BLE strength, as well as a request including a registration request, is generated and transmitted to the AI server 100, and the activity information is registered in the knowledge base 12. The activity information is registered in association with the identification information of the nursery teacher or child related to the activity information, the date and time information when the activity information was acquired, or the location information where the activity information was acquired, etc. Thereby, the activity information of a plurality of children is registered as knowledge data.

[0062] [Registration of Basic Information, etc.] At the nursery terminal 200 or the nursery teacher terminal 210 (hereinafter referred to as "the nursery teacher terminal 210, etc."), at a predetermined time (for example, every 10 minutes) or at a predetermined or arbitrary timing, a request including basic information, environmental information, qualitative information, quantitative information, image information, or other information and a registration request is sent to the generation AI server 100, 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, nursery teacher, or child related to the basic information, etc., the date and time information when the basic information, etc. was acquired, or the position information, etc. where the basic information, etc. was acquired.

[0063] Examples of the basic information include, for example, (1) information regarding the name, address, number of nursery teachers belonging, number of children belonging, and other attributes of the nursery, (2) information regarding the name, age, gender, nursery belonging, and other attributes of the nursery teacher, (3) information regarding the name, age, gender, height, weight, body temperature, allergy information, vaccination history, medical history, nursery belonging, and other attributes of the child, (4) information regarding comments of the nursery teacher or guardian regarding the child, or (5) information regarding an emergency of the child.

[0064] Examples of the environmental information include, for example, (1) information regarding the temperature, humidity, atmospheric pressure, wind direction, wind speed, light quantity, noise, intensity of sunlight (for example, ultraviolet rays), intensity of electromagnetic waves, concentration of carbon dioxide, etc., weather, or smell in the nursery or other environment where childcare is provided, or (2) information regarding development measures. These are obtained by installing a temperature sensor, etc. in the nursery or other environment where childcare is provided, and at the nursery teacher terminal 210, etc., the detection result of the temperature sensor, etc. is acquired, and a request including the acquired detection result as environmental information is sent to the generation AI server 100.

[0065] Examples of qualitative information (information that is difficult to quantify) include, for example: (1) information regarding behavior (e.g., how to play, how to interact with friends, characteristics of behavior), (2) information regarding emotions (e.g., expressions of joy, anger, sorrow, and pleasure, expressions of achievement, expressions at the time of failure, emotional stability), (3) information regarding thinking (e.g., methods of problem-solving, curiosity, imagination), (4) information regarding language (e.g., vocabulary, speaking style, comprehension), and (5) information regarding sociality (e.g., cooperation, consideration, sense of rules). Note that information that partially overlaps with basic information may be regarded as qualitative information, or information that does not overlap with basic information may be regarded as qualitative information.

[0066] Examples of quantitative information (information that can be quantified) include, for example: (1) information regarding development, growth, or maturation (e.g., height, weight, number of vocabulary words, motor abilities such as walking, running, jumping), (2) information regarding lifestyle habits (e.g., diet content, amount of food intake, sleep time, play time), (3) information regarding learning (e.g., number of correct answers and incorrect answers to problems, number of books that can be read), and (4) information regarding health (e.g., body temperature, number of visits to medical institutions, medication status, allergy information). Note that information that partially overlaps with activity information, basic information, and environmental information may be regarded as quantitative information, or information that does not overlap with activity information, basic information, and environmental information may be regarded as quantitative information.

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

[0068] As the image information, for example, corresponding to the above examples of qualitative information and quantitative information, it includes image information related to behavior, image information related to emotion, image information related to thinking, image information related to language, image information related to sociality, image information related to development, growth or development, image information related to lifestyle, image information related to learning, and image information related to health.

[0069] 〔Answer Information Generation〕 Next, the case where the generation AI server 100 generates answer information by the AI model 10 will be described.

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

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

[0072] Next, it proceeds to step S202, and based on the generation request included in the received request, a prompt for instructing the AI model 10 is generated. When 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, proceed to step S204 and input the generated prompt into AI model 10. Here, if the received request includes a reference request, input the reference request into AI model 10. If the request includes both a reference request and identification information, input the reference request and the identification information into AI model 10.

[0074] When the AI model 10 receives a prompt, it infers response information from the input prompt. As a result of this inference by the AI model 10, response information that conforms to the learning data of the AI model 10 and the generation request is obtained.

[0075] When the AI model 10 receives a prompt and a reference request, it refers to all the data in the knowledge base 12 based on the input reference request and infers response information from the input prompt. As a result of this inference by the AI model 10, response information that conforms to the learning data of the AI model 10, all the data in the knowledge base 12, and the generation request is obtained.

