system

Abstract

We provide the system. [Solution] Camera image analysis means, Means for collecting behavioral data of childcare recipients, A means of generating text using artificial intelligence based on collected behavioral data, A means of displaying the generated text in a format that allows for editing, A means of recording and distributing the revised text, A method for collecting and analyzing dietary data, generating results, and analyzing them using artificial intelligence, A means of proposing and distributing recipes for overcoming challenges based on the analysis results, A system that includes this.

Description

Technical Field

[0005]

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a childcare setting, the daily burden on childcare workers is to fill out the contact book. Also, for parents, there is a problem that it is difficult to grasp the child's eating situation, especially the leftovers, and to propose improvement methods. In response to these problems, it is desired to introduce the latest artificial intelligence technology to improve the efficiency of administrative work and the quality of information provided to parents.

Means for Solving the Problems

[0005] This invention is a system that includes camera image analysis means, means for collecting behavioral data of children under childcare, means for generating text using generative artificial intelligence based on the collected behavioral data, means for displaying the generated text in an editable format, means for recording and distributing the edited text, means for collecting and analyzing meal data and analyzing the results using generative artificial intelligence, and means for proposing and distributing recipes to overcome eating difficulties based on the analysis results. This system can reduce the administrative workload of childcare workers and provide parents with detailed information on their child's eating habits and suggestions for improvement.

[0006] "Camera image analysis means" refers to devices and software that use cameras installed in a nursery school to analyze children's behavior and eating habits.

[0007] "Behavioral data of children in childcare" refers to information about children's daily activities during childcare, such as their play, emotional changes, and interactions.

[0008] "Generative artificial intelligence" refers to AI algorithms and models that automatically generate text and suggestions based on collected data.

[0009] "Means of displaying in an editable format" refers to interfaces and functions that allow childcare workers to review generated text and edit it as needed.

[0010] "Means of recording and distributing" refers to a system for saving revised documents and reports in a database and sending them to relevant parties such as parents or guardians.

[0011] "Meal data" refers to information about the foods a child ate, the foods they left uneaten, and the quantities they consumed.

[0012] "Means of analysis" refers to devices and software used to analyze collected meal data and understand trends in food waste.

[0013] "Methods for suggesting recipes to overcome food waste" refers to AI algorithms and models that suggest ways to overcome food waste and propose new recipes based on the analysis of dietary data. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of the data processing device and smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention aims to streamline administrative tasks in childcare settings and improve the quality of information provided to parents through a series of systems that link camera image analysis means, generating artificial intelligence, and terminals used by childcare workers and parents. The specific implementation of this system will now be described.

[0036] System Configuration

[0037] 1. Camera image analysis means:

[0038] Multiple cameras will be installed inside the nursery school. These cameras will record the children's daily activities and mealtimes in real time.

[0039] The server acquires video data transmitted from the camera and uses analysis software to analyze the children's behavior and eating habits.

[0040] 2. Data collection and analysis:

[0041] Server: Collects data on children's behavior from camera footage. For example, it analyzes the type of play (e.g., playing with blocks, playing in the sandbox), changes in emotions (e.g., smiling, crying), and interactions with friends.

[0042] Server: Similarly, it analyzes video footage of meals to measure the amount of food eaten and left over. This allows for an understanding of the child's nutritional intake.

[0043] 3. Sentence generation:

[0044] Server: Based on the analyzed behavioral data, it uses generative artificial intelligence to automatically generate text for the contact log. For example, it creates a report such as, "Today, XX-chan played in the sandbox and was smiling."

[0045] Server: Based on meal data, it generates trends in food waste, analyzes them using artificial intelligence, and generates specific improvement suggestions and recipes.

[0046] 4. Viewing and editing data:

[0047] Terminal (caregiver's tablet): The app displays automatically generated communication log messages sent from the server. The caregiver reviews the messages and makes manual corrections as needed. For example, they might edit it to read, "Today, XX-chan was playing in the sandbox and had fun with her friends."

[0048] Device (Parent's Smartphone): The app displays corrected communication logs, meal reports, and recipes sent from the server. Parents can check details of their child's daily life and meals.

[0049] 5. Data distribution:

[0050] Server: Records corrected text and suggested recipes in a database and distributes them to the parent's device.

[0051] Device (parent's smartphone): Receives and displays information sent from the server via the app. This allows parents to have a detailed understanding of their child's daily activities and eating habits.

[0052] Specific example

[0053] For example, when recording what happened at daycare on a particular day, the process would be as follows:

[0054] 1. The server analyzes the video from the camera and collects data such as, "○○ played with blocks in the morning and drew pictures in the afternoon," and "She left some bell peppers at lunch."

[0055] 2. Based on the collected data, the server generates a communication log entry that reads, "Today, [child's name] enjoyed playing with blocks. In the afternoon, she drew a picture and then shared it with her friends. She left some bell peppers at lunch," and a recipe for overcoming her aversion to bell peppers, such as "A recipe for baking bell peppers with cheese to make them easier to eat."

[0056] 3. Device (caregiver's tablet): The caregiver reviews the generated text and makes corrections such as, "Today, XX-chan really enjoyed playing with blocks."

[0057] 4. Device (Parent's smartphone): The parent checks the corrected contact log and the cheese bake recipe.

[0058] This streamlines the administrative work of childcare workers and allows parents to receive detailed information about their child's daily routine and meals.

[0059] The following describes the processing flow.

[0060] Step 1:

[0061] The server acquires live video from cameras within the nursery school and inputs the video data into a camera image analysis system. The camera image analysis system analyzes data on children's behavior and emotions (e.g., smiling, crying) and collects it in real time.

[0062] Step 2:

[0063] The server stores the analyzed behavioral data in a database. Specifically, it records the type of play, changes in emotions, and the content of interactions in the database.

[0064] Step 3:

[0065] The server also acquires video data during meals and inputs it into the camera image analysis system. The analysis system automatically measures the type and amount of food eaten and the type and amount of food left uneaten, and collects this data.

[0066] Step 4:

[0067] The server stores the collected meal data in a database. This meal information includes details such as calorie intake and nutritional balance.

[0068] Step 5:

[0069] The server uses generative artificial intelligence (AI) to generate messages for the contact log based on stored behavioral and eating data. For example, it automatically generates messages such as, "Today, [child's name] played in the sandbox and had a great time with a smile on their face."

[0070] Step 6:

[0071] The server simultaneously uses AI generated from meal data to suggest recipes that help overcome food waste. For example, if bell peppers are left over, it will suggest a recipe for baked bell peppers with cheese.

[0072] Step 7:

[0073] The server distributes the generated communication log entries and suggested coping recipes to the childcare worker's terminal. The childcare worker can then review the entries using a tablet or other device.

[0074] Step 8:

[0075] Device (childcare worker's tablet): The childcare worker displays the generated text sent from the server on the app and checks its content. They manually correct the text as needed.

[0076] Step 9:

[0077] The user (childcare worker) confirms the corrected communication log entry by pressing the "Send" button in the app. The confirmed entry is then sent back to the server.

[0078] Step 10:

[0079] The server saves the revised text and suggested coping strategies to a database and distributes them to the parents' devices.

[0080] Step 11:

[0081] Device (Parent's Smartphone): Parents receive and view the final message from the server, meal reports, and recovery recipes via the app.

[0082] Step 12:

[0083] Users (parents) can check their child's daily behavior, eating habits, and suggested recipes on the app, which can help them with home care and meal planning.

[0084] This will significantly reduce the administrative burden on childcare workers and enable the provision of high-value information to parents.

[0085] (Example 1)

[0086] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0087] The current administrative work in daycare centers is extremely cumbersome, increasing the workload of childcare workers. In particular, the task of meticulously recording children's behavior and eating habits and providing this information to parents in the form of a communication log is time-consuming and laborious. Furthermore, the quality of information provided varies, and sometimes parents receive insufficient information. To address these issues, a system is needed that reduces the workload of childcare workers and improves the quality of information provided to parents.

[0088] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0089] In this invention, the server includes means for analyzing camera images, means for collecting behavioral data of children under childcare, means for generating text using generative artificial intelligence based on the collected behavioral data, means for displaying the generated text in a modifiable form, means for recording and distributing the modified text, means for collecting and analyzing meal data and analyzing the results using generative artificial intelligence, means for analyzing behavior and meal situations using analysis software, means for saving the modified communication log text and recipes to a database and distributing them to terminals, and means for inputting prompt sentences into an AI model to generate communication log text and meal improvement suggestions. This makes it possible to streamline administrative work in childcare centers, reduce the workload of childcare workers, and improve the quality of information provided to parents.

[0090] "Camera image analysis means" refers to a combination of a device and software that analyzes video data acquired from a camera to detect and identify the movement of objects and people within the image.

[0091] "Means for collecting behavioral data of children in childcare" refers to devices and software for collecting various behaviors of children within a nursery school as data.

[0092] "Methods for generating text using generative artificial intelligence" refers to artificial intelligence software that performs natural language processing based on collected data and automatically generates text.

[0093] "Means for displaying generated text in a modifiable format" refers to a display device and software for displaying automatically generated text in a viewable and editable format.

[0094] "Means for recording and distributing revised text" refers to a database and communication device for saving edited text and transmitting it to the necessary terminals.

[0095] "Methods for collecting and analyzing meal data and generating results using artificial intelligence" refers to devices and software that acquire data during meals, analyze it, and then use artificial intelligence to analyze the results.

[0096] "Means of analyzing behavior and eating habits using analysis software" refers to software used to analyze acquired video data, behavioral data, and eating data.

[0097] "Means for saving revised contact log entries and recipes to a database and distributing them to terminals" refers to the device and software for saving the final revised entries and generated recipes to a database and distributing them to each terminal.

[0098] "Means for generating contact log entries and dietary improvement suggestions by inputting prompt sentences into an AI model" refers to a system and software for automatically generating contact log entries and dietary improvement suggestions by inputting specific prompt sentences into a generating AI model.

[0099] This invention aims to streamline administrative tasks in childcare settings and improve the quality of information provided to parents through a series of systems that link camera image analysis means, generating artificial intelligence, and terminals used by childcare workers and parents.

[0100] 1. Setting up camera image analysis means and video analysis

[0101] Multiple cameras will be installed within the nursery school. These cameras will capture the children's daily activities and mealtimes in real time. A server will acquire the video data transmitted from the cameras and analyze the children's behavior and eating habits using analysis software (e.g., OpenCV or TENSORFLOW®).

[0102] As a concrete example, the server analyzes the morning footage to determine that "○○ was playing with building blocks," and the afternoon footage to determine that "○○ was drawing a picture." It also analyzes the mealtime footage to determine that "○○ left some bell peppers."

[0103] 2. Collection and storage of behavioral and dietary data

[0104] The server collects behavioral and eating data based on the analysis results and stores it in a database. Behavioral data includes the type of play (e.g., playing with blocks, playing in a sandbox), changes in emotion (e.g., smiling, crying), and interactions with friends. Eating data includes the amount of food eaten and leftovers.

[0105] For example, you can save data such as "2023-10-01 09:00:00 ○○-chan playing with blocks" or "2023-10-01 12:00:00 ○○-chan left bell peppers, amount: 15g".

[0106] 3. Automatic generation of communication log entries and dietary improvement suggestions.

[0107] The server uses generated artificial intelligence based on collected behavioral and dietary data to automatically generate messages for the contact book and suggestions for dietary improvements. The server inputs the necessary prompts into the generated AI model.

[0108] Examples of specific prompt messages are as follows:

[0109] Camera image analysis results:

[0110] Morning activities: Playing with building blocks

[0111] Afternoon activity: Drawing pictures

[0112] Meal details: Left the bell peppers uneaten at lunch.

[0113] Based on this, please automatically generate the following contact log message and dietary improvement suggestions:

[0114] Contact book entry:

[0115] Dietary improvement suggestions:

[0116] As a result, the server generates a communication log entry such as, "Today, [child's name] enjoyed playing with blocks. In the afternoon, she drew pictures with her friends. At lunch, she left some bell peppers," and a suggestion for improving meals such as, "A recipe for baking bell peppers with cheese to make them easier to eat."

[0117] 4. Displaying and editing data

[0118] The childcare worker's device (tablet) displays automatically generated communication log documents sent from the server, allowing the childcare worker to review and edit them. The childcare worker then sends the edited document to the server, completing the revision process.

[0119] Afterward, the parent's device (smartphone) displays the corrected communication log, meal reports, and recipes for overcoming challenges that were sent from the server via the app. Through the app, the parent can check details of their child's daily life and meals.

[0120] 5. Data distribution and viewing

[0121] The server saves the corrected contact log entries and generated recipes to a database and distributes them to the parent's device. Parents can check the information received from the server through the app. This allows parents to have a detailed understanding of their child's daily activities and eating habits.

[0122] As described above, the present invention makes it possible to improve the efficiency of administrative work in nurseries, reduce the workload of childcare workers, and improve the quality of information provided to parents.

[0123] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0124] Step 1:

[0125] Acquiring camera images

[0126] The server acquires video data in real time from multiple cameras within the nursery school. The cameras are installed to monitor the children's daily activities and mealtimes.

[0127] Specific actions:

[0128] 1.1 The server receives the video stream via the camera's IP address.

[0129] 1.2 The server saves the received video to storage in real time.

[0130] Input: Camera IP address and video data

[0131] Output: Saved video data

[0132] Step 2:

[0133] Analysis of video data

[0134] The server analyzes the acquired video data using analysis software (e.g., OpenCV or TensorFlow) to identify the children's behavior and eating habits.

[0135] Specific actions:

[0136] 2.1 The server extracts frames from the video data and applies specific algorithms to perform face and object recognition.

[0137] 2.2 The server converts the recognition results into vector data and extracts behavioral and dietary information.

[0138] Input: Saved video data

[0139] Output: Behavioral data and dietary data

[0140] Step 3:

[0141] Collection and storage of behavioral and dietary data

[0142] The server collects behavioral data (e.g., type of play, emotional changes) and eating data (e.g., amount of food eaten and leftovers) from the analysis results and stores them in a database.

[0143] Specific actions:

[0144] 3.1 The server saves the activity data to the database. For example, it saves data such as "2023-10-01 09:00:00 ○○-chan playing with blocks".

[0145] 3.2 The server saves meal data to a database. For example, it saves data such as "2023-10-01 12:00:00 ○○-chan Bell pepper leftovers Amount: 15g".

[0146] Input: Behavioral data and dietary data

[0147] Output: Behavioral and dietary data stored in the database

[0148] Step 4:

[0149] Automatic generation of communication log entries and meal improvement suggestions.

[0150] The server uses generated artificial intelligence based on collected behavioral and dietary data to automatically generate messages for the contact book and suggestions for dietary improvements. The server inputs the necessary prompts into the generated AI model.

[0151] Specific actions:

[0152] 4.1 The server converts the behavioral data into a prompt message. For example, it might convert it to something like, "Today, XX enjoyed playing with building blocks. In the afternoon, she drew pictures with her friends."

[0153] 4.2 The server converts the meal data into a prompt message and generates a "cheese bake recipe to make bell peppers easier to eat".

[0154] Input: Behavioral data and dietary data

[0155] Output: Communication log entries and suggestions for improving meals

[0156] Step 5:

[0157] Viewing and editing data

[0158] The terminal (the childcare worker's tablet) displays automatically generated communication log documents sent from the server, allowing the childcare worker to review and edit them.

[0159] Specific actions:

[0160] 5.1 The device sends an API request to the server to retrieve automatically generated contact log entries and meal improvement suggestions.

[0161] 5.2 The device displays the acquired information within the app, allowing childcare workers to freely edit the text.

[0162] 5.3 The terminal sends the edited text back to the server, and the correction is complete.

[0163] Input: Automated contact log entries and meal improvement suggestions

[0164] Output: Communication log document edited by the childcare worker

[0165] Step 6:

[0166] Data distribution and viewing

[0167] The server saves the corrected contact log entries and generated recipes to a database and distributes them to the parents' devices.

[0168] Specific actions:

[0169] 6.1 The server saves the corrected contact log entries and recipes to the database.

[0170] 6.2 The server sends a notification to the parent's device informing them that new data is available.

[0171] 6.3 The device (the parent's smartphone) receives and displays information sent from the server via the app. Parents can gain a detailed understanding of their child's daily activities and eating habits.

[0172] Input: Communication log entries edited by childcare workers and generated recipes

[0173] Output: Communication log entries and meal improvement suggestions for parents to view.

[0174] (Application Example 1)

[0175] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0176] In daycare operations, there is a need to understand children's behavior and eating habits in detail and to streamline the provision of information to parents. Similarly, in physical stores, there is a need for a system that analyzes customer behavior in real time to efficiently support store operations. Existing methods require a great deal of time and effort to collect and analyze individual data, resulting in a heavy workload and limitations in the quality of customer service.

[0177] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0178] In this invention, the server includes camera image analysis means, means for collecting behavioral data of childcare recipients, means for generating text using generative artificial intelligence based on the collected behavioral data, means for displaying the generated text in an editable format, means for recording and distributing the edited text, means for collecting and analyzing meal data and analyzing the results using generative artificial intelligence, means for proposing and distributing recipes to overcome challenges based on the analysis results, means for analyzing customer trends in real time, means for generating in-store discount coupons and product recommendations based on the analysis results, and means for distributing the generated recommendation information to staff. This enables improved operational efficiency in childcare centers and customer behavior analysis and optimal service provision in physical stores.

[0179] A "camera image analysis means" is a means of analyzing video data acquired from a camera and extracting specific information.

[0180] "Means for collecting behavioral data of children in childcare" refers to methods for observing children's behavior in a nursery school and collecting that data.

[0181] "Methods for generating text using artificial intelligence based on behavioral data" refers to an artificial intelligence system that analyzes collected behavioral data and automatically generates text based on the results.

[0182] "Means for displaying generated text in an editable format" refers to means for displaying automatically generated text in a way that allows users to edit it.

[0183] "Means for recording and distributing revised text" refers to methods for recording the revised text in a database and distributing it to the necessary stakeholders.

[0184] "A means of collecting meal data, analyzing the results, and generating analysis using artificial intelligence" refers to a means of collecting data on meals for those receiving childcare and analyzing it using artificial intelligence.

[0185] "A method for proposing and distributing recipes to overcome dietary problems based on analysis results" refers to a method of proposing dietary improvement measures based on the results of analyzing dietary data and distributing that information.

[0186] "Methods for analyzing customer behavior in real time" refers to methods for monitoring and analyzing customer behavior within a store in real time.

[0187] "Methods for generating in-store discount coupons and product recommendations based on analysis results" refers to methods for generating appropriate discount coupons and product recommendations based on the results of customer behavior analysis.

[0188] "Means for distributing generated recommendation information to staff" refers to the means for distributing automatically generated recommendation information to store staff.

[0189] This invention aims to improve operational efficiency and the quality of information provision through a system that links camera image analysis means, generating artificial intelligence, and terminals in daycare centers and physical stores. The following describes specific embodiments for implementing this invention.

[0190] System Configuration

[0191] The system of the present invention includes the following means:

[0192] 1. Camera image analysis means

[0193] Multiple cameras will be installed in daycare centers and stores to capture children's behavior and customers' movements in real time.

[0194] The server acquires video data transmitted from the camera and uses image analysis software such as OpenCV or TensorFlow to analyze behavior and trends.

[0195] 2. Data Collection and Analysis

[0196] Server: Collects behavioral data and customer behavior data from camera footage. Behavioral data includes the types of play children engage in and changes in their emotions, while customer behavior data includes movement patterns within the store and products they show interest in.

[0197] Server: Analyzes video footage of meals to measure the amount of food eaten and left over. Store systems analyze which items customers showed interest in within the shopping area.

[0198] 3. Sentence generation

[0199] Server: Based on analyzed behavioral data, it automatically generates text using generative artificial intelligence (AI model). For example, in a nursery school, it might create a report saying, "Today, XX played in the sandbox and was smiling," and in a store, it might create a customer behavior report saying, "She spent a particularly long time looking at item A in the cosmetics section."

[0200] Server: Based on the analysis data, it generates recipes to overcome dietary restrictions, in-store discount coupons, and product recommendations.

[0201] 4. Displaying and editing data

[0202] Devices (tablets in daycare centers, smartphones for store staff): Automatically generated text is displayed in the app, and childcare workers and staff can review the text and manually correct it as needed.

[0203] Device (parent's smartphone, store's customer app): Displays corrected contact information and meal reports sent from the server, as well as discount coupons and product recommendations, within the app.

[0204] 5. Data distribution

[0205] Server: Records corrected text and suggested information in a database and distributes it to parents' and customers' devices.

[0206] Device (parent's smartphone, store's customer app): Displays received information in detail through the app.

[0207] Specific examples of hardware and software

[0208] Hardware: IP cameras, servers (such as Amazon AWS®), tablets, smartphones.

[0209] Software: Image analysis libraries (OpenCV, TensorFlow), data analysis libraries (NumPy, Pandas), notification system (Firebase).

[0210] Specific example

[0211] For example, when recording what happened at daycare on a particular day, the process would be as follows:

[0212] The server analyzes the camera footage and collects data such as, "○○-chan played with blocks in the morning and drew pictures in the afternoon."

[0213] Based on the collected data, the server generates a communication log entry such as, "Today, [child's name] enjoyed playing with blocks," which is then reviewed by the childcare worker and distributed to the parents.

[0214] Device (caregiver's tablet): The caregiver reviews the generated text and manually corrects it to, "Today, XX-chan really enjoyed playing with blocks."

[0215] Device (Parent's smartphone): The parent / guardian checks the corrected contact log.

[0216] The same applies to stores:

[0217] The server analyzes camera footage to detect customers who are lingering in front of specific products for extended periods.

[0218] Based on that data, the server generates recommendation information such as "Offer a discount coupon for item A" and distributes it to the staff.

[0219] Terminal (store staff's smartphone): Checks the generated recommendation information and provides coupons to customers.

[0220] Example of a prompt

[0221] Input the following prompts into the AI ​​model to generate information:

[0222] According to today's in-store analytics data, several customers showed interest in the cosmetics section. Based on this, please generate the following actions.

[0223] Offering discount coupons in the cosmetics section.

[0224] Notification to staff

[0225] Product recommendations for your next visit

[0226] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0227] Step 1:

[0228] Acquiring camera images

[0229] The server acquires video data in real time from cameras installed in daycare centers and physical stores. This input data is video frames, and its output is a stream of video data for image analysis processing.

[0230] Step 2:

[0231] Image analysis and extraction of behavioral data

[0232] The server analyzes the acquired video data using tools such as OpenCV and TensorFlow. Specifically, it identifies children's behavior and customer movements from video frames, extracting data such as "a child is playing with blocks" or "a customer is staying with a specific product for an extended period." The input is camera video data, and the output is analyzed behavioral and movement data.

