System

Abstract

A system is provided.SOLUTION: A system comprising: means for using a generative model to automatically generate a nursery curriculum based on basic information input by a nursery teacher; means for displaying the nursery curriculum generated by the generative model on a terminal of the nursery teacher; means for collecting feedback from a guardian; means for storing the feedback in a database; and means for generating a next nursery curriculum in consideration of the feedback.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] It is difficult for nurseries and kindergartens to create appropriate childcare curricula that take into account children's developmental stages, interests, weather, and seasons. Furthermore, the time and effort required to create a curriculum places a significant burden on childcare workers. Furthermore, it is difficult to reflect parents' opinions and perspectives in the curriculum, which can lead to insufficient communication with parents. Technologies and methods to solve these problems are needed. [Means for solving the problem]

[0005] The present invention provides a system that uses a generative model to automatically generate a childcare curriculum based on basic information entered by a childcare worker. Specifically, the system includes a means for sending prompts to the generative model based on the basic information entered by the childcare worker and displaying the childcare curriculum generated by the generative model on the childcare worker's terminal. The system also includes a means for collecting feedback from parents and storing that feedback in a database. Furthermore, by constructing a system that includes a means for generating the next childcare curriculum taking this feedback into consideration, the quality of childcare can be improved, the burden on childcare workers can be reduced, and smooth communication with parents can be achieved.

[0006] A "childcare worker" is a professional who supports the growth and development of children in kindergartens and nursery schools and carries out childcare activities.

[0007] "Basic information" refers to input data required to generate a childcare curriculum, such as children's ages, interests, weather, and seasons.

[0008] A "generative model" is an artificial intelligence (AI) model that automatically generates the optimal childcare curriculum based on input basic information.

[0009] A "childcare curriculum" is a plan planned by childcare workers that includes children's daily activities and learning content.

[0010] "Device" refers to an electronic device (e.g., PC, tablet, smartphone) used by childcare workers and parents to generate childcare curriculum and send and receive feedback.

[0011] "Feedback" is information provided by parents to reflect their opinions and requests about their children in the childcare curriculum.

[0012] "Database" means an information system that stores collected feedback and other information and makes it accessible as needed.

[0013] A "prompt" is input data that provides the generative model with the basic information it needs to generate a childcare curriculum. [Brief explanation of the drawings]

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

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

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

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

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

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

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

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

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

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

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

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0035] This invention is a system that automatically generates a childcare curriculum based on basic information entered by childcare workers. This system uses a generative model to reduce the burden on childcare workers and achieve smooth communication with parents.

[0036] System configuration and processing flow

[0037] 1. Enter basic information

[0038] Users (childcare workers) use devices such as PCs and tablets to input basic information, such as the children's ages, interests, weather, and season. This information is entered through a web form or dedicated application on the device.

[0039] 2. Request for curriculum generation

[0040] The device sends the basic information entered in JSON format to the server, which is built using a web framework such as Flask and receives the request.

[0041] 3. Use of generative models

[0042] The server receives the request and sends basic information as a prompt to the generative model. Based on the content of this prompt, the generative model generates a childcare curriculum. For example, GPT, a generative AI, is used as the generative model.

[0043] 4. Return and display of curriculum

[0044] The generated curriculum is sent back to the device in JSON format from the server. The device analyzes the curriculum and displays it on a user interface for childcare workers. This allows the childcare workers to check and adapt the generated curriculum.

[0045] 5. Gathering feedback from parents

[0046] Users (parents) use communication tools (such as dedicated apps or chatbots) to input feedback, which includes the parents' opinions and insights about their children.

[0047] 6. Sending and Saving Feedback

[0048] The device sends feedback in JSON format to the server, which receives the feedback, stores it in a database such as Firestore, and takes it into account when generating the next curriculum.

[0049] 7. Next curriculum generation

[0050] When generating a new childcare curriculum, the server retrieves relevant feedback from the database and provides it to the generative model, allowing for the generation of a more customized childcare curriculum based on this information and other information.

[0051] Specific examples

[0052] 1. The user (childcare worker) enters basic information such as "3-year-old child, sunny day, interest in animals" and requests curriculum generation.

[0053] 2. The generative model generates a curriculum such as "10:00 - 11:00 Outdoor animal observation."

[0054] 3. This curriculum is displayed on the terminal, and the nursery school teacher confirms and adopts the contents.

[0055] 4. The user (parent) enters feedback such as "My child wants to go to the zoo this weekend," which is saved in the database.

[0056] 5. The next time the curriculum is generated, the generative model will take the stored feedback into account and suggest zoo-related activities.

[0057] This system will provide a curriculum that is closer to the interests of children and will also allow childcare to be provided in a way that reflects the opinions of parents, thereby improving the quality of childcare and streamlining the work of childcare workers.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The user (childcare worker) enters basic information about the children (age, interests, weather, season, etc.) through a web form or dedicated application on their device (PC or tablet) and clicks the "Generate" button.

[0061] Step 2:

[0062] The device sends the entered basic information to the server in JSON format using the HTTP POST method.

[0063] Step 3:

[0064] The server receives the request using a web framework such as Flask, which includes basic information entered by the childcare worker.

[0065] Step 4:

[0066] The server then sends the received basic information to a generative AI model (e.g., GPT) as a prompt. This prompt contains the basic information and instructs the generation of a curriculum.

[0067] Step 5:

[0068] The generative model generates a childcare curriculum based on the received prompts, and the generated curriculum is sent back to the server in text format.

[0069] Step 6:

[0070] The server converts the childcare curriculum returned from the generative model into JSON format and returns it to the device using an HTTP response.

[0071] Step 7:

[0072] The device receives the JSON data returned from the server and displays it on the user interface, allowing childcare workers to check the generated curriculum.

[0073] Step 8:

[0074] Users (parents) input and send feedback (e.g., "My child wants to go to the zoo") via a dedicated app or chatbot.

[0075] Step 9:

[0076] The device sends the input feedback in JSON format to the server, and this request is also made using the HTTP POST method.

[0077] Step 10:

[0078] The server saves the received feedback in a database such as Firestore, and notifies the device that the saving is complete.

[0079] Step 11:

[0080] The next time a curriculum is generated, the server retrieves the relevant feedback from the database and again sends a prompt to the generative model, this time containing the new basic information and the previous feedback.

[0081] Step 12:

[0082] The generative model generates a new childcare curriculum that takes the feedback into account and sends it back to the server, which then receives it and sends it back to the device in JSON format.

[0083] Step 13:

[0084] The terminal displays the received new curriculum, and the user (childcare worker) checks and adapts the content.

[0085] Example 1

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

[0087] Childcare workers spend a lot of time and effort creating daily childcare curricula. Furthermore, there is no efficient way to incorporate parental feedback into the curriculum, making it difficult to improve the quality of childcare. Furthermore, when automatically generating childcare curricula, it is difficult to appropriately reflect the latest childcare information and children's interests.

[0088] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0089] In this invention, the server includes means for using a generative model to automatically generate a childcare curriculum based on basic information input by a childcare worker, means for displaying the childcare curriculum generated by the generative model on the childcare worker's terminal, means for collecting feedback from parents, means for saving the feedback in a database, means for generating the next childcare curriculum taking the feedback into consideration, means for inputting basic information through a user interface, means for converting the basic information into JSON format and sending it to the server, means for returning the generated curriculum in JSON format to the terminal, means for parents to input feedback using a communication tool, and means for sending the feedback to the server in JSON format. This enables childcare workers to efficiently create curricula and provide high-quality childcare that reflects parental feedback.

[0090] A "childcare worker" is a professional who is responsible for caring for and educating children in a childcare facility.

[0091] "Basic information" refers to information necessary for creating a curriculum, such as the children's ages, interests, weather, and season.

[0092] A "childcare curriculum" is a plan of activities and education that childcare workers provide to children.

[0093] A "generative model" is an AI technique that generates new text or plans based on input prompts.

[0094] A "terminal" is a device, such as a computer or tablet, that a user uses to enter information or view results.

[0095] A "server" is a computer system that provides services to client terminals over a network.

[0096] "Feedback" refers to opinions and thoughts about their children provided by parents.

[0097] A "database" is a system for storing and managing information efficiently and safely.

[0098] A "user interface" is a component such as a screen, menu, or form that allows a user to access and operate a system.

[0099] A "prompt" is text that is input as an instruction or question to a generative model.

[0100] "JSON format" is a format for describing data in a structured text format.

[0101] "Communication means" refers to technologies and systems for sending and receiving information and data.

[0102] This invention is a system that automatically generates a childcare curriculum based on basic information entered by childcare workers, and by using a generative model, it reduces the burden on childcare workers and realizes smooth communication with parents. This system is composed of users (childcare workers and parents), terminals, a server, and a generative AI model.

[0103] Enter basic information

[0104] Users (childcare workers) use devices such as PCs and tablets to enter basic information, such as the child's age, interests, weather, and season. This basic information is entered through a web form displayed on the device or a dedicated app.

[0105] Request curriculum generation

[0106] The terminal converts the basic information entered by the user into JSON format data and sends it to the server using an HTTP request, which is built with a web framework such as Flask.

[0107] Using generative models

[0108] The server sends the received basic information in JSON format as prompts to a generative AI model (e.g., GPT-3), which then generates a new childcare curriculum based on the prompts.

[0109] Return and view curriculum

[0110] After the generative AI model generates the childcare curriculum, the generated results are sent back to the server in JSON format, which is then sent to the device, which then displays the curriculum on the user interface.

[0111] Gathering feedback from parents

[0112] Users (parents) can use a dedicated app or chatbot to input feedback, which includes opinions and reactions about their children.

[0113] Send and save feedback

[0114] The device sends the input feedback in JSON format to the server, which stores it in a database such as Firestore, so that it can take this feedback into account when generating the next curriculum.

[0115] Next curriculum generation

[0116] When generating a new curriculum, the server retrieves the stored feedback from the database and provides it to the generative model. By providing the generative model with information including the feedback as prompts, the next generated curriculum can be further customized.

[0117] Specific examples

[0118] For example, suppose a user (a nursery teacher) enters basic information such as "3-year-old child, sunny day, interest in animals." Based on this information, the prompt sent to the generative model is as follows:

[0119] Child's age: 3 years old

[0120] Weather: Sunny

[0121] Interests: Animals

[0122] Based on this prompt, the generative model generates a curriculum such as "10:00 - 11:00 Outdoor animal observation." This curriculum is displayed on the device, and the nursery teacher can review and adopt the content.

[0123] In addition, the user (parent) can input feedback such as "My child wants to go to the zoo this weekend," and this feedback is saved in the database. By providing this feedback to the generative model the next time a curriculum is generated, it will be more likely to suggest zoo-related activities.

[0124] This system allows childcare workers to create curriculums more efficiently, improving the quality of childcare. In addition, by incorporating parents' opinions into the curriculum, more individualized childcare can be achieved.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1:

[0127] The user (childcare worker) uses a device such as a PC or tablet to enter basic information into a web form or dedicated app. For example, information such as "3-year-old child, sunny day, interest in animals." This input data is stored as is in the device's memory. Input: Basic information. Output: Input data in the device.

[0128] Step 2:

[0129] The terminal converts the basic information entered in step 1 into JSON format. This data conversion process uses a serialization library within the program. The converted JSON data is sent to the server as an HTTP POST request. Input: Basic information. Output: Basic information in JSON format.

[0130] Step 3:

[0131] The server receives an HTTP POST request and obtains the JSON data within it. This data is processed by an API endpoint within the server. The server parses the received basic information and sends it as a prompt to the generative AI model (e.g., GPT-3). Input: Basic information in JSON format. Output: Prompt to the generative AI model.

[0132] Step 4:

[0133] The generative AI model generates a childcare curriculum based on the prompts it receives. During this generation process, the model uses its internal neural network to analyze and generate data. The generated curriculum is sent back to the server in JSON format. Input: Prompt. Output: Childcare curriculum in JSON format.

[0134] Step 5:

[0135] The server receives the childcare curriculum in JSON format returned from the generative AI model. This data is parsed again and sent back to the device. The server sends the data as an HTTP response. Input: Childcare curriculum in JSON format. Output: HTTP response to the device.

[0136] Step 6:

[0137] The terminal analyzes the JSON formatted childcare curriculum received from the server and displays it on the user interface. This display process uses a front-end library to render the analysis results on the screen. Input: Childcare curriculum in JSON format. Output: Data displayed on the user interface.

[0138] Step 7:

[0139] The user (parent) enters feedback using a dedicated app or chatbot. The feedback includes the child's reactions and opinions. This input data is stored in the device's memory. Input: Feedback. Output: Input data in the device.