[0076] When the AI model 10 receives a prompt, a reference request, and identification information, it refers to specific data in the knowledge base 12 based on the input reference request and identification information and infers response information from the input prompt. As a result of this inference by the AI model 10, response information that conforms to the learning data of the AI model 10, specific data in the knowledge base 12, and the generation request is obtained.

[0077] Next, proceed to step S206 to obtain the inference result of the AI model 10, and then proceed to step S208 to transmit the response information including the obtained inference result to the terminal that made the request, thus ending the series of processes.

[0078] [1. Generation of group childcare plan information] FIG. 7 and FIG. 8 are diagrams showing the data structures when generating group childcare plan information. In the figure, (a) shows the data structure of the request, (b) shows the data structure of the information in the knowledge base 12 referred to by the AI model 10, and (c) shows the data structure of the response information from the generation AI server 100.

[0079] The first example is an example of generating planned information for afternoon group childcare from morning information. When a childcare worker wants to obtain planned information regarding the plan for group childcare, which is a plan based on the number of contacts of the childcare worker and the activity level and number of contacts of the child, the childcare worker inputs a generation request for the planned information on a childcare worker terminal 210 or the like. When a generation request for the planned information is input on the childcare worker terminal 210 or the like, a request including the input generation request and parameters is transmitted to the generation AI server 100. The request is composed of, for example, as shown in FIG. 7(a), the generation request "Morning data... Please consider measures." and, as parameters, a reference request and identification information "Nursery: Midori no Oka Nursery... Information regarding the childcare guidelines of the nursery". Among these parameters, "Reference Information 1" is information during the morning stay in the nursery among the information in the knowledge base 12, and includes (1) child identification information, (2) the name of the child, (3) activity information 1 indicating measured values when the child played freely in the park for 1 hour in the morning, (4) activity information 2 indicating measured values when the child was read to in the nursery for 1 hour in the morning, and (5) indicating that the AI model 10 should refer to the physical examination comments. Activity information 1 is information regarding the activity level (e.g., number of steps) of the child, the number of contacts of the childcare worker, and the number of contacts of the child. The same applies to activity information 2. Therefore, the information in the knowledge base 12 that the AI model 10 refers to is configured as shown in FIG. 7(b), for example. Also, "Reference Information 2" indicates that the AI model 10 should refer to information regarding the childcare guidelines of the nursery among the information in the knowledge base 12.

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

[0081] The second example is an example of generating planned information for the remaining 40 minutes of group childcare when the child plays freely in the park for 20 minutes.

[0082] When a generation request for planning information is input at 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. The request is composed of, for example, as shown in Fig. 8(a), the generation request "Regarding playing in the park for 1 hour... Please also create reasons." and, as parameters, a reference request and identification information "Nursery: Midori no Oka Nursery... Play menu information". Among these parameters, "reference information 1" is information in the knowledge base 12 regarding free play in the park as a stroll outing, and includes (1) child identification information, (2) the child's name, (3) activity information 1 indicating measured values when free play in the park has been carried out for 20 minutes from the start, (4) activity information 2 indicating actual performance values when free play in the park has been carried out for 20 minutes from the start in the past, and (5) indicating that the BLE intensity is to be referred to by the AI model 10. Activity information 1 is information regarding the child's activity level (e.g., number of steps) and the number of contacts of the child. The same applies to activity information 2. Therefore, the information in the knowledge base 12 referred to by the AI model 10 is configured, for example, as shown in Fig. 8(b). Also, "reference information 2" indicates that the play menu information in the knowledge base 12 is to be referred to by the AI model 10.

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

[0084] [2. Generation of Evaluation Information for Group Childcare] Figs. 9 and 10 are diagrams showing the data structures in the case of generating evaluation information for group childcare. Fig. (a) of the same figure shows the data structure of the request, Fig. (b) shows the data structure of the information in the knowledge base 12 to be referred to by the AI model 10, and Fig. (c) shows the data structure of the response information from the generation AI server 100.

[0085] The first example is an example of generating evaluation information for group childcare when "hide-and-seek" is carried out after free play in the park has been carried out for 20 minutes from the start.