[0233] Step 3:

[0234] Text generation based on behavioral data

[0235] The server uses a generative AI model to generate appropriate sentences based on the analyzed behavioral data. For example, it automatically generates sentences such as "○○ played in the sandbox" in a nursery school setting, or "○○ showed interest in product A" in a physical store setting. The input is the analyzed behavioral data, and the output is the generated sentences.

[0236] Step 4:

[0237] Display and edit the generated text

[0238] The devices (tablets in daycare centers or smartphones for store staff) display the generated text in an editable format. Childcare workers and staff review this text and make manual corrections as needed. Specifically, they edit the text displayed on the screen using touch input or a keyboard. This input is the generated raw text, and the output is the corrected version.

[0239] Step 5:

[0240] Recording and distribution of revised text

[0241] The server records the corrected text in a database and distributes it to the parents' and customers' devices. Specifically, it saves the corrected text to a cloud-based database and distributes it to each device in a pre-encoded format. The input is the corrected text, and the output is the information displayed on the parents' and customers' devices.

[0242] Step 6:

[0243] Analysis of meal data and customer behavior data

[0244] The server collects and analyzes meal data from daycare centers and customer behavior data from physical stores. Specifically, it acquires data such as "○○ left some bell peppers" from meals and "a customer stayed in front of a particular product for a long time" from stores. The input is raw data on meals and customer behavior, and the output is the analyzed data.

[0245] Step 7:

[0246] Generating recommended information and improvement measures

[0247] The server generates recipes to overcome difficulties, discount coupons, and product recommendations based on the analysis results. Specifically, the AI ​​model generates recipes to make bell peppers easier to eat, or creates discount coupons for specific products, based on the analysis data. The input is the analysis results data, and the output is the generated recommendations and improvement measures.

[0248] Step 8:

[0249] Distribution of recommended information and improvement measures

[0250] The server distributes the generated recommendations and improvement suggestions to childcare workers, staff, parents, and customers. Specifically, it inputs prompts into an AI model to generate recommendations and then distributes the results. This input consists of the generated recommendations and improvement suggestions, and the output is the information distributed to the devices of parents and customers.

[0251] Example of a prompt

[0252] Input the following prompts into the AI ​​model to generate information:

[0253] According to today's in-store analytics data, several customers showed interest in the cosmetics section. Based on this, please generate the following actions.

[0254] Offering discount coupons in the cosmetics section.

[0255] Notification to staff

[0256] Product recommendations for your next visit

[0257] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0258] This invention is a system that improves the efficiency of administrative work in childcare settings and the quality of information provided to parents by linking camera image analysis means, generative artificial intelligence (AI), an emotion engine, and terminals used by childcare workers and parents. This system collects children's behavioral and emotional data in real time and automatically generates text, meal reports, and overcoming recipes using generative AI.

[0259] System Configuration

[0260] 1. Camera image analysis means:

[0261] Multiple cameras are installed within the nursery school to capture the children's daily activities and mealtimes in real time.

[0262] The server acquires video data transmitted from the camera and uses camera image analysis tools to analyze the children's behavior.

[0263] 2. Emotional Engine:

[0264] The server analyzes the children's facial expressions from the camera footage and collects emotional data in real time, such as smiles, crying faces, and focused faces.

[0265] The emotional data recognized by the emotion engine is recorded in the database as behavioral data and dietary data.

[0266] 3. Data collection and analysis:

[0267] The server collects behavioral and emotional data from camera footage and stores it in a database. Behavioral data includes the type of play and interactions with friends.

[0268] The server analyzes video footage of the meal, recording the types and quantities of food eaten, the types and quantities of food left uneaten, and the emotions experienced during the meal (e.g., expressions of displeasure, expressions of satisfaction), and stores this information in a database.

[0269] 4. Text generation using artificial intelligence (AI):

[0270] The server automatically generates messages for the contact log using a generative AI based on collected behavioral and emotional data. For example, it might generate a message like, "Today, [child's name] played in the sandbox and had a great time with a smile on their face."

[0271] The server uses AI to generate recipes to help overcome food waste, based on meal and emotional data. For example, if a customer leaves bell peppers uneaten, it will suggest a "Bell Pepper and Cheese Bake Recipe."

[0272] 5. Viewing and editing data:

[0273] Device (childcare worker's tablet): Provides an app that displays generated text sent from the server and allows childcare workers to manually edit the text. For example, "Today, XX-chan played in the sandbox and had fun with a smile." → "Today, XX-chan built a sandcastle and had fun with her friends."

[0274] Device (parent's smartphone): Provided via an app that displays corrected contact logs, meal reports, and recipes sent from the server.

[0275] 6. Data distribution:

[0276] The server saves the revised contact log entries and suggested coping strategies to a database and automatically distributes them to the parents' devices.

[0277] Device (Parent's smartphone): Allows parents to view the information sent via the app.

[0278] Specific example

[0279] Collecting data on children's behavior

[0280] For example, during a day at the nursery school, the server analyzes camera footage and collects behavioral data such as, "○○ played with blocks in the morning and drew pictures in the afternoon," as well as emotional data such as, "She was smiling while playing with blocks," and "She had a focused expression while drawing."

[0281] Contact book message generation

[0282] Based on the collected behavioral and emotional data, the server generates a message for the communication log, such as, "Today, [child's name] enjoyed playing with blocks, and in the afternoon, she was focused on drawing."

[0283] Collection and analysis of dietary data

[0284] The server analyzes the lunchtime video and collects meal data such as "Child XX ate all the rice and left the green peppers." and emotion data such as "The expression of dislike when eating green peppers."

[0285] Generation of Overcoming Recipes

[0286] Based on the collected meal data and emotion data, the server proposes a "cheese grilling recipe to make green peppers easier to eat."

[0287] Display and Editing of Data

[0288] Terminal (nursery teacher's tablet): The nursery teacher checks the contact book text generated and revises the text such as "Today, child XX enjoyed playing with blocks and concentrated on painting in the afternoon."

[0289] Terminal (parent's smartphone): The parent checks the revised contact book text and the overcoming recipe and uses it as a reference for cooking.

[0290] As a result, the administrative work of the nursery teacher is streamlined, and the parents can receive detailed information and specific suggestions regarding their child's daily life and meals.

[0291] The following explains the processing flow.

[0292] Step 1:

[0293] The server acquires live video from the camera installed in the nursery and inputs the video data into the camera image analysis means. The camera image analysis means analyzes the child's actions (e.g., type of play, movement route) and generates action data in real time.

[0294] Step 2:

[0295] The server inputs the same video data into the emotion engine. The emotion engine analyzes the child's facial expressions and generates emotion data in real time, such as smiles, crying faces, and surprised expressions. This allows for a detailed record of the child's emotional changes.

[0296] Step 3:

[0297] The server stores behavioral and emotional data generated by the camera image analysis system and emotion engine in a database. This allows for a detailed record of the child's daily life.

[0298] Step 4:

[0299] The server inputs video data from lunchtime into a camera image analysis system to analyze eating behavior. It measures the type and amount of food eaten and the type and amount of food left uneaten, and generates meal data.

[0300] Step 5:

[0301] The server inputs video data from the meal into an emotion engine and analyzes the child's facial expressions while eating. It generates emotional data such as joy, disgust, and satisfaction during the meal. This also records the child's feelings towards eating.

[0302] Step 6:

[0303] The server stores meal data and emotional data generated by the camera image analysis system and emotion engine in a database. This allows for a detailed record of the eating situation.

[0304] Step 7:

[0305] The server uses generative artificial intelligence (AI) to generate messages for the contact book based on stored behavioral and emotional data. For example, it automatically generates a message like, "Today, XX-chan was playing in the sandbox and was having fun with a smile on her face."

[0306] Step 8:

[0307] Based on the saved meal data and emotion data, the server uses a generative artificial intelligence (AI) to generate recipes for overcoming food waste. For example, if peppers are left uneaten, it proposes a "pepper cheese bake recipe".

[0308] Step 9:

[0309] The server distributes the generated contact book text and the overcoming recipe to the caregiver's terminal. The caregiver can check the text using a terminal such as a tablet.

[0310] Step 10:

[0311] Terminal (caregiver's tablet): The caregiver displays the generated text sent from the server on the app and checks the content. Manually corrects the text if necessary and performs a final check.

[0312] Step 11:

[0313] The user (caregiver) confirms the corrected contact book text by pressing the "Send" button in the app. The confirmed text is sent back to the server again and saved in the database.

[0314] Step 12:

[0315] The server distributes the corrected contact book text and the proposed overcoming recipe to the guardian's terminal. The guardian can check this information through the app.

[0316] Step 13:

[0317] Terminal (guardian's smartphone): The guardian browses the contact book text, meal report, and overcoming recipe sent from the server through the app.

[0318] Step 14:

[0319] Users (parents) can check their child's daily behavior, eating habits, and suggested recipes on the app, and use this information to improve home care and meal planning.

[0320] This reduces the administrative burden on childcare workers and provides parents with detailed information about their child's daily life and meals.

[0321] (Example 2)

[0322] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0323] In childcare settings, childcare workers are burdened with a wide range of administrative tasks, including observing and recording children's behavior and emotions, writing in communication notebooks, and managing meals. Furthermore, while parents want detailed information about their children's daily lives and meals, this information is often insufficient. Therefore, there is a need to streamline the administrative work of childcare workers and improve the quality of information provided to parents.

[0324] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0325] In this invention, the server includes means for analyzing camera images, means for collecting behavioral and emotional data of the child being cared for, means for generating text using generative artificial intelligence based on the collected behavioral and emotional data, means for displaying the generated text in a modifiable form, means for recording and distributing the modified text, means for collecting and analyzing meal data and analyzing the results using generative artificial intelligence, and means for proposing and distributing recipes to overcome difficulties based on the analysis results. This streamlines the administrative work of childcare workers, and allows parents to receive detailed information about their child's daily life and meals, as well as specific suggestions.

[0326] "Means of analyzing camera images" refers to devices and software that analyze video data acquired by cameras installed within the nursery school, and are used to recognize children's behavior and facial expressions.

[0327] "Action data of children in childcare" refers to information about the various activities and behaviors that children engage in within the nursery school, including, for example, the types of play and interactions.

[0328] "Emotional data" refers to information about emotions recognized from children's facial expressions, including smiles, crying faces, and focused faces.

[0329] "Means of generating text using generative artificial intelligence" refers to artificial intelligence technology that automatically generates text in natural language based on collected data, and this includes, for example, generative AI models.

[0330] "Means of displaying generated text in an editable format" refers to devices or software that allow childcare workers to review automatically generated text and make corrections as needed, and includes, for example, tablet devices.

[0331] "Means for recording and distributing revised text" refers to systems and methods for saving text revised by childcare workers in a database and distributing it to parents in real time.

[0332] "Mealtime data" refers to information about the types and quantities of food children ate during meals, as well as the types and quantities of food they left uneaten.

[0333] "Methods of analysis using generative artificial intelligence" refers to artificial intelligence technology that analyzes collected dietary data and automatically generates new insights and suggestions based on it, and includes, for example, AI models.

[0334] The method of proposing and distributing "recipes to overcome allergies" refers to a method of automatically generating cooking recipes that make it easier for children to eat specific foods, based on analyzed dietary data, and then distributing these recipes to parents.

[0335] The present invention is configured as a system to improve the efficiency of administrative work in childcare settings and the quality of information provided to parents. This system includes means for analyzing camera images, means for collecting behavioral and emotional data, means for generating text using generative artificial intelligence based on the collected data, means for displaying the generated text in an editable format, means for recording and distributing the edited text, means for collecting, analyzing, and analyzing meal data using generative artificial intelligence, and means for proposing and distributing recipes for overcoming health challenges.

[0336] Hardware and software configuration

[0337] The system consists of the following hardware and software.

[0338] Camera: High-resolution camera (e.g., general-purpose high-resolution camera)

[0339] Server: A server for analyzing video data and collecting and analyzing behavioral data, emotional data, and dietary data.

[0340] Software: Camera image analysis libraries (e.g., OpenCV), emotion recognition libraries (e.g., Emotion Recognition API), generative AI models (e.g., GPT-3®)

[0341] Devices: Tablet devices used by childcare workers, and smartphones used by parents.

[0342] Program Implementation

[0343] 1. Acquisition of video data

[0344] The server acquires video data from the camera in real time. This video data is acquired using, for example, the RTSP protocol.

[0345] 2. Analysis of video data

[0346] The server uses OpenCV to analyze video data and recognize the children's behavior (e.g., type of play, interactions).

[0347] For example, one might observe a child playing with building blocks in the morning.

[0348] 3. Recognition and collection of emotional data

[0349] The server uses an emotion recognition API to analyze the children's facial expressions from the video data and recognize emotional data (e.g., smiling, crying, concentrating).

[0350] For example, we may recognize a smile while a child is playing with building blocks.

[0351] 4. Storage of behavioral and emotional data

[0352] The server stores the analyzed and recognized behavioral and emotional data in a database. Transaction management is performed to ensure data integrity and security.

[0353] For example, the system saves data indicating that the child played with building blocks in the morning and was smiling at that time.

[0354] 5. Automatic sentence generation

[0355] The server automatically generates contact book entries using a generative AI model (e.g., GPT-3) based on the collected data.

[0356] For example, it can generate sentences like, "Today, [Name] enjoyed playing with building blocks, and in the afternoon, she was concentrating on drawing."

[0357] Example of a prompt:

[0358] Today, [Name] enjoyed playing with building blocks, and in the afternoon, she was concentrating on drawing.

[0359] 6. Correction and display of generated text

[0360] The device (the childcare worker's tablet) displays the generated communication log document, and the childcare worker makes corrections as needed.

[0361] For example, change "Today, XX enjoyed playing with blocks, and in the afternoon, she was focused on drawing." to "Today, XX built a sandcastle and had fun with her friends."

[0362] 7. Collection and analysis of dietary data

[0363] The server analyzes video footage of meals and collects meal data (e.g., types and amounts of food eaten, types and amounts of food left over).

[0364] For example, we collect data such as "○○-chan ate all her rice but left the bell peppers."

[0365] 8. Generating a recipe for overcoming the problem

[0366] The server generates recipes to help overcome food waste based on the collected meal data.

[0367] For example, I'd like to suggest a recipe for "cheese-baked bell peppers to make them easier to eat."

[0368] 9. Distribution of revised text and recipes

[0369] The server saves the revised contact log entries and suggested recipes to a database and distributes them to the parents' devices.

[0370] The device (the parent's smartphone) receives information sent from the server and displays it to the user.

[0371] For example, a parent might see a message in the communication notebook saying, "Today, [child's name] built a sandcastle and had fun with their friends," as well as a recipe for "baked bell peppers with cheese."

[0372] This will streamline the administrative work of childcare workers, and allow parents to receive detailed information about their child's daily life and meals, as well as specific suggestions.

[0373] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0374] Step 1: Acquire video data

[0375] The server acquires video data in real time from multiple cameras installed within the nursery school. The input is the video stream transmitted from the cameras (for example, using the RTSP protocol). The acquired video data is stored in a temporary storage area. For example, the server receives the video via the camera's IP address and saves it to the temporary storage area.

[0376] Step 2: Analysis of video data

[0377] The server uses OpenCV to analyze video data stored in a temporary storage area. The input is video data. As data processing, an object detection algorithm (e.g., YOLO) is applied to each frame to recognize children's actions. The output is the recognized action data. For example, the server detects children playing with blocks in the morning.

[0378] Step 3: Recognizing and collecting emotional data

[0379] The server uses an emotion recognition API to analyze children's facial expressions from analyzed video data. The input is the analyzed video data. As part of the data processing, an emotion recognition algorithm is applied to recognize emotions such as smiles, crying faces, and focused faces. The output is the recognized emotion data. For example, the server recognizes a smile while a child is playing with blocks.

[0380] Step 4: Saving behavioral and emotional data

[0381] The server stores recognized behavioral and emotional data in a database. The input consists of behavioral and emotional data. Data processing involves converting the data into a well-formed format (e.g., JSON) and inserting it into the database using SQL queries. The output is the record in the database. For example, the server might store data about playing with building blocks in the morning and the smile associated with that activity in the database.

[0382] Step 5: Automatic text generation

[0383] The server generates contact log entries using a generative AI model (e.g., GPT-3) based on behavioral and emotional data stored in the database. The input consists of behavioral and emotional data. As a data operation, prompt sentences are provided to the generative AI model for inference. The output is an automatically generated contact log entry. For example, it might generate an entry like, "Today, XX enjoyed playing with blocks, and in the afternoon, she was concentrating on drawing."

[0384] Step 6: Modify and display the generated text

[0385] The terminal (the childcare worker's tablet) displays the generated text sent from the server, and the childcare worker makes corrections as needed. The input is the automatically generated communication log text. The output is the corrected communication log text. For example, the childcare worker might change "Today, XX enjoyed playing with blocks, and in the afternoon, she was concentrating while drawing pictures." to "Today, XX built a sandcastle and enjoyed playing with her friends."

[0386] Step 7: Collection and analysis of dietary data

[0387] The server analyzes video footage of meals and collects meal data. The input is video data of the meal. As part of the data processing, a video analysis algorithm is applied to extract the contents of the meal and any leftovers. The output is the analyzed meal data. For example, the server collects data such as, "○○-chan ate all of her rice, but left the bell peppers."

[0388] Step 8: Generating a Recipe for Overcoming Challenges

[0389] The server generates recipes to overcome food allergies using a generative AI model based on meal data. The input is meal data. As a data calculation, prompts are provided to the generative AI model for inference. The output is the generated recipe. For example, it might generate a "cheese bake recipe to make bell peppers easier to eat."

[0390] Step 9: Distribute the revised text and recipe.

[0391] The server saves the revised contact log entries and suggested recipes to a database and distributes them to the parent's device. The input is the revised entries and generated recipes. The output is the notification and display information on the parent's device. For example, the parent's smartphone might receive a contact log entry that reads, "Today, [child's name] built a sandcastle and had fun with their friends," along with a recipe for "Grilled bell peppers with cheese."

[0392] (Application Example 2)

[0393] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0394] In modern brick-and-mortar stores, it is difficult to collect real-time data on children's behavior and emotional changes in play areas and provide detailed reports to parents. Therefore, parents have difficulty understanding their child's play status and emotional changes. Furthermore, manually creating these reports is burdensome, and efficiency improvements are needed.

[0395] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a camera image analysis means, a means for collecting subject behavior data, a means for generating text using generative artificial intelligence based on the collected behavior data, a means for displaying the generated text in a modifiable form, a means for recording and distributing the modified text, a means for collecting and analyzing meal data and analyzing the results using generative artificial intelligence, a means for proposing and distributing overcoming recipes based on the analysis results, and a means for generating and distributing a play status report based on behavior data and emotional data. This makes it possible for parents to check their child's play status and emotional changes in real time via their smartphone.

[0396] A "camera image analysis means" is a device or system that uses a camera to analyze the behavior and facial expressions of a subject in real time and collect the data.

[0397] "Subject behavior data" refers to information about the subject's behavior acquired through sensors such as cameras, and includes, for example, the type of play and details of their actions.

[0398] "Generative artificial intelligence" is an artificial intelligence technology that has the ability to automatically generate text and reports based on collected data.

[0399] "Methods for generating text" refers to a system that automatically generates text using generative artificial intelligence based on collected behavioral and emotional data.

[0400] "Means for displaying generated text in an editable format" refers to a system that provides an interface allowing users to review and edit generated text.

[0401] "Means for recording and distributing revised text" refers to a system for saving revised text and distributing it to relevant parties.

[0402] "Dietary data" refers to detailed information about a person's diet, such as the amount of food they consumed and the amount of food they left uneaten.

[0403] "A means of analyzing the results using generative artificial intelligence" refers to a technology that analyzes collected dietary data and then uses generative artificial intelligence to analyze the results.

[0404] A "recipe to overcome a dislike" is a recipe suggestion designed to make it easier for a person to consume foods they dislike, and may include suggestions for cooking methods or ingredient combinations.

[0405] "Behavioral and emotional data" refers to data about the subject's behavior and the emotional changes associated with that behavior.

[0406] A "play activity report" is a detailed report describing a child's play activities and emotional changes, intended for parents to review.

[0407] "Means of distribution" refers to a system that automatically sends documents and reports generated or modified by generative artificial intelligence to relevant parties.

[0408] "Through a parent's smartphone" refers to a method of viewing and manipulating information and data using a smartphone.

[0409] This invention is a system that collects behavioral and emotional data of children in play areas within physical stores and provides detailed reports to parents in real time. The following describes a specific form for implementing this system.

[0410] System Configuration

[0411] The system consists of the following elements:

[0412] 1. Camera image analysis means:

[0413] Multiple cameras will be installed within the play area. These cameras will capture children's daily behavior and emotional changes in real time.

[0414] The server acquires video data transmitted from the camera and uses camera image analysis tools to analyze the children's behavior.

[0415] 2. Means for collecting behavioral and emotional data:

[0416] The server collects behavioral and emotional data from camera footage and stores it in a database. Behavioral data includes the type of play and interactions with friends.

[0417] The emotion engine analyzes facial expressions from video and collects emotional data in real time, such as smiles, crying faces, and focused faces.

[0418] 3. Text generation methods using AI:

[0419] The server uses a generative AI to automatically generate playtime reports based on collected behavioral and emotional data. For example, it might generate a sentence like, "Today, [child's name] had a lot of fun playing on the slide and smiled a lot."

[0420] 4. Means for correcting the generated text:

[0421] Device (parent's smartphone): Displays generated text sent from the server, allowing the parent to manually review the text.

[0422] 5. Means of recording and distributing documents:

[0423] The server saves the corrected text to a database and automatically delivers it to the parent's device. Parents can view the transmitted information through a smartphone app.

[0424] Examples

[0425] Specific examples of data collection and analysis

[0426] Parents install a smartphone app, and when their child enters the play area, multiple cameras track the child's actions and send behavioral and emotional data to a server. For example, when a child is playing on a slide, the camera films the action, and the server analyzes the footage to collect behavioral data such as "playing on a slide" and emotional data such as "smiling a lot."

[0427] Report generation and distribution

[0428] The server uses generative AI to generate reports based on collected behavioral and emotional data. For example, it might generate a sentence like, "Today, [child's name] was playing on the slide and laughing happily." The generated report is sent to a smartphone app, allowing parents to check their child's play status in real time.

[0429] Example of a prompt

[0430] "Please generate a detailed report based on the child's behavior and emotional data in the play area. The child's behavior is 'playing on the slide,' and their emotion is 'smiling a lot.'"

[0431] In this way, parents can instantly grasp their child's playing situation and emotional changes, allowing them to let their children play in the play area of ​​the physical store with peace of mind.

[0432] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0433] Step 1:

[0434] The server acquires video data in real time from cameras installed within the play area. The cameras capture the children's actions and expressions within the play area and transmit this video data to the server. Camera video data serves as input, forming the basis for behavioral and emotional data.