[0140] Step 8:

[0141] The terminal converts the feedback entered in step 7 into JSON format. A serialization library is used for this conversion process. The converted JSON data is sent to the server as an HTTP POST request. Input: Feedback. Output: Feedback in JSON format.

[0142] Step 9:

[0143] The server receives an HTTP POST request and retrieves JSON data within it. This data is processed by an API endpoint on the server and saved in a database such as Firestore. Input: Feedback in JSON format. Output: Data saved in the database.

[0144] Step 10:

[0145] The server retrieves the stored feedback from the database when generating a new curriculum. This retrieved data is included in the prompts provided to the generative model. Input: Feedback data from the database. Output: Updated prompts to the generative model.

[0146] Through specific operations that take into account input and output, this system can improve the work efficiency of childcare workers and effectively reflect parental feedback in the curriculum.

[0147] (Application example 1)

[0148] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0149] Efficiently and flexibly managing robot task schedules in factories requires consideration of a vast amount of work information and operating status. However, this requires a great deal of time and effort, which increases the burden on workers and managers and reduces production efficiency. In addition, it is difficult to generate an optimal schedule that takes into account real-time factors such as environmental conditions and task priorities. To solve these issues, a system that efficiently and automatically generates work schedules is needed.

[0150] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0151] In this invention, the server includes means for using a generative model to automatically generate a work schedule based on basic information entered by a manager, means for displaying the work schedule generated by the generative model on the manager's terminal, means for collecting feedback from workers, means for saving the feedback in a database, and means for generating the next work schedule taking the feedback into consideration. This reduces the burden on workers and managers and makes it possible to efficiently generate and apply optimal work schedules in real time.

[0152] An "administrator" is a person who is responsible for managing and supervising the task schedules of robots and workers in factory operations.

[0153] "Basic information" refers to data such as the type of work, priority, operating status, and work environment that must be entered by the administrator.

[0154] A "work schedule" is a specific work plan for factory robots and workers that is automatically generated based on a generative model.

[0155] A "generative model" is a system that includes an algorithm that generates an optimal work schedule based on input basic information.

[0156] A "terminal" is a device such as a computer or tablet that allows an administrator to enter basic information and check the generated work schedule.

[0157] "Feedback" refers to evaluations and opinions provided by workers and other stakeholders regarding the actual work situation and robot performance.

[0158] A "server" is a central processing unit for running generative models, processing requests from terminals, and storing feedback in a database.

[0159] A "database" is an information storage system for storing and managing feedback, basic information, etc.

[0160] A "prompt" is an instruction containing basic information entered that the generative model uses to generate a work schedule.

[0161] The "JSON format" is a text format for structuring, storing, and transmitting data, and is commonly used when exchanging data between programs.

[0162] This invention is a system for efficiently and automatically generating work schedules for robots in a factory, reducing the burden on managers and improving production efficiency. The configuration and operation of this system are described below.

[0163] 1. System Configuration

[0164] The system consists of an administrator's terminal, a server, a generative model, and a database. The hardware used includes factory PCs and tablets, as well as industrial robots. The software uses a Flask web framework, generative AI (e.g., GPT), and Firestore (Google's NoSQL database).

[0165] 2. Program processing flow and explanation

[0166] Enter basic information

[0167] Managers use terminals to enter basic information such as product type, work priority, operating status, and work environment information, etc. The information is entered through a web form or a dedicated application.

[0168] Request to generate a task schedule

[0169] The terminal converts the input basic information into JSON format and sends it to the server, which uses Flask to receive the request and begin processing.

[0170] Using generative models

[0171] The server receives the request and sends basic information as prompts to a generative model (e.g., GPT), which then generates an optimal work schedule based on the content of the prompts.

[0172] Return and view schedules

[0173] The generated schedule is sent back to the administrator's terminal in JSON format from the server. The terminal parses the returned schedule and displays it in the administrator's user interface. This allows the administrator to check and apply the generated schedule.

[0174] Feedback collection

[0175] Workers use communication tools to input feedback, which includes information about actual work results and robot performance.

[0176] Send and save feedback

[0177] The device sends feedback in JSON format to the server, which receives this feedback, stores it in Firestore, and takes this feedback into account when generating the next schedule.

[0178] Next schedule generation

[0179] When generating a new work schedule, the server retrieves relevant feedback from the database and feeds it into the generative model, which then generates a more customized schedule based on this information.

[0180] Examples of concrete examples and prompts

[0181] Specific examples

[0182] Suppose a manager inputs basic information such as "Production of Product A, high priority, machine 1, humidity 70%" and requests schedule generation. The generative model generates a task schedule such as "10:00 - 11:00 Product A Line 1, production speed 120%." This schedule is displayed on the manager's terminal, and the manager can confirm and adopt the contents.

[0183] The worker provides feedback such as "the robot's speed was appropriate" or "the operating time was short," which is then stored in Firestore. The next time the schedule is generated, the generative model takes this feedback into account and proposes an optimal task schedule.

[0184] Prompt Sentence Examples

[0185] Factory task schedule generation:

[0186] Product name: Product A

[0187] Work priority: High

[0188] Operation status: Machine 1

[0189] Working environment: 70% humidity

[0190] Feedback Consideration:

[0191] Speed: 120%

[0192] Feedback: Good

[0193] In this way, this system reduces the burden on managers and workers and enables them to efficiently manage and operate work schedules.

[0194] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0195] Step 1:

[0196] Administrator enters basic information

[0197] The administrator uses the terminal to enter basic information such as the product type, work priority, operating status, and work environment information. This information is entered through the terminal's web form or a dedicated application, and the entered information is converted into JSON format.

[0198] Input: Product type, work priority, operation status, work environment information

[0199] Output: Basic information in JSON format

[0200] Step 2:

[0201] Send basic information

[0202] The device sends the basic information entered in JSON format to the server, which uses Flask to receive the request and begin processing.

[0203] Input: Basic information in JSON format

[0204] Output: The request received by the server

[0205] Step 3:

[0206] Using generative models

[0207] The server sends the received basic information to the generative model as prompts, which the generative model (e.g., GPT) uses to generate an optimal work schedule.

[0208] Input: Basic information in JSON format, prompt statement

[0209] Output: Generated work schedule

[0210] Specific working example:

[0211] Factory task schedule generation:

[0212] Product name: Product A

[0213] Work priority: High

[0214] Operation status: Machine 1

[0215] Working environment: 70% humidity

[0216] Step 4:

[0217] Return and view schedules

[0218] The server returns the generated work schedule in JSON format to the terminal, which then analyzes the returned schedule and displays it in a user interface for administrators, allowing them to check and apply the generated schedule.

[0219] Input: Generated work schedule (JSON format)

[0220] Output: Schedule displayed on the administrator's terminal

[0221] Step 5:

[0222] Enter your feedback

[0223] Workers use communication tools to provide feedback, including evaluations and opinions on the actual work results and the robot's performance.

[0224] Input: Work results, robot performance

[0225] Output: Feedback information

[0226] Step 6:

[0227] Send and save feedback

[0228] The device sends the collected feedback in JSON format to the server, which receives this feedback and stores it in Firestore, so that it can take this feedback into account when generating the next schedule.

[0229] Input: Feedback information (JSON format)

[0230] Output: Feedback stored in Firestore

[0231] Step 7:

[0232] Next schedule generation

[0233] When generating a new work schedule, the server retrieves relevant feedback from the database (Firestore) and feeds it into the generative model, which then generates a more customized schedule based on this information.

[0234] Input: Feedback information, Basic information

[0235] Output: Next best schedule

[0236] This reduces the burden on managers and workers and makes it possible to efficiently generate and apply optimal work schedules in real time.

[0237] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0238] This system combines a generative model that automatically generates a childcare curriculum based on basic information entered by childcare workers with an emotion engine that recognizes feedback from parents and the user's emotions. This reduces the burden on childcare workers, enables smooth communication with parents, and enables the generation of an optimal childcare curriculum based on emotions.

[0239] System configuration and processing flow

[0240] 1. Enter basic information

[0241] Users (childcare workers) use devices such as PCs and tablets to enter basic information, including the children's ages, interests, weather, and seasons. Input is done through a web form or a dedicated application, and is completed by clicking the "Generate" button.

[0242] 2. Emotional Recognition

[0243] The emotion engine installed in the device recognizes the emotions of the childcare worker, and this emotion information is sent to the server along with basic information.

[0244] 3. Request for curriculum generation

[0245] The device sends basic information and emotional information in JSON format to the server, which receives the request using a web framework such as Flask.

[0246] 4. Using Generative Models

[0247] The server receives basic information and emotion information and sends it to the generative model as a prompt. This prompt takes into account the emotions of the childcare worker. The generative model generates a childcare curriculum based on the prompt and sends the result back to the server.

[0248] 5. Return and display of curriculum

[0249] The generated curriculum is sent back to the device in JSON format from the server. The device displays the curriculum on the user interface, allowing the childcare worker to review and adapt it.

[0250] 6. Gathering feedback from parents

[0251] The user (parent) enters feedback through a dedicated app or chatbot. At this time, the emotion engine also recognizes the parent's emotions. The feedback, along with the emotional information, is sent from the device to the server.

[0252] 7. Sending and Saving Feedback

[0253] The device sends the input feedback and emotion information in JSON format to the server. The server receives it, stores it in a database such as Firestore, and notifies the device that the saving is complete.

[0254] 8. Next curriculum generation

[0255] When generating a new childcare curriculum, the server retrieves relevant feedback and emotional information from the database and supplies it to the generative model. The generative model generates a new childcare curriculum that takes the feedback and emotional information into account and sends the results back to the server. The server receives this and sends it back to the device in JSON format.

[0256] Specific examples

[0257] 1. The user (childcare worker) enters basic information such as "3-year-old child, sunny day, interest in animals," and the emotion engine recognizes that the user is in a very good mood.

[0258] 2. The generative model generates a childcare curriculum such as "10:00 - 11:00 Outdoor animal observation" and recommends activities that also reflect the positive emotions of the childcare workers.

[0259] 3. This curriculum is displayed on the terminal, and the nursery school teacher confirms and adopts the contents.

[0260] 4. The user (parent) inputs feedback such as "My child wants to go to the zoo this weekend," and the emotion engine recognizes the parent's happy feelings.

[0261] 5. The feedback and parental sentiment information will be stored in a database and taken into consideration when generating the next curriculum.

[0262] 6. Next time, the generative model will take into account parents’ feedback and emotions to generate a new curriculum and recommend “zoo-related activities.”

[0263] This will provide a more personalized childcare curriculum that takes into account the user's emotions, improving the quality of childcare and increasing the work efficiency of childcare workers.

[0264] The processing flow will be explained below.

[0265] Step 1:

[0266] The user (childcare worker) uses a device such as a PC or tablet to enter basic information (child's age, interests, weather, season, etc.) into a web form or dedicated application and clicks the "Generate" button.

[0267] Step 2:

[0268] The device converts the input basic information into JSON format and simultaneously recognizes the childcare worker's emotions using an emotion engine. This emotional information is also compiled in JSON format and sent to the server.

[0269] Step 3:

[0270] The server receives basic information and emotional information from the device through a web framework such as Flask.

[0271] Step 4:

[0272] The server sends the received basic information and emotional information to the generative model as a prompt, which includes the emotional state of the caregiver (e.g., "I feel very good").

[0273] Step 5:

[0274] The generative model generates a childcare curriculum based on the prompts. The generative model analyzes the information and creates an optimal childcare curriculum based on the feelings of the childcare workers.

[0275] Step 6:

[0276] The generated childcare curriculum returned from the generative model is sent back to the server, which then sends it back to the device in JSON format.

[0277] Step 7:

[0278] The device receives the JSON data returned from the server and displays the generated curriculum on the user interface. The childcare worker can check and apply the content.

[0279] Step 8:

[0280] Users (parents) input feedback through a dedicated app or chatbot, and this feedback is recognized by the emotion engine, including the parent's emotions (e.g., happy feelings).

[0281] Step 9:

[0282] The device converts the input feedback and emotion information into JSON format and sends it to the server using the HTTP POST method.

[0283] Step 10:

[0284] The server receives the feedback and emotion information, stores it in a database such as Firestore, and notifies the device once the storage is complete.

[0285] Step 11:

[0286] When generating the next curriculum, the server retrieves the relevant feedback and emotion information from the database and sends it to the generative model as a prompt, which includes the new basic information, the previous feedback, and the parent's emotion information.

[0287] Step 12:

[0288] The generative model takes into account the feedback and emotional information to generate a new childcare curriculum and sends it back to the server, which then receives it and sends it back to the device in JSON format.