[0086] When a nursery teacher wants to obtain evaluation information regarding the evaluation of group childcare, which is an evaluation based on the number of contacts of the nursery teacher and the activity level of the children, the nursery teacher terminal 210 or the like inputs a generation request for the evaluation information. When a generation request for evaluation information is input to the nursery teacher terminal 210 or the like, a request including the input generation request and parameters is sent to the generation AI server 100. The request is composed of, for example, as shown in Fig. 9(a), the generation request "Please evaluate 20 minutes after the event starts..." and, as parameters, a reference request and identification information "Nursery: Midori no Oka Nursery... Information regarding the childcare guidelines of the nursery". Among these parameters, "Reference Information 1" is information among the information in the knowledge base 12 during free play in the park as a stroll outside, and includes (1) identification information of the child, (2) the name of the child, (3) activity information 1 showing the measured values 20 minutes after the start of free play in the park, (4) activity information 2 showing the measured values 60 minutes after the start of free play in the park, and (5) indicating that the nursery teacher comment is to be referred to by the AI model 10. Activity information 1 is information regarding the activity level of the child (e.g., the number of steps) and the number of contacts of the nursery teacher. The same applies to activity information 2. Therefore, the information in the knowledge base 12 referred to by the AI model 10 is configured as shown in Fig. 9(b), for example. Also, "Reference Information 2" indicates that the AI model 10 is to refer to information regarding the childcare guidelines of the nursery among the information in the knowledge base 12.

[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 the evaluation of group childcare continuously performed for a specific child over a certain period.

[0089] When a nursery teacher wants to obtain evaluation information regarding the evaluation of group childcare, which is an evaluation based on the number of contacts of the nursery teacher and the activity level and number of contacts of the children, the teacher inputs a request for generating evaluation information on a nursery teacher terminal 210 or the like. When a request for generating evaluation information is input on the nursery teacher terminal 210 or the like, a request including the input generation request and parameters is sent to the generation AI server 100. The request is composed of, for example, as shown in Fig. 10(a), the generation request "Please evaluate the childcare guidelines of the nursery...", and as parameters, a reference request and identification information "Nursery: Midori no Oka Nursery... Information regarding the childcare guidelines of the nursery". Among these parameters, "reference information 1" is information in the knowledge base 12 during free play in the park and during reading aloud in the nursery as a walk outside, and indicates (1) identification information of the child, (2) name of the child, (3) age of the child (in months), (4) activity information 1 showing measured values when the child has one hour of free play in the park, and (5) activity information 2 showing measured values when the child has one hour of reading aloud in the nursery, for the AI model 10 to refer to. Activity information 1 is information regarding the activity level of the child (e.g., number of steps), the number of contacts of the nursery teacher, the number of contacts of the child, and the nursery teacher's comments. The same applies to activity information 2. Therefore, the information in the knowledge base 12 that the AI model 10 refers to is configured as shown in Fig. 10(b), for example. Also, "reference information 2" indicates that the AI model 10 should refer to information regarding the childcare guidelines of the nursery in the knowledge base 12.

[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. 10(c).

[0091] [3. Generation of improvement information for group childcare] Fig. 11 is a diagram showing the data structure when generating improvement information for group childcare. Fig. (a) of the same figure shows the data structure of the request, Fig. (b) shows the data structure of the information in the knowledge base 12 to be referred to by the AI model 10, and Fig. (c) shows the data structure of the response information from the generation AI server 100.

[0092] When a childcare worker wants to obtain improvement information regarding group childcare, which is an improvement based on the number of contacts of the childcare worker and the activity level of the children, the childcare worker inputs a generation request for the improvement information on the childcare worker terminal 210 or the like. When a generation request for improvement information is input on the childcare worker terminal 210 or the like, a request including the input generation request and parameters is transmitted to the generation AI server 100. The request is composed of, for example, as shown in Fig. 11(a), the generation request "Please provide the measured value indicating the result of executing Do and..." and, as parameters, a reference request and identification information "Nursery: Midori no Oka Nursery... Play menu information". Among these parameters, "Reference Information 1" is information among the information in the knowledge base 12 during free play in the park as a walk outside, and includes (1) children's identification information, (2) children's names, (3) activity information 1 indicating the measured value when free play in the park has been carried out for 20 minutes from the start, (4) activity information 2 indicating the measured value when free play in the park has been carried out for 60 minutes from the start, and (5) indicating that the childcare worker comment is to be referred to by the AI model 10. Activity information 1 is information regarding the activity level of the children (e.g., number of steps) and the number of contacts of the childcare worker. The same applies to activity information 2. Therefore, the information in the knowledge base 12 referred to by the AI model 10 is configured, for example, as shown in Fig. 11(b). Also, "Reference Information 2" indicates that the AI model 10 is to refer to information regarding the childcare guidelines of the nursery among the information in the knowledge base 12.

[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. 11(c).

[0094] [4. Generation of Planning Information for Developmental Measures] Fig. 12 is a diagram showing the data structure when generating planning information for developmental measures. Fig. (a) of the same figure shows the data structure of the request, Fig. (b) shows the data structure of the information in the knowledge base 12 to be referred to by the AI model 10, and Fig. (c) shows the data structure of the response information from the generation AI server 100.