[0435] Step 2:

[0436] The server analyzes camera video data using camera image analysis tools. Specifically, it detects specific actions from the video data and analyzes facial expressions to extract emotion data. For example, it can detect actions such as playing on a slide or facial expressions such as smiling. Video data is the input, and action data and emotion data are obtained as output.

[0437] Step 3:

[0438] The server stores the analyzed behavioral and emotional data in a database. This data is used for subsequent processing. Behavioral and emotional data are the inputs, and the output is stored in the database.

[0439] Step 4:

[0440] The server uses a generative AI to generate a play situation report based on stored behavioral and emotional data. The generative AI is given a prompt, for example, "The child's behavior is 'playing on the slide,' and their emotion is 'smiling a lot.' Please generate a detailed report based on this." The output is an automatically generated report document.

[0441] Step 5:

[0442] The device (the parent's smartphone) receives the generated report document sent from the server. The parent can review this report and make corrections as needed. The generated report document is the input, and the corrected report document is the output.

[0443] Step 6:

[0444] The server saves the corrected report document to the database and then distributes it again to the parent's device. The input is the corrected report document, and the output is saving to the database and distributing it to the parent.

[0445] Step 7:

[0446] Users (parents) can review the final report via their device, gaining real-time insights into their child's play status and emotional changes. The final report is the input, and the output provides parents with peace of mind and a clear understanding of the information.

[0447] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0448] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0449] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0450] [Second Embodiment]

[0451] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0452] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0453] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0454] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0455] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0456] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0457] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0458] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0459] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0460] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0461] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0462] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0463] This invention aims to streamline administrative tasks in childcare settings and improve the quality of information provided to parents through a series of systems that link camera image analysis means, generating artificial intelligence, and terminals used by childcare workers and parents. The specific implementation of this system will now be described.

[0464] System Configuration

[0465] 1. Camera image analysis means:

[0466] Multiple cameras will be installed inside the nursery school. These cameras will record the children's daily activities and mealtimes in real time.

[0467] The server acquires video data transmitted from the camera and uses analysis software to analyze the children's behavior and eating habits.

[0468] 2. Data collection and analysis:

[0469] Server: Collects data on children's behavior from camera footage. For example, it analyzes the type of play (e.g., playing with blocks, playing in the sandbox), changes in emotions (e.g., smiling, crying), and interactions with friends.

[0470] Server: Similarly, it analyzes video footage of meals to measure the amount of food eaten and left over. This allows for an understanding of the child's nutritional intake.

[0471] 3. Sentence generation:

[0472] Server: Based on the analyzed behavioral data, it uses generative artificial intelligence to automatically generate text for the contact log. For example, it creates a report such as, "Today, XX-chan played in the sandbox and was smiling."

[0473] Server: Based on meal data, it generates trends in food waste, analyzes them using artificial intelligence, and generates specific improvement suggestions and recipes.

[0474] 4. Viewing and editing data:

[0475] Terminal (caregiver's tablet): The app displays automatically generated communication log messages sent from the server. The caregiver reviews the messages and makes manual corrections as needed. For example, they might edit it to read, "Today, XX-chan was playing in the sandbox and had fun with her friends."

[0476] Device (Parent's Smartphone): The app displays corrected communication logs, meal reports, and recipes sent from the server. Parents can check details of their child's daily life and meals.

[0477] 5. Data distribution:

[0478] Server: Records corrected text and suggested recipes in a database and distributes them to the parent's device.

[0479] Device (parent's smartphone): Receives and displays information sent from the server via the app. This allows parents to have a detailed understanding of their child's daily activities and eating habits.

[0480] Specific example

[0481] For example, when recording what happened at daycare on a particular day, the process would be as follows:

[0482] 1. The server analyzes the video from the camera and collects data such as, "○○ played with blocks in the morning and drew pictures in the afternoon," and "She left some bell peppers at lunch."

[0483] 2. Based on the collected data, the server generates a communication log entry that reads, "Today, [child's name] enjoyed playing with blocks. In the afternoon, she drew a picture and then shared it with her friends. She left some bell peppers at lunch," and a recipe for overcoming her aversion to bell peppers, such as "A recipe for baking bell peppers with cheese to make them easier to eat."

[0484] 3. Device (caregiver's tablet): The caregiver reviews the generated text and makes corrections such as, "Today, XX-chan really enjoyed playing with blocks."

[0485] 4. Device (Parent's smartphone): The parent checks the corrected contact log and the cheese bake recipe.

[0486] This streamlines the administrative work of childcare workers and allows parents to receive detailed information about their child's daily routine and meals.

[0487] The following describes the processing flow.

[0488] Step 1:

[0489] The server acquires live video from cameras within the nursery school and inputs the video data into a camera image analysis system. The camera image analysis system analyzes data on children's behavior and emotions (e.g., smiling, crying) and collects it in real time.

[0490] Step 2:

[0491] The server stores the analyzed behavioral data in a database. Specifically, it records the type of play, changes in emotions, and the content of interactions in the database.

[0492] Step 3:

[0493] The server also acquires video data during meals and inputs it into the camera image analysis system. The analysis system automatically measures the type and amount of food eaten and the type and amount of food left uneaten, and collects this data.

[0494] Step 4:

[0495] The server stores the collected meal data in a database. This meal information includes details such as calorie intake and nutritional balance.

[0496] Step 5:

[0497] The server uses generative artificial intelligence (AI) to generate messages for the contact log based on stored behavioral and eating data. For example, it automatically generates messages such as, "Today, [child's name] played in the sandbox and had a great time with a smile on their face."

[0498] Step 6:

[0499] The server simultaneously uses AI generated from meal data to suggest recipes that help overcome food waste. For example, if bell peppers are left over, it will suggest a recipe for baked bell peppers with cheese.

[0500] Step 7:

[0501] The server distributes the generated communication log entries and suggested coping recipes to the childcare worker's terminal. The childcare worker can then review the entries using a tablet or other device.

[0502] Step 8:

[0503] Device (childcare worker's tablet): The childcare worker displays the generated text sent from the server on the app and checks its content. They manually correct the text as needed.

[0504] Step 9:

[0505] The user (childcare worker) confirms the corrected communication log entry by pressing the "Send" button in the app. The confirmed entry is then sent back to the server.

[0506] Step 10:

[0507] The server saves the revised text and suggested coping strategies to a database and distributes them to the parents' devices.

[0508] Step 11:

[0509] Device (Parent's Smartphone): Parents receive and view the final message from the server, meal reports, and recovery recipes via the app.

[0510] Step 12:

[0511] Users (parents) can check their child's daily behavior, eating habits, and suggested recipes on the app, which can help them with home care and meal planning.

[0512] This will significantly reduce the administrative burden on childcare workers and enable the provision of high-value information to parents.

[0513] (Example 1)

[0514] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0515] The current administrative work in daycare centers is extremely cumbersome, increasing the workload of childcare workers. In particular, the task of meticulously recording children's behavior and eating habits and providing this information to parents in the form of a communication log is time-consuming and laborious. Furthermore, the quality of information provided varies, and sometimes parents receive insufficient information. To address these issues, a system is needed that reduces the workload of childcare workers and improves the quality of information provided to parents.

[0516] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0517] In this invention, the server includes means for analyzing camera images, means for collecting behavioral data of children under childcare, means for generating text using generative artificial intelligence based on the collected behavioral data, means for displaying the generated text in a modifiable form, means for recording and distributing the modified text, means for collecting and analyzing meal data and analyzing the results using generative artificial intelligence, means for analyzing behavior and meal situations using analysis software, means for saving the modified communication log text and recipes to a database and distributing them to terminals, and means for inputting prompt sentences into an AI model to generate communication log text and meal improvement suggestions. This makes it possible to streamline administrative work in childcare centers, reduce the workload of childcare workers, and improve the quality of information provided to parents.

[0518] "Camera image analysis means" refers to a combination of a device and software that analyzes video data acquired from a camera to detect and identify the movement of objects and people within the image.

[0519] "Means for collecting behavioral data of children in childcare" refers to devices and software for collecting various behaviors of children within a nursery school as data.

[0520] "Methods for generating text using generative artificial intelligence" refers to artificial intelligence software that performs natural language processing based on collected data and automatically generates text.

[0521] "Means for displaying generated text in a modifiable format" refers to a display device and software for displaying automatically generated text in a viewable and editable format.

[0522] "Means for recording and distributing revised text" refers to a database and communication device for saving edited text and transmitting it to the necessary terminals.

[0523] "Methods for collecting and analyzing meal data and generating results using artificial intelligence" refers to devices and software that acquire data during meals, analyze it, and then use artificial intelligence to analyze the results.

[0524] "Means of analyzing behavior and eating habits using analysis software" refers to software used to analyze acquired video data, behavioral data, and eating data.

[0525] "Means for saving revised contact log entries and recipes to a database and distributing them to terminals" refers to the device and software for saving the final revised entries and generated recipes to a database and distributing them to each terminal.

[0526] "Means for generating contact log entries and dietary improvement suggestions by inputting prompt sentences into an AI model" refers to a system and software for automatically generating contact log entries and dietary improvement suggestions by inputting specific prompt sentences into a generating AI model.

[0527] This invention aims to streamline administrative tasks in childcare settings and improve the quality of information provided to parents through a series of systems that link camera image analysis means, generating artificial intelligence, and terminals used by childcare workers and parents.

[0528] 1. Setting up camera image analysis means and video analysis

[0529] Multiple cameras will be installed within the nursery school. These cameras will capture the children's daily activities and mealtimes in real time. A server will acquire the video data transmitted from the cameras and analyze the children's behavior and eating habits using analysis software (e.g., OpenCV or TensorFlow).

[0530] As a concrete example, the server analyzes the morning footage to determine that "○○ was playing with building blocks," and the afternoon footage to determine that "○○ was drawing a picture." It also analyzes the mealtime footage to determine that "○○ left some bell peppers."

[0531] 2. Collection and storage of behavioral and dietary data

[0532] The server collects behavioral and eating data based on the analysis results and stores it in a database. Behavioral data includes the type of play (e.g., playing with blocks, playing in a sandbox), changes in emotion (e.g., smiling, crying), and interactions with friends. Eating data includes the amount of food eaten and leftovers.

[0533] For example, you can save data such as "2023-10-01 09:00:00 ○○-chan playing with blocks" or "2023-10-01 12:00:00 ○○-chan left bell peppers, amount: 15g".

[0534] 3. Automatic generation of communication log entries and dietary improvement suggestions.

[0535] The server uses generated artificial intelligence based on collected behavioral and dietary data to automatically generate messages for the contact book and suggestions for dietary improvements. The server inputs the necessary prompts into the generated AI model.

[0536] Examples of specific prompt messages are as follows:

[0537] Camera image analysis results:

[0538] Morning activities: Playing with building blocks

[0539] Afternoon activity: Drawing pictures

[0540] Meal details: Left the bell peppers uneaten at lunch.

[0541] Based on this, please automatically generate the following contact log message and dietary improvement suggestions:

[0542] Contact book entry:

[0543] Dietary improvement suggestions:

[0544] As a result, the server generates a communication log entry such as, "Today, [child's name] enjoyed playing with blocks. In the afternoon, she drew pictures with her friends. At lunch, she left some bell peppers," and a suggestion for improving meals such as, "A recipe for baking bell peppers with cheese to make them easier to eat."

[0545] 4. Displaying and editing data

[0546] The childcare worker's device (tablet) displays automatically generated communication log documents sent from the server, allowing the childcare worker to review and edit them. The childcare worker then sends the edited document to the server, completing the revision process.

[0547] Afterward, the parent's device (smartphone) displays the corrected communication log, meal reports, and recipes for overcoming challenges that were sent from the server via the app. Through the app, the parent can check details of their child's daily life and meals.

[0548] 5. Data distribution and viewing

[0549] The server saves the corrected contact log entries and generated recipes to a database and distributes them to the parent's device. Parents can check the information received from the server through the app. This allows parents to have a detailed understanding of their child's daily activities and eating habits.

[0550] As described above, the present invention makes it possible to improve the efficiency of administrative work in nurseries, reduce the workload of childcare workers, and improve the quality of information provided to parents.

[0551] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0552] Step 1:

[0553] Acquiring camera images

[0554] The server acquires video data in real time from multiple cameras within the nursery school. The cameras are installed to monitor the children's daily activities and mealtimes.

[0555] Specific actions:

[0556] 1.1 The server receives the video stream via the camera's IP address.

[0557] 1.2 The server saves the received video to storage in real time.

[0558] Input: Camera IP address and video data

[0559] Output: Saved video data

[0560] Step 2:

[0561] Analysis of video data

[0562] The server analyzes the acquired video data using analysis software (e.g., OpenCV or TensorFlow) to identify the children's behavior and eating habits.

[0563] Specific actions:

[0564] 2.1 The server extracts frames from the video data and applies specific algorithms to perform face and object recognition.

[0565] 2.2 The server converts the recognition results into vector data and extracts behavioral and dietary information.

[0566] Input: Saved video data

[0567] Output: Behavioral data and dietary data

[0568] Step 3:

[0569] Collection and storage of behavioral and dietary data

[0570] The server collects behavioral data (e.g., type of play, emotional changes) and eating data (e.g., amount of food eaten and leftovers) from the analysis results and stores them in a database.

[0571] Specific actions:

[0572] 3.1 The server saves the activity data to the database. For example, it saves data such as "2023-10-01 09:00:00 ○○-chan playing with blocks".

[0573] 3.2 The server saves meal data to a database. For example, it saves data such as "2023-10-01 12:00:00 ○○-chan Bell pepper leftovers Amount: 15g".

[0574] Input: Behavioral data and dietary data

[0575] Output: Behavioral and dietary data stored in the database

[0576] Step 4:

[0577] Automatic generation of communication log entries and meal improvement suggestions.

[0578] The server uses generated artificial intelligence based on collected behavioral and dietary data to automatically generate messages for the contact book and suggestions for dietary improvements. The server inputs the necessary prompts into the generated AI model.

[0579] Specific actions:

[0580] 4.1 The server converts the behavioral data into a prompt message. For example, it might convert it to something like, "Today, XX enjoyed playing with building blocks. In the afternoon, she drew pictures with her friends."

[0581] 4.2 The server converts the meal data into a prompt message and generates a "cheese bake recipe to make bell peppers easier to eat".

[0582] Input: Behavioral data and dietary data

[0583] Output: Communication log entries and suggestions for improving meals

[0584] Step 5:

[0585] Viewing and editing data

[0586] The terminal (the childcare worker's tablet) displays automatically generated communication log documents sent from the server, allowing the childcare worker to review and edit them.

[0587] Specific actions:

[0588] 5.1 The device sends an API request to the server to retrieve automatically generated contact log entries and meal improvement suggestions.

[0589] 5.2 The device displays the acquired information within the app, allowing childcare workers to freely edit the text.

[0590] 5.3 The terminal sends the edited text back to the server, and the correction is complete.

[0591] Input: Automated contact log entries and meal improvement suggestions

[0592] Output: Communication log document edited by the childcare worker

[0593] Step 6:

[0594] Data distribution and viewing

[0595] The server saves the corrected contact log entries and generated recipes to a database and distributes them to the parents' devices.

[0596] Specific actions:

[0597] 6.1 The server saves the corrected contact log entries and recipes to the database.

[0598] 6.2 The server sends a notification to the parent's device informing them that new data is available.

[0599] 6.3 The device (the parent's smartphone) receives and displays information sent from the server via the app. Parents can gain a detailed understanding of their child's daily activities and eating habits.

[0600] Input: Communication log entries edited by childcare workers and generated recipes

[0601] Output: Communication log entries and meal improvement suggestions for parents to view.

[0602] (Application Example 1)

[0603] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0604] In daycare operations, there is a need to understand children's behavior and eating habits in detail and to streamline the provision of information to parents. Similarly, in physical stores, there is a need for a system that analyzes customer behavior in real time to efficiently support store operations. Existing methods require a great deal of time and effort to collect and analyze individual data, resulting in a heavy workload and limitations in the quality of customer service.

[0605] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0606] In this invention, the server includes camera image analysis means, means for collecting behavioral data of childcare recipients, means for generating text using generative artificial intelligence based on the collected behavioral data, means for displaying the generated text in an editable format, means for recording and distributing the edited text, means for collecting and analyzing meal data and analyzing the results using generative artificial intelligence, means for proposing and distributing recipes to overcome challenges based on the analysis results, means for analyzing customer trends in real time, means for generating in-store discount coupons and product recommendations based on the analysis results, and means for distributing the generated recommendation information to staff. This enables improved operational efficiency in childcare centers and customer behavior analysis and optimal service provision in physical stores.

[0607] A "camera image analysis means" is a means of analyzing video data acquired from a camera and extracting specific information.

[0608] "Means for collecting behavioral data of children in childcare" refers to methods for observing children's behavior in a nursery school and collecting that data.

[0609] "Methods for generating text using artificial intelligence based on behavioral data" refers to an artificial intelligence system that analyzes collected behavioral data and automatically generates text based on the results.

[0610] "Means for displaying generated text in an editable format" refers to means for displaying automatically generated text in a way that allows users to edit it.

[0611] "Means for recording and distributing revised text" refers to methods for recording the revised text in a database and distributing it to the necessary stakeholders.

[0612] "A means of collecting meal data, analyzing the results, and generating analysis using artificial intelligence" refers to a means of collecting data on meals for those receiving childcare and analyzing it using artificial intelligence.

[0613] "A method for proposing and distributing recipes to overcome dietary problems based on analysis results" refers to a method of proposing dietary improvement measures based on the results of analyzing dietary data and distributing that information.

[0614] "Methods for analyzing customer behavior in real time" refers to methods for monitoring and analyzing customer behavior within a store in real time.

[0615] "Methods for generating in-store discount coupons and product recommendations based on analysis results" refers to methods for generating appropriate discount coupons and product recommendations based on the results of customer behavior analysis.

[0616] "Means for distributing generated recommendation information to staff" refers to the means for distributing automatically generated recommendation information to store staff.

[0617] This invention aims to improve operational efficiency and the quality of information provision through a system that links camera image analysis means, generating artificial intelligence, and terminals in daycare centers and physical stores. The following describes specific embodiments for implementing this invention.

[0618] System Configuration

[0619] The system of the present invention includes the following means:

[0620] 1. Camera image analysis means

[0621] Multiple cameras will be installed in daycare centers and stores to capture children's behavior and customers' movements in real time.

[0622] The server acquires video data transmitted from the camera and uses image analysis software such as OpenCV or TensorFlow to analyze behavior and trends.

[0623] 2. Data Collection and Analysis

[0624] Server: Collects behavioral data and customer behavior data from camera footage. Behavioral data includes the types of play children engage in and changes in their emotions, while customer behavior data includes movement patterns within the store and products they show interest in.

[0625] Server: Analyzes video footage of meals to measure the amount of food eaten and left over. Store systems analyze which items customers showed interest in within the shopping area.

[0626] 3. Sentence generation

[0627] Server: Based on analyzed behavioral data, it automatically generates text using generative artificial intelligence (AI model). For example, in a nursery school, it might create a report saying, "Today, XX played in the sandbox and was smiling," and in a store, it might create a customer behavior report saying, "She spent a particularly long time looking at item A in the cosmetics section."

[0628] Server: Based on the analysis data, it generates recipes to overcome dietary restrictions, in-store discount coupons, and product recommendations.

[0629] 4. Displaying and editing data

[0630] Devices (tablets in daycare centers, smartphones for store staff): Automatically generated text is displayed in the app, and childcare workers and staff can review the text and manually correct it as needed.

[0631] Device (parent's smartphone, store's customer app): Displays corrected contact information and meal reports sent from the server, as well as discount coupons and product recommendations, within the app.

[0632] 5. Data distribution

[0633] Server: Records corrected text and suggested information in a database and distributes it to parents' and customers' devices.

[0634] Device (parent's smartphone, store's customer app): Displays received information in detail through the app.

[0635] Specific examples of hardware and software

[0636] Hardware: IP cameras, servers (such as Amazon AWS), tablets, smartphones.

[0637] Software: Image analysis libraries (OpenCV, TensorFlow), data analysis libraries (NumPy, Pandas), notification system (Firebase).

[0638] Specific example

[0639] For example, when recording what happened at daycare on a particular day, the process would be as follows:

[0640] The server analyzes the camera footage and collects data such as, "○○-chan played with blocks in the morning and drew pictures in the afternoon."

[0641] Based on the collected data, the server generates a communication log entry such as, "Today, [child's name] enjoyed playing with blocks," which is then reviewed by the childcare worker and distributed to the parents.

[0642] Device (caregiver's tablet): The caregiver reviews the generated text and manually corrects it to, "Today, XX-chan really enjoyed playing with blocks."

[0643] Device (Parent's smartphone): The parent / guardian checks the corrected contact log.

[0644] The same applies to stores:

[0645] The server analyzes camera footage to detect customers who are lingering in front of specific products for extended periods.

[0646] Based on that data, the server generates recommendation information such as "Offer a discount coupon for item A" and distributes it to the staff.

[0647] Terminal (store staff's smartphone): Checks the generated recommendation information and provides coupons to customers.

[0648] Example of a prompt

[0649] Input the following prompts into the AI ​​model to generate information:

[0650] According to today's in-store analytics data, several customers showed interest in the cosmetics section. Based on this, please generate the following actions.

[0651] Offering discount coupons in the cosmetics section.

[0652] Notification to staff

[0653] Product recommendations for your next visit

[0654] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0655] Step 1:

[0656] Acquiring camera images

[0657] The server acquires video data in real time from cameras installed in daycare centers and physical stores. This input data is video frames, and its output is a stream of video data for image analysis processing.

[0658] Step 2:

[0659] Image analysis and extraction of behavioral data

[0660] The server analyzes the acquired video data using tools such as OpenCV and TensorFlow. Specifically, it identifies children's behavior and customer movements from video frames, extracting data such as "a child is playing with blocks" or "a customer is staying with a specific product for an extended period." The input is camera video data, and the output is analyzed behavioral and movement data.

[0661] Step 3:

[0662] Text generation based on behavioral data

[0663] The server uses a generative AI model to generate appropriate sentences based on the analyzed behavioral data. For example, it automatically generates sentences such as "○○ played in the sandbox" in a nursery school setting, or "○○ showed interest in product A" in a physical store setting. The input is the analyzed behavioral data, and the output is the generated sentences.

[0664] Step 4:

[0665] Display and edit the generated text

[0666] The devices (tablets in daycare centers or smartphones for store staff) display the generated text in an editable format. Childcare workers and staff review this text and make manual corrections as needed. Specifically, they edit the text displayed on the screen using touch input or a keyboard. This input is the generated raw text, and the output is the corrected version.