[0289] Step 13:

[0290] The terminal displays the received new curriculum, and the user (childcare worker) checks and applies the contents.

[0291] Specifically, a childcare worker inputs basic information such as "3-year-old child, sunny day, interest in animals," and the emotion engine recognizes that the childcare worker is in a "very good mood." The generative model then generates a curriculum of "10:00 - 11:00 outdoor animal observation" and recommends activities that reflect the childcare worker's good mood. Similarly, if a parent inputs feedback such as "my child wants to go to the zoo this weekend" and recognizes that the child is in a happy mood, this information will be taken into account when generating the next curriculum, and "zoo-related activities" will be recommended.

[0292] This provides a more personalized childcare curriculum that takes into account the user's emotions.

[0293] Example 2

[0294] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0295] Conventional childcare curriculum generation systems were unable to consider the emotions of childcare workers or the feedback of parents, and instead created a uniform curriculum. This placed a heavy burden on childcare workers and made communication with parents difficult. Furthermore, because the curriculum did not reflect the interests and emotions of individual children, it was difficult to improve the quality of childcare.

[0296] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0297] In this invention, the server includes a means for using a terminal equipped with an emotion engine that recognizes the emotions of childcare workers, a means for recognizing feedback from parents and their emotions, and a means for storing the feedback from parents and emotion information in a database. This makes it possible to generate an individually optimized childcare curriculum that takes into account the emotions of childcare workers and the feedback and emotion information from parents.

[0298] "Basic information" refers to data entered by childcare workers, such as children's ages, interests, weather, and seasons.

[0299] A "generative model" refers to an artificial intelligence algorithm that automatically generates a childcare curriculum based on input basic information and emotional information.

[0300] "Emotion engine" refers to software or a device that recognizes and analyzes the emotions of childcare workers and parents.

[0301] "Devices" refers to electronic devices such as PCs, tablets, and smartphones used by childcare workers and parents.

[0302] "Feedback" refers to opinions, requests, and impressions from parents.

[0303] "Database" refers to an electronic information storage system for storing feedback, emotional information, etc.

[0304] A "prompt" refers to input data that provides basic and emotional information to a generative model.

[0305] "JSON format" refers to a text-based data exchange format that expresses data concisely and in a highly readable manner.

[0306] This invention is a system that automatically generates an optimal childcare curriculum based on basic information and emotional information entered by childcare workers. The purpose of this system is to reduce the burden on childcare workers, facilitate communication with parents, and provide individually optimized childcare curricula.

[0307] Enter basic information

[0308] Users (childcare workers) enter basic information using devices such as PCs or tablets. For example, they can open a dedicated application or web form and enter information such as the children's ages, interests, weather, and season. Once the information is complete, they click the "Generate" button, and the information is saved on the device.

[0309] Emotion recognition

[0310] The device is equipped with an emotion engine that recognizes the emotions of the childcare worker. This engine uses sensor devices such as cameras and microphones to analyze emotions from the childcare worker's facial expressions and tone of voice. For example, if the childcare worker's facial expression is smiling, the emotion engine will determine that the childcare worker is in a "very good mood." This emotion information is sent to the server along with basic information.

[0311] Request curriculum generation

[0312] The device sends basic information and emotional information to the server in JSON format. The device uses a web framework such as Flask to send this data to the server as an HTTP request. Specific examples of transmitted data include the following formats:

[0313] {

[0314] "age": "3 years old",

[0315] "Interests": "Animals",

[0316] "Weather": "Sunny",

[0317] "season": "spring",

[0318] "Childcare worker's feelings": "I feel very good"

[0319] }

[0320] Using generative models

[0321] The server analyzes the received basic information and emotional information and sends it as prompts to the generative AI model. The generative AI model automatically generates a childcare curriculum based on this information. For example, given prompts such as "The childcare worker is in a good mood," "For 3-year-olds," "It's a sunny day," and "Interested in animals," the generative AI model generates a curriculum such as "10:00 - 11:00 Outdoor animal observation."

[0322] Return and view curriculum

[0323] The generated childcare curriculum is sent back to the device in JSON format from the server. The device's dedicated application or web application parses this JSON data and displays the curriculum content on the user interface. Childcare workers can check the content and adjust it as necessary. For example, the following display content is possible:

[0324] 10:00 - 11:00 Outdoor animal observation

[0325] 11:00 - 12:00 Indoor animal picture book reading

[0326] Gathering feedback from parents

[0327] Users (parents) input feedback using a dedicated app or chatbot. During this input process, the emotion engine analyzes the parent's emotions. For example, if a parent inputs "My child wants to go to the zoo this weekend" and looks happy while doing so, the emotion engine will recognize this as "feeling happy."

[0328] Send and save feedback

[0329] The device sends parental feedback and emotional information in JSON format to the server. The server receives the data and stores it in a database such as Firestore. Once the data is saved, a notification of success is displayed on the device.

[0330] Next curriculum generation

[0331] When generating a new childcare curriculum, the server retrieves previously saved feedback and emotional information from the database and supplies it to the generative AI model. This makes it possible to generate a more optimal childcare curriculum that takes past feedback and emotions into account. The generative AI model generates a new curriculum based on this information and sends the results back to the server. The server receives this and sends it back to the device in JSON format, which then displays it.

[0332] As described above, the system of the present invention effectively utilizes the emotions of childcare workers and feedback from parents to provide individually optimized childcare curricula, thereby improving the work efficiency of childcare workers and the quality of childcare.

[0333] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0334] Step 1:

[0335] The user (childcare worker) uses a device such as a PC or tablet to enter basic information. This basic information includes the children's ages, interests, weather, season, etc. This basic information is entered through a dedicated application or web form. Once the entry is complete, the user clicks the "Generate" button, and the basic information is sent to the device. Specific data is entered using text boxes and drop-down menus, and the basic information is saved on the device as output.

[0336] Step 2:

[0337] The device's emotion engine recognizes the emotions of the childcare worker through sensor devices such as cameras and microphones. For example, if a childcare worker is smiling while entering information, the emotion engine will analyze this and recognize it as a "very good mood." This emotional information is then stored directly on the device.

[0338] Step 3:

[0339] The device sends the basic information entered by the childcare worker and the recognized emotional information to the server in JSON format. The device uses a web framework such as Flask to send this data to the server as an HTTP request. The following JSON format is used as an example of specific data to be sent. The basic information and emotional information are used as input, and the output is sent to the server in JSON format.

[0340] {

[0341] "age": "3 years old",

[0342] "Interests": "Animals",

[0343] "Weather": "Sunny",

[0344] "season": "spring",

[0345] "Childcare worker's feelings": "I feel very good"

[0346] }

[0347] Step 4:

[0348] The server analyzes the received basic information and emotional information and sends it as a prompt to the generative AI model. The generative AI model automatically generates a childcare curriculum based on this information. For example, given prompts such as "The childcare worker is in a good mood," "For 3-year-olds," "It's a sunny day," and "Interested in animals," the generative AI model generates a curriculum such as "10:00 - 11:00 Outdoor animal observation." In this step, the server receives the basic information and emotional information as input and obtains an output that sends a prompt to the generative AI model.

[0349] Step 5:

[0350] The generated childcare curriculum is sent from the server to the device again in JSON format. A dedicated application or web application on the device parses this JSON data and displays the curriculum content on the user interface. For example, a curriculum such as "10:00 - 11:00 Outdoor animal observation" is displayed, allowing childcare workers to review the content and adjust it as necessary. In this step, the output of the generative AI model (childcare curriculum) is sent to the device in JSON format, where it is parsed and displayed.

[0351] Step 6:

[0352] The user (parent) inputs feedback using a dedicated app or chatbot. During this input process, the emotion engine analyzes the parent's emotions. For example, if the parent inputs "My child wants to go to the zoo this weekend" and has a happy expression while doing so, the emotion engine will recognize this as "a happy feeling." In this step, feedback and emotional information are input and saved as output on the device.

[0353] Step 7:

[0354] The device sends the parent's feedback and emotion information in JSON format to the server. The server receives this and stores it in a database such as Firestore. Once the storage is complete, a notification of successful storage is displayed on the device. In this step, the input feedback and emotion information are sent to the server, and the output is stored in a database.

[0355] Step 8:

[0356] When generating a new childcare curriculum, the server retrieves previously saved feedback and emotional information from the database and supplies it to the generative AI model. This allows for the generation of a more optimal childcare curriculum that takes past feedback and emotions into account. For example, a childcare curriculum that suggests "zoo-related activities" based on parental feedback may be generated. In this step, past feedback and emotional information are input, and the generative AI model outputs a newly generated childcare curriculum.

[0357] (Application example 2)

[0358] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0359] In childcare operations such as automatically generating childcare curricula and collecting feedback, there are issues related to reducing the burden on childcare workers and smooth communication with parents.In addition, there is a need to improve the efficiency of sales promotion activities and customer satisfaction by making optimal product suggestions based on basic information and emotional information of customers in physical stores.

[0360] The specific processing 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 means for using a generative model to automatically generate a childcare curriculum based on basic information input by a childcare worker, means for displaying the childcare curriculum generated by the generative model on the childcare worker's terminal, means for collecting feedback from parents, means for storing the feedback in a database, means for generating the next childcare curriculum taking the feedback into consideration, means for using a generative model to generate optimal product proposals based on basic information and emotional information of customers, and means for displaying the generated product proposals on the salesperson's terminal. This reduces the workload of childcare workers, facilitates communication with parents, and further enables more efficient sales promotion activities in physical stores and improved customer satisfaction.

[0361] A "childcare worker" refers to a person whose occupation is to specialize in caring for infants and children.

[0362] "Basic information" refers to basic information about the user or subject that is entered into the system, such as age, interests, weather, and season.

[0363] A "generative model" refers to an artificial intelligence model that automatically generates outputs suitable for a specific purpose based on input data.

[0364] "Terminal" refers to an electronic device for inputting, outputting, and processing information, and includes smartphones, tablets, PCs, etc.

[0365] "Feedback" refers to opinions expressed by users of the system, such as their impressions after using it and areas for improvement.

[0366] A "database" refers to a collection of data that is systematically organized and stored so that it can be searched and used as needed.

[0367] A "server" refers to a computer system that provides services to clients over a network.

[0368] "Childcare curriculum" refers to programs and schedules for systematically carrying out childcare activities for infants and young children.

[0369] "Salesperson" refers to the staff in charge of selling products in physical stores, etc.

[0370] "Basic information and emotional information" refers to basic data about the customer as well as information that indicates their emotional state at the time.

[0371] "Product Recommendations" refers to products or services recommended based on a customer's interests and needs.

[0372] "JSON format" is a data exchange format, an abbreviation for JavaScript Object Notation, and refers to a method of expressing data in text format.

[0373] This system combines a generative model that automatically generates a childcare curriculum based on basic information entered by childcare workers with an emotion engine that recognizes feedback from parents and the user's emotions. It can also be applied to a system in brick-and-mortar stores that allows sales staff to recommend optimal products to customers based on their basic and emotional information.

[0374] The system's program exchanges information between the server and the device, and generates childcare curriculum and product proposals using a generative model and emotion engine. The main hardware used includes the server, smartphones, tablets, PCs, and other devices. The main software used includes web frameworks such as Flask, emotion engines, and generative models.

[0375] The server receives the basic information and emotional information entered by the nursery teacher, or the basic information and emotional information of the customer entered by the salesperson. This information is sent from the device in JSON format and stored in a database on the server. The database can be something like Firestore.

[0376] The server sends a prompt to the generative model based on the received basic information and emotion information. This prompt includes specific input data and instructions based on that data. For example, the following prompt sentence could be considered:

[0377] "Customer basic information: Interests - Healthy foods, Previous purchases - Protein bars, Product viewed in store - Vitamin supplements. Currently, the customer is smiling. Generate optimal product suggestions based on this."

[0378] The generative model generates optimal childcare curriculum and product recommendations based on the input prompts and sends the results back to the server. This information is then sent back to the device in JSON format and displayed on the device screen.

[0379] As a specific example, if a nursery teacher inputs basic information such as "3-year-old child, sunny day, interest in animals" and the emotion engine recognizes that the nursery teacher is in a good mood, the generative model will generate a nursery curriculum of "10:00 - 11:00 outdoor animal observation." Similarly, if a salesperson inputs basic information such as "interests: health foods, past purchases: protein bars, products viewed in the store: vitamin supplements" and the generative model recognizes that the customer is smiling, the generative model will generate suggestions such as "introduction to vitamin supplements" and "suggestion for new protein bar products."