[0095] When a childcare worker wants to obtain planning information regarding a plan for developmental measures, which is a plan based on the number of contacts of the childcare worker and the activity level and number of contacts of the child, the childcare worker inputs a generation request for the planning information on the childcare worker terminal 210 or the like. When a generation request for planning information is input on 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. The request is composed of, for example, as shown in Fig. 12(a), the generation request "Please propose the introduction of an atelier..." and, as parameters, a reference request and identification information "Nursery: Midori no Oka Nursery... Information regarding the childcare guidelines of the nursery". Among these parameters, "Reference Information 1" indicates that, among the information in the knowledge base 12, the information during in-facility activities is to be referred to by the AI model 10, and includes (1) the identification information of the child, (2) the name of the child, and (3) activity information indicating measured values when in-facility activities were carried out before the introduction of the atelier. The activity information is information regarding the activity level (e.g., number of steps) of the child, the number of contacts of the childcare worker, and the number of contacts of the child. Therefore, the information in the knowledge base 12 that the AI model 10 refers to is configured as shown in Fig. 12(b), for example. Also, "Reference Information 2" indicates that, among the information in the knowledge base 12, the information regarding the childcare guidelines of the nursery is to be referred to by the AI model 10.

[0096] And in response to this request, planning information is obtained from the generation AI server 100. The planning information is configured as shown in Fig. 12(c).

[0097] [5. Generation of Evaluation Information for Developmental Measures] Fig. 13 is a diagram showing the data structure when generating evaluation information for developmental measures. Fig. (a) of the same figure shows the data structure of the request, Fig. (b) shows the data structure of the information in the knowledge base 12 to be referred to by the AI model 10, and Fig. (c) shows the data structure of the response information from the generation AI server 100.

[0098] When a nursery teacher wants to obtain evaluation information regarding the evaluation of development measures, which is an evaluation based on the number of contacts of the nursery teacher and the activity level and number of contacts of the child, the nursery teacher inputs a generation request for evaluation information on the nursery teacher terminal 210 or the like. When a generation request for evaluation information is input on the nursery teacher terminal 210 or the like, a request including the input generation request and parameters is sent to the generation AI server 100. The request is composed of, for example, as shown in Fig. 13(a), the generation request "Please evaluate the atelier..." and, as parameters, a reference request and identification information "Nursery: Midori no Oka Nursery... Information on the nursery's childcare guidelines". Among these parameters, "Reference Information 1" is information in the knowledge base 12 during on-site activities, including (1) the identification information of the child, (2) the name of the child, (3) activity information 1 indicating the measured values when on-site activities were carried out before the introduction of the atelier, (4) activity information 2 indicating the measured values when on-site activities were carried out after the introduction of the atelier, and (5) indicating that the nursery teacher's comment is to be referred to by the AI model 10. Activity information 1 is information regarding the activity level of the child (e.g., number of steps), the number of contacts of the nursery teacher, and the number of contacts of the child. The same applies to activity information 2. Therefore, the information in the knowledge base 12 that the AI model 10 refers to is configured, for example, as shown in Fig. 13(b). Also, "Reference Information 2" indicates that the information regarding the nursery's childcare guidelines in the knowledge base 12 is to be referred to by the AI model 10.

[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. 13(c).

[0100] [[6. Generation of Improvement Information for Development Measures]] When a nursery teacher wants to obtain improvement information regarding the improvement of development measures, which is an improvement based on the number of contacts of the nursery teacher and the activity level and number of contacts of the child, the nursery teacher inputs a generation request for improvement information on the nursery teacher terminal 210 or the like. Here, the request, the information in the knowledge base 12 to be referred to, and the response information from the generation AI server 100 can be configured with the same data structure as in Fig. 11.

[0101] [7. Generation of Safety Management Information] FIG. 14 is a diagram showing a data structure in the case of generating safety management information for children. FIG. 14(a) shows the data structure of a request, FIG. 14(b) shows the data structure of information in the knowledge base 12 referred to by the AI model 10, and FIG. 14(c) shows the data structure of response information from the generation AI server 100.

[0102] When a nursery teacher wants to obtain safety management information for one or more children, which is based on the number of contacts of the nursery teacher and the activity level and number of contacts of the children, the nursery teacher inputs a generation request for safety management information on the nursery teacher terminal 210 or the like. When a generation request for safety management information is input on the nursery teacher terminal 210 or the like, a request including the input generation request and parameters is transmitted to the generation AI server 100. The request is composed of, for example, as shown in FIG. 14(a), the generation request "Is there a risk for the child... Please comment by comparison." and, as parameters, a reference request and identification information "Nursery: Midori no Oka Nursery... BLE intensity". Among these parameters, the "reference information" is information during free play in the park as a walk outside, among the information in the knowledge base 12, and indicates (1) identification information of the child, (2) name of the child, (3) activity information 1 showing measured values when free play in the park was carried out, (4) activity information 2 showing actual values when free play in the park was carried out in the past, and (5) BLE intensity for the AI model 10 to refer to. Activity information 1 is information regarding the activity level (e.g., number of steps) of the child, the number of contacts of the nursery teacher, and the number of contacts of the child. The same applies to activity information 2. Therefore, the information in the knowledge base 12 referred to by the AI model 10 is configured as shown in FIG. 14(b), for example.