[0667] Step 5:

[0668] Recording and distribution of revised text

[0669] The server records the corrected text in a database and distributes it to the parents' and customers' devices. Specifically, it saves the corrected text to a cloud-based database and distributes it to each device in a pre-encoded format. The input is the corrected text, and the output is the information displayed on the parents' and customers' devices.

[0670] Step 6:

[0671] Analysis of meal data and customer behavior data

[0672] The server collects and analyzes meal data from daycare centers and customer behavior data from physical stores. Specifically, it acquires data such as "○○ left some bell peppers" from meals and "a customer stayed in front of a particular product for a long time" from stores. The input is raw data on meals and customer behavior, and the output is the analyzed data.

[0673] Step 7:

[0674] Generating recommended information and improvement measures

[0675] The server generates recipes to overcome difficulties, discount coupons, and product recommendations based on the analysis results. Specifically, the AI ​​model generates recipes to make bell peppers easier to eat, or creates discount coupons for specific products, based on the analysis data. The input is the analysis results data, and the output is the generated recommendations and improvement measures.

[0676] Step 8:

[0677] Distribution of recommended information and improvement measures

[0678] The server distributes the generated recommendations and improvement suggestions to childcare workers, staff, parents, and customers. Specifically, it inputs prompts into an AI model to generate recommendations and then distributes the results. This input consists of the generated recommendations and improvement suggestions, and the output is the information distributed to the devices of parents and customers.

[0679] Example of a prompt

[0680] Input the following prompts into the AI ​​model to generate information:

[0681] According to today's in-store analytics data, several customers showed interest in the cosmetics section. Based on this, please generate the following actions.

[0682] Offering discount coupons in the cosmetics section.

[0683] Notification to staff

[0684] Product recommendations for your next visit

[0685] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0686] This invention is a system that improves the efficiency of administrative work in childcare settings and the quality of information provided to parents by linking camera image analysis means, generative artificial intelligence (AI), an emotion engine, and terminals used by childcare workers and parents. This system collects children's behavioral and emotional data in real time and automatically generates text, meal reports, and overcoming recipes using generative AI.

[0687] System Configuration

[0688] 1. Camera image analysis means:

[0689] Multiple cameras are installed within the nursery school to capture the children's daily activities and mealtimes in real time.

[0690] The server acquires video data transmitted from the camera and uses camera image analysis tools to analyze the children's behavior.

[0691] 2. Emotional Engine:

[0692] The server analyzes the children's facial expressions from the camera footage and collects emotional data in real time, such as smiles, crying faces, and focused faces.

[0693] The emotional data recognized by the emotion engine is recorded in the database as behavioral data and dietary data.

[0694] 3. Data collection and analysis:

[0695] The server collects behavioral and emotional data from camera footage and stores it in a database. Behavioral data includes the type of play and interactions with friends.

[0696] The server analyzes video footage of the meal, recording the types and quantities of food eaten, the types and quantities of food left uneaten, and the emotions experienced during the meal (e.g., expressions of displeasure, expressions of satisfaction), and stores this information in a database.

[0697] 4. Text generation using artificial intelligence (AI):

[0698] The server automatically generates messages for the contact log using a generative AI based on collected behavioral and emotional data. For example, it might generate a message like, "Today, [child's name] played in the sandbox and had a great time with a smile on their face."

[0699] The server uses AI to generate recipes to help overcome food waste, based on meal and emotional data. For example, if a customer leaves bell peppers uneaten, it will suggest a "Bell Pepper and Cheese Bake Recipe."

[0700] 5. Viewing and editing data:

[0701] Device (childcare worker's tablet): Provides an app that displays generated text sent from the server and allows childcare workers to manually edit the text. For example, "Today, XX-chan played in the sandbox and had fun with a smile." → "Today, XX-chan built a sandcastle and had fun with her friends."

[0702] Device (parent's smartphone): Provided via an app that displays corrected contact logs, meal reports, and recipes sent from the server.

[0703] 6. Data distribution:

[0704] The server saves the revised contact log entries and suggested coping strategies to a database and automatically distributes them to the parents' devices.

[0705] Device (Parent's smartphone): Allows parents to view the information sent via the app.

[0706] Specific example

[0707] Collecting data on children's behavior

[0708] For example, during a day at the nursery school, the server analyzes camera footage and collects behavioral data such as, "○○ played with blocks in the morning and drew pictures in the afternoon," as well as emotional data such as, "She was smiling while playing with blocks," and "She had a focused expression while drawing."

[0709] Contact book message generation

[0710] Based on the collected behavioral and emotional data, the server generates a message for the communication log, such as, "Today, [child's name] enjoyed playing with blocks, and in the afternoon, she was focused on drawing."

[0711] Collection and analysis of dietary data

[0712] The server analyzes the video from lunchtime and collects meal data such as, "○○-chan ate all her rice but left the bell peppers," and emotion data such as, "She made a displeased face when eating the bell peppers."

[0713] Generating recipes for overcoming challenges

[0714] Based on the collected food and emotional data, the server suggests a "cheese bake recipe to make bell peppers easier to eat."

[0715] Viewing and editing data

[0716] Terminal (caregiver's tablet): The caregiver checks the generated communication log entry and revises the sentence, such as, "Today, XX enjoyed playing with blocks, and in the afternoon, she was concentrating while drawing pictures."

[0717] Device (Parent's smartphone): Parents can review the corrected communication log entries and recipes for overcoming challenges, and use them as a reference for cooking.

[0718] This streamlines the administrative work of childcare workers, and allows parents to receive detailed information and specific suggestions regarding their child's daily routine and meals.

[0719] The following describes the processing flow.

[0720] Step 1:

[0721] The server acquires live video from cameras installed within the nursery school and inputs the video data into a camera image analysis system. The camera image analysis system analyzes the children's behavior (e.g., type of play, movement path) and generates behavioral data in real time.

[0722] Step 2:

[0723] The server inputs the same video data into the emotion engine. The emotion engine analyzes the child's facial expressions and generates emotion data in real time, such as smiles, crying faces, and surprised expressions. This allows for a detailed record of the child's emotional changes.

[0724] Step 3:

[0725] The server stores behavioral and emotional data generated by the camera image analysis system and emotion engine in a database. This allows for a detailed record of the child's daily life.

[0726] Step 4:

[0727] The server inputs video data from lunchtime into a camera image analysis system to analyze eating behavior. It measures the type and amount of food eaten and the type and amount of food left uneaten, and generates meal data.

[0728] Step 5:

[0729] The server inputs video data from the meal into an emotion engine and analyzes the child's facial expressions while eating. It generates emotional data such as joy, disgust, and satisfaction during the meal. This also records the child's feelings towards eating.

[0730] Step 6:

[0731] The server stores meal data and emotional data generated by the camera image analysis system and emotion engine in a database. This allows for a detailed record of the eating situation.

[0732] Step 7:

[0733] The server uses generative artificial intelligence (AI) to generate messages for the contact book based on stored behavioral and emotional data. For example, it automatically generates a message like, "Today, XX-chan was playing in the sandbox and was having fun with a smile on her face."

[0734] Step 8:

[0735] The server uses generative artificial intelligence (AI) to generate recipes to help overcome food waste, based on stored meal and emotional data. For example, if bell peppers are left uneaten, it will suggest a "Bell Pepper and Cheese Bake Recipe."

[0736] Step 9:

[0737] The server distributes the generated communication log entries and overcoming recipes to the childcare worker's terminal. The childcare worker can then review the entries using a tablet or other device.

[0738] Step 10:

[0739] Device (childcare worker's tablet): Childcare workers view the generated text sent from the server on the app and review its content. They manually revise the text as needed and perform a final check.

[0740] Step 11:

[0741] The user (childcare worker) confirms the corrected communication log entry by pressing the "Send" button in the app. The confirmed entry is then returned to the server and saved in the database.

[0742] Step 12:

[0743] The server delivers the revised contact log entries and suggested coping recipes to the parent's device. Parents can view this information through the app.

[0744] Step 13:

[0745] Device (Parent's smartphone): Parents can view communication logs, meal reports, and recipes for overcoming illness sent from the server via the app.

[0746] Step 14:

[0747] Users (parents) can check their child's daily behavior, eating habits, and suggested recipes on the app, and use this information to improve home care and meal planning.

[0748] This reduces the administrative burden on childcare workers and provides parents with detailed information about their child's daily life and meals.

[0749] (Example 2)

[0750] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0751] In childcare settings, childcare workers are burdened with a wide range of administrative tasks, including observing and recording children's behavior and emotions, writing in communication notebooks, and managing meals. Furthermore, while parents want detailed information about their children's daily lives and meals, this information is often insufficient. Therefore, there is a need to streamline the administrative work of childcare workers and improve the quality of information provided to parents.

[0752] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0753] In this invention, the server includes means for analyzing camera images, means for collecting behavioral and emotional data of the child being cared for, means for generating text using generative artificial intelligence based on the collected behavioral and emotional data, means for displaying the generated text in a modifiable form, means for recording and distributing the modified text, means for collecting and analyzing meal data and analyzing the results using generative artificial intelligence, and means for proposing and distributing recipes to overcome difficulties based on the analysis results. This streamlines the administrative work of childcare workers, and allows parents to receive detailed information about their child's daily life and meals, as well as specific suggestions.

[0754] "Means of analyzing camera images" refers to devices and software that analyze video data acquired by cameras installed within the nursery school, and are used to recognize children's behavior and facial expressions.

[0755] "Action data of children in childcare" refers to information about the various activities and behaviors that children engage in within the nursery school, including, for example, the types of play and interactions.

[0756] "Emotional data" refers to information about emotions recognized from children's facial expressions, including smiles, crying faces, and focused faces.

[0757] "Means of generating text using generative artificial intelligence" refers to artificial intelligence technology that automatically generates text in natural language based on collected data, and this includes, for example, generative AI models.

[0758] "Means of displaying generated text in an editable format" refers to devices or software that allow childcare workers to review automatically generated text and make corrections as needed, and includes, for example, tablet devices.

[0759] "Means for recording and distributing revised text" refers to systems and methods for saving text revised by childcare workers in a database and distributing it to parents in real time.

[0760] "Mealtime data" refers to information about the types and quantities of food children ate during meals, as well as the types and quantities of food they left uneaten.

[0761] "Methods of analysis using generative artificial intelligence" refers to artificial intelligence technology that analyzes collected dietary data and automatically generates new insights and suggestions based on it, and includes, for example, AI models.

[0762] The method of proposing and distributing "recipes to overcome allergies" refers to a method of automatically generating cooking recipes that make it easier for children to eat specific foods, based on analyzed dietary data, and then distributing these recipes to parents.

[0763] The present invention is configured as a system to improve the efficiency of administrative work in childcare settings and the quality of information provided to parents. This system includes means for analyzing camera images, means for collecting behavioral and emotional data, means for generating text using generative artificial intelligence based on the collected data, means for displaying the generated text in an editable format, means for recording and distributing the edited text, means for collecting, analyzing, and analyzing meal data using generative artificial intelligence, and means for proposing and distributing recipes for overcoming health challenges.

[0764] Hardware and software configuration

[0765] The system consists of the following hardware and software.

[0766] Camera: High-resolution camera (e.g., general-purpose high-resolution camera)

[0767] Server: A server for analyzing video data and collecting and analyzing behavioral data, emotional data, and dietary data.

[0768] Software: Camera image analysis libraries (e.g., OpenCV), emotion recognition libraries (e.g., Emotion Recognition API), generative AI models (e.g., GPT-3)

[0769] Devices: Tablet devices used by childcare workers, and smartphones used by parents.

[0770] Program Implementation

[0771] 1. Acquisition of video data

[0772] The server acquires video data from the camera in real time. This video data is acquired using, for example, the RTSP protocol.

[0773] 2. Analysis of video data

[0774] The server uses OpenCV to analyze video data and recognize the children's behavior (e.g., type of play, interactions).

[0775] For example, one might observe a child playing with building blocks in the morning.

[0776] 3. Recognition and collection of emotional data

[0777] The server uses an emotion recognition API to analyze the children's facial expressions from the video data and recognize emotional data (e.g., smiling, crying, concentrating).

[0778] For example, we may recognize a smile while a child is playing with building blocks.

[0779] 4. Storage of behavioral and emotional data

[0780] The server stores the analyzed and recognized behavioral and emotional data in a database. Transaction management is performed to ensure data integrity and security.

[0781] For example, the system saves data indicating that the child played with building blocks in the morning and was smiling at that time.

[0782] 5. Automatic sentence generation

[0783] The server automatically generates contact book entries using a generative AI model (e.g., GPT-3) based on the collected data.

[0784] For example, it can generate sentences like, "Today, [Name] enjoyed playing with building blocks, and in the afternoon, she was concentrating on drawing."

[0785] Example of a prompt:

[0786] Today, [Name] enjoyed playing with building blocks, and in the afternoon, she was concentrating on drawing.

[0787] 6. Correction and display of generated text

[0788] The device (the childcare worker's tablet) displays the generated communication log document, and the childcare worker makes corrections as needed.

[0789] For example, change "Today, XX enjoyed playing with blocks, and in the afternoon, she was focused on drawing." to "Today, XX built a sandcastle and had fun with her friends."

[0790] 7. Collection and analysis of dietary data

[0791] The server analyzes video footage of meals and collects meal data (e.g., types and amounts of food eaten, types and amounts of food left over).

[0792] For example, we collect data such as "○○-chan ate all her rice but left the bell peppers."

[0793] 8. Generating a recipe for overcoming the problem

[0794] The server generates recipes to help overcome food waste based on the collected meal data.

[0795] For example, I'd like to suggest a recipe for "cheese-baked bell peppers to make them easier to eat."

[0796] 9. Distribution of revised text and recipes

[0797] The server saves the revised contact log entries and suggested recipes to a database and distributes them to the parents' devices.

[0798] The device (the parent's smartphone) receives information sent from the server and displays it to the user.

[0799] For example, a parent might see a message in the communication notebook saying, "Today, [child's name] built a sandcastle and had fun with their friends," as well as a recipe for "baked bell peppers with cheese."

[0800] This will streamline the administrative work of childcare workers, and allow parents to receive detailed information about their child's daily life and meals, as well as specific suggestions.

[0801] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0802] Step 1: Acquire video data

[0803] The server acquires video data in real time from multiple cameras installed within the nursery school. The input is the video stream transmitted from the cameras (for example, using the RTSP protocol). The acquired video data is stored in a temporary storage area. For example, the server receives the video via the camera's IP address and saves it to the temporary storage area.

[0804] Step 2: Analysis of video data

[0805] The server uses OpenCV to analyze video data stored in a temporary storage area. The input is video data. As data processing, an object detection algorithm (e.g., YOLO) is applied to each frame to recognize children's actions. The output is the recognized action data. For example, the server detects children playing with blocks in the morning.

[0806] Step 3: Recognizing and collecting emotional data

[0807] The server uses an emotion recognition API to analyze children's facial expressions from analyzed video data. The input is the analyzed video data. As part of the data processing, an emotion recognition algorithm is applied to recognize emotions such as smiles, crying faces, and focused faces. The output is the recognized emotion data. For example, the server recognizes a smile while a child is playing with blocks.

[0808] Step 4: Saving behavioral and emotional data

[0809] The server stores recognized behavioral and emotional data in a database. The input consists of behavioral and emotional data. Data processing involves converting the data into a well-formed format (e.g., JSON) and inserting it into the database using SQL queries. The output is the record in the database. For example, the server might store data about playing with building blocks in the morning and the smile associated with that activity in the database.

[0810] Step 5: Automatic text generation

[0811] The server generates contact log entries using a generative AI model (e.g., GPT-3) based on behavioral and emotional data stored in the database. The input consists of behavioral and emotional data. As a data operation, prompt sentences are provided to the generative AI model for inference. The output is an automatically generated contact log entry. For example, it might generate an entry like, "Today, XX enjoyed playing with blocks, and in the afternoon, she was concentrating on drawing."

[0812] Step 6: Modify and display the generated text

[0813] The terminal (the childcare worker's tablet) displays the generated text sent from the server, and the childcare worker makes corrections as needed. The input is the automatically generated communication log text. The output is the corrected communication log text. For example, the childcare worker might change "Today, XX enjoyed playing with blocks, and in the afternoon, she was concentrating while drawing pictures." to "Today, XX built a sandcastle and enjoyed playing with her friends."

[0814] Step 7: Collection and analysis of dietary data

[0815] The server analyzes video footage of meals and collects meal data. The input is video data of the meal. As part of the data processing, a video analysis algorithm is applied to extract the contents of the meal and any leftovers. The output is the analyzed meal data. For example, the server collects data such as, "○○-chan ate all of her rice, but left the bell peppers."

[0816] Step 8: Generating a Recipe for Overcoming Challenges

[0817] The server generates recipes to overcome food allergies using a generative AI model based on meal data. The input is meal data. As a data calculation, prompts are provided to the generative AI model for inference. The output is the generated recipe. For example, it might generate a "cheese bake recipe to make bell peppers easier to eat."

[0818] Step 9: Distribute the revised text and recipe.

[0819] The server saves the revised contact log entries and suggested recipes to a database and distributes them to the parent's device. The input is the revised entries and generated recipes. The output is the notification and display information on the parent's device. For example, the parent's smartphone might receive a contact log entry that reads, "Today, [child's name] built a sandcastle and had fun with their friends," along with a recipe for "Grilled bell peppers with cheese."

[0820] (Application Example 2)

[0821] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0822] In modern brick-and-mortar stores, it is difficult to collect real-time data on children's behavior and emotional changes in play areas and provide detailed reports to parents. Therefore, parents have difficulty understanding their child's play status and emotional changes. Furthermore, manually creating these reports is burdensome, and efficiency improvements are needed.

[0823] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a camera image analysis means, a means for collecting subject behavior data, a means for generating text using generative artificial intelligence based on the collected behavior data, a means for displaying the generated text in a modifiable form, a means for recording and distributing the modified text, a means for collecting and analyzing meal data and analyzing the results using generative artificial intelligence, a means for proposing and distributing overcoming recipes based on the analysis results, and a means for generating and distributing a play status report based on behavior data and emotional data. This makes it possible for parents to check their child's play status and emotional changes in real time via their smartphone.

[0824] A "camera image analysis means" is a device or system that uses a camera to analyze the behavior and facial expressions of a subject in real time and collect the data.

[0825] "Subject behavior data" refers to information about the subject's behavior acquired through sensors such as cameras, and includes, for example, the type of play and details of their actions.

[0826] "Generative artificial intelligence" is an artificial intelligence technology that has the ability to automatically generate text and reports based on collected data.

[0827] "Methods for generating text" refers to a system that automatically generates text using generative artificial intelligence based on collected behavioral and emotional data.

[0828] "Means for displaying generated text in an editable format" refers to a system that provides an interface allowing users to review and edit generated text.

[0829] "Means for recording and distributing revised text" refers to a system for saving revised text and distributing it to relevant parties.

[0830] "Dietary data" refers to detailed information about a person's diet, such as the amount of food they consumed and the amount of food they left uneaten.

[0831] "A means of analyzing the results using generative artificial intelligence" refers to a technology that analyzes collected dietary data and then uses generative artificial intelligence to analyze the results.

[0832] A "recipe to overcome a dislike" is a recipe suggestion designed to make it easier for a person to consume foods they dislike, and may include suggestions for cooking methods or ingredient combinations.

[0833] "Behavioral and emotional data" refers to data about the subject's behavior and the emotional changes associated with that behavior.

[0834] A "play activity report" is a detailed report describing a child's play activities and emotional changes, intended for parents to review.

[0835] "Means of distribution" refers to a system that automatically sends documents and reports generated or modified by generative artificial intelligence to relevant parties.

[0836] "Through a parent's smartphone" refers to a method of viewing and manipulating information and data using a smartphone.

[0837] This invention is a system that collects behavioral and emotional data of children in play areas within physical stores and provides detailed reports to parents in real time. The following describes a specific form for implementing this system.

[0838] System Configuration

[0839] The system consists of the following elements:

[0840] 1. Camera image analysis means:

[0841] Multiple cameras will be installed within the play area. These cameras will capture children's daily behavior and emotional changes in real time.

[0842] The server acquires video data transmitted from the camera and uses camera image analysis tools to analyze the children's behavior.

[0843] 2. Means for collecting behavioral and emotional data:

[0844] The server collects behavioral and emotional data from camera footage and stores it in a database. Behavioral data includes the type of play and interactions with friends.

[0845] The emotion engine analyzes facial expressions from video and collects emotional data in real time, such as smiles, crying faces, and focused faces.

[0846] 3. Text generation methods using AI:

[0847] The server uses a generative AI to automatically generate playtime reports based on collected behavioral and emotional data. For example, it might generate a sentence like, "Today, [child's name] had a lot of fun playing on the slide and smiled a lot."

[0848] 4. Means for correcting the generated text:

[0849] Device (parent's smartphone): Displays generated text sent from the server, allowing the parent to manually review the text.

[0850] 5. Means of recording and distributing documents:

[0851] The server saves the corrected text to a database and automatically delivers it to the parent's device. Parents can view the transmitted information through a smartphone app.

[0852] Examples

[0853] Specific examples of data collection and analysis

[0854] Parents install a smartphone app, and when their child enters the play area, multiple cameras track the child's actions and send behavioral and emotional data to a server. For example, when a child is playing on a slide, the camera films the action, and the server analyzes the footage to collect behavioral data such as "playing on a slide" and emotional data such as "smiling a lot."

[0855] Report generation and distribution

[0856] The server uses generative AI to generate reports based on collected behavioral and emotional data. For example, it might generate a sentence like, "Today, [child's name] was playing on the slide and laughing happily." The generated report is sent to a smartphone app, allowing parents to check their child's play status in real time.

[0857] Example of a prompt

[0858] "Please generate a detailed report based on the child's behavior and emotional data in the play area. The child's behavior is 'playing on the slide,' and their emotion is 'smiling a lot.'"

[0859] In this way, parents can instantly grasp their child's playing situation and emotional changes, allowing them to let their children play in the play area of ​​the physical store with peace of mind.

[0860] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0861] Step 1:

[0862] The server acquires video data in real time from cameras installed within the play area. The cameras capture the children's actions and expressions within the play area and transmit this video data to the server. Camera video data serves as input, forming the basis for behavioral and emotional data.

[0863] Step 2:

[0864] The server analyzes camera video data using camera image analysis tools. Specifically, it detects specific actions from the video data and analyzes facial expressions to extract emotion data. For example, it can detect actions such as playing on a slide or facial expressions such as smiling. Video data is the input, and action data and emotion data are obtained as output.

[0865] Step 3:

[0866] The server stores the analyzed behavioral and emotional data in a database. This data is used for subsequent processing. Behavioral and emotional data are the inputs, and the output is stored in the database.

[0867] Step 4:

[0868] The server uses a generative AI to generate a play situation report based on stored behavioral and emotional data. The generative AI is given a prompt, for example, "The child's behavior is 'playing on the slide,' and their emotion is 'smiling a lot.' Please generate a detailed report based on this." The output is an automatically generated report document.