[0380] The childcare curriculum and product proposals generated in this way are displayed on the devices of childcare workers and sales staff, allowing users to check and adapt them. Feedback from parents and customers is also sent from the devices to the server and used for the next generation. This system reduces the workload of childcare workers, facilitates communication with parents, and also makes sales promotion activities in physical stores more efficient and improves customer satisfaction.

[0381] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0382] Step 1:

[0383] The user (childcare worker or salesperson) enters basic information using a device (smartphone, tablet, PC, etc.). For childcare workers, basic information includes the child's age, interests, weather, season, etc. For salespeople, basic information includes the customer's interests, past purchase history, current situation, etc. The entered basic information is temporarily saved on the device.

[0384] Step 2:

[0385] The device uses a camera and microphone to capture the facial expressions and voice of the user or customer. The emotion engine analyzes this captured data and recognizes the user's emotions. The recognized emotion information is collected on the device along with basic information.

[0386] Step 3:

[0387] The device converts the collected basic information and emotional information into JSON format and sends it to the server. For example, JSON format data might include "Age: 3 years old, Interests: Animals, Weather: Sunny, Emotion: Good." The sent data is then received by the server.

[0388] Step 4:

[0389] The server generates a prompt based on the received basic information and emotion information and sends it to the generative model. For example, the prompt may contain information such as "3-year-old child, sunny day, interest in animals, and good emotion of the caregiver." The prompt is sent in a format that the generative model can understand.

[0390] Step 5:

[0391] The generative model calculates data based on the input prompts and generates optimal childcare curriculum and product suggestions. For example, it generates a childcare curriculum of "10:00 - 11:00 Outdoor animal observation" and a product suggestion of "Introduction to vitamin supplements." This generated information is sent back to the server.

[0392] Step 6:

[0393] The server receives the childcare curriculum and product suggestions returned by the generative model and converts them into JSON format. The converted data is then sent to the device, which parses the received JSON data and displays it on the user interface.

[0394] Step 7:

[0395] The user (childcare worker or salesperson) checks the childcare curriculum and product suggestions displayed on the terminal, implements them, and inputs any feedback they may have about the implementation through the terminal.

[0396] Step 8:

[0397] The device converts the user feedback back into JSON format and sends it to the server, which stores the received feedback in a database. This stored feedback is used as information for generating the next curriculum and product proposals.

[0398] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0399] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0400] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0401] [Second embodiment]

[0402] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0403] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0404] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0405] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0406] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0407] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0408] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0409] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0410] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0411] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0412] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0413] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0414] This invention is a system that automatically generates a childcare curriculum based on basic information entered by childcare workers. This system uses a generative model to reduce the burden on childcare workers and achieve smooth communication with parents.

[0415] System configuration and processing flow

[0416] 1. Enter basic information

[0417] Users (childcare workers) use devices such as PCs and tablets to input basic information, such as the children's ages, interests, weather, and season. This information is entered through a web form or dedicated application on the device.

[0418] 2. Request for curriculum generation

[0419] The device sends the basic information entered in JSON format to the server, which is built using a web framework such as Flask and receives the request.

[0420] 3. Use of generative models

[0421] The server receives the request and sends basic information as a prompt to the generative model. Based on the content of this prompt, the generative model generates a childcare curriculum. For example, GPT, a generative AI, is used as the generative model.

[0422] 4. Return and display of curriculum

[0423] The generated curriculum is sent back to the device in JSON format from the server. The device analyzes the curriculum and displays it on a user interface for childcare workers. This allows the childcare workers to check and adapt the generated curriculum.

[0424] 5. Gathering feedback from parents

[0425] Users (parents) use communication tools (such as dedicated apps or chatbots) to input feedback, which includes the parents' opinions and insights about their children.

[0426] 6. Sending and Saving Feedback

[0427] The device sends feedback in JSON format to the server, which receives the feedback, stores it in a database such as Firestore, and takes it into account when generating the next curriculum.

[0428] 7. Next curriculum generation

[0429] When generating a new childcare curriculum, the server retrieves relevant feedback from the database and provides it to the generative model, allowing for the generation of a more customized childcare curriculum based on this information and other information.

[0430] Specific examples

[0431] 1. The user (childcare worker) enters basic information such as "3-year-old child, sunny day, interest in animals" and requests curriculum generation.

[0432] 2. The generative model generates a curriculum such as "10:00 - 11:00 Outdoor animal observation."

[0433] 3. This curriculum is displayed on the terminal, and the nursery school teacher confirms and adopts the contents.

[0434] 4. The user (parent) enters feedback such as "My child wants to go to the zoo this weekend," which is saved in the database.

[0435] 5. The next time the curriculum is generated, the generative model will take the stored feedback into account and suggest zoo-related activities.

[0436] This system will provide a curriculum that is closer to the interests of children and will also allow childcare to be provided in a way that reflects the opinions of parents, thereby improving the quality of childcare and streamlining the work of childcare workers.

[0437] The processing flow will be explained below.

[0438] Step 1:

[0439] The user (childcare worker) enters basic information about the children (age, interests, weather, season, etc.) through a web form or dedicated application on their device (PC or tablet) and clicks the "Generate" button.

[0440] Step 2:

[0441] The device sends the entered basic information to the server in JSON format using the HTTP POST method.

[0442] Step 3:

[0443] The server receives the request using a web framework such as Flask, which includes basic information entered by the childcare worker.

[0444] Step 4:

[0445] The server then sends the received basic information to a generative AI model (e.g., GPT) as a prompt. This prompt contains the basic information and instructs the generation of a curriculum.

[0446] Step 5:

[0447] The generative model generates a childcare curriculum based on the received prompts, and the generated curriculum is sent back to the server in text format.

[0448] Step 6:

[0449] The server converts the childcare curriculum returned from the generative model into JSON format and returns it to the device using an HTTP response.

[0450] Step 7:

[0451] The device receives the JSON data returned from the server and displays it on the user interface, allowing childcare workers to check the generated curriculum.

[0452] Step 8:

[0453] Users (parents) input and send feedback (e.g., "My child wants to go to the zoo") via a dedicated app or chatbot.

[0454] Step 9:

[0455] The device sends the input feedback in JSON format to the server, and this request is also made using the HTTP POST method.

[0456] Step 10:

[0457] The server saves the received feedback in a database such as Firestore, and notifies the device that the saving is complete.

[0458] Step 11:

[0459] The next time a curriculum is generated, the server retrieves the relevant feedback from the database and again sends a prompt to the generative model, this time containing the new basic information and the previous feedback.

[0460] Step 12:

[0461] The generative model generates a new childcare curriculum that takes the feedback into account and sends it back to the server, which then receives it and sends it back to the device in JSON format.

[0462] Step 13:

[0463] The terminal displays the received new curriculum, and the user (childcare worker) checks and adapts the content.

[0464] Example 1

[0465] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0466] Childcare workers spend a lot of time and effort creating daily childcare curricula. Furthermore, there is no efficient way to incorporate parental feedback into the curriculum, making it difficult to improve the quality of childcare. Furthermore, when automatically generating childcare curricula, it is difficult to appropriately reflect the latest childcare information and children's interests.

[0467] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0468] In this invention, the server includes means for using a generative model to automatically generate a childcare curriculum based on basic information input by a childcare worker, means for displaying the childcare curriculum generated by the generative model on the childcare worker's terminal, means for collecting feedback from parents, means for saving the feedback in a database, means for generating the next childcare curriculum taking the feedback into consideration, means for inputting basic information through a user interface, means for converting the basic information into JSON format and sending it to the server, means for returning the generated curriculum in JSON format to the terminal, means for parents to input feedback using a communication tool, and means for sending the feedback to the server in JSON format. This enables childcare workers to efficiently create curricula and provide high-quality childcare that reflects parental feedback.

[0469] A "childcare worker" is a professional who is responsible for caring for and educating children in a childcare facility.

[0470] "Basic information" refers to information necessary for creating a curriculum, such as the children's ages, interests, weather, and season.

[0471] A "childcare curriculum" is a plan of activities and education that childcare workers provide to children.

[0472] A "generative model" is an AI technique that generates new text or plans based on input prompts.

[0473] A "terminal" is a device, such as a computer or tablet, that a user uses to enter information or view results.

[0474] A "server" is a computer system that provides services to client terminals over a network.

[0475] "Feedback" refers to opinions and thoughts about their children provided by parents.

[0476] A "database" is a system for storing and managing information efficiently and safely.

[0477] A "user interface" is a component such as a screen, menu, or form that allows a user to access and operate a system.

[0478] A "prompt" is text that is input as an instruction or question to a generative model.

[0479] "JSON format" is a format for describing data in a structured text format.

[0480] "Communication means" refers to technologies and systems for sending and receiving information and data.

[0481] This invention is a system that automatically generates a childcare curriculum based on basic information entered by childcare workers, and by using a generative model, it reduces the burden on childcare workers and realizes smooth communication with parents. This system is composed of users (childcare workers and parents), terminals, a server, and a generative AI model.

[0482] Enter basic information

[0483] Users (childcare workers) use devices such as PCs and tablets to enter basic information, such as the child's age, interests, weather, and season. This basic information is entered through a web form displayed on the device or a dedicated app.

[0484] Request curriculum generation

[0485] The terminal converts the basic information entered by the user into JSON format data and sends it to the server using an HTTP request, which is built with a web framework such as Flask.

[0486] Using generative models

[0487] The server sends the received basic information in JSON format as prompts to a generative AI model (e.g., GPT-3), which then generates a new childcare curriculum based on the prompts.

[0488] Return and view curriculum

[0489] After the generative AI model generates the childcare curriculum, the generated results are sent back to the server in JSON format, which is then sent to the device, which then displays the curriculum on the user interface.

[0490] Gathering feedback from parents

[0491] Users (parents) can use a dedicated app or chatbot to input feedback, which includes opinions and reactions about their children.

[0492] Send and save feedback

[0493] The device sends the input feedback in JSON format to the server, which stores it in a database such as Firestore, so that it can take this feedback into account when generating the next curriculum.

[0494] Next curriculum generation

[0495] When generating a new curriculum, the server retrieves the stored feedback from the database and provides it to the generative model. By providing the generative model with information including the feedback as prompts, the next generated curriculum can be further customized.

[0496] Specific examples

[0497] For example, suppose a user (a nursery teacher) enters basic information such as "3-year-old child, sunny day, interest in animals." Based on this information, the prompt sent to the generative model is as follows:

[0498] Child's age: 3 years old

[0499] Weather: Sunny

[0500] Interests: Animals

[0501] Based on this prompt, the generative model generates a curriculum such as "10:00 - 11:00 Outdoor animal observation." This curriculum is displayed on the device, and the nursery teacher can review and adopt the content.

[0502] In addition, the user (parent) can input feedback such as "My child wants to go to the zoo this weekend," and this feedback is saved in the database. By providing this feedback to the generative model the next time a curriculum is generated, it will be more likely to suggest zoo-related activities.

[0503] This system allows childcare workers to create curriculums more efficiently, improving the quality of childcare. In addition, by incorporating parents' opinions into the curriculum, more individualized childcare can be achieved.

[0504] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0505] Step 1:

[0506] The user (childcare worker) uses a device such as a PC or tablet to enter basic information into a web form or dedicated app. For example, information such as "3-year-old child, sunny day, interest in animals." This input data is stored as is in the device's memory. Input: Basic information. Output: Input data in the device.

[0507] Step 2:

[0508] The terminal converts the basic information entered in step 1 into JSON format. This data conversion process uses a serialization library within the program. The converted JSON data is sent to the server as an HTTP POST request. Input: Basic information. Output: Basic information in JSON format.

[0509] Step 3:

[0510] The server receives an HTTP POST request and obtains the JSON data within it. This data is processed by an API endpoint within the server. The server parses the received basic information and sends it as a prompt to the generative AI model (e.g., GPT-3). Input: Basic information in JSON format. Output: Prompt to the generative AI model.

[0511] Step 4:

[0512] The generative AI model generates a childcare curriculum based on the prompts it receives. During this generation process, the model uses its internal neural network to analyze and generate data. The generated curriculum is sent back to the server in JSON format. Input: Prompt. Output: Childcare curriculum in JSON format.

[0513] Step 5:

[0514] The server receives the childcare curriculum in JSON format returned from the generative AI model. This data is parsed again and sent back to the device. The server sends the data as an HTTP response. Input: Childcare curriculum in JSON format. Output: HTTP response to the device.

[0515] Step 6:

[0516] The terminal analyzes the JSON formatted childcare curriculum received from the server and displays it on the user interface. This display process uses a front-end library to render the analysis results on the screen. Input: Childcare curriculum in JSON format. Output: Data displayed on the user interface.

[0517] Step 7:

[0518] The user (parent) enters feedback using a dedicated app or chatbot. The feedback includes the child's reactions and opinions. This input data is stored in the device's memory. Input: Feedback. Output: Input data in the device.