[0103] Then, safety management information is obtained from the generation AI server 100 in response to this request. The safety management information is configured as shown in FIG. 14(c).

[0104] [8. Generation of Health Management Information] FIG. 15 is a diagram showing a data structure when generating children's health management information. FIG. (a) shows the data structure of a request, FIG. (b) shows the data structure of information in the knowledge base 12 referred to by the AI model 10, and FIG. (c) shows the data structure of response information from the generation AI server 100.

[0105] When a nursery teacher wants to obtain health management information of one or more children, the nursery teacher inputs a generation request for health management information on the nursery teacher terminal 210 or the like. When a generation request for health management information is input on the nursery teacher terminal 210 or the like, a request including the input generation request and parameters is sent to the generation AI server 100. The request is composed of, for example, as shown in FIG. 15(a), the generation request "Please tell me the points to note for health management..." and, as parameters, a reference request and identification information "Nursery: Midori no Oka Nursery... Physical examination / Guardian's comment". Among these parameters, the "reference information" indicates that, among the information in the knowledge base 12, the information at the time of enrollment, namely, (1) children's identification information, (2) children's names, (3) children's body temperatures, and (4) physical examination / guardian's comment, is to be referred to by the AI model 10. Therefore, the information in the knowledge base 12 referred to by the AI model 10 is configured as shown in FIG. 15(b), for example.

[0106] Then, health management information is obtained from the generation AI server 100 in response to this request. The health management information is configured as shown in FIG. 15(c).

[0107] As health management information, information regarding the administration of medicine to children is included. The administration of medicine means, for example, when a child receives a prescription for a medicine to be taken three times a day from a doctor, a nursery teacher gives the child one dose of the medicine to be taken after lunch. The nursery teacher needs to pay meticulous attention to ensure that they do not forget to administer the medicine, do not administer the medicine to other children, do not make a mistake in the medicine to be administered, and do not miss the timing of administration. However, since different children come to the nursery every day, it is difficult to grasp the details of the medicine administration for the children on that day, and it is difficult to conduct appropriate health management. Therefore, by causing the AI model 10 to generate information regarding the administration of medicine to one or more children, the nursery teacher can grasp the details of the medicine administration for the children. For example, as shown in FIG. 15(b), when "administer medicine after lunch (with a medicine administration request form)" is given as a physical examination / guardian comment, as shown in FIG. 15(c), as information regarding the administration of medicine to the child, "For Ayaka-chan (medicine administration after lunch): It is important to administer the medicine at the correct timing. After administering the medicine, carefully monitor whether there are any changes in the physical condition and leave a record." can be obtained.

[0108] [9. Meal Management Information] FIG. 16 is a diagram showing the data structure in the case of generating children's meal management information. FIG. (a) of the same figure shows the data structure of the request, FIG. (b) shows the data structure of the information in the knowledge base 12 to be referred to by the AI model 10, and FIG. (c) shows the data structure of the response information from the generation AI server 100.

[0109] When a childcare worker wants to obtain meal management information for one or more children, the childcare worker inputs a generation request for meal management information and image information of the school lunch menu on the childcare worker terminal 210 or the like. When the generation request for meal management information and the image information are input on the childcare worker terminal 210 or the like, a request including the input generation request, parameters, and image information is transmitted to the generation AI server 100. The request is composed of, for example, as shown in Fig. 16(a), the generation request "Is there a risk for the child... Is there a risk?", the reference request and identification information "Nursery: Midori no Oka Nursery... Allergy information" as parameters, and image information (not shown). Among these parameters, the "reference information" indicates that the AI model 10 should refer to the information in the knowledge base 12, which is the information at lunchtime, including (1) the identification information of the child, (2) the name of the child, (3) the physical examination / guardian comment, and (4) the allergy information of the child. Therefore, the information in the knowledge base 12 that the AI model 10 refers to is configured as shown in Fig. 16(b), for example.

[0110] In response to this request, meal management information is obtained from the generation AI server 100. The meal management information is configured as shown in Fig. 16(c).