[0869] Step 5:

[0870] The device (the parent's smartphone) receives the generated report document sent from the server. The parent can review this report and make corrections as needed. The generated report document is the input, and the corrected report document is the output.

[0871] Step 6:

[0872] The server saves the corrected report document to the database and then distributes it again to the parent's device. The input is the corrected report document, and the output is saving to the database and distributing it to the parent.

[0873] Step 7:

[0874] Users (parents) can review the final report via their device, gaining real-time insights into their child's play status and emotional changes. The final report is the input, and the output provides parents with peace of mind and a clear understanding of the information.

[0875] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0876] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0877] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0878] [Third Embodiment]

[0879] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0880] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0881] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0882] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0883] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0884] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0885] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0886] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0887] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0888] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0889] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0890] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0891] This invention aims to streamline administrative tasks in childcare settings and improve the quality of information provided to parents through a series of systems that link camera image analysis means, generating artificial intelligence, and terminals used by childcare workers and parents. The specific implementation of this system will now be described.

[0892] System Configuration

[0893] 1. Camera image analysis means:

[0894] Multiple cameras will be installed inside the nursery school. These cameras will record the children's daily activities and mealtimes in real time.

[0895] The server acquires video data transmitted from the camera and uses analysis software to analyze the children's behavior and eating habits.

[0896] 2. Data collection and analysis:

[0897] Server: Collects data on children's behavior from camera footage. For example, it analyzes the type of play (e.g., playing with blocks, playing in the sandbox), changes in emotions (e.g., smiling, crying), and interactions with friends.

[0898] Server: Similarly, it analyzes video footage of meals to measure the amount of food eaten and left over. This allows for an understanding of the child's nutritional intake.

[0899] 3. Sentence generation:

[0900] Server: Based on the analyzed behavioral data, it uses generative artificial intelligence to automatically generate text for the contact log. For example, it creates a report such as, "Today, XX-chan played in the sandbox and was smiling."

[0901] Server: Based on meal data, it generates trends in food waste, analyzes them using artificial intelligence, and generates specific improvement suggestions and recipes.

[0902] 4. Viewing and editing data:

[0903] Terminal (caregiver's tablet): The app displays automatically generated communication log messages sent from the server. The caregiver reviews the messages and makes manual corrections as needed. For example, they might edit it to read, "Today, XX-chan was playing in the sandbox and had fun with her friends."

[0904] Device (Parent's Smartphone): The app displays corrected communication logs, meal reports, and recipes sent from the server. Parents can check details of their child's daily life and meals.

[0905] 5. Data distribution:

[0906] Server: Records corrected text and suggested recipes in a database and distributes them to the parent's device.

[0907] Device (parent's smartphone): Receives and displays information sent from the server via the app. This allows parents to have a detailed understanding of their child's daily activities and eating habits.

[0908] Specific example

[0909] For example, when recording what happened at daycare on a particular day, the process would be as follows:

[0910] 1. The server analyzes the video from the camera and collects data such as, "○○ played with blocks in the morning and drew pictures in the afternoon," and "She left some bell peppers at lunch."

[0911] 2. Based on the collected data, the server generates a communication log entry that reads, "Today, [child's name] enjoyed playing with blocks. In the afternoon, she drew a picture and then shared it with her friends. She left some bell peppers at lunch," and a recipe for overcoming her aversion to bell peppers, such as "A recipe for baking bell peppers with cheese to make them easier to eat."

[0912] 3. Device (caregiver's tablet): The caregiver reviews the generated text and makes corrections such as, "Today, XX-chan really enjoyed playing with blocks."

[0913] 4. Device (Parent's smartphone): The parent checks the corrected contact log and the cheese bake recipe.

[0914] This streamlines the administrative work of childcare workers and allows parents to receive detailed information about their child's daily routine and meals.

[0915] The following describes the processing flow.

[0916] Step 1:

[0917] The server acquires live video from cameras within the nursery school and inputs the video data into a camera image analysis system. The camera image analysis system analyzes data on children's behavior and emotions (e.g., smiling, crying) and collects it in real time.

[0918] Step 2:

[0919] The server stores the analyzed behavioral data in a database. Specifically, it records the type of play, changes in emotions, and the content of interactions in the database.

[0920] Step 3:

[0921] The server also acquires video data during meals and inputs it into the camera image analysis system. The analysis system automatically measures the type and amount of food eaten and the type and amount of food left uneaten, and collects this data.

[0922] Step 4:

[0923] The server stores the collected meal data in a database. This meal information includes details such as calorie intake and nutritional balance.

[0924] Step 5:

[0925] The server uses generative artificial intelligence (AI) to generate messages for the contact log based on stored behavioral and eating data. For example, it automatically generates messages such as, "Today, [child's name] played in the sandbox and had a great time with a smile on their face."

[0926] Step 6:

[0927] The server simultaneously uses AI generated from meal data to suggest recipes that help overcome food waste. For example, if bell peppers are left over, it will suggest a recipe for baked bell peppers with cheese.

[0928] Step 7:

[0929] The server distributes the generated communication log entries and suggested coping recipes to the childcare worker's terminal. The childcare worker can then review the entries using a tablet or other device.

[0930] Step 8:

[0931] Device (childcare worker's tablet): The childcare worker displays the generated text sent from the server on the app and checks its content. They manually correct the text as needed.

[0932] Step 9:

[0933] The user (childcare worker) confirms the corrected communication log entry by pressing the "Send" button in the app. The confirmed entry is then sent back to the server.

[0934] Step 10:

[0935] The server saves the revised text and suggested coping strategies to a database and distributes them to the parents' devices.

[0936] Step 11:

[0937] Device (Parent's Smartphone): Parents receive and view the final message from the server, meal reports, and recovery recipes via the app.

[0938] Step 12:

[0939] Users (parents) can check their child's daily behavior, eating habits, and suggested recipes on the app, which can help them with home care and meal planning.

[0940] This will significantly reduce the administrative burden on childcare workers and enable the provision of high-value information to parents.

[0941] (Example 1)

[0942] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0943] The current administrative work in daycare centers is extremely cumbersome, increasing the workload of childcare workers. In particular, the task of meticulously recording children's behavior and eating habits and providing this information to parents in the form of a communication log is time-consuming and laborious. Furthermore, the quality of information provided varies, and sometimes parents receive insufficient information. To address these issues, a system is needed that reduces the workload of childcare workers and improves the quality of information provided to parents.

[0944] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0945] In this invention, the server includes means for analyzing camera images, means for collecting behavioral data of children under childcare, means for generating text using generative artificial intelligence based on the collected behavioral data, means for displaying the generated text in a modifiable form, means for recording and distributing the modified text, means for collecting and analyzing meal data and analyzing the results using generative artificial intelligence, means for analyzing behavior and meal situations using analysis software, means for saving the modified communication log text and recipes to a database and distributing them to terminals, and means for inputting prompt sentences into an AI model to generate communication log text and meal improvement suggestions. This makes it possible to streamline administrative work in childcare centers, reduce the workload of childcare workers, and improve the quality of information provided to parents.

[0946] "Camera image analysis means" refers to a combination of a device and software that analyzes video data acquired from a camera to detect and identify the movement of objects and people within the image.

[0947] "Means for collecting behavioral data of children in childcare" refers to devices and software for collecting various behaviors of children within a nursery school as data.

[0948] "Methods for generating text using generative artificial intelligence" refers to artificial intelligence software that performs natural language processing based on collected data and automatically generates text.

[0949] "Means for displaying generated text in a modifiable format" refers to a display device and software for displaying automatically generated text in a viewable and editable format.

[0950] "Means for recording and distributing revised text" refers to a database and communication device for saving edited text and transmitting it to the necessary terminals.

[0951] "Methods for collecting and analyzing meal data and generating results using artificial intelligence" refers to devices and software that acquire data during meals, analyze it, and then use artificial intelligence to analyze the results.

[0952] "Means of analyzing behavior and eating habits using analysis software" refers to software used to analyze acquired video data, behavioral data, and eating data.

[0953] "Means for saving revised contact log entries and recipes to a database and distributing them to terminals" refers to the device and software for saving the final revised entries and generated recipes to a database and distributing them to each terminal.

[0954] "Means for generating contact log entries and dietary improvement suggestions by inputting prompt sentences into an AI model" refers to a system and software for automatically generating contact log entries and dietary improvement suggestions by inputting specific prompt sentences into a generating AI model.

[0955] This invention aims to streamline administrative tasks in childcare settings and improve the quality of information provided to parents through a series of systems that link camera image analysis means, generating artificial intelligence, and terminals used by childcare workers and parents.

[0956] 1. Setting up camera image analysis means and video analysis

[0957] Multiple cameras will be installed within the nursery school. These cameras will capture the children's daily activities and mealtimes in real time. A server will acquire the video data transmitted from the cameras and analyze the children's behavior and eating habits using analysis software (e.g., OpenCV or TensorFlow).

[0958] As a concrete example, the server analyzes the morning footage to determine that "○○ was playing with building blocks," and the afternoon footage to determine that "○○ was drawing a picture." It also analyzes the mealtime footage to determine that "○○ left some bell peppers."

[0959] 2. Collection and storage of behavioral and dietary data

[0960] The server collects behavioral and eating data based on the analysis results and stores it in a database. Behavioral data includes the type of play (e.g., playing with blocks, playing in a sandbox), changes in emotion (e.g., smiling, crying), and interactions with friends. Eating data includes the amount of food eaten and leftovers.

[0961] For example, you can save data such as "2023-10-01 09:00:00 ○○-chan playing with blocks" or "2023-10-01 12:00:00 ○○-chan left bell peppers, amount: 15g".

[0962] 3. Automatic generation of communication log entries and dietary improvement suggestions.

[0963] The server uses generated artificial intelligence based on collected behavioral and dietary data to automatically generate messages for the contact book and suggestions for dietary improvements. The server inputs the necessary prompts into the generated AI model.

[0964] Examples of specific prompt messages are as follows:

[0965] Camera image analysis results:

[0966] Morning activities: Playing with building blocks

[0967] Afternoon activity: Drawing pictures

[0968] Meal details: Left the bell peppers uneaten at lunch.

[0969] Based on this, please automatically generate the following contact log message and dietary improvement suggestions:

[0970] Contact book entry:

[0971] Dietary improvement suggestions:

[0972] As a result, the server generates a communication log entry such as, "Today, [child's name] enjoyed playing with blocks. In the afternoon, she drew pictures with her friends. At lunch, she left some bell peppers," and a suggestion for improving meals such as, "A recipe for baking bell peppers with cheese to make them easier to eat."

[0973] 4. Displaying and editing data

[0974] The childcare worker's device (tablet) displays automatically generated communication log documents sent from the server, allowing the childcare worker to review and edit them. The childcare worker then sends the edited document to the server, completing the revision process.

[0975] Afterward, the parent's device (smartphone) displays the corrected communication log, meal reports, and recipes for overcoming challenges that were sent from the server via the app. Through the app, the parent can check details of their child's daily life and meals.

[0976] 5. Data distribution and viewing

[0977] The server saves the corrected contact log entries and generated recipes to a database and distributes them to the parent's device. Parents can check the information received from the server through the app. This allows parents to have a detailed understanding of their child's daily activities and eating habits.

[0978] As described above, the present invention makes it possible to improve the efficiency of administrative work in nurseries, reduce the workload of childcare workers, and improve the quality of information provided to parents.

[0979] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0980] Step 1:

[0981] Acquiring camera images

[0982] The server acquires video data in real time from multiple cameras within the nursery school. The cameras are installed to monitor the children's daily activities and mealtimes.

[0983] Specific actions:

[0984] 1.1 The server receives the video stream via the camera's IP address.

[0985] 1.2 The server saves the received video to storage in real time.

[0986] Input: Camera IP address and video data

[0987] Output: Saved video data

[0988] Step 2:

[0989] Analysis of video data

[0990] The server analyzes the acquired video data using analysis software (e.g., OpenCV or TensorFlow) to identify the children's behavior and eating habits.

[0991] Specific actions:

[0992] 2.1 The server extracts frames from the video data and applies specific algorithms to perform face and object recognition.

[0993] 2.2 The server converts the recognition results into vector data and extracts behavioral and dietary information.

[0994] Input: Saved video data

[0995] Output: Behavioral data and dietary data

[0996] Step 3:

[0997] Collection and storage of behavioral and dietary data

[0998] The server collects behavioral data (e.g., type of play, emotional changes) and eating data (e.g., amount of food eaten and leftovers) from the analysis results and stores them in a database.

[0999] Specific actions:

[1000] 3.1 The server saves the activity data to the database. For example, it saves data such as "2023-10-01 09:00:00 ○○-chan playing with blocks".

[1001] 3.2 The server saves meal data to a database. For example, it saves data such as "2023-10-01 12:00:00 ○○-chan Bell pepper leftovers Amount: 15g".

[1002] Input: Behavioral data and dietary data

[1003] Output: Behavioral and dietary data stored in the database

[1004] Step 4:

[1005] Automatic generation of communication log entries and meal improvement suggestions.

[1006] The server uses generated artificial intelligence based on collected behavioral and dietary data to automatically generate messages for the contact book and suggestions for dietary improvements. The server inputs the necessary prompts into the generated AI model.

[1007] Specific actions:

[1008] 4.1 The server converts the behavioral data into a prompt message. For example, it might convert it to something like, "Today, XX enjoyed playing with building blocks. In the afternoon, she drew pictures with her friends."

[1009] 4.2 The server converts the meal data into a prompt message and generates a "cheese bake recipe to make bell peppers easier to eat".

[1010] Input: Behavioral data and dietary data

[1011] Output: Communication log entries and suggestions for improving meals

[1012] Step 5:

[1013] Viewing and editing data

[1014] The terminal (the childcare worker's tablet) displays automatically generated communication log documents sent from the server, allowing the childcare worker to review and edit them.

[1015] Specific actions:

[1016] 5.1 The device sends an API request to the server to retrieve automatically generated contact log entries and meal improvement suggestions.

[1017] 5.2 The device displays the acquired information within the app, allowing childcare workers to freely edit the text.

[1018] 5.3 The terminal sends the edited text back to the server, and the correction is complete.

[1019] Input: Automated contact log entries and meal improvement suggestions

[1020] Output: Communication log document edited by the childcare worker

[1021] Step 6:

[1022] Data distribution and viewing

[1023] The server saves the corrected contact log entries and generated recipes to a database and distributes them to the parents' devices.

[1024] Specific actions:

[1025] 6.1 The server saves the corrected contact log entries and recipes to the database.

[1026] 6.2 The server sends a notification to the parent's device informing them that new data is available.

[1027] 6.3 The device (the parent's smartphone) receives and displays information sent from the server via the app. Parents can gain a detailed understanding of their child's daily activities and eating habits.

[1028] Input: Communication log entries edited by childcare workers and generated recipes

[1029] Output: Communication log entries and meal improvement suggestions for parents to view.

[1030] (Application Example 1)

[1031] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1032] In daycare operations, there is a need to understand children's behavior and eating habits in detail and to streamline the provision of information to parents. Similarly, in physical stores, there is a need for a system that analyzes customer behavior in real time to efficiently support store operations. Existing methods require a great deal of time and effort to collect and analyze individual data, resulting in a heavy workload and limitations in the quality of customer service.

[1033] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1034] In this invention, the server includes camera image analysis means, means for collecting behavioral data of childcare recipients, means for generating text using generative artificial intelligence based on the collected behavioral data, means for displaying the generated text in an editable format, means for recording and distributing the edited text, means for collecting and analyzing meal data and analyzing the results using generative artificial intelligence, means for proposing and distributing recipes to overcome challenges based on the analysis results, means for analyzing customer trends in real time, means for generating in-store discount coupons and product recommendations based on the analysis results, and means for distributing the generated recommendation information to staff. This enables improved operational efficiency in childcare centers and customer behavior analysis and optimal service provision in physical stores.

[1035] A "camera image analysis means" is a means of analyzing video data acquired from a camera and extracting specific information.

[1036] "Means for collecting behavioral data of children in childcare" refers to methods for observing children's behavior in a nursery school and collecting that data.

[1037] "Methods for generating text using artificial intelligence based on behavioral data" refers to an artificial intelligence system that analyzes collected behavioral data and automatically generates text based on the results.

[1038] "Means for displaying generated text in an editable format" refers to means for displaying automatically generated text in a way that allows users to edit it.

[1039] "Means for recording and distributing revised text" refers to methods for recording the revised text in a database and distributing it to the necessary stakeholders.

[1040] "A means of collecting meal data, analyzing the results, and generating analysis using artificial intelligence" refers to a means of collecting data on meals for those receiving childcare and analyzing it using artificial intelligence.

[1041] "A method for proposing and distributing recipes to overcome dietary problems based on analysis results" refers to a method of proposing dietary improvement measures based on the results of analyzing dietary data and distributing that information.

[1042] "Methods for analyzing customer behavior in real time" refers to methods for monitoring and analyzing customer behavior within a store in real time.

[1043] "Methods for generating in-store discount coupons and product recommendations based on analysis results" refers to methods for generating appropriate discount coupons and product recommendations based on the results of customer behavior analysis.

[1044] "Means for distributing generated recommendation information to staff" refers to the means for distributing automatically generated recommendation information to store staff.

[1045] This invention aims to improve operational efficiency and the quality of information provision through a system that links camera image analysis means, generating artificial intelligence, and terminals in daycare centers and physical stores. The following describes specific embodiments for implementing this invention.

[1046] System Configuration

[1047] The system of the present invention includes the following means:

[1048] 1. Camera image analysis means

[1049] Multiple cameras will be installed in daycare centers and stores to capture children's behavior and customers' movements in real time.

[1050] The server acquires video data transmitted from the camera and uses image analysis software such as OpenCV or TensorFlow to analyze behavior and trends.

[1051] 2. Data Collection and Analysis

[1052] Server: Collects behavioral data and customer behavior data from camera footage. Behavioral data includes the types of play children engage in and changes in their emotions, while customer behavior data includes movement patterns within the store and products they show interest in.

[1053] Server: Analyzes video footage of meals to measure the amount of food eaten and left over. Store systems analyze which items customers showed interest in within the shopping area.

[1054] 3. Sentence generation

[1055] Server: Based on analyzed behavioral data, it automatically generates text using generative artificial intelligence (AI model). For example, in a nursery school, it might create a report saying, "Today, XX played in the sandbox and was smiling," and in a store, it might create a customer behavior report saying, "She spent a particularly long time looking at item A in the cosmetics section."

[1056] Server: Based on the analysis data, it generates recipes to overcome dietary restrictions, in-store discount coupons, and product recommendations.

[1057] 4. Displaying and editing data

[1058] Devices (tablets in daycare centers, smartphones for store staff): Automatically generated text is displayed in the app, and childcare workers and staff can review the text and manually correct it as needed.

[1059] Device (parent's smartphone, store's customer app): Displays corrected contact information and meal reports sent from the server, as well as discount coupons and product recommendations, within the app.

[1060] 5. Data distribution

[1061] Server: Records corrected text and suggested information in a database and distributes it to parents' and customers' devices.

[1062] Device (parent's smartphone, store's customer app): Displays received information in detail through the app.

[1063] Specific examples of hardware and software

[1064] Hardware: IP cameras, servers (such as Amazon AWS), tablets, smartphones.

[1065] Software: Image analysis libraries (OpenCV, TensorFlow), data analysis libraries (NumPy, Pandas), notification system (Firebase).

[1066] Specific example

[1067] For example, when recording what happened at daycare on a particular day, the process would be as follows:

[1068] The server analyzes the camera footage and collects data such as, "○○-chan played with blocks in the morning and drew pictures in the afternoon."

[1069] Based on the collected data, the server generates a communication log entry such as, "Today, [child's name] enjoyed playing with blocks," which is then reviewed by the childcare worker and distributed to the parents.

[1070] Device (caregiver's tablet): The caregiver reviews the generated text and manually corrects it to, "Today, XX-chan really enjoyed playing with blocks."

[1071] Device (Parent's smartphone): The parent / guardian checks the corrected contact log.

[1072] The same applies to stores:

[1073] The server analyzes camera footage to detect customers who are lingering in front of specific products for extended periods.

[1074] Based on that data, the server generates recommendation information such as "Offer a discount coupon for item A" and distributes it to the staff.

[1075] Terminal (store staff's smartphone): Checks the generated recommendation information and provides coupons to customers.

[1076] Example of a prompt

[1077] Input the following prompts into the AI ​​model to generate information:

[1078] According to today's in-store analytics data, several customers showed interest in the cosmetics section. Based on this, please generate the following actions.

[1079] Offering discount coupons in the cosmetics section.

[1080] Notification to staff

[1081] Product recommendations for your next visit

[1082] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1083] Step 1:

[1084] Acquiring camera images

[1085] The server acquires video data in real time from cameras installed in daycare centers and physical stores. This input data is video frames, and its output is a stream of video data for image analysis processing.

[1086] Step 2:

[1087] Image analysis and extraction of behavioral data

[1088] The server analyzes the acquired video data using tools such as OpenCV and TensorFlow. Specifically, it identifies children's behavior and customer movements from video frames, extracting data such as "a child is playing with blocks" or "a customer is staying with a specific product for an extended period." The input is camera video data, and the output is analyzed behavioral and movement data.

[1089] Step 3:

[1090] Text generation based on behavioral data

[1091] The server uses a generative AI model to generate appropriate sentences based on the analyzed behavioral data. For example, it automatically generates sentences such as "○○ played in the sandbox" in a nursery school setting, or "○○ showed interest in product A" in a physical store setting. The input is the analyzed behavioral data, and the output is the generated sentences.

[1092] Step 4:

[1093] Display and edit the generated text

[1094] The devices (tablets in daycare centers or smartphones for store staff) display the generated text in an editable format. Childcare workers and staff review this text and make manual corrections as needed. Specifically, they edit the text displayed on the screen using touch input or a keyboard. This input is the generated raw text, and the output is the corrected version.

[1095] Step 5:

[1096] Recording and distribution of revised text

[1097] The server records the corrected text in a database and distributes it to the parents' and customers' devices. Specifically, it saves the corrected text to a cloud-based database and distributes it to each device in a pre-encoded format. The input is the corrected text, and the output is the information displayed on the parents' and customers' devices.

[1098] Step 6:

[1099] Analysis of meal data and customer behavior data

[1100] The server collects and analyzes meal data from daycare centers and customer behavior data from physical stores. Specifically, it acquires data such as "○○ left some bell peppers" from meals and "a customer stayed in front of a particular product for a long time" from stores. The input is raw data on meals and customer behavior, and the output is the analyzed data.

[1101] Step 7:

[1102] Generating recommended information and improvement measures

[1103] The server generates recipes to overcome difficulties, discount coupons, and product recommendations based on the analysis results. Specifically, the AI ​​model generates recipes to make bell peppers easier to eat, or creates discount coupons for specific products, based on the analysis data. The input is the analysis results data, and the output is the generated recommendations and improvement measures.