[0519] Step 8:

[0520] The terminal converts the feedback entered in step 7 into JSON format. A serialization library is used for this conversion process. The converted JSON data is sent to the server as an HTTP POST request. Input: Feedback. Output: Feedback in JSON format.

[0521] Step 9:

[0522] The server receives an HTTP POST request and retrieves JSON data within it. This data is processed by an API endpoint on the server and saved in a database such as Firestore. Input: Feedback in JSON format. Output: Data saved in the database.

[0523] Step 10:

[0524] The server retrieves the stored feedback from the database when generating a new curriculum. This retrieved data is included in the prompts provided to the generative model. Input: Feedback data from the database. Output: Updated prompts to the generative model.

[0525] Through specific operations that take into account input and output, this system can improve the work efficiency of childcare workers and effectively reflect parental feedback in the curriculum.

[0526] (Application example 1)

[0527] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0528] Efficiently and flexibly managing robot task schedules in factories requires consideration of a vast amount of work information and operating status. However, this requires a great deal of time and effort, which increases the burden on workers and managers and reduces production efficiency. In addition, it is difficult to generate an optimal schedule that takes into account real-time factors such as environmental conditions and task priorities. To solve these issues, a system that efficiently and automatically generates work schedules is needed.

[0529] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0530] In this invention, the server includes means for using a generative model to automatically generate a work schedule based on basic information entered by a manager, means for displaying the work schedule generated by the generative model on the manager's terminal, means for collecting feedback from workers, means for saving the feedback in a database, and means for generating the next work schedule taking the feedback into consideration. This reduces the burden on workers and managers and makes it possible to efficiently generate and apply optimal work schedules in real time.

[0531] An "administrator" is a person who is responsible for managing and supervising the task schedules of robots and workers in factory operations.

[0532] "Basic information" refers to data such as the type of work, priority, operating status, and work environment that must be entered by the administrator.

[0533] A "work schedule" is a specific work plan for factory robots and workers that is automatically generated based on a generative model.

[0534] A "generative model" is a system that includes an algorithm that generates an optimal work schedule based on input basic information.

[0535] A "terminal" is a device such as a computer or tablet that allows an administrator to enter basic information and check the generated work schedule.

[0536] "Feedback" refers to evaluations and opinions provided by workers and other stakeholders regarding the actual work situation and robot performance.

[0537] A "server" is a central processing unit for running generative models, processing requests from terminals, and storing feedback in a database.

[0538] A "database" is an information storage system for storing and managing feedback, basic information, etc.

[0539] A "prompt" is an instruction containing basic information entered that the generative model uses to generate a work schedule.

[0540] The "JSON format" is a text format for structuring, storing, and transmitting data, and is commonly used when exchanging data between programs.

[0541] This invention is a system for efficiently and automatically generating work schedules for robots in a factory, reducing the burden on managers and improving production efficiency. The configuration and operation of this system are described below.

[0542] 1. System Configuration

[0543] The system consists of an administrator's terminal, a server, a generative model, and a database. The hardware used includes factory PCs and tablets, as well as industrial robots. The software uses a Flask web framework, generative AI (e.g., GPT), and Firestore (Google's NoSQL database).

[0544] 2. Program processing flow and explanation

[0545] Enter basic information

[0546] Managers use terminals to enter basic information such as product type, work priority, operating status, and work environment information, etc. The information is entered through a web form or a dedicated application.

[0547] Request to generate a task schedule

[0548] The terminal converts the input basic information into JSON format and sends it to the server, which uses Flask to receive the request and begin processing.

[0549] Using generative models

[0550] The server receives the request and sends basic information as prompts to a generative model (e.g., GPT), which then generates an optimal work schedule based on the content of the prompts.

[0551] Return and view schedules

[0552] The generated schedule is sent back to the administrator's terminal in JSON format from the server. The terminal parses the returned schedule and displays it in the administrator's user interface. This allows the administrator to check and apply the generated schedule.

[0553] Feedback collection

[0554] Workers use communication tools to input feedback, which includes information about actual work results and robot performance.

[0555] Send and save feedback

[0556] The device sends feedback in JSON format to the server, which receives this feedback, stores it in Firestore, and takes this feedback into account when generating the next schedule.

[0557] Next schedule generation

[0558] When generating a new work schedule, the server retrieves relevant feedback from the database and feeds it into the generative model, which then generates a more customized schedule based on this information.

[0559] Examples of concrete examples and prompts

[0560] Specific examples

[0561] Suppose a manager inputs basic information such as "Production of Product A, high priority, machine 1, humidity 70%" and requests schedule generation. The generative model generates a task schedule such as "10:00 - 11:00 Product A Line 1, production speed 120%." This schedule is displayed on the manager's terminal, and the manager can confirm and adopt the contents.

[0562] The worker provides feedback such as "the robot's speed was appropriate" or "the operating time was short," which is then stored in Firestore. The next time the schedule is generated, the generative model takes this feedback into account and proposes an optimal task schedule.

[0563] Prompt Sentence Examples

[0564] Factory task schedule generation:

[0565] Product name: Product A

[0566] Work priority: High

[0567] Operation status: Machine 1

[0568] Working environment: 70% humidity

[0569] Feedback Consideration:

[0570] Speed: 120%

[0571] Feedback: Good

[0572] In this way, this system reduces the burden on managers and workers and enables them to efficiently manage and operate work schedules.

[0573] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0574] Step 1:

[0575] Administrator enters basic information

[0576] The administrator uses the terminal to enter basic information such as the product type, work priority, operating status, and work environment information. This information is entered through the terminal's web form or a dedicated application, and the entered information is converted into JSON format.

[0577] Input: Product type, work priority, operation status, work environment information

[0578] Output: Basic information in JSON format

[0579] Step 2:

[0580] Send basic information

[0581] The device sends the basic information entered in JSON format to the server, which uses Flask to receive the request and begin processing.

[0582] Input: Basic information in JSON format

[0583] Output: The request received by the server

[0584] Step 3:

[0585] Using generative models

[0586] The server sends the received basic information to the generative model as prompts, which the generative model (e.g., GPT) uses to generate an optimal work schedule.

[0587] Input: Basic information in JSON format, prompt statement

[0588] Output: Generated work schedule

[0589] Specific working example:

[0590] Factory task schedule generation:

[0591] Product name: Product A

[0592] Work priority: High

[0593] Operation status: Machine 1

[0594] Working environment: 70% humidity

[0595] Step 4:

[0596] Return and view schedules

[0597] The server returns the generated work schedule in JSON format to the terminal, which then analyzes the returned schedule and displays it in a user interface for administrators, allowing them to check and apply the generated schedule.

[0598] Input: Generated work schedule (JSON format)

[0599] Output: Schedule displayed on the administrator's terminal

[0600] Step 5:

[0601] Enter your feedback

[0602] Workers use communication tools to provide feedback, including evaluations and opinions on the actual work results and the robot's performance.

[0603] Input: Work results, robot performance

[0604] Output: Feedback information

[0605] Step 6:

[0606] Send and save feedback

[0607] The device sends the collected feedback in JSON format to the server, which receives this feedback and stores it in Firestore, so that it can take this feedback into account when generating the next schedule.

[0608] Input: Feedback information (JSON format)

[0609] Output: Feedback stored in Firestore

[0610] Step 7:

[0611] Next schedule generation

[0612] When generating a new work schedule, the server retrieves relevant feedback from the database (Firestore) and feeds it into the generative model, which then generates a more customized schedule based on this information.

[0613] Input: Feedback information, Basic information

[0614] Output: Next best schedule

[0615] This reduces the burden on managers and workers and makes it possible to efficiently generate and apply optimal work schedules in real time.

[0616] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0617] This system combines a generative model that automatically generates a childcare curriculum based on basic information entered by childcare workers with an emotion engine that recognizes feedback from parents and the user's emotions. This reduces the burden on childcare workers, enables smooth communication with parents, and enables the generation of an optimal childcare curriculum based on emotions.

[0618] System configuration and processing flow

[0619] 1. Enter basic information

[0620] Users (childcare workers) use devices such as PCs and tablets to enter basic information, including the children's ages, interests, weather, and seasons. Input is done through a web form or a dedicated application, and is completed by clicking the "Generate" button.

[0621] 2. Emotional Recognition

[0622] The emotion engine installed in the device recognizes the emotions of the childcare worker, and this emotion information is sent to the server along with basic information.

[0623] 3. Request for curriculum generation

[0624] The device sends basic information and emotional information in JSON format to the server, which receives the request using a web framework such as Flask.

[0625] 4. Using Generative Models

[0626] The server receives basic information and emotion information and sends it to the generative model as a prompt. This prompt takes into account the emotions of the childcare worker. The generative model generates a childcare curriculum based on the prompt and sends the result back to the server.

[0627] 5. Return and display of curriculum

[0628] The generated curriculum is sent back to the device in JSON format from the server. The device displays the curriculum on the user interface, allowing the childcare worker to review and adapt it.

[0629] 6. Gathering feedback from parents

[0630] The user (parent) enters feedback through a dedicated app or chatbot. At this time, the emotion engine also recognizes the parent's emotions. The feedback, along with the emotional information, is sent from the device to the server.

[0631] 7. Sending and Saving Feedback

[0632] The device sends the input feedback and emotion information in JSON format to the server. The server receives it, stores it in a database such as Firestore, and notifies the device that the saving is complete.

[0633] 8. Next curriculum generation

[0634] When generating a new childcare curriculum, the server retrieves relevant feedback and emotional information from the database and supplies it to the generative model. The generative model generates a new childcare curriculum that takes the feedback and emotional information into account and sends the results back to the server. The server receives this and sends it back to the device in JSON format.

[0635] Specific examples

[0636] 1. The user (childcare worker) enters basic information such as "3-year-old child, sunny day, interest in animals," and the emotion engine recognizes that the user is in a very good mood.

[0637] 2. The generative model generates a childcare curriculum such as "10:00 - 11:00 Outdoor animal observation" and recommends activities that also reflect the positive emotions of the childcare workers.

[0638] 3. This curriculum is displayed on the terminal, and the nursery school teacher confirms and adopts the contents.

[0639] 4. The user (parent) inputs feedback such as "My child wants to go to the zoo this weekend," and the emotion engine recognizes the parent's happy feelings.

[0640] 5. The feedback and parental sentiment information will be stored in a database and taken into consideration when generating the next curriculum.

[0641] 6. Next time, the generative model will take into account parents’ feedback and emotions to generate a new curriculum and recommend “zoo-related activities.”

[0642] This will provide a more personalized childcare curriculum that takes into account the user's emotions, improving the quality of childcare and increasing the work efficiency of childcare workers.

[0643] The processing flow will be explained below.

[0644] Step 1:

[0645] The user (childcare worker) uses a device such as a PC or tablet to enter basic information (child's age, interests, weather, season, etc.) into a web form or dedicated application and clicks the "Generate" button.

[0646] Step 2:

[0647] The device converts the input basic information into JSON format and simultaneously recognizes the childcare worker's emotions using an emotion engine. This emotional information is also compiled in JSON format and sent to the server.

[0648] Step 3:

[0649] The server receives basic information and emotional information from the device through a web framework such as Flask.

[0650] Step 4:

[0651] The server sends the received basic information and emotional information to the generative model as a prompt, which includes the emotional state of the caregiver (e.g., "I feel very good").

[0652] Step 5:

[0653] The generative model generates a childcare curriculum based on the prompts. The generative model analyzes the information and creates an optimal childcare curriculum based on the feelings of the childcare workers.

[0654] Step 6:

[0655] The generated childcare curriculum returned from the generative model is sent back to the server, which then sends it back to the device in JSON format.

[0656] Step 7:

[0657] The device receives the JSON data returned from the server and displays the generated curriculum on the user interface. The childcare worker can check and apply the content.

[0658] Step 8:

[0659] Users (parents) input feedback through a dedicated app or chatbot, and this feedback is recognized by the emotion engine, including the parent's emotions (e.g., happy feelings).

[0660] Step 9:

[0661] The device converts the input feedback and emotion information into JSON format and sends it to the server using the HTTP POST method.

[0662] Step 10:

[0663] The server receives the feedback and emotion information, stores it in a database such as Firestore, and notifies the device once the storage is complete.

[0664] Step 11:

[0665] When generating the next curriculum, the server retrieves the relevant feedback and emotion information from the database and sends it to the generative model as a prompt, which includes the new basic information, the previous feedback, and the parent's emotion information.

[0666] Step 12:

[0667] The generative model takes into account the feedback and emotional information to generate a new childcare curriculum and sends it back to the server, which then receives it and sends it back to the device in JSON format.