[0111] [10. Generation of Emergency Response Information] Fig. 17 is a diagram showing the data structure when generating emergency response information regarding a child's health. Fig. (a) of the figure shows the data structure of the request, Fig. (b) shows the data structure of the information in the knowledge base 12 that the AI model 10 refers to, and Fig. (c) shows the data structure of the response information from the generation AI server 100.

[0112] When a childcare worker wants to obtain emergency response information regarding 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 a request for generating emergency response information is input on the childcare worker terminal 210 or the like, a request including the input generation request and parameters is transmitted to the generation AI server 100. The request is composed of, for example, as shown in FIG. 17(a), the generation request "Please explain what has occurred from the occurrence details... and share it." and, as parameters, a reference request and identification information "Nursery: Midori no Oka Nursery... Emergency response information regarding health". Among these parameters, "Reference Information 1" is information in the knowledge base 12 when an emergency occurs during meal provision, and indicates that the AI model 10 should refer to (1) child identification information, (2) child name, (3) details of the emergency occurrence, (4) child body temperature, (5) visual examination / guardian comments, (5) child allergy information, and (6) vaccination history. Therefore, the information in the knowledge base 12 that the AI model 10 refers to is configured as shown in FIG. 17(b), for example. Also, "Reference Information 2" indicates that the AI model 10 should refer to emergency response information regarding health among the information in 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, as emergency response information, (1) emergency response information regarding the environment, (2) emergency response information regarding security, or (3) other emergency response information can be obtained.

[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] With any of the following configurations, rapid reports, signals, alerts, and other notifications are sent to the childcare worker terminal 210 or the like.

[0117] The first configuration inputs a predetermined prompt and necessary reference requests into the AI model 10 when a predetermined condition is satisfied. Here, the necessary reference requests mean that they are input when reference requests or reference requests and identification information are necessary, but not input when they are unnecessary. The same applies to the second to fourth configurations. Then, the inference result of the AI model 10 is obtained, and notification information including the obtained inference result is transmitted to the caregiver terminal 210 or the like. As the prompt, for example, a prompt corresponding to the request exemplified in the response information generation process of FIG. 6 (a prompt generated based on the generation request included in the request) can be adopted. As the conditions, for example, (1) whether the current time is a predetermined date, time, or day of the week, (2) whether the place where the childcare to be carried out, the childcare being carried out, or the childcare that has been completed (hereinafter simply referred to as "childcare" in this paragraph) is a predetermined place, (3) whether the caregiver carrying out the childcare is a predetermined person or group, (4) whether the childcare is of a predetermined content, and (5) whether the activity level, contact frequency, or BLE intensity of the child is equal to or greater than or less than a predetermined value can be adopted.

[0118] The second configuration stores in the storage device 42 a table in which conditions, prompts, and necessary reference requests are registered in association with each other. When the condition of the table is satisfied, the corresponding prompt and necessary reference requests are acquired from the table, and the acquired prompt and necessary reference requests are input into the AI model 10. Then, the inference result of the AI model 10 is obtained, and notification information including the obtained inference result is transmitted to the caregiver terminal 210 or the like.

[0119] The third configuration inputs a predetermined prompt and necessary reference requests into the AI model 10 and obtains the inference result of the AI model 10. Then, when the inference result satisfies a predetermined condition, notification information including the inference result is transmitted to the caregiver terminal 210 or the like.

[0120] The fourth configuration stores in the storage device 42 a table in which conditions, prompts, and necessary reference requests are registered in association with each other, retrieves the prompts and necessary reference requests from the table, inputs the retrieved prompts and necessary reference requests into the AI model 10, and obtains the inference result of the AI model 10. Then, when the inference result satisfies the corresponding condition in the table, notification information including the inference result is transmitted to the caregiver terminal 210 or the like.

[0121] Next, the effects of the present embodiment will be described. In the present embodiment, activity information regarding the number of contacts of the caregiver and activity information regarding the activity level and the number of contacts of the child are registered in the knowledge base 12, a request including a request for generating information regarding the child is input into the AI model 10, and information output from the AI model 10 is obtained by referring to the activity information in the knowledge base 12 for the request.

[0122] Thereby, information based on the number of contacts of the caregiver and the activity level and the number of contacts of the child can be obtained, so that information based on the personality and needs of the child can be grasped as compared with the conventional case.

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

[0124] Thereby, information based on the activity levels and the number of contacts of a plurality of children can be obtained, so that information based on the personalities of the plurality of children can be grasped when caring for the plurality of children.

[0125] Furthermore, in the present embodiment, the request for generating information regarding the child is a request for generating information regarding the plan, evaluation, or improvement of group care.

[0126] Thereby, information regarding the plan, evaluation, or improvement of group care can be obtained, so that the plan, evaluation, or improvement of group care becomes easy.