[1104] Step 8:

[1105] Distribution of recommended information and improvement measures

[1106] The server distributes the generated recommendations and improvement suggestions to childcare workers, staff, parents, and customers. Specifically, it inputs prompts into an AI model to generate recommendations and then distributes the results. This input consists of the generated recommendations and improvement suggestions, and the output is the information distributed to the devices of parents and customers.

[1107] Example of a prompt

[1108] Input the following prompts into the AI ​​model to generate information:

[1109] According to today's in-store analytics data, several customers showed interest in the cosmetics section. Based on this, please generate the following actions.

[1110] Offering discount coupons in the cosmetics section.

[1111] Notification to staff

[1112] Product recommendations for your next visit

[1113] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1114] This invention is a system that improves the efficiency of administrative work in childcare settings and the quality of information provided to parents by linking camera image analysis means, generative artificial intelligence (AI), an emotion engine, and terminals used by childcare workers and parents. This system collects children's behavioral and emotional data in real time and automatically generates text, meal reports, and overcoming recipes using generative AI.

[1115] System Configuration

[1116] 1. Camera image analysis means:

[1117] Multiple cameras are installed within the nursery school to capture the children's daily activities and mealtimes in real time.

[1118] The server acquires video data transmitted from the camera and uses camera image analysis tools to analyze the children's behavior.

[1119] 2. Emotional Engine:

[1120] The server analyzes the children's facial expressions from the camera footage and collects emotional data in real time, such as smiles, crying faces, and focused faces.

[1121] The emotional data recognized by the emotion engine is recorded in the database as behavioral data and dietary data.

[1122] 3. Data collection and analysis:

[1123] The server collects behavioral and emotional data from camera footage and stores it in a database. Behavioral data includes the type of play and interactions with friends.

[1124] The server analyzes video footage of the meal, recording the types and quantities of food eaten, the types and quantities of food left uneaten, and the emotions experienced during the meal (e.g., expressions of displeasure, expressions of satisfaction), and stores this information in a database.

[1125] 4. Text generation using artificial intelligence (AI):

[1126] The server automatically generates messages for the contact log using a generative AI based on collected behavioral and emotional data. For example, it might generate a message like, "Today, [child's name] played in the sandbox and had a great time with a smile on their face."

[1127] The server uses AI to generate recipes to help overcome food waste, based on meal and emotional data. For example, if a customer leaves bell peppers uneaten, it will suggest a "Bell Pepper and Cheese Bake Recipe."

[1128] 5. Viewing and editing data:

[1129] Device (childcare worker's tablet): Provides an app that displays generated text sent from the server and allows childcare workers to manually edit the text. For example, "Today, XX-chan played in the sandbox and had fun with a smile." → "Today, XX-chan built a sandcastle and had fun with her friends."

[1130] Device (parent's smartphone): Provided via an app that displays corrected contact logs, meal reports, and recipes sent from the server.

[1131] 6. Data distribution:

[1132] The server saves the revised contact log entries and suggested coping strategies to a database and automatically distributes them to the parents' devices.

[1133] Device (Parent's smartphone): Allows parents to view the information sent via the app.

[1134] Specific example

[1135] Collecting data on children's behavior

[1136] For example, during a day at the nursery school, the server analyzes camera footage and collects behavioral data such as, "○○ played with blocks in the morning and drew pictures in the afternoon," as well as emotional data such as, "She was smiling while playing with blocks," and "She had a focused expression while drawing."

[1137] Contact book message generation

[1138] Based on the collected behavioral and emotional data, the server generates a message for the communication log, such as, "Today, [child's name] enjoyed playing with blocks, and in the afternoon, she was focused on drawing."

[1139] Collection and analysis of dietary data

[1140] The server analyzes the video from lunchtime and collects meal data such as, "○○-chan ate all her rice but left the bell peppers," and emotion data such as, "She made a displeased face when eating the bell peppers."

[1141] Generating recipes for overcoming challenges

[1142] Based on the collected food and emotional data, the server suggests a "cheese bake recipe to make bell peppers easier to eat."

[1143] Viewing and editing data

[1144] Terminal (caregiver's tablet): The caregiver checks the generated communication log entry and revises the sentence, such as, "Today, XX enjoyed playing with blocks, and in the afternoon, she was concentrating while drawing pictures."

[1145] Device (Parent's smartphone): Parents can review the corrected communication log entries and recipes for overcoming challenges, and use them as a reference for cooking.

[1146] This streamlines the administrative work of childcare workers, and allows parents to receive detailed information and specific suggestions regarding their child's daily routine and meals.

[1147] The following describes the processing flow.

[1148] Step 1:

[1149] The server acquires live video from cameras installed within the nursery school and inputs the video data into a camera image analysis system. The camera image analysis system analyzes the children's behavior (e.g., type of play, movement path) and generates behavioral data in real time.

[1150] Step 2:

[1151] The server inputs the same video data into the emotion engine. The emotion engine analyzes the child's facial expressions and generates emotion data in real time, such as smiles, crying faces, and surprised expressions. This allows for a detailed record of the child's emotional changes.

[1152] Step 3:

[1153] The server stores behavioral and emotional data generated by the camera image analysis system and emotion engine in a database. This allows for a detailed record of the child's daily life.

[1154] Step 4:

[1155] The server inputs video data from lunchtime into a camera image analysis system to analyze eating behavior. It measures the type and amount of food eaten and the type and amount of food left uneaten, and generates meal data.

[1156] Step 5:

[1157] The server inputs video data from the meal into an emotion engine and analyzes the child's facial expressions while eating. It generates emotional data such as joy, disgust, and satisfaction during the meal. This also records the child's feelings towards eating.

[1158] Step 6:

[1159] The server stores meal data and emotional data generated by the camera image analysis system and emotion engine in a database. This allows for a detailed record of the eating situation.

[1160] Step 7:

[1161] The server uses generative artificial intelligence (AI) to generate messages for the contact book based on stored behavioral and emotional data. For example, it automatically generates a message like, "Today, XX-chan was playing in the sandbox and was having fun with a smile on her face."

[1162] Step 8:

[1163] The server uses generative artificial intelligence (AI) to generate recipes to help overcome food waste, based on stored meal and emotional data. For example, if bell peppers are left uneaten, it will suggest a "Bell Pepper and Cheese Bake Recipe."

[1164] Step 9:

[1165] The server distributes the generated communication log entries and overcoming recipes to the childcare worker's terminal. The childcare worker can then review the entries using a tablet or other device.

[1166] Step 10:

[1167] Device (childcare worker's tablet): Childcare workers view the generated text sent from the server on the app and review its content. They manually revise the text as needed and perform a final check.

[1168] Step 11:

[1169] The user (childcare worker) confirms the corrected communication log entry by pressing the "Send" button in the app. The confirmed entry is then returned to the server and saved in the database.

[1170] Step 12:

[1171] The server delivers the revised contact log entries and suggested coping recipes to the parent's device. Parents can view this information through the app.

[1172] Step 13:

[1173] Device (Parent's smartphone): Parents can view communication logs, meal reports, and recipes for overcoming illness sent from the server via the app.

[1174] Step 14:

[1175] Users (parents) can check their child's daily behavior, eating habits, and suggested recipes on the app, and use this information to improve home care and meal planning.

[1176] This reduces the administrative burden on childcare workers and provides parents with detailed information about their child's daily life and meals.

[1177] (Example 2)

[1178] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1179] In childcare settings, childcare workers are burdened with a wide range of administrative tasks, including observing and recording children's behavior and emotions, writing in communication notebooks, and managing meals. Furthermore, while parents want detailed information about their children's daily lives and meals, this information is often insufficient. Therefore, there is a need to streamline the administrative work of childcare workers and improve the quality of information provided to parents.

[1180] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1181] In this invention, the server includes means for analyzing camera images, means for collecting behavioral and emotional data of the child being cared for, means for generating text using generative artificial intelligence based on the collected behavioral and emotional data, means for displaying the generated text in a modifiable form, means for recording and distributing the modified text, means for collecting and analyzing meal data and analyzing the results using generative artificial intelligence, and means for proposing and distributing recipes to overcome difficulties based on the analysis results. This streamlines the administrative work of childcare workers, and allows parents to receive detailed information about their child's daily life and meals, as well as specific suggestions.

[1182] "Means of analyzing camera images" refers to devices and software that analyze video data acquired by cameras installed within the nursery school, and are used to recognize children's behavior and facial expressions.

[1183] "Action data of children in childcare" refers to information about the various activities and behaviors that children engage in within the nursery school, including, for example, the types of play and interactions.

[1184] "Emotional data" refers to information about emotions recognized from children's facial expressions, including smiles, crying faces, and focused faces.

[1185] "Means of generating text using generative artificial intelligence" refers to artificial intelligence technology that automatically generates text in natural language based on collected data, and this includes, for example, generative AI models.

[1186] "Means of displaying generated text in an editable format" refers to devices or software that allow childcare workers to review automatically generated text and make corrections as needed, and includes, for example, tablet devices.

[1187] "Means for recording and distributing revised text" refers to systems and methods for saving text revised by childcare workers in a database and distributing it to parents in real time.

[1188] "Mealtime data" refers to information about the types and quantities of food children ate during meals, as well as the types and quantities of food they left uneaten.

[1189] "Methods of analysis using generative artificial intelligence" refers to artificial intelligence technology that analyzes collected dietary data and automatically generates new insights and suggestions based on it, and includes, for example, AI models.

[1190] The method of proposing and distributing "recipes to overcome allergies" refers to a method of automatically generating cooking recipes that make it easier for children to eat specific foods, based on analyzed dietary data, and then distributing these recipes to parents.

[1191] The present invention is configured as a system to improve the efficiency of administrative work in childcare settings and the quality of information provided to parents. This system includes means for analyzing camera images, means for collecting behavioral and emotional data, means for generating text using generative artificial intelligence based on the collected data, means for displaying the generated text in an editable format, means for recording and distributing the edited text, means for collecting, analyzing, and analyzing meal data using generative artificial intelligence, and means for proposing and distributing recipes for overcoming health challenges.

[1192] Hardware and software configuration

[1193] The system consists of the following hardware and software.

[1194] Camera: High-resolution camera (e.g., general-purpose high-resolution camera)

[1195] Server: A server for analyzing video data and collecting and analyzing behavioral data, emotional data, and dietary data.

[1196] Software: Camera image analysis libraries (e.g., OpenCV), emotion recognition libraries (e.g., Emotion Recognition API), generative AI models (e.g., GPT-3)

[1197] Devices: Tablet devices used by childcare workers, and smartphones used by parents.

[1198] Program Implementation

[1199] 1. Acquisition of video data

[1200] The server acquires video data from the camera in real time. This video data is acquired using, for example, the RTSP protocol.

[1201] 2. Analysis of video data

[1202] The server uses OpenCV to analyze video data and recognize the children's behavior (e.g., type of play, interactions).

[1203] For example, one might observe a child playing with building blocks in the morning.

[1204] 3. Recognition and collection of emotional data

[1205] The server uses an emotion recognition API to analyze the children's facial expressions from the video data and recognize emotional data (e.g., smiling, crying, concentrating).

[1206] For example, we may recognize a smile while a child is playing with building blocks.

[1207] 4. Storage of behavioral and emotional data

[1208] The server stores the analyzed and recognized behavioral and emotional data in a database. Transaction management is performed to ensure data integrity and security.

[1209] For example, the system saves data indicating that the child played with building blocks in the morning and was smiling at that time.

[1210] 5. Automatic sentence generation

[1211] The server automatically generates contact book entries using a generative AI model (e.g., GPT-3) based on the collected data.

[1212] For example, it can generate sentences like, "Today, [Name] enjoyed playing with building blocks, and in the afternoon, she was concentrating on drawing."

[1213] Example of a prompt:

[1214] Today, [Name] enjoyed playing with building blocks, and in the afternoon, she was concentrating on drawing.

[1215] 6. Correction and display of generated text

[1216] The device (the childcare worker's tablet) displays the generated communication log document, and the childcare worker makes corrections as needed.

[1217] For example, change "Today, XX enjoyed playing with blocks, and in the afternoon, she was focused on drawing." to "Today, XX built a sandcastle and had fun with her friends."

[1218] 7. Collection and analysis of dietary data

[1219] The server analyzes video footage of meals and collects meal data (e.g., types and amounts of food eaten, types and amounts of food left over).

[1220] For example, we collect data such as "○○-chan ate all her rice but left the bell peppers."

[1221] 8. Generating a recipe for overcoming the problem

[1222] The server generates recipes to help overcome food waste based on the collected meal data.

[1223] For example, I'd like to suggest a recipe for "cheese-baked bell peppers to make them easier to eat."

[1224] 9. Distribution of revised text and recipes

[1225] The server saves the revised contact log entries and suggested recipes to a database and distributes them to the parents' devices.

[1226] The device (the parent's smartphone) receives information sent from the server and displays it to the user.

[1227] For example, a parent might see a message in the communication notebook saying, "Today, [child's name] built a sandcastle and had fun with their friends," as well as a recipe for "baked bell peppers with cheese."

[1228] This will streamline the administrative work of childcare workers, and allow parents to receive detailed information about their child's daily life and meals, as well as specific suggestions.

[1229] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1230] Step 1: Acquire video data

[1231] The server acquires video data in real time from multiple cameras installed within the nursery school. The input is the video stream transmitted from the cameras (for example, using the RTSP protocol). The acquired video data is stored in a temporary storage area. For example, the server receives the video via the camera's IP address and saves it to the temporary storage area.

[1232] Step 2: Analysis of video data

[1233] The server uses OpenCV to analyze video data stored in a temporary storage area. The input is video data. As data processing, an object detection algorithm (e.g., YOLO) is applied to each frame to recognize children's actions. The output is the recognized action data. For example, the server detects children playing with blocks in the morning.

[1234] Step 3: Recognizing and collecting emotional data

[1235] The server uses an emotion recognition API to analyze children's facial expressions from analyzed video data. The input is the analyzed video data. As part of the data processing, an emotion recognition algorithm is applied to recognize emotions such as smiles, crying faces, and focused faces. The output is the recognized emotion data. For example, the server recognizes a smile while a child is playing with blocks.

[1236] Step 4: Saving behavioral and emotional data

[1237] The server stores recognized behavioral and emotional data in a database. The input consists of behavioral and emotional data. Data processing involves converting the data into a well-formed format (e.g., JSON) and inserting it into the database using SQL queries. The output is the record in the database. For example, the server might store data about playing with building blocks in the morning and the smile associated with that activity in the database.

[1238] Step 5: Automatic text generation

[1239] The server generates contact log entries using a generative AI model (e.g., GPT-3) based on behavioral and emotional data stored in the database. The input consists of behavioral and emotional data. As a data operation, prompt sentences are provided to the generative AI model for inference. The output is an automatically generated contact log entry. For example, it might generate an entry like, "Today, XX enjoyed playing with blocks, and in the afternoon, she was concentrating on drawing."

[1240] Step 6: Modify and display the generated text

[1241] The terminal (the childcare worker's tablet) displays the generated text sent from the server, and the childcare worker makes corrections as needed. The input is the automatically generated communication log text. The output is the corrected communication log text. For example, the childcare worker might change "Today, XX enjoyed playing with blocks, and in the afternoon, she was concentrating while drawing pictures." to "Today, XX built a sandcastle and enjoyed playing with her friends."

[1242] Step 7: Collection and analysis of dietary data

[1243] The server analyzes video footage of meals and collects meal data. The input is video data of the meal. As part of the data processing, a video analysis algorithm is applied to extract the contents of the meal and any leftovers. The output is the analyzed meal data. For example, the server collects data such as, "○○-chan ate all of her rice, but left the bell peppers."

[1244] Step 8: Generating a Recipe for Overcoming Challenges

[1245] The server generates recipes to overcome food allergies using a generative AI model based on meal data. The input is meal data. As a data calculation, prompts are provided to the generative AI model for inference. The output is the generated recipe. For example, it might generate a "cheese bake recipe to make bell peppers easier to eat."

[1246] Step 9: Distribute the revised text and recipe.

[1247] The server saves the revised contact log entries and suggested recipes to a database and distributes them to the parent's device. The input is the revised entries and generated recipes. The output is the notification and display information on the parent's device. For example, the parent's smartphone might receive a contact log entry that reads, "Today, [child's name] built a sandcastle and had fun with their friends," along with a recipe for "Grilled bell peppers with cheese."

[1248] (Application Example 2)

[1249] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1250] In modern brick-and-mortar stores, it is difficult to collect real-time data on children's behavior and emotional changes in play areas and provide detailed reports to parents. Therefore, parents have difficulty understanding their child's play status and emotional changes. Furthermore, manually creating these reports is burdensome, and efficiency improvements are needed.

[1251] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a camera image analysis means, a means for collecting subject behavior data, a means for generating text using generative artificial intelligence based on the collected behavior data, a means for displaying the generated text in a modifiable form, a means for recording and distributing the modified text, a means for collecting and analyzing meal data and analyzing the results using generative artificial intelligence, a means for proposing and distributing overcoming recipes based on the analysis results, and a means for generating and distributing a play status report based on behavior data and emotional data. This makes it possible for parents to check their child's play status and emotional changes in real time via their smartphone.

[1252] A "camera image analysis means" is a device or system that uses a camera to analyze the behavior and facial expressions of a subject in real time and collect the data.

[1253] "Subject behavior data" refers to information about the subject's behavior acquired through sensors such as cameras, and includes, for example, the type of play and details of their actions.

[1254] "Generative artificial intelligence" is an artificial intelligence technology that has the ability to automatically generate text and reports based on collected data.

[1255] "Methods for generating text" refers to a system that automatically generates text using generative artificial intelligence based on collected behavioral and emotional data.

[1256] "Means for displaying generated text in an editable format" refers to a system that provides an interface allowing users to review and edit generated text.

[1257] "Means for recording and distributing revised text" refers to a system for saving revised text and distributing it to relevant parties.

[1258] "Dietary data" refers to detailed information about a person's diet, such as the amount of food they consumed and the amount of food they left uneaten.

[1259] "A means of analyzing the results using generative artificial intelligence" refers to a technology that analyzes collected dietary data and then uses generative artificial intelligence to analyze the results.

[1260] A "recipe to overcome a dislike" is a recipe suggestion designed to make it easier for a person to consume foods they dislike, and may include suggestions for cooking methods or ingredient combinations.

[1261] "Behavioral and emotional data" refers to data about the subject's behavior and the emotional changes associated with that behavior.

[1262] A "play activity report" is a detailed report describing a child's play activities and emotional changes, intended for parents to review.

[1263] "Means of distribution" refers to a system that automatically sends documents and reports generated or modified by generative artificial intelligence to relevant parties.

[1264] "Through a parent's smartphone" refers to a method of viewing and manipulating information and data using a smartphone.

[1265] This invention is a system that collects behavioral and emotional data of children in play areas within physical stores and provides detailed reports to parents in real time. The following describes a specific form for implementing this system.

[1266] System Configuration

[1267] The system consists of the following elements:

[1268] 1. Camera image analysis means:

[1269] Multiple cameras will be installed within the play area. These cameras will capture children's daily behavior and emotional changes in real time.

[1270] The server acquires video data transmitted from the camera and uses camera image analysis tools to analyze the children's behavior.

[1271] 2. Means for collecting behavioral and emotional data:

[1272] The server collects behavioral and emotional data from camera footage and stores it in a database. Behavioral data includes the type of play and interactions with friends.

[1273] The emotion engine analyzes facial expressions from video and collects emotional data in real time, such as smiles, crying faces, and focused faces.

[1274] 3. Text generation methods using AI:

[1275] The server uses a generative AI to automatically generate playtime reports based on collected behavioral and emotional data. For example, it might generate a sentence like, "Today, [child's name] had a lot of fun playing on the slide and smiled a lot."

[1276] 4. Means for correcting the generated text:

[1277] Device (parent's smartphone): Displays generated text sent from the server, allowing the parent to manually review the text.

[1278] 5. Means of recording and distributing documents:

[1279] The server saves the corrected text to a database and automatically delivers it to the parent's device. Parents can view the transmitted information through a smartphone app.

[1280] Examples

[1281] Specific examples of data collection and analysis

[1282] Parents install a smartphone app, and when their child enters the play area, multiple cameras track the child's actions and send behavioral and emotional data to a server. For example, when a child is playing on a slide, the camera films the action, and the server analyzes the footage to collect behavioral data such as "playing on a slide" and emotional data such as "smiling a lot."

[1283] Report generation and distribution

[1284] The server uses generative AI to generate reports based on collected behavioral and emotional data. For example, it might generate a sentence like, "Today, [child's name] was playing on the slide and laughing happily." The generated report is sent to a smartphone app, allowing parents to check their child's play status in real time.

[1285] Example of a prompt

[1286] "Please generate a detailed report based on the child's behavior and emotional data in the play area. The child's behavior is 'playing on the slide,' and their emotion is 'smiling a lot.'"

[1287] In this way, parents can instantly grasp their child's playing situation and emotional changes, allowing them to let their children play in the play area of ​​the physical store with peace of mind.

[1288] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1289] Step 1:

[1290] The server acquires video data in real time from cameras installed within the play area. The cameras capture the children's actions and expressions within the play area and transmit this video data to the server. Camera video data serves as input, forming the basis for behavioral and emotional data.

[1291] Step 2:

[1292] The server analyzes camera video data using camera image analysis tools. Specifically, it detects specific actions from the video data and analyzes facial expressions to extract emotion data. For example, it can detect actions such as playing on a slide or facial expressions such as smiling. Video data is the input, and action data and emotion data are obtained as output.

[1293] Step 3:

[1294] The server stores the analyzed behavioral and emotional data in a database. This data is used for subsequent processing. Behavioral and emotional data are the inputs, and the output is stored in the database.

[1295] Step 4:

[1296] The server uses a generative AI to generate a play situation report based on stored behavioral and emotional data. The generative AI is given a prompt, for example, "The child's behavior is 'playing on the slide,' and their emotion is 'smiling a lot.' Please generate a detailed report based on this." The output is an automatically generated report document.

[1297] Step 5:

[1298] The device (the parent's smartphone) receives the generated report document sent from the server. The parent can review this report and make corrections as needed. The generated report document is the input, and the corrected report document is the output.

[1299] Step 6:

[1300] The server saves the corrected report document to the database and then distributes it again to the parent's device. The input is the corrected report document, and the output is saving to the database and distributing it to the parent.

[1301] Step 7:

[1302] Users (parents) can review the final report via their device, gaining real-time insights into their child's play status and emotional changes. The final report is the input, and the output provides parents with peace of mind and a clear understanding of the information.