[0668] Step 13:

[0669] The terminal displays the received new curriculum, and the user (childcare worker) checks and applies the contents.

[0670] Specifically, a childcare worker inputs basic information such as "3-year-old child, sunny day, interest in animals," and the emotion engine recognizes that the childcare worker is in a "very good mood." The generative model then generates a curriculum of "10:00 - 11:00 outdoor animal observation" and recommends activities that reflect the childcare worker's good mood. Similarly, if a parent inputs feedback such as "my child wants to go to the zoo this weekend" and recognizes that the child is in a happy mood, this information will be taken into account when generating the next curriculum, and "zoo-related activities" will be recommended.

[0671] This provides a more personalized childcare curriculum that takes into account the user's emotions.

[0672] Example 2

[0673] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0674] Conventional childcare curriculum generation systems were unable to consider the emotions of childcare workers or the feedback of parents, and instead created a uniform curriculum. This placed a heavy burden on childcare workers and made communication with parents difficult. Furthermore, because the curriculum did not reflect the interests and emotions of individual children, it was difficult to improve the quality of childcare.

[0675] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0676] In this invention, the server includes a means for using a terminal equipped with an emotion engine that recognizes the emotions of childcare workers, a means for recognizing feedback from parents and their emotions, and a means for storing the feedback from parents and emotion information in a database. This makes it possible to generate an individually optimized childcare curriculum that takes into account the emotions of childcare workers and the feedback and emotion information from parents.

[0677] "Basic information" refers to data entered by childcare workers, such as children's ages, interests, weather, and seasons.

[0678] A "generative model" refers to an artificial intelligence algorithm that automatically generates a childcare curriculum based on input basic information and emotional information.

[0679] "Emotion engine" refers to software or a device that recognizes and analyzes the emotions of childcare workers and parents.

[0680] "Devices" refers to electronic devices such as PCs, tablets, and smartphones used by childcare workers and parents.

[0681] "Feedback" refers to opinions, requests, and impressions from parents.

[0682] "Database" refers to an electronic information storage system for storing feedback, emotional information, etc.

[0683] A "prompt" refers to input data that provides basic and emotional information to a generative model.

[0684] "JSON format" refers to a text-based data exchange format that expresses data concisely and in a highly readable manner.

[0685] This invention is a system that automatically generates an optimal childcare curriculum based on basic information and emotional information entered by childcare workers. The purpose of this system is to reduce the burden on childcare workers, facilitate communication with parents, and provide individually optimized childcare curricula.

[0686] Enter basic information

[0687] Users (childcare workers) enter basic information using devices such as PCs or tablets. For example, they can open a dedicated application or web form and enter information such as the children's ages, interests, weather, and season. Once the information is complete, they click the "Generate" button, and the information is saved on the device.

[0688] Emotion recognition

[0689] The device is equipped with an emotion engine that recognizes the emotions of the childcare worker. This engine uses sensor devices such as cameras and microphones to analyze emotions from the childcare worker's facial expressions and tone of voice. For example, if the childcare worker's facial expression is smiling, the emotion engine will determine that the childcare worker is in a "very good mood." This emotion information is sent to the server along with basic information.

[0690] Request curriculum generation

[0691] The device sends basic information and emotional information to the server in JSON format. The device uses a web framework such as Flask to send this data to the server as an HTTP request. Specific examples of transmitted data include the following formats:

[0692] {

[0693] "age": "3 years old",

[0694] "Interests": "Animals",

[0695] "Weather": "Sunny",

[0696] "season": "spring",

[0697] "Childcare worker's feelings": "I feel very good"

[0698] }

[0699] Using generative models

[0700] The server analyzes the received basic information and emotional information and sends it as prompts to the generative AI model. The generative AI model automatically generates a childcare curriculum based on this information. For example, given prompts such as "The childcare worker is in a good mood," "For 3-year-olds," "It's a sunny day," and "Interested in animals," the generative AI model generates a curriculum such as "10:00 - 11:00 Outdoor animal observation."

[0701] Return and view curriculum

[0702] The generated childcare curriculum is sent back to the device in JSON format from the server. The device's dedicated application or web application parses this JSON data and displays the curriculum content on the user interface. Childcare workers can check the content and adjust it as necessary. For example, the following display content is possible:

[0703] 10:00 - 11:00 Outdoor animal observation

[0704] 11:00 - 12:00 Indoor animal picture book reading

[0705] Gathering feedback from parents

[0706] Users (parents) input feedback using a dedicated app or chatbot. During this input process, the emotion engine analyzes the parent's emotions. For example, if a parent inputs "My child wants to go to the zoo this weekend" and looks happy while doing so, the emotion engine will recognize this as "feeling happy."

[0707] Send and save feedback

[0708] The device sends parental feedback and emotional information in JSON format to the server. The server receives the data and stores it in a database such as Firestore. Once the data is saved, a notification of success is displayed on the device.

[0709] Next curriculum generation

[0710] When generating a new childcare curriculum, the server retrieves previously saved feedback and emotional information from the database and supplies it to the generative AI model. This makes it possible to generate a more optimal childcare curriculum that takes past feedback and emotions into account. The generative AI model generates a new curriculum based on this information and sends the results back to the server. The server receives this and sends it back to the device in JSON format, which then displays it.

[0711] As described above, the system of the present invention effectively utilizes the emotions of childcare workers and feedback from parents to provide individually optimized childcare curricula, thereby improving the work efficiency of childcare workers and the quality of childcare.

[0712] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0713] Step 1:

[0714] The user (childcare worker) uses a device such as a PC or tablet to enter basic information. This basic information includes the children's ages, interests, weather, season, etc. This basic information is entered through a dedicated application or web form. Once the entry is complete, the user clicks the "Generate" button, and the basic information is sent to the device. Specific data is entered using text boxes and drop-down menus, and the basic information is saved on the device as output.

[0715] Step 2:

[0716] The device's emotion engine recognizes the emotions of the childcare worker through sensor devices such as cameras and microphones. For example, if a childcare worker is smiling while entering information, the emotion engine will analyze this and recognize it as a "very good mood." This emotional information is then stored directly on the device.

[0717] Step 3:

[0718] The device sends the basic information entered by the childcare worker and the recognized emotional information to the server in JSON format. The device uses a web framework such as Flask to send this data to the server as an HTTP request. The following JSON format is used as an example of specific data to be sent. The basic information and emotional information are used as input, and the output is sent to the server in JSON format.

[0719] {

[0720] "age": "3 years old",

[0721] "Interests": "Animals",

[0722] "Weather": "Sunny",

[0723] "season": "spring",

[0724] "Childcare worker's feelings": "I feel very good"

[0725] }

[0726] Step 4:

[0727] The server analyzes the received basic information and emotional information and sends it as a prompt to the generative AI model. The generative AI model automatically generates a childcare curriculum based on this information. For example, given prompts such as "The childcare worker is in a good mood," "For 3-year-olds," "It's a sunny day," and "Interested in animals," the generative AI model generates a curriculum such as "10:00 - 11:00 Outdoor animal observation." In this step, the server receives the basic information and emotional information as input and obtains an output that sends a prompt to the generative AI model.

[0728] Step 5:

[0729] The generated childcare curriculum is sent from the server to the device again in JSON format. A dedicated application or web application on the device parses this JSON data and displays the curriculum content on the user interface. For example, a curriculum such as "10:00 - 11:00 Outdoor animal observation" is displayed, allowing childcare workers to review the content and adjust it as necessary. In this step, the output of the generative AI model (childcare curriculum) is sent to the device in JSON format, where it is parsed and displayed.

[0730] Step 6:

[0731] The user (parent) inputs feedback using a dedicated app or chatbot. During this input process, the emotion engine analyzes the parent's emotions. For example, if the parent inputs "My child wants to go to the zoo this weekend" and has a happy expression while doing so, the emotion engine will recognize this as "a happy feeling." In this step, feedback and emotional information are input and saved as output on the device.

[0732] Step 7:

[0733] The device sends the parent's feedback and emotion information in JSON format to the server. The server receives this and stores it in a database such as Firestore. Once the storage is complete, a notification of successful storage is displayed on the device. In this step, the input feedback and emotion information are sent to the server, and the output is stored in a database.

[0734] Step 8:

[0735] When generating a new childcare curriculum, the server retrieves previously saved feedback and emotional information from the database and supplies it to the generative AI model. This allows for the generation of a more optimal childcare curriculum that takes past feedback and emotions into account. For example, a childcare curriculum that suggests "zoo-related activities" based on parental feedback may be generated. In this step, past feedback and emotional information are input, and the generative AI model outputs a newly generated childcare curriculum.

[0736] (Application example 2)

[0737] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0738] In childcare operations such as automatically generating childcare curricula and collecting feedback, there are issues related to reducing the burden on childcare workers and smooth communication with parents.In addition, there is a need to improve the efficiency of sales promotion activities and customer satisfaction by making optimal product suggestions based on basic information and emotional information of customers in physical stores.

[0739] The specific processing 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 means for using a generative model to automatically generate a childcare curriculum based on basic information input by a childcare worker, means for displaying the childcare curriculum generated by the generative model on the childcare worker's terminal, means for collecting feedback from parents, means for storing the feedback in a database, means for generating the next childcare curriculum taking the feedback into consideration, means for using a generative model to generate optimal product proposals based on basic information and emotional information of customers, and means for displaying the generated product proposals on the salesperson's terminal. This reduces the workload of childcare workers, facilitates communication with parents, and further enables more efficient sales promotion activities in physical stores and improved customer satisfaction.

[0740] A "childcare worker" refers to a person whose occupation is to specialize in caring for infants and children.

[0741] "Basic information" refers to basic information about the user or subject that is entered into the system, such as age, interests, weather, and season.

[0742] A "generative model" refers to an artificial intelligence model that automatically generates outputs suitable for a specific purpose based on input data.

[0743] "Terminal" refers to an electronic device for inputting, outputting, and processing information, and includes smartphones, tablets, PCs, etc.

[0744] "Feedback" refers to opinions expressed by users of the system, such as their impressions after using it and areas for improvement.

[0745] A "database" refers to a collection of data that is systematically organized and stored so that it can be searched and used as needed.

[0746] A "server" refers to a computer system that provides services to clients over a network.

[0747] "Childcare curriculum" refers to programs and schedules for systematically carrying out childcare activities for infants and young children.

[0748] "Salesperson" refers to the staff in charge of selling products in physical stores, etc.

[0749] "Basic information and emotional information" refers to basic data about the customer as well as information that indicates their emotional state at the time.

[0750] "Product Recommendations" refers to products or services recommended based on a customer's interests and needs.

[0751] "JSON format" is a data exchange format, an abbreviation for JavaScript Object Notation, and refers to a method of expressing data in text format.

[0752] This system combines a generative model that automatically generates a childcare curriculum based on basic information entered by childcare workers with an emotion engine that recognizes feedback from parents and the user's emotions. It can also be applied to a system in brick-and-mortar stores that allows sales staff to recommend optimal products to customers based on their basic and emotional information.

[0753] The system's program exchanges information between the server and the device, and generates childcare curriculum and product proposals using a generative model and emotion engine. The main hardware used includes the server, smartphones, tablets, PCs, and other devices. The main software used includes web frameworks such as Flask, emotion engines, and generative models.

[0754] The server receives the basic information and emotional information entered by the nursery teacher, or the basic information and emotional information of the customer entered by the salesperson. This information is sent from the device in JSON format and stored in a database on the server. The database can be something like Firestore.

[0755] The server sends a prompt to the generative model based on the received basic information and emotion information. This prompt includes specific input data and instructions based on that data. For example, the following prompt sentence could be considered:

[0756] "Customer basic information: Interests - Healthy foods, Previous purchases - Protein bars, Product viewed in store - Vitamin supplements. Currently, the customer is smiling. Generate optimal product suggestions based on this."

[0757] The generative model generates optimal childcare curriculum and product recommendations based on the input prompts and sends the results back to the server. This information is then sent back to the device in JSON format and displayed on the device screen.

[0758] As a specific example, if a nursery teacher inputs basic information such as "3-year-old child, sunny day, interest in animals" and the emotion engine recognizes that the nursery teacher is in a good mood, the generative model will generate a nursery curriculum of "10:00 - 11:00 outdoor animal observation." Similarly, if a salesperson inputs basic information such as "interests: health foods, past purchases: protein bars, products viewed in the store: vitamin supplements" and the generative model recognizes that the customer is smiling, the generative model will generate suggestions such as "introduction to vitamin supplements" and "suggestion for new protein bar products."