[0127] Furthermore, in the present embodiment, the request for generating information about a child is a request for generating evaluation information regarding the evaluation of development measures.

[0128] Thereby, evaluation information regarding the evaluation of measures or the evaluation of childcare workers with respect to measures can be obtained, facilitating the evaluation of measures or the evaluation of childcare workers with respect to measures.

[0129] Furthermore, in the present embodiment, the request for generating information about a child is a request for generating safety management information regarding the safety management of a child.

[0130] Thereby, safety management information regarding the safety management of a child can be obtained, facilitating safety management.

[0131] In the present 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 Example〕 In the above embodiment and its modification example, the information in the knowledge base 12 is referred to by the AI model 10. However, this is not the only case, and information to be referred to by 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. Thereby, it can be applied even in a configuration without the knowledge base 12.

[0133] Also, in the above embodiment and its modification example, the activity information is configured as information regarding the activity amount, the number of contacts, and the BLE intensity. However, this is not the only case, and it can be configured as information regarding one or two of the activity amount, the number of contacts, and the BLE intensity.

[0134] In addition, in the above-described embodiments and their modifications, as in the cases of FIGS. 7, 9 to 14, the activity information regarding the number of contacts of the nursery teacher was referred to the AI model 10. However, this is not the only case, and it is also possible not to refer to the activity information regarding the number of contacts of the nursery teacher. Also, as in the cases of FIGS. 8, 15 to 17, the activity information regarding the number of contacts of the nursery teacher was not referred to the AI model 10. However, this is not the only case, and it is also possible to refer to the activity information regarding the number of contacts of the nursery teacher.

[0135] In addition, in the above-described embodiments and their modifications, as in the cases of FIGS. 7 to 15, the activity information regarding the activity amount of the nursery teacher was not referred to the AI model 10. However, this is not the only case, and it is also possible to refer to the activity information regarding the activity amount of the nursery teacher.

[0136] In addition, in the above-described embodiments and their modifications, as in the cases of FIGS. 7, 8, 11 to 14, the activity information regarding the number of contacts of the child was referred to the AI model 10. However, this is not the only case, and it is also possible not to refer to the activity information regarding the number of contacts of the child. Also, as in the cases of FIGS. 9, 10, 15 to 17, the activity information regarding the number of contacts of the child was not referred to the AI model 10. However, this is not the only case, and it is also possible to refer to the activity information regarding the number of contacts of the child.

[0137] In addition, in the above-described embodiments and their modifications, as in the cases of FIGS. 7 to 14, the activity information regarding the activity amount of the child was referred to the AI model 10. However, this is not the only case, and it is also possible not to refer to the activity information regarding the activity amount of the child. Also, as in the cases of FIGS. 15 to 17, the activity information regarding the activity amount of the child was not referred to the AI model 10. However, this is not the only case, and it is also possible to refer to the activity information regarding the activity amount of the child.

[0138] Also, in the above-described embodiments and their modifications, as in the case of FIGS. 7 to 14, the activity information regarding the activity amounts or contact frequencies acquired at two different points in time or locations was referred to the AI model 10. However, it is not limited thereto, and the activity information regarding the differences, sums, variances, standard errors, standard deviations, deviation values, average values, medians, mode values, kurtosis, skewness, minimum values, maximum values, and other statistics of those activity amounts or contact frequencies can be referred to. Also, not limited to two different points in time or locations, the activity information regarding the activity amounts or contact frequencies acquired at one point in time or location, or at three or more points in time or locations can be referred to.

[0139] Also, in the above-described embodiments and their modifications, as in the case of FIG. 13, information regarding the planning, evaluation, or improvement of development measures was generated. However, it is not limited thereto, and information regarding the planning, evaluation, or improvement of the childcare workers or their group for the development measures proposed or implemented by the childcare workers or their group can be generated. Thereby, the childcare workers or their group who proposed or implemented the development measures can be planned, evaluated, or improved.

[0140] Also, in the above-described embodiments and their modifications, as in the case of FIG. 13, information regarding the planning, evaluation, or improvement of development measures was generated. However, it is not limited thereto, and information regarding the planning, evaluation, or improvement of the children or their group who utilized the development measures can be generated. Thereby, the children or their group who utilized the development measures can be planned, evaluated, or improved.

[0141] Also, in the above-described embodiments and their modifications, as in the case of FIGS. 7 to 10 and FIGS. 12 to 17, information regarding a plurality of children was generated. However, it is not limited thereto, and information regarding one child can be generated. Also, as in the case of FIG. 11, information regarding one child was generated. However, it is not limited thereto, and information regarding a plurality of children can be generated.