[1303] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1304] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1305] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1306] [Fourth Embodiment]

[1307] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1308] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1309] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1310] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1311] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1312] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1313] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1314] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1315] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1316] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1317] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1318] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1319] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1320] This invention aims to streamline administrative tasks in childcare settings and improve the quality of information provided to parents through a series of systems that link camera image analysis means, generating artificial intelligence, and terminals used by childcare workers and parents. The specific implementation of this system will now be described.

[1321] System Configuration

[1322] 1. Camera image analysis means:

[1323] Multiple cameras will be installed inside the nursery school. These cameras will record the children's daily activities and mealtimes in real time.

[1324] The server acquires video data transmitted from the camera and uses analysis software to analyze the children's behavior and eating habits.

[1325] 2. Data collection and analysis:

[1326] Server: Collects data on children's behavior from camera footage. For example, it analyzes the type of play (e.g., playing with blocks, playing in the sandbox), changes in emotions (e.g., smiling, crying), and interactions with friends.

[1327] Server: Similarly, it analyzes video footage of meals to measure the amount of food eaten and left over. This allows for an understanding of the child's nutritional intake.

[1328] 3. Sentence generation:

[1329] Server: Based on the analyzed behavioral data, it uses generative artificial intelligence to automatically generate text for the contact log. For example, it creates a report such as, "Today, XX-chan played in the sandbox and was smiling."

[1330] Server: Based on meal data, it generates trends in food waste, analyzes them using artificial intelligence, and generates specific improvement suggestions and recipes.

[1331] 4. Viewing and editing data:

[1332] Terminal (caregiver's tablet): The app displays automatically generated communication log messages sent from the server. The caregiver reviews the messages and makes manual corrections as needed. For example, they might edit it to read, "Today, XX-chan was playing in the sandbox and had fun with her friends."

[1333] Device (Parent's Smartphone): The app displays corrected communication logs, meal reports, and recipes sent from the server. Parents can check details of their child's daily life and meals.

[1334] 5. Data distribution:

[1335] Server: Records corrected text and suggested recipes in a database and distributes them to the parent's device.

[1336] Device (parent's smartphone): Receives and displays information sent from the server via the app. This allows parents to have a detailed understanding of their child's daily activities and eating habits.

[1337] Specific example

[1338] For example, when recording what happened at daycare on a particular day, the process would be as follows:

[1339] 1. The server analyzes the video from the camera and collects data such as, "○○ played with blocks in the morning and drew pictures in the afternoon," and "She left some bell peppers at lunch."

[1340] 2. Based on the collected data, the server generates a communication log entry that reads, "Today, [child's name] enjoyed playing with blocks. In the afternoon, she drew a picture and then shared it with her friends. She left some bell peppers at lunch," and a recipe for overcoming her aversion to bell peppers, such as "A recipe for baking bell peppers with cheese to make them easier to eat."

[1341] 3. Device (caregiver's tablet): The caregiver reviews the generated text and makes corrections such as, "Today, XX-chan really enjoyed playing with blocks."

[1342] 4. Device (Parent's smartphone): The parent checks the corrected contact log and the cheese bake recipe.

[1343] This streamlines the administrative work of childcare workers and allows parents to receive detailed information about their child's daily routine and meals.

[1344] The following describes the processing flow.

[1345] Step 1:

[1346] The server acquires live video from cameras within the nursery school and inputs the video data into a camera image analysis system. The camera image analysis system analyzes data on children's behavior and emotions (e.g., smiling, crying) and collects it in real time.

[1347] Step 2:

[1348] The server stores the analyzed behavioral data in a database. Specifically, it records the type of play, changes in emotions, and the content of interactions in the database.

[1349] Step 3:

[1350] The server also acquires video data during meals and inputs it into the camera image analysis system. The analysis system automatically measures the type and amount of food eaten and the type and amount of food left uneaten, and collects this data.

[1351] Step 4:

[1352] The server stores the collected meal data in a database. This meal information includes details such as calorie intake and nutritional balance.

[1353] Step 5:

[1354] The server uses generative artificial intelligence (AI) to generate messages for the contact log based on stored behavioral and eating data. For example, it automatically generates messages such as, "Today, [child's name] played in the sandbox and had a great time with a smile on their face."

[1355] Step 6:

[1356] The server simultaneously uses AI generated from meal data to suggest recipes that help overcome food waste. For example, if bell peppers are left over, it will suggest a recipe for baked bell peppers with cheese.

[1357] Step 7:

[1358] The server distributes the generated communication log entries and suggested coping recipes to the childcare worker's terminal. The childcare worker can then review the entries using a tablet or other device.

[1359] Step 8:

[1360] Device (childcare worker's tablet): The childcare worker displays the generated text sent from the server on the app and checks its content. They manually correct the text as needed.

[1361] Step 9:

[1362] The user (childcare worker) confirms the corrected communication log entry by pressing the "Send" button in the app. The confirmed entry is then sent back to the server.

[1363] Step 10:

[1364] The server saves the revised text and suggested coping strategies to a database and distributes them to the parents' devices.

[1365] Step 11:

[1366] Device (Parent's Smartphone): Parents receive and view the final message from the server, meal reports, and recovery recipes via the app.

[1367] Step 12:

[1368] Users (parents) can check their child's daily behavior, eating habits, and suggested recipes on the app, which can help them with home care and meal planning.

[1369] This will significantly reduce the administrative burden on childcare workers and enable the provision of high-value information to parents.

[1370] (Example 1)

[1371] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1372] The current administrative work in daycare centers is extremely cumbersome, increasing the workload of childcare workers. In particular, the task of meticulously recording children's behavior and eating habits and providing this information to parents in the form of a communication log is time-consuming and laborious. Furthermore, the quality of information provided varies, and sometimes parents receive insufficient information. To address these issues, a system is needed that reduces the workload of childcare workers and improves the quality of information provided to parents.

[1373] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1374] In this invention, the server includes means for analyzing camera images, means for collecting behavioral data of children under childcare, means for generating text using generative artificial intelligence based on the collected behavioral data, means for displaying the generated text in a modifiable form, means for recording and distributing the modified text, means for collecting and analyzing meal data and analyzing the results using generative artificial intelligence, means for analyzing behavior and meal situations using analysis software, means for saving the modified communication log text and recipes to a database and distributing them to terminals, and means for inputting prompt sentences into an AI model to generate communication log text and meal improvement suggestions. This makes it possible to streamline administrative work in childcare centers, reduce the workload of childcare workers, and improve the quality of information provided to parents.

[1375] "Camera image analysis means" refers to a combination of a device and software that analyzes video data acquired from a camera to detect and identify the movement of objects and people within the image.

[1376] "Means for collecting behavioral data of children in childcare" refers to devices and software for collecting various behaviors of children within a nursery school as data.

[1377] "Methods for generating text using generative artificial intelligence" refers to artificial intelligence software that performs natural language processing based on collected data and automatically generates text.

[1378] "Means for displaying generated text in a modifiable format" refers to a display device and software for displaying automatically generated text in a viewable and editable format.

[1379] "Means for recording and distributing revised text" refers to a database and communication device for saving edited text and transmitting it to the necessary terminals.

[1380] "Methods for collecting and analyzing meal data and generating results using artificial intelligence" refers to devices and software that acquire data during meals, analyze it, and then use artificial intelligence to analyze the results.

[1381] "Means of analyzing behavior and eating habits using analysis software" refers to software used to analyze acquired video data, behavioral data, and eating data.

[1382] "Means for saving revised contact log entries and recipes to a database and distributing them to terminals" refers to the device and software for saving the final revised entries and generated recipes to a database and distributing them to each terminal.

[1383] "Means for generating contact log entries and dietary improvement suggestions by inputting prompt sentences into an AI model" refers to a system and software for automatically generating contact log entries and dietary improvement suggestions by inputting specific prompt sentences into a generating AI model.

[1384] This invention aims to streamline administrative tasks in childcare settings and improve the quality of information provided to parents through a series of systems that link camera image analysis means, generating artificial intelligence, and terminals used by childcare workers and parents.

[1385] 1. Setting up camera image analysis means and video analysis

[1386] Multiple cameras will be installed within the nursery school. These cameras will capture the children's daily activities and mealtimes in real time. A server will acquire the video data transmitted from the cameras and analyze the children's behavior and eating habits using analysis software (e.g., OpenCV or TensorFlow).

[1387] As a concrete example, the server analyzes the morning footage to determine that "○○ was playing with building blocks," and the afternoon footage to determine that "○○ was drawing a picture." It also analyzes the mealtime footage to determine that "○○ left some bell peppers."

[1388] 2. Collection and storage of behavioral and dietary data

[1389] The server collects behavioral and eating data based on the analysis results and stores it in a database. Behavioral data includes the type of play (e.g., playing with blocks, playing in a sandbox), changes in emotion (e.g., smiling, crying), and interactions with friends. Eating data includes the amount of food eaten and leftovers.

[1390] For example, you can save data such as "2023-10-01 09:00:00 ○○-chan playing with blocks" or "2023-10-01 12:00:00 ○○-chan left bell peppers, amount: 15g".

[1391] 3. Automatic generation of communication log entries and dietary improvement suggestions.

[1392] The server uses generated artificial intelligence based on collected behavioral and dietary data to automatically generate messages for the contact book and suggestions for dietary improvements. The server inputs the necessary prompts into the generated AI model.

[1393] Examples of specific prompt messages are as follows:

[1394] Camera image analysis results:

[1395] Morning activities: Playing with building blocks

[1396] Afternoon activity: Drawing pictures

[1397] Meal details: Left the bell peppers uneaten at lunch.

[1398] Based on this, please automatically generate the following contact log message and dietary improvement suggestions:

[1399] Contact book entry:

[1400] Dietary improvement suggestions:

[1401] As a result, the server generates a communication log entry such as, "Today, [child's name] enjoyed playing with blocks. In the afternoon, she drew pictures with her friends. At lunch, she left some bell peppers," and a suggestion for improving meals such as, "A recipe for baking bell peppers with cheese to make them easier to eat."

[1402] 4. Displaying and editing data

[1403] The childcare worker's device (tablet) displays automatically generated communication log documents sent from the server, allowing the childcare worker to review and edit them. The childcare worker then sends the edited document to the server, completing the revision process.

[1404] Afterward, the parent's device (smartphone) displays the corrected communication log, meal reports, and recipes for overcoming challenges that were sent from the server via the app. Through the app, the parent can check details of their child's daily life and meals.

[1405] 5. Data distribution and viewing

[1406] The server saves the corrected contact log entries and generated recipes to a database and distributes them to the parent's device. Parents can check the information received from the server through the app. This allows parents to have a detailed understanding of their child's daily activities and eating habits.

[1407] As described above, the present invention makes it possible to improve the efficiency of administrative work in nurseries, reduce the workload of childcare workers, and improve the quality of information provided to parents.

[1408] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1409] Step 1:

[1410] Acquiring camera images

[1411] The server acquires video data in real time from multiple cameras within the nursery school. The cameras are installed to monitor the children's daily activities and mealtimes.

[1412] Specific actions:

[1413] 1.1 The server receives the video stream via the camera's IP address.

[1414] 1.2 The server saves the received video to storage in real time.

[1415] Input: Camera IP address and video data

[1416] Output: Saved video data

[1417] Step 2:

[1418] Analysis of video data

[1419] The server analyzes the acquired video data using analysis software (e.g., OpenCV or TensorFlow) to identify the children's behavior and eating habits.

[1420] Specific actions:

[1421] 2.1 The server extracts frames from the video data and applies specific algorithms to perform face and object recognition.

[1422] 2.2 The server converts the recognition results into vector data and extracts behavioral and dietary information.

[1423] Input: Saved video data

[1424] Output: Behavioral data and dietary data

[1425] Step 3:

[1426] Collection and storage of behavioral and dietary data

[1427] The server collects behavioral data (e.g., type of play, emotional changes) and eating data (e.g., amount of food eaten and leftovers) from the analysis results and stores them in a database.

[1428] Specific actions:

[1429] 3.1 The server saves the activity data to the database. For example, it saves data such as "2023-10-01 09:00:00 ○○-chan playing with blocks".

[1430] 3.2 The server saves meal data to a database. For example, it saves data such as "2023-10-01 12:00:00 ○○-chan Bell pepper leftovers Amount: 15g".

[1431] Input: Behavioral data and dietary data

[1432] Output: Behavioral and dietary data stored in the database

[1433] Step 4:

[1434] Automatic generation of communication log entries and meal improvement suggestions.

[1435] The server uses generated artificial intelligence based on collected behavioral and dietary data to automatically generate messages for the contact book and suggestions for dietary improvements. The server inputs the necessary prompts into the generated AI model.

[1436] Specific actions:

[1437] 4.1 The server converts the behavioral data into a prompt message. For example, it might convert it to something like, "Today, XX enjoyed playing with building blocks. In the afternoon, she drew pictures with her friends."

[1438] 4.2 The server converts the meal data into a prompt message and generates a "cheese bake recipe to make bell peppers easier to eat".

[1439] Input: Behavioral data and dietary data

[1440] Output: Communication log entries and suggestions for improving meals

[1441] Step 5:

[1442] Viewing and editing data

[1443] The terminal (the childcare worker's tablet) displays automatically generated communication log documents sent from the server, allowing the childcare worker to review and edit them.

[1444] Specific actions:

[1445] 5.1 The device sends an API request to the server to retrieve automatically generated contact log entries and meal improvement suggestions.

[1446] 5.2 The device displays the acquired information within the app, allowing childcare workers to freely edit the text.

[1447] 5.3 The terminal sends the edited text back to the server, and the correction is complete.

[1448] Input: Automated contact log entries and meal improvement suggestions

[1449] Output: Communication log document edited by the childcare worker

[1450] Step 6:

[1451] Data distribution and viewing

[1452] The server saves the corrected contact log entries and generated recipes to a database and distributes them to the parents' devices.

[1453] Specific actions:

[1454] 6.1 The server saves the corrected contact log entries and recipes to the database.

[1455] 6.2 The server sends a notification to the parent's device informing them that new data is available.

[1456] 6.3 The device (the parent's smartphone) receives and displays information sent from the server via the app. Parents can gain a detailed understanding of their child's daily activities and eating habits.

[1457] Input: Communication log entries edited by childcare workers and generated recipes

[1458] Output: Communication log entries and meal improvement suggestions for parents to view.

[1459] (Application Example 1)

[1460] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1461] In daycare operations, there is a need to understand children's behavior and eating habits in detail and to streamline the provision of information to parents. Similarly, in physical stores, there is a need for a system that analyzes customer behavior in real time to efficiently support store operations. Existing methods require a great deal of time and effort to collect and analyze individual data, resulting in a heavy workload and limitations in the quality of customer service.

[1462] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1463] In this invention, the server includes camera image analysis means, means for collecting behavioral data of childcare recipients, means for generating text using generative artificial intelligence based on the collected behavioral data, means for displaying the generated text in an editable format, means for recording and distributing the edited text, means for collecting and analyzing meal data and analyzing the results using generative artificial intelligence, means for proposing and distributing recipes to overcome challenges based on the analysis results, means for analyzing customer trends in real time, means for generating in-store discount coupons and product recommendations based on the analysis results, and means for distributing the generated recommendation information to staff. This enables improved operational efficiency in childcare centers and customer behavior analysis and optimal service provision in physical stores.

[1464] A "camera image analysis means" is a means of analyzing video data acquired from a camera and extracting specific information.

[1465] "Means for collecting behavioral data of children in childcare" refers to methods for observing children's behavior in a nursery school and collecting that data.

[1466] "Methods for generating text using artificial intelligence based on behavioral data" refers to an artificial intelligence system that analyzes collected behavioral data and automatically generates text based on the results.

[1467] "Means for displaying generated text in an editable format" refers to means for displaying automatically generated text in a way that allows users to edit it.

[1468] "Means for recording and distributing revised text" refers to methods for recording the revised text in a database and distributing it to the necessary stakeholders.

[1469] "A means of collecting meal data, analyzing the results, and generating analysis using artificial intelligence" refers to a means of collecting data on meals for those receiving childcare and analyzing it using artificial intelligence.

[1470] "A method for proposing and distributing recipes to overcome dietary problems based on analysis results" refers to a method of proposing dietary improvement measures based on the results of analyzing dietary data and distributing that information.

[1471] "Methods for analyzing customer behavior in real time" refers to methods for monitoring and analyzing customer behavior within a store in real time.

[1472] "Methods for generating in-store discount coupons and product recommendations based on analysis results" refers to methods for generating appropriate discount coupons and product recommendations based on the results of customer behavior analysis.

[1473] "Means for distributing generated recommendation information to staff" refers to the means for distributing automatically generated recommendation information to store staff.

[1474] This invention aims to improve operational efficiency and the quality of information provision through a system that links camera image analysis means, generating artificial intelligence, and terminals in daycare centers and physical stores. The following describes specific embodiments for implementing this invention.

[1475] System Configuration

[1476] The system of the present invention includes the following means:

[1477] 1. Camera image analysis means

[1478] Multiple cameras will be installed in daycare centers and stores to capture children's behavior and customers' movements in real time.

[1479] The server acquires video data transmitted from the camera and uses image analysis software such as OpenCV or TensorFlow to analyze behavior and trends.

[1480] 2. Data Collection and Analysis

[1481] Server: Collects behavioral data and customer behavior data from camera footage. Behavioral data includes the types of play children engage in and changes in their emotions, while customer behavior data includes movement patterns within the store and products they show interest in.

[1482] Server: Analyzes video footage of meals to measure the amount of food eaten and left over. Store systems analyze which items customers showed interest in within the shopping area.

[1483] 3. Sentence generation

[1484] Server: Based on analyzed behavioral data, it automatically generates text using generative artificial intelligence (AI model). For example, in a nursery school, it might create a report saying, "Today, XX played in the sandbox and was smiling," and in a store, it might create a customer behavior report saying, "She spent a particularly long time looking at item A in the cosmetics section."

[1485] Server: Based on the analysis data, it generates recipes to overcome dietary restrictions, in-store discount coupons, and product recommendations.

[1486] 4. Displaying and editing data

[1487] Devices (tablets in daycare centers, smartphones for store staff): Automatically generated text is displayed in the app, and childcare workers and staff can review the text and manually correct it as needed.

[1488] Device (parent's smartphone, store's customer app): Displays corrected contact information and meal reports sent from the server, as well as discount coupons and product recommendations, within the app.

[1489] 5. Data distribution

[1490] Server: Records corrected text and suggested information in a database and distributes it to parents' and customers' devices.

[1491] Device (parent's smartphone, store's customer app): Displays received information in detail through the app.

[1492] Specific examples of hardware and software

[1493] Hardware: IP cameras, servers (such as Amazon AWS), tablets, smartphones.

[1494] Software: Image analysis libraries (OpenCV, TensorFlow), data analysis libraries (NumPy, Pandas), notification system (Firebase).

[1495] Specific example

[1496] For example, when recording what happened at daycare on a particular day, the process would be as follows:

[1497] The server analyzes the camera footage and collects data such as, "○○-chan played with blocks in the morning and drew pictures in the afternoon."

[1498] Based on the collected data, the server generates a communication log entry such as, "Today, [child's name] enjoyed playing with blocks," which is then reviewed by the childcare worker and distributed to the parents.

[1499] Device (caregiver's tablet): The caregiver reviews the generated text and manually corrects it to, "Today, XX-chan really enjoyed playing with blocks."

[1500] Device (Parent's smartphone): The parent / guardian checks the corrected contact log.

[1501] The same applies to stores:

[1502] The server analyzes camera footage to detect customers who are lingering in front of specific products for extended periods.

[1503] Based on that data, the server generates recommendation information such as "Offer a discount coupon for item A" and distributes it to the staff.

[1504] Terminal (store staff's smartphone): Checks the generated recommendation information and provides coupons to customers.

[1505] Example of a prompt

[1506] Input the following prompts into the AI ​​model to generate information:

[1507] According to today's in-store analytics data, several customers showed interest in the cosmetics section. Based on this, please generate the following actions.

[1508] Offering discount coupons in the cosmetics section.

[1509] Notification to staff

[1510] Product recommendations for your next visit

[1511] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1512] Step 1:

[1513] Acquiring camera images

[1514] The server acquires video data in real time from cameras installed in daycare centers and physical stores. This input data is video frames, and its output is a stream of video data for image analysis processing.

[1515] Step 2:

[1516] Image analysis and extraction of behavioral data

[1517] The server analyzes the acquired video data using tools such as OpenCV and TensorFlow. Specifically, it identifies children's behavior and customer movements from video frames, extracting data such as "a child is playing with blocks" or "a customer is staying with a specific product for an extended period." The input is camera video data, and the output is analyzed behavioral and movement data.

[1518] Step 3:

[1519] Text generation based on behavioral data

[1520] The server uses a generative AI model to generate appropriate sentences based on the analyzed behavioral data. For example, it automatically generates sentences such as "○○ played in the sandbox" in a nursery school setting, or "○○ showed interest in product A" in a physical store setting. The input is the analyzed behavioral data, and the output is the generated sentences.

[1521] Step 4:

[1522] Display and edit the generated text

[1523] The devices (tablets in daycare centers or smartphones for store staff) display the generated text in an editable format. Childcare workers and staff review this text and make manual corrections as needed. Specifically, they edit the text displayed on the screen using touch input or a keyboard. This input is the generated raw text, and the output is the corrected version.

[1524] Step 5:

[1525] Recording and distribution of revised text

[1526] The server records the corrected text in a database and distributes it to the parents' and customers' devices. Specifically, it saves the corrected text to a cloud-based database and distributes it to each device in a pre-encoded format. The input is the corrected text, and the output is the information displayed on the parents' and customers' devices.

[1527] Step 6:

[1528] Analysis of meal data and customer behavior data

[1529] The server collects and analyzes meal data from daycare centers and customer behavior data from physical stores. Specifically, it acquires data such as "○○ left some bell peppers" from meals and "a customer stayed in front of a particular product for a long time" from stores. The input is raw data on meals and customer behavior, and the output is the analyzed data.

[1530] Step 7:

[1531] Generating recommended information and improvement measures

[1532] The server generates recipes to overcome difficulties, discount coupons, and product recommendations based on the analysis results. Specifically, the AI ​​model generates recipes to make bell peppers easier to eat, or creates discount coupons for specific products, based on the analysis data. The input is the analysis results data, and the output is the generated recommendations and improvement measures.

[1533] Step 8:

[1534] Distribution of recommended information and improvement measures

[1535] The server distributes the generated recommendations and improvement suggestions to childcare workers, staff, parents, and customers. Specifically, it inputs prompts into an AI model to generate recommendations and then distributes the results. This input consists of the generated recommendations and improvement suggestions, and the output is the information distributed to the devices of parents and customers.

[1536] Example of a prompt

[1537] Input the following prompts into the AI ​​model to generate information:

[1538] According to today's in-store analytics data, several customers showed interest in the cosmetics section. Based on this, please generate the following actions.