[0759] The childcare curriculum and product proposals generated in this way are displayed on the devices of childcare workers and sales staff, allowing users to check and adapt them. Feedback from parents and customers is also sent from the devices to the server and used for the next generation. This system reduces the workload of childcare workers, facilitates communication with parents, and also makes sales promotion activities in physical stores more efficient and improves customer satisfaction.

[0760] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0761] Step 1:

[0762] The user (childcare worker or salesperson) enters basic information using a device (smartphone, tablet, PC, etc.). For childcare workers, basic information includes the child's age, interests, weather, season, etc. For salespeople, basic information includes the customer's interests, past purchase history, current situation, etc. The entered basic information is temporarily saved on the device.

[0763] Step 2:

[0764] The device uses a camera and microphone to capture the facial expressions and voice of the user or customer. The emotion engine analyzes this captured data and recognizes the user's emotions. The recognized emotion information is collected on the device along with basic information.

[0765] Step 3:

[0766] The device converts the collected basic information and emotional information into JSON format and sends it to the server. For example, JSON format data might include "Age: 3 years old, Interests: Animals, Weather: Sunny, Emotion: Good." The sent data is then received by the server.

[0767] Step 4:

[0768] The server generates a prompt based on the received basic information and emotion information and sends it to the generative model. For example, the prompt may contain information such as "3-year-old child, sunny day, interest in animals, and good emotion of the caregiver." The prompt is sent in a format that the generative model can understand.

[0769] Step 5:

[0770] The generative model calculates data based on the input prompts and generates optimal childcare curriculum and product suggestions. For example, it generates a childcare curriculum of "10:00 - 11:00 Outdoor animal observation" and a product suggestion of "Introduction to vitamin supplements." This generated information is sent back to the server.

[0771] Step 6:

[0772] The server receives the childcare curriculum and product suggestions returned by the generative model and converts them into JSON format. The converted data is then sent to the device, which parses the received JSON data and displays it on the user interface.

[0773] Step 7:

[0774] The user (childcare worker or salesperson) checks the childcare curriculum and product suggestions displayed on the terminal, implements them, and inputs any feedback they may have about the implementation through the terminal.

[0775] Step 8:

[0776] The device converts the user feedback back into JSON format and sends it to the server, which stores the received feedback in a database. This stored feedback is used as information for generating the next curriculum and product proposals.

[0777] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0778] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0779] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0780] [Third embodiment]

[0781] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0782] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0783] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0784] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0785] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0786] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0787] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0788] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0789] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0790] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0791] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0792] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0793] This invention is a system that automatically generates a childcare curriculum based on basic information entered by childcare workers. This system uses a generative model to reduce the burden on childcare workers and achieve smooth communication with parents.

[0794] System configuration and processing flow

[0795] 1. Enter basic information

[0796] Users (childcare workers) use devices such as PCs and tablets to input basic information, such as the children's ages, interests, weather, and season. This information is entered through a web form or dedicated application on the device.

[0797] 2. Request for curriculum generation

[0798] The device sends the basic information entered in JSON format to the server, which is built using a web framework such as Flask and receives the request.

[0799] 3. Use of generative models

[0800] The server receives the request and sends basic information as a prompt to the generative model. Based on the content of this prompt, the generative model generates a childcare curriculum. For example, GPT, a generative AI, is used as the generative model.

[0801] 4. Return and display of curriculum

[0802] The generated curriculum is sent back to the device in JSON format from the server. The device analyzes the curriculum and displays it on a user interface for childcare workers. This allows the childcare workers to check and adapt the generated curriculum.

[0803] 5. Gathering feedback from parents

[0804] Users (parents) use communication tools (such as dedicated apps or chatbots) to input feedback, which includes the parents' opinions and insights about their children.

[0805] 6. Sending and Saving Feedback

[0806] The device sends feedback in JSON format to the server, which receives the feedback, stores it in a database such as Firestore, and takes it into account when generating the next curriculum.

[0807] 7. Next curriculum generation

[0808] When generating a new childcare curriculum, the server retrieves relevant feedback from the database and provides it to the generative model, allowing for the generation of a more customized childcare curriculum based on this information and other information.

[0809] Specific examples

[0810] 1. The user (childcare worker) enters basic information such as "3-year-old child, sunny day, interest in animals" and requests curriculum generation.

[0811] 2. The generative model generates a curriculum such as "10:00 - 11:00 Outdoor animal observation."

[0812] 3. This curriculum is displayed on the terminal, and the nursery school teacher confirms and adopts the contents.

[0813] 4. The user (parent) enters feedback such as "My child wants to go to the zoo this weekend," which is saved in the database.

[0814] 5. The next time the curriculum is generated, the generative model will take the stored feedback into account and suggest zoo-related activities.

[0815] This system will provide a curriculum that is closer to the interests of children and will also allow childcare to be provided in a way that reflects the opinions of parents, thereby improving the quality of childcare and streamlining the work of childcare workers.

[0816] The processing flow will be explained below.

[0817] Step 1:

[0818] The user (childcare worker) enters basic information about the children (age, interests, weather, season, etc.) through a web form or dedicated application on their device (PC or tablet) and clicks the "Generate" button.

[0819] Step 2:

[0820] The device sends the entered basic information to the server in JSON format using the HTTP POST method.

[0821] Step 3:

[0822] The server receives the request using a web framework such as Flask, which includes basic information entered by the childcare worker.

[0823] Step 4:

[0824] The server then sends the received basic information to a generative AI model (e.g., GPT) as a prompt. This prompt contains the basic information and instructs the generation of a curriculum.

[0825] Step 5:

[0826] The generative model generates a childcare curriculum based on the received prompts, and the generated curriculum is sent back to the server in text format.

[0827] Step 6:

[0828] The server converts the childcare curriculum returned from the generative model into JSON format and returns it to the device using an HTTP response.

[0829] Step 7:

[0830] The device receives the JSON data returned from the server and displays it on the user interface, allowing childcare workers to check the generated curriculum.

[0831] Step 8:

[0832] Users (parents) input and send feedback (e.g., "My child wants to go to the zoo") via a dedicated app or chatbot.

[0833] Step 9:

[0834] The device sends the input feedback in JSON format to the server, and this request is also made using the HTTP POST method.

[0835] Step 10:

[0836] The server saves the received feedback in a database such as Firestore, and notifies the device that the saving is complete.

[0837] Step 11:

[0838] The next time a curriculum is generated, the server retrieves the relevant feedback from the database and again sends a prompt to the generative model, this time containing the new basic information and the previous feedback.

[0839] Step 12:

[0840] The generative model generates a new childcare curriculum that takes the feedback into account and sends it back to the server, which then receives it and sends it back to the device in JSON format.

[0841] Step 13:

[0842] The terminal displays the received new curriculum, and the user (childcare worker) checks and adapts the content.

[0843] Example 1

[0844] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0845] Childcare workers spend a lot of time and effort creating daily childcare curricula. Furthermore, there is no efficient way to incorporate parental feedback into the curriculum, making it difficult to improve the quality of childcare. Furthermore, when automatically generating childcare curricula, it is difficult to appropriately reflect the latest childcare information and children's interests.

[0846] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0847] In this invention, the server includes means for using a generative model to automatically generate a childcare curriculum based on basic information input by a childcare worker, means for displaying the childcare curriculum generated by the generative model on the childcare worker's terminal, means for collecting feedback from parents, means for saving the feedback in a database, means for generating the next childcare curriculum taking the feedback into consideration, means for inputting basic information through a user interface, means for converting the basic information into JSON format and sending it to the server, means for returning the generated curriculum in JSON format to the terminal, means for parents to input feedback using a communication tool, and means for sending the feedback to the server in JSON format. This enables childcare workers to efficiently create curricula and provide high-quality childcare that reflects parental feedback.

[0848] A "childcare worker" is a professional who is responsible for caring for and educating children in a childcare facility.

[0849] "Basic information" refers to information necessary for creating a curriculum, such as the children's ages, interests, weather, and season.

[0850] A "childcare curriculum" is a plan of activities and education that childcare workers provide to children.

[0851] A "generative model" is an AI technique that generates new text or plans based on input prompts.

[0852] A "terminal" is a device, such as a computer or tablet, that a user uses to enter information or view results.

[0853] A "server" is a computer system that provides services to client terminals over a network.

[0854] "Feedback" refers to opinions and thoughts about their children provided by parents.

[0855] A "database" is a system for storing and managing information efficiently and safely.

[0856] A "user interface" is a component such as a screen, menu, or form that allows a user to access and operate a system.

[0857] A "prompt" is text that is input as an instruction or question to a generative model.

[0858] "JSON format" is a format for describing data in a structured text format.

[0859] "Communication means" refers to technologies and systems for sending and receiving information and data.

[0860] This invention is a system that automatically generates a childcare curriculum based on basic information entered by childcare workers, and by using a generative model, it reduces the burden on childcare workers and realizes smooth communication with parents. This system is composed of users (childcare workers and parents), terminals, a server, and a generative AI model.

[0861] Enter basic information

[0862] Users (childcare workers) use devices such as PCs and tablets to enter basic information, such as the child's age, interests, weather, and season. This basic information is entered through a web form displayed on the device or a dedicated app.

[0863] Request curriculum generation

[0864] The terminal converts the basic information entered by the user into JSON format data and sends it to the server using an HTTP request, which is built with a web framework such as Flask.

[0865] Using generative models

[0866] The server sends the received basic information in JSON format as prompts to a generative AI model (e.g., GPT-3), which then generates a new childcare curriculum based on the prompts.

[0867] Return and view curriculum

[0868] After the generative AI model generates the childcare curriculum, the generated results are sent back to the server in JSON format, which is then sent to the device, which then displays the curriculum on the user interface.

[0869] Gathering feedback from parents

[0870] Users (parents) can use a dedicated app or chatbot to input feedback, which includes opinions and reactions about their children.

[0871] Send and save feedback

[0872] The device sends the input feedback in JSON format to the server, which stores it in a database such as Firestore, so that it can take this feedback into account when generating the next curriculum.

[0873] Next curriculum generation

[0874] When generating a new curriculum, the server retrieves the stored feedback from the database and provides it to the generative model. By providing the generative model with information including the feedback as prompts, the next generated curriculum can be further customized.

[0875] Specific examples

[0876] For example, suppose a user (a nursery teacher) enters basic information such as "3-year-old child, sunny day, interest in animals." Based on this information, the prompt sent to the generative model is as follows:

[0877] Child's age: 3 years old

[0878] Weather: Sunny

[0879] Interests: Animals

[0880] Based on this prompt, the generative model generates a curriculum such as "10:00 - 11:00 Outdoor animal observation." This curriculum is displayed on the device, and the nursery teacher can review and adopt the content.

[0881] In addition, the user (parent) can input feedback such as "My child wants to go to the zoo this weekend," and this feedback is saved in the database. By providing this feedback to the generative model the next time a curriculum is generated, it will be more likely to suggest zoo-related activities.

[0882] This system allows childcare workers to create curriculums more efficiently, improving the quality of childcare. In addition, by incorporating parents' opinions into the curriculum, more individualized childcare can be achieved.

[0883] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0884] Step 1:

[0885] The user (childcare worker) uses a device such as a PC or tablet to enter basic information into a web form or dedicated app. For example, information such as "3-year-old child, sunny day, interest in animals." This input data is stored as is in the device's memory. Input: Basic information. Output: Input data in the device.

[0886] Step 2:

[0887] The terminal converts the basic information entered in step 1 into JSON format. This data conversion process uses a serialization library within the program. The converted JSON data is sent to the server as an HTTP POST request. Input: Basic information. Output: Basic information in JSON format.

[0888] Step 3:

[0889] The server receives an HTTP POST request and obtains the JSON data within it. This data is processed by an API endpoint within the server. The server parses the received basic information and sends it as a prompt to the generative AI model (e.g., GPT-3). Input: Basic information in JSON format. Output: Prompt to the generative AI model.

[0890] Step 4:

[0891] The generative AI model generates a childcare curriculum based on the prompts it receives. During this generation process, the model uses its internal neural network to analyze and generate data. The generated curriculum is sent back to the server in JSON format. Input: Prompt. Output: Childcare curriculum in JSON format.

[0892] Step 5:

[0893] The server receives the childcare curriculum in JSON format returned from the generative AI model. This data is parsed again and sent back to the device. The server sends the data as an HTTP response. Input: Childcare curriculum in JSON format. Output: HTTP response to the device.

[0894] Step 6:

[0895] The terminal analyzes the JSON formatted childcare curriculum received from the server and displays it on the user interface. This display process uses a front-end library to render the analysis results on the screen. Input: Childcare curriculum in JSON format. Output: Data displayed on the user interface.