[0142] Also, in the above-described embodiments and their modifications, information about one or more children was generated as in the case of FIGS. 7 to 17. However, this is not limiting, or in addition to this, information about one or more childcare workers involved in the group childcare, development measures, and other events of FIGS. 7 to 17 can be generated.

[0143] Also, in the above-described embodiments and their modifications, the configurations of FIGS. 15 to 17 were described as independent configurations. However, this is not limiting, and they can be additional configurations to the configurations of FIGS. 7 to 14.

[0144] Also, in the above-described embodiments and their modifications, a request including a generation request and a reference request and identification information as parameters was transmitted. However, this is not limiting, and (1) a request including a generation request, or (2) a request including a generation request and a reference request as parameters can be transmitted. That is, with respect to the AI model 10, (1) it can be made to perform inference without referring to the data in the knowledge base 12, or (2) it can be made to perform inference by referring to all the data in the knowledge base 12.

[0145] Also, in the above-described embodiments and their modifications, vector data was registered in the knowledge base 12 in association with identification information. However, this is not limiting, and vector data can be registered without being associated with identification information. Also, not limited to vector data, any form of data can be adopted.

[0146] Also, in the above-described embodiments and their modifications, the distance between the childcare worker and the child was measured based on the BLE intensity. However, this is not limiting, and the wearable devices 220 worn by the childcare worker and the child are provided with a position information sensor such as GPS, and the distance between the childcare worker and the child can be calculated based on the detection result of the position information sensor.

[0147] Also, in the above-described embodiments and their modifications, the wearable device 220 is adopted. However, the present invention is not limited to this, and any device can be adopted as long as it can acquire activity information. For example, an acceleration-trigger-equipped multi-advantage BLE beacon can be adopted.

[0148] Also, in the above-described embodiments and their modifications, the generation AI server 100 integrally constitutes each function including the AI model 10, the knowledge base 12, and the processes of steps S100 to S106 and S200 to S208. However, the present invention is not limited to this, and some functions can be configured by another server or the like.

[0149] Also, in the above-described embodiments and their modifications, it is realized as a network system. However, the present invention is not limited to this, and it can be realized as a single device or application.

[0150] Also, in the above-described embodiments and their modifications, the case of applying to a network system composed of the Internet 199 has been described. However, the present invention is not limited to this. For example, it may be applied to a so-called intranet that communicates in the same manner as the Internet 199. Of course, the present invention is not limited to a network that communicates in the same manner as the Internet 199, and can be applied to a network of any communication method.

[0151] Also, in the above-described embodiments and their modifications, when executing the processes shown in the flowcharts of FIGS. 4 and 6, the case of executing a program pre-stored in the ROM 32 has been described. However, the present invention is not limited to this, and the program showing these procedures may be read from a storage medium storing the program into the RAM 34 and executed.

[0152] Also, the above-described embodiments and their modifications can be applied to each other. In addition, in the above-described embodiment and its modifications, the present invention is applied to the case where a nursery teacher provides childcare for children. However, the present invention is not limited to this, and can also be applied to other cases without departing from the gist of the present invention. For example, the present invention can also be applied when a caregiver other than a nursery teacher provides childcare, or when the childcare target is a person other than a child.

Explanation of Signs

[0153] 100…Generative 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 Terminal, 210…Nursery Teacher Terminal, 220…Wearable Device, 199…Internet

Claims

1. A registration means for registering activity information regarding the number of contacts between a childcare provider and a childcare recipient or activity information regarding the amount of activity of the childcare recipient in a knowledge base that can be referenced by an 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. In claim 1, A childcare support system characterized in that the registration means registers activity information regarding the number of times the caregiver has contact with the care recipient or activity information regarding the amount of activity of the care recipient, and activity information regarding the number of times the care recipient has contact with others in the knowledge base.

3. An input means for inputting a request including activity information regarding the number of contacts between a caregiver and a care recipient or activity information regarding the amount of activity of the care recipient into an AI model, the request including a request to generate information regarding the care recipient; A childcare support system characterized by having an acquisition means for acquiring information about the childcare recipient based on the number of contacts between the caregiver and the childcare recipient or the amount of activity of the childcare recipient, which is output from the AI ​​model in response to the request.

4. In claim 3, A childcare support system characterized in that the request includes activity information regarding the number of times the caregiver has contacted the care recipient or activity information regarding the amount of activity of the care recipient, and activity information regarding the number of times the care recipient has contacted others.

5. In any one of claims 1 to 4, A childcare support system characterized in that the request to generate information regarding the child is a request to generate information regarding planning, evaluation, or improvement of a group of childcare to be implemented collectively for multiple childcare recipients.

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

7. In any one of claims 1 to 4, A childcare support system, characterized in that the request to generate information about the child is a request to generate safety management information regarding the safety management of the child.

Images