[1539] Offering discount coupons in the cosmetics section.

[1540] Notification to staff

[1541] Product recommendations for your next visit

[1542] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1543] This invention is a system that improves the efficiency of administrative work in childcare settings and the quality of information provided to parents by linking camera image analysis means, generative artificial intelligence (AI), an emotion engine, and terminals used by childcare workers and parents. This system collects children's behavioral and emotional data in real time and automatically generates text, meal reports, and overcoming recipes using generative AI.

[1544] System Configuration

[1545] 1. Camera image analysis means:

[1546] Multiple cameras are installed within the nursery school to capture the children's daily activities and mealtimes in real time.

[1547] The server acquires video data transmitted from the camera and uses camera image analysis tools to analyze the children's behavior.

[1548] 2. Emotional Engine:

[1549] The server analyzes the children's facial expressions from the camera footage and collects emotional data in real time, such as smiles, crying faces, and focused faces.

[1550] The emotional data recognized by the emotion engine is recorded in the database as behavioral data and dietary data.

[1551] 3. Data collection and analysis:

[1552] The server collects behavioral and emotional data from camera footage and stores it in a database. Behavioral data includes the type of play and interactions with friends.

[1553] The server analyzes video footage of the meal, recording the types and quantities of food eaten, the types and quantities of food left uneaten, and the emotions experienced during the meal (e.g., expressions of displeasure, expressions of satisfaction), and stores this information in a database.

[1554] 4. Text generation using artificial intelligence (AI):

[1555] The server automatically generates messages for the contact log using a generative AI based on collected behavioral and emotional data. For example, it might generate a message like, "Today, [child's name] played in the sandbox and had a great time with a smile on their face."

[1556] The server uses AI to generate recipes to help overcome food waste, based on meal and emotional data. For example, if a customer leaves bell peppers uneaten, it will suggest a "Bell Pepper and Cheese Bake Recipe."

[1557] 5. Viewing and editing data:

[1558] Device (childcare worker's tablet): Provides an app that displays generated text sent from the server and allows childcare workers to manually edit the text. For example, "Today, XX-chan played in the sandbox and had fun with a smile." → "Today, XX-chan built a sandcastle and had fun with her friends."

[1559] Device (parent's smartphone): Provided via an app that displays corrected contact logs, meal reports, and recipes sent from the server.

[1560] 6. Data distribution:

[1561] The server saves the revised contact log entries and suggested coping strategies to a database and automatically distributes them to the parents' devices.

[1562] Device (Parent's smartphone): Allows parents to view the information sent via the app.

[1563] Specific example

[1564] Collecting data on children's behavior

[1565] For example, during a day at the nursery school, the server analyzes camera footage and collects behavioral data such as, "○○ played with blocks in the morning and drew pictures in the afternoon," as well as emotional data such as, "She was smiling while playing with blocks," and "She had a focused expression while drawing."

[1566] Contact book message generation

[1567] Based on the collected behavioral and emotional data, the server generates a message for the communication log, such as, "Today, [child's name] enjoyed playing with blocks, and in the afternoon, she was focused on drawing."

[1568] Collection and analysis of dietary data

[1569] The server analyzes the video from lunchtime and collects meal data such as, "○○-chan ate all her rice but left the bell peppers," and emotion data such as, "She made a displeased face when eating the bell peppers."

[1570] Generating recipes for overcoming challenges

[1571] Based on the collected food and emotional data, the server suggests a "cheese bake recipe to make bell peppers easier to eat."

[1572] Viewing and editing data

[1573] Terminal (caregiver's tablet): The caregiver checks the generated communication log entry and revises the sentence, such as, "Today, XX enjoyed playing with blocks, and in the afternoon, she was concentrating while drawing pictures."

[1574] Device (Parent's smartphone): Parents can review the corrected communication log entries and recipes for overcoming challenges, and use them as a reference for cooking.

[1575] This streamlines the administrative work of childcare workers, and allows parents to receive detailed information and specific suggestions regarding their child's daily routine and meals.

[1576] The following describes the processing flow.

[1577] Step 1:

[1578] The server acquires live video from cameras installed within the nursery school and inputs the video data into a camera image analysis system. The camera image analysis system analyzes the children's behavior (e.g., type of play, movement path) and generates behavioral data in real time.

[1579] Step 2:

[1580] The server inputs the same video data into the emotion engine. The emotion engine analyzes the child's facial expressions and generates emotion data in real time, such as smiles, crying faces, and surprised expressions. This allows for a detailed record of the child's emotional changes.

[1581] Step 3:

[1582] The server stores behavioral and emotional data generated by the camera image analysis system and emotion engine in a database. This allows for a detailed record of the child's daily life.

[1583] Step 4:

[1584] The server inputs video data from lunchtime into a camera image analysis system to analyze eating behavior. It measures the type and amount of food eaten and the type and amount of food left uneaten, and generates meal data.

[1585] Step 5:

[1586] The server inputs video data from the meal into an emotion engine and analyzes the child's facial expressions while eating. It generates emotional data such as joy, disgust, and satisfaction during the meal. This also records the child's feelings towards eating.

[1587] Step 6:

[1588] The server stores meal data and emotional data generated by the camera image analysis system and emotion engine in a database. This allows for a detailed record of the eating situation.

[1589] Step 7:

[1590] The server uses generative artificial intelligence (AI) to generate messages for the contact book based on stored behavioral and emotional data. For example, it automatically generates a message like, "Today, XX-chan was playing in the sandbox and was having fun with a smile on her face."

[1591] Step 8:

[1592] The server uses generative artificial intelligence (AI) to generate recipes to help overcome food waste, based on stored meal and emotional data. For example, if bell peppers are left uneaten, it will suggest a "Bell Pepper and Cheese Bake Recipe."

[1593] Step 9:

[1594] The server distributes the generated communication log entries and overcoming recipes to the childcare worker's terminal. The childcare worker can then review the entries using a tablet or other device.

[1595] Step 10:

[1596] Device (childcare worker's tablet): Childcare workers view the generated text sent from the server on the app and review its content. They manually revise the text as needed and perform a final check.

[1597] Step 11:

[1598] The user (childcare worker) confirms the corrected communication log entry by pressing the "Send" button in the app. The confirmed entry is then returned to the server and saved in the database.

[1599] Step 12:

[1600] The server delivers the revised contact log entries and suggested coping recipes to the parent's device. Parents can view this information through the app.

[1601] Step 13:

[1602] Device (Parent's smartphone): Parents can view communication logs, meal reports, and recipes for overcoming illness sent from the server via the app.

[1603] Step 14:

[1604] Users (parents) can check their child's daily behavior, eating habits, and suggested recipes on the app, and use this information to improve home care and meal planning.

[1605] This reduces the administrative burden on childcare workers and provides parents with detailed information about their child's daily life and meals.

[1606] (Example 2)

[1607] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1608] In childcare settings, childcare workers are burdened with a wide range of administrative tasks, including observing and recording children's behavior and emotions, writing in communication notebooks, and managing meals. Furthermore, while parents want detailed information about their children's daily lives and meals, this information is often insufficient. Therefore, there is a need to streamline the administrative work of childcare workers and improve the quality of information provided to parents.

[1609] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1610] In this invention, the server includes means for analyzing camera images, means for collecting behavioral and emotional data of the child being cared for, means for generating text using generative artificial intelligence based on the collected behavioral and emotional data, means for displaying the generated text in a modifiable form, means for recording and distributing the modified text, means for collecting and analyzing meal data and analyzing the results using generative artificial intelligence, and means for proposing and distributing recipes to overcome difficulties based on the analysis results. This streamlines the administrative work of childcare workers, and allows parents to receive detailed information about their child's daily life and meals, as well as specific suggestions.

[1611] "Means of analyzing camera images" refers to devices and software that analyze video data acquired by cameras installed within the nursery school, and are used to recognize children's behavior and facial expressions.

[1612] "Action data of children in childcare" refers to information about the various activities and behaviors that children engage in within the nursery school, including, for example, the types of play and interactions.

[1613] "Emotional data" refers to information about emotions recognized from children's facial expressions, including smiles, crying faces, and focused faces.

[1614] "Means of generating text using generative artificial intelligence" refers to artificial intelligence technology that automatically generates text in natural language based on collected data, and this includes, for example, generative AI models.

[1615] "Means of displaying generated text in an editable format" refers to devices or software that allow childcare workers to review automatically generated text and make corrections as needed, and includes, for example, tablet devices.

[1616] "Means for recording and distributing revised text" refers to systems and methods for saving text revised by childcare workers in a database and distributing it to parents in real time.

[1617] "Mealtime data" refers to information about the types and quantities of food children ate during meals, as well as the types and quantities of food they left uneaten.

[1618] "Methods of analysis using generative artificial intelligence" refers to artificial intelligence technology that analyzes collected dietary data and automatically generates new insights and suggestions based on it, and includes, for example, AI models.

[1619] The method of proposing and distributing "recipes to overcome allergies" refers to a method of automatically generating cooking recipes that make it easier for children to eat specific foods, based on analyzed dietary data, and then distributing these recipes to parents.

[1620] The present invention is configured as a system to improve the efficiency of administrative work in childcare settings and the quality of information provided to parents. This system includes means for analyzing camera images, means for collecting behavioral and emotional data, means for generating text using generative artificial intelligence based on the collected data, means for displaying the generated text in an editable format, means for recording and distributing the edited text, means for collecting, analyzing, and analyzing meal data using generative artificial intelligence, and means for proposing and distributing recipes for overcoming health challenges.

[1621] Hardware and software configuration

[1622] The system consists of the following hardware and software.

[1623] Camera: High-resolution camera (e.g., general-purpose high-resolution camera)

[1624] Server: A server for analyzing video data and collecting and analyzing behavioral data, emotional data, and dietary data.

[1625] Software: Camera image analysis libraries (e.g., OpenCV), emotion recognition libraries (e.g., Emotion Recognition API), generative AI models (e.g., GPT-3)

[1626] Devices: Tablet devices used by childcare workers, and smartphones used by parents.

[1627] Program Implementation

[1628] 1. Acquisition of video data

[1629] The server acquires video data from the camera in real time. This video data is acquired using, for example, the RTSP protocol.

[1630] 2. Analysis of video data

[1631] The server uses OpenCV to analyze video data and recognize the children's behavior (e.g., type of play, interactions).

[1632] For example, one might observe a child playing with building blocks in the morning.

[1633] 3. Recognition and collection of emotional data

[1634] The server uses an emotion recognition API to analyze the children's facial expressions from the video data and recognize emotional data (e.g., smiling, crying, concentrating).

[1635] For example, we may recognize a smile while a child is playing with building blocks.

[1636] 4. Storage of behavioral and emotional data

[1637] The server stores the analyzed and recognized behavioral and emotional data in a database. Transaction management is performed to ensure data integrity and security.

[1638] For example, the system saves data indicating that the child played with building blocks in the morning and was smiling at that time.

[1639] 5. Automatic sentence generation

[1640] The server automatically generates contact book entries using a generative AI model (e.g., GPT-3) based on the collected data.

[1641] For example, it can generate sentences like, "Today, [Name] enjoyed playing with building blocks, and in the afternoon, she was concentrating on drawing."

[1642] Example of a prompt:

[1643] Today, [Name] enjoyed playing with building blocks, and in the afternoon, she was concentrating on drawing.

[1644] 6. Correction and display of generated text

[1645] The device (the childcare worker's tablet) displays the generated communication log document, and the childcare worker makes corrections as needed.

[1646] For example, change "Today, XX enjoyed playing with blocks, and in the afternoon, she was focused on drawing." to "Today, XX built a sandcastle and had fun with her friends."

[1647] 7. Collection and analysis of dietary data

[1648] The server analyzes video footage of meals and collects meal data (e.g., types and amounts of food eaten, types and amounts of food left over).

[1649] For example, we collect data such as "○○-chan ate all her rice but left the bell peppers."

[1650] 8. Generating a recipe for overcoming the problem

[1651] The server generates recipes to help overcome food waste based on the collected meal data.

[1652] For example, I'd like to suggest a recipe for "cheese-baked bell peppers to make them easier to eat."

[1653] 9. Distribution of revised text and recipes

[1654] The server saves the revised contact log entries and suggested recipes to a database and distributes them to the parents' devices.

[1655] The device (the parent's smartphone) receives information sent from the server and displays it to the user.

[1656] For example, a parent might see a message in the communication notebook saying, "Today, [child's name] built a sandcastle and had fun with their friends," as well as a recipe for "baked bell peppers with cheese."

[1657] This will streamline the administrative work of childcare workers, and allow parents to receive detailed information about their child's daily life and meals, as well as specific suggestions.

[1658] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1659] Step 1: Acquire video data

[1660] The server acquires video data in real time from multiple cameras installed within the nursery school. The input is the video stream transmitted from the cameras (for example, using the RTSP protocol). The acquired video data is stored in a temporary storage area. For example, the server receives the video via the camera's IP address and saves it to the temporary storage area.

[1661] Step 2: Analysis of video data

[1662] The server uses OpenCV to analyze video data stored in a temporary storage area. The input is video data. As data processing, an object detection algorithm (e.g., YOLO) is applied to each frame to recognize children's actions. The output is the recognized action data. For example, the server detects children playing with blocks in the morning.

[1663] Step 3: Recognizing and collecting emotional data

[1664] The server uses an emotion recognition API to analyze children's facial expressions from analyzed video data. The input is the analyzed video data. As part of the data processing, an emotion recognition algorithm is applied to recognize emotions such as smiles, crying faces, and focused faces. The output is the recognized emotion data. For example, the server recognizes a smile while a child is playing with blocks.

[1665] Step 4: Saving behavioral and emotional data

[1666] The server stores recognized behavioral and emotional data in a database. The input consists of behavioral and emotional data. Data processing involves converting the data into a well-formed format (e.g., JSON) and inserting it into the database using SQL queries. The output is the record in the database. For example, the server might store data about playing with building blocks in the morning and the smile associated with that activity in the database.

[1667] Step 5: Automatic text generation

[1668] The server generates contact log entries using a generative AI model (e.g., GPT-3) based on behavioral and emotional data stored in the database. The input consists of behavioral and emotional data. As a data operation, prompt sentences are provided to the generative AI model for inference. The output is an automatically generated contact log entry. For example, it might generate an entry like, "Today, XX enjoyed playing with blocks, and in the afternoon, she was concentrating on drawing."

[1669] Step 6: Modify and display the generated text

[1670] The terminal (the childcare worker's tablet) displays the generated text sent from the server, and the childcare worker makes corrections as needed. The input is the automatically generated communication log text. The output is the corrected communication log text. For example, the childcare worker might change "Today, XX enjoyed playing with blocks, and in the afternoon, she was concentrating while drawing pictures." to "Today, XX built a sandcastle and enjoyed playing with her friends."

[1671] Step 7: Collection and analysis of dietary data

[1672] The server analyzes video footage of meals and collects meal data. The input is video data of the meal. As part of the data processing, a video analysis algorithm is applied to extract the contents of the meal and any leftovers. The output is the analyzed meal data. For example, the server collects data such as, "○○-chan ate all of her rice, but left the bell peppers."

[1673] Step 8: Generating a Recipe for Overcoming Challenges

[1674] The server generates recipes to overcome food allergies using a generative AI model based on meal data. The input is meal data. As a data calculation, prompts are provided to the generative AI model for inference. The output is the generated recipe. For example, it might generate a "cheese bake recipe to make bell peppers easier to eat."

[1675] Step 9: Distribute the revised text and recipe.

[1676] The server saves the revised contact log entries and suggested recipes to a database and distributes them to the parent's device. The input is the revised entries and generated recipes. The output is the notification and display information on the parent's device. For example, the parent's smartphone might receive a contact log entry that reads, "Today, [child's name] built a sandcastle and had fun with their friends," along with a recipe for "Grilled bell peppers with cheese."

[1677] (Application Example 2)

[1678] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1679] In modern brick-and-mortar stores, it is difficult to collect real-time data on children's behavior and emotional changes in play areas and provide detailed reports to parents. Therefore, parents have difficulty understanding their child's play status and emotional changes. Furthermore, manually creating these reports is burdensome, and efficiency improvements are needed.

[1680] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a camera image analysis means, a means for collecting subject behavior data, a means for generating text using generative artificial intelligence based on the collected behavior data, a means for displaying the generated text in a modifiable form, a means for recording and distributing the modified text, a means for collecting and analyzing meal data and analyzing the results using generative artificial intelligence, a means for proposing and distributing overcoming recipes based on the analysis results, and a means for generating and distributing a play status report based on behavior data and emotional data. This makes it possible for parents to check their child's play status and emotional changes in real time via their smartphone.

[1681] A "camera image analysis means" is a device or system that uses a camera to analyze the behavior and facial expressions of a subject in real time and collect the data.

[1682] "Subject behavior data" refers to information about the subject's behavior acquired through sensors such as cameras, and includes, for example, the type of play and details of their actions.

[1683] "Generative artificial intelligence" is an artificial intelligence technology that has the ability to automatically generate text and reports based on collected data.

[1684] "Methods for generating text" refers to a system that automatically generates text using generative artificial intelligence based on collected behavioral and emotional data.

[1685] "Means for displaying generated text in an editable format" refers to a system that provides an interface allowing users to review and edit generated text.

[1686] "Means for recording and distributing revised text" refers to a system for saving revised text and distributing it to relevant parties.

[1687] "Dietary data" refers to detailed information about a person's diet, such as the amount of food they consumed and the amount of food they left uneaten.

[1688] "A means of analyzing the results using generative artificial intelligence" refers to a technology that analyzes collected dietary data and then uses generative artificial intelligence to analyze the results.

[1689] A "recipe to overcome a dislike" is a recipe suggestion designed to make it easier for a person to consume foods they dislike, and may include suggestions for cooking methods or ingredient combinations.

[1690] "Behavioral and emotional data" refers to data about the subject's behavior and the emotional changes associated with that behavior.

[1691] A "play activity report" is a detailed report describing a child's play activities and emotional changes, intended for parents to review.

[1692] "Means of distribution" refers to a system that automatically sends documents and reports generated or modified by generative artificial intelligence to relevant parties.

[1693] "Through a parent's smartphone" refers to a method of viewing and manipulating information and data using a smartphone.

[1694] This invention is a system that collects behavioral and emotional data of children in play areas within physical stores and provides detailed reports to parents in real time. The following describes a specific form for implementing this system.

[1695] System Configuration

[1696] The system consists of the following elements:

[1697] 1. Camera image analysis means:

[1698] Multiple cameras will be installed within the play area. These cameras will capture children's daily behavior and emotional changes in real time.

[1699] The server acquires video data transmitted from the camera and uses camera image analysis tools to analyze the children's behavior.

[1700] 2. Means for collecting behavioral and emotional data:

[1701] The server collects behavioral and emotional data from camera footage and stores it in a database. Behavioral data includes the type of play and interactions with friends.

[1702] The emotion engine analyzes facial expressions from video and collects emotional data in real time, such as smiles, crying faces, and focused faces.

[1703] 3. Text generation methods using AI:

[1704] The server uses a generative AI to automatically generate playtime reports based on collected behavioral and emotional data. For example, it might generate a sentence like, "Today, [child's name] had a lot of fun playing on the slide and smiled a lot."

[1705] 4. Means for correcting the generated text:

[1706] Device (parent's smartphone): Displays generated text sent from the server, allowing the parent to manually review the text.

[1707] 5. Means of recording and distributing documents:

[1708] The server saves the corrected text to a database and automatically delivers it to the parent's device. Parents can view the transmitted information through a smartphone app.

[1709] Examples

[1710] Specific examples of data collection and analysis

[1711] Parents install a smartphone app, and when their child enters the play area, multiple cameras track the child's actions and send behavioral and emotional data to a server. For example, when a child is playing on a slide, the camera films the action, and the server analyzes the footage to collect behavioral data such as "playing on a slide" and emotional data such as "smiling a lot."

[1712] Report generation and distribution

[1713] The server uses generative AI to generate reports based on collected behavioral and emotional data. For example, it might generate a sentence like, "Today, [child's name] was playing on the slide and laughing happily." The generated report is sent to a smartphone app, allowing parents to check their child's play status in real time.

[1714] Example of a prompt

[1715] "Please generate a detailed report based on the child's behavior and emotional data in the play area. The child's behavior is 'playing on the slide,' and their emotion is 'smiling a lot.'"

[1716] In this way, parents can instantly grasp their child's playing situation and emotional changes, allowing them to let their children play in the play area of ​​the physical store with peace of mind.

[1717] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1718] Step 1:

[1719] The server acquires video data in real time from cameras installed within the play area. The cameras capture the children's actions and expressions within the play area and transmit this video data to the server. Camera video data serves as input, forming the basis for behavioral and emotional data.

[1720] Step 2:

[1721] The server analyzes camera video data using camera image analysis tools. Specifically, it detects specific actions from the video data and analyzes facial expressions to extract emotion data. For example, it can detect actions such as playing on a slide or facial expressions such as smiling. Video data is the input, and action data and emotion data are obtained as output.

[1722] Step 3:

[1723] The server stores the analyzed behavioral and emotional data in a database. This data is used for subsequent processing. Behavioral and emotional data are the inputs, and the output is stored in the database.

[1724] Step 4:

[1725] The server uses a generative AI to generate a play situation report based on stored behavioral and emotional data. The generative AI is given a prompt, for example, "The child's behavior is 'playing on the slide,' and their emotion is 'smiling a lot.' Please generate a detailed report based on this." The output is an automatically generated report document.

[1726] Step 5:

[1727] The device (the parent's smartphone) receives the generated report document sent from the server. The parent can review this report and make corrections as needed. The generated report document is the input, and the corrected report document is the output.

[1728] Step 6:

[1729] The server saves the corrected report document to the database and then distributes it again to the parent's device. The input is the corrected report document, and the output is saving to the database and distributing it to the parent.

[1730] Step 7:

[1731] Users (parents) can review the final report via their device, gaining real-time insights into their child's play status and emotional changes. The final report is the input, and the output provides parents with peace of mind and a clear understanding of the information.

[1732] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1733] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1734] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1735] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1736] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1737] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1738] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1739] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1740] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1741] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1742] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1743] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1744] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1745] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1746] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1747] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1748] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1749] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1750] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1751] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1752] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specif...

Claims

1. Camera image analysis means, Means for collecting behavioral data of childcare recipients, A means of generating text using artificial intelligence based on collected behavioral data, A means of displaying the generated text in a format that allows for editing, A means of recording and distributing the revised text, A method for collecting and analyzing dietary data, generating results, and analyzing them using artificial intelligence, A means of proposing and distributing recipes for overcoming challenges based on the analysis results, A system that includes this.

2. The behavioral data of the children in childcare includes the types of play they engage in and changes in their emotions. The system according to claim 1.

3. The meal data includes the amount of food eaten and leftovers. The system according to claim 1.

Images