[0896] Step 7:

[0897] The user (parent) enters feedback using a dedicated app or chatbot. The feedback includes the child's reactions and opinions. This input data is stored in the device's memory. Input: Feedback. Output: Input data in the device.

[0898] Step 8:

[0899] The terminal converts the feedback entered in step 7 into JSON format. A serialization library is used for this conversion process. The converted JSON data is sent to the server as an HTTP POST request. Input: Feedback. Output: Feedback in JSON format.

[0900] Step 9:

[0901] The server receives an HTTP POST request and retrieves JSON data within it. This data is processed by an API endpoint on the server and saved in a database such as Firestore. Input: Feedback in JSON format. Output: Data saved in the database.

[0902] Step 10:

[0903] The server retrieves the stored feedback from the database when generating a new curriculum. This retrieved data is included in the prompts provided to the generative model. Input: Feedback data from the database. Output: Updated prompts to the generative model.

[0904] Through specific operations that take into account input and output, this system can improve the work efficiency of childcare workers and effectively reflect parental feedback in the curriculum.

[0905] (Application example 1)

[0906] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0907] Efficiently and flexibly managing robot task schedules in factories requires consideration of a vast amount of work information and operating status. However, this requires a great deal of time and effort, which increases the burden on workers and managers and reduces production efficiency. In addition, it is difficult to generate an optimal schedule that takes into account real-time factors such as environmental conditions and task priorities. To solve these issues, a system that efficiently and automatically generates work schedules is needed.

[0908] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0909] In this invention, the server includes means for using a generative model to automatically generate a work schedule based on basic information entered by a manager, means for displaying the work schedule generated by the generative model on the manager's terminal, means for collecting feedback from workers, means for saving the feedback in a database, and means for generating the next work schedule taking the feedback into consideration. This reduces the burden on workers and managers and makes it possible to efficiently generate and apply optimal work schedules in real time.

[0910] An "administrator" is a person who is responsible for managing and supervising the task schedules of robots and workers in factory operations.

[0911] "Basic information" refers to data such as the type of work, priority, operating status, and work environment that must be entered by the administrator.

[0912] A "work schedule" is a specific work plan for factory robots and workers that is automatically generated based on a generative model.

[0913] A "generative model" is a system that includes an algorithm that generates an optimal work schedule based on input basic information.

[0914] A "terminal" is a device such as a computer or tablet that allows an administrator to enter basic information and check the generated work schedule.

[0915] "Feedback" refers to evaluations and opinions provided by workers and other stakeholders regarding the actual work situation and robot performance.

[0916] A "server" is a central processing unit for running generative models, processing requests from terminals, and storing feedback in a database.

[0917] A "database" is an information storage system for storing and managing feedback, basic information, etc.

[0918] A "prompt" is an instruction containing basic information entered that the generative model uses to generate a work schedule.

[0919] The "JSON format" is a text format for structuring, storing, and transmitting data, and is commonly used when exchanging data between programs.

[0920] This invention is a system for efficiently and automatically generating work schedules for robots in a factory, reducing the burden on managers and improving production efficiency. The configuration and operation of this system are described below.

[0921] 1. System Configuration

[0922] The system consists of an administrator's terminal, a server, a generative model, and a database. The hardware used includes factory PCs and tablets, as well as industrial robots. The software uses a Flask web framework, generative AI (e.g., GPT), and Firestore (Google's NoSQL database).

[0923] 2. Program processing flow and explanation

[0924] Enter basic information

[0925] Managers use terminals to enter basic information such as product type, work priority, operating status, and work environment information, etc. The information is entered through a web form or a dedicated application.

[0926] Request to generate a task schedule

[0927] The terminal converts the input basic information into JSON format and sends it to the server, which uses Flask to receive the request and begin processing.

[0928] Using generative models

[0929] The server receives the request and sends basic information as prompts to a generative model (e.g., GPT), which then generates an optimal work schedule based on the content of the prompts.

[0930] Return and view schedules

[0931] The generated schedule is sent back to the administrator's terminal in JSON format from the server. The terminal parses the returned schedule and displays it in the administrator's user interface. This allows the administrator to check and apply the generated schedule.

[0932] Feedback collection

[0933] Workers use communication tools to input feedback, which includes information about actual work results and robot performance.

[0934] Send and save feedback

[0935] The device sends feedback in JSON format to the server, which receives this feedback, stores it in Firestore, and takes this feedback into account when generating the next schedule.

[0936] Next schedule generation

[0937] When generating a new work schedule, the server retrieves relevant feedback from the database and feeds it into the generative model, which then generates a more customized schedule based on this information.

[0938] Examples of concrete examples and prompts

[0939] Specific examples

[0940] Suppose a manager inputs basic information such as "Production of Product A, high priority, machine 1, humidity 70%" and requests schedule generation. The generative model generates a task schedule such as "10:00 - 11:00 Product A Line 1, production speed 120%." This schedule is displayed on the manager's terminal, and the manager can confirm and adopt the contents.

[0941] The worker provides feedback such as "the robot's speed was appropriate" or "the operating time was short," which is then stored in Firestore. The next time the schedule is generated, the generative model takes this feedback into account and proposes an optimal task schedule.

[0942] Prompt Sentence Examples

[0943] Factory task schedule generation:

[0944] Product name: Product A

[0945] Work priority: High

[0946] Operation status: Machine 1

[0947] Working environment: 70% humidity

[0948] Feedback Consideration:

[0949] Speed: 120%

[0950] Feedback: Good

[0951] In this way, this system reduces the burden on managers and workers and enables them to efficiently manage and operate work schedules.

[0952] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0953] Step 1:

[0954] Administrator enters basic information

[0955] The administrator uses the terminal to enter basic information such as the product type, work priority, operating status, and work environment information. This information is entered through the terminal's web form or a dedicated application, and the entered information is converted into JSON format.

[0956] Input: Product type, work priority, operation status, work environment information

[0957] Output: Basic information in JSON format

[0958] Step 2:

[0959] Send basic information

[0960] The device sends the basic information entered in JSON format to the server, which uses Flask to receive the request and begin processing.

[0961] Input: Basic information in JSON format

[0962] Output: The request received by the server

[0963] Step 3:

[0964] Using generative models

[0965] The server sends the received basic information to the generative model as prompts, which the generative model (e.g., GPT) uses to generate an optimal work schedule.

[0966] Input: Basic information in JSON format, prompt statement

[0967] Output: Generated work schedule

[0968] Specific working example:

[0969] Factory task schedule generation:

[0970] Product name: Product A

[0971] Work priority: High

[0972] Operation status: Machine 1

[0973] Working environment: 70% humidity

[0974] Step 4:

[0975] Return and view schedules

[0976] The server returns the generated work schedule in JSON format to the terminal, which then analyzes the returned schedule and displays it in a user interface for administrators, allowing them to check and apply the generated schedule.

[0977] Input: Generated work schedule (JSON format)

[0978] Output: Schedule displayed on the administrator's terminal

[0979] Step 5:

[0980] Enter your feedback

[0981] Workers use communication tools to provide feedback, including evaluations and opinions on the actual work results and the robot's performance.

[0982] Input: Work results, robot performance

[0983] Output: Feedback information

[0984] Step 6:

[0985] Send and save feedback

[0986] The device sends the collected feedback in JSON format to the server, which receives this feedback and stores it in Firestore, so that it can take this feedback into account when generating the next schedule.

[0987] Input: Feedback information (JSON format)

[0988] Output: Feedback stored in Firestore

[0989] Step 7:

[0990] Next schedule generation

[0991] When generating a new work schedule, the server retrieves relevant feedback from the database (Firestore) and feeds it into the generative model, which then generates a more customized schedule based on this information.

[0992] Input: Feedback information, Basic information

[0993] Output: Next best schedule

[0994] This reduces the burden on managers and workers and makes it possible to efficiently generate and apply optimal work schedules in real time.

[0995] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0996] This system combines a generative model that automatically generates a childcare curriculum based on basic information entered by childcare workers with an emotion engine that recognizes feedback from parents and the user's emotions. This reduces the burden on childcare workers, enables smooth communication with parents, and enables the generation of an optimal childcare curriculum based on emotions.

[0997] System configuration and processing flow

[0998] 1. Enter basic information

[0999] Users (childcare workers) use devices such as PCs and tablets to enter basic information, including the children's ages, interests, weather, and seasons. Input is done through a web form or a dedicated application, and is completed by clicking the "Generate" button.

[1000] 2. Emotional Recognition

[1001] The emotion engine installed in the device recognizes the emotions of the childcare worker, and this emotion information is sent to the server along with basic information.

[1002] 3. Request for curriculum generation

[1003] The device sends basic information and emotional information in JSON format to the server, which receives the request using a web framework such as Flask.

[1004] 4. Using Generative Models

[1005] The server receives basic information and emotion information and sends it to the generative model as a prompt. This prompt takes into account the emotions of the childcare worker. The generative model generates a childcare curriculum based on the prompt and sends the result back to the server.

[1006] 5. Return and display of curriculum

[1007] The generated curriculum is sent back to the device in JSON format from the server. The device displays the curriculum on the user interface, allowing the childcare worker to review and adapt it.

[1008] 6. Gathering feedback from parents

[1009] The user (parent) enters feedback through a dedicated app or chatbot. At this time, the emotion engine also recognizes the parent's emotions. The feedback, along with the emotional information, is sent from the device to the server.

[1010] 7. Sending and Saving Feedback

[1011] The device sends the input feedback and emotion information in JSON format to the server. The server receives it, stores it in a database such as Firestore, and notifies the device that the saving is complete.

[1012] 8. Next curriculum generation

[1013] When generating a new childcare curriculum, the server retrieves relevant feedback and emotional information from the database and supplies it to the generative model. The generative model generates a new childcare curriculum that takes the feedback and emotional information into account and sends the results back to the server. The server receives this and sends it back to the device in JSON format.

[1014] Specific examples

[1015] 1. The user (childcare worker) enters basic information such as "3-year-old child, sunny day, interest in animals," and the emotion engine recognizes that the user is in a very good mood.

[1016] 2. The generative model generates a childcare curriculum such as "10:00 - 11:00 Outdoor animal observation" and recommends activities that also reflect the positive emotions of the childcare workers.

[1017] 3. This curriculum is displayed on the terminal, and the nursery school teacher confirms and adopts the contents.

[1018] 4. The user (parent) inputs feedback such as "My child wants to go to the zoo this weekend," and the emotion engine recognizes the parent's happy feelings.

[1019] 5. The feedback and parental sentiment information will be stored in a database and taken into consideration when generating the next curriculum.

[1020] 6. Next time, the generative model will take into account parents’ feedback and emotions to generate a new curriculum and recommend “zoo-related activities.”

[1021] This will provide a more personalized childcare curriculum that takes into account the user's emotions, improving the quality of childcare and increasing the work efficiency of childcare workers.

[1022] The processing flow will be explained below.

[1023] Step 1:

[1024] The user (childcare worker) uses a device such as a PC or tablet to enter basic information (child's age, interests, weather, season, etc.) into a web form or dedicated application and clicks the "Generate" button.

[1025] Step 2:

[1026] The device converts the input basic information into JSON format and simultaneously recognizes the childcare worker's emotions using an emotion engine. This emotional information is also compiled in JSON format and sent to the server.

[1027] Step 3:

[1028] The server receives basic information and emotional information from the device through a web framework such as Flask.

[1029] Step 4:

[1030] The server sends the received basic information and emotional information to the generative model as a prompt, which includes the emotional state of the caregiver (e.g., "I feel very good").

[1031] Step 5:

[1032] The generative model generates a childcare curriculum based on the prompts. The generative model analyzes the information and creates an optimal childcare curriculum based on the feelings of the childcare workers.

[1033] Step 6:

[1034] The generated childcare curriculum returned from the generative model is sent back to the server, which then sends it back to the device in JSON format.

[1035] Step 7:

[1036] The device receives the JSON data returned from the server and displays the generated curriculum on the user interface. The childcare worker can check and apply the content.

[1037] Step 8:

[1038] Users (parents) input feedback through a dedicated app or chatbot, and this feedback is recognized by the emotion engine, including the parent's emotions (e.g., happy feelings).

[1039] Step 9:

[1040] The device converts the input feedback and emotion information into JSON format and sends it to the server using the HTTP POST method.

[1041] Step 10:

[1042] The server receives the feedback and emotion information, stores it in a database such as Firestore, and notifies the device once the storage is complete.

[1043] Step 11:

[1044] When generating the next curriculum, the server retrieves the relevant feedback and emotion information from the database and sends it to the generative model as a prompt, which includes the new basic information, the previous feedback, and the parent's emotion information.

[1045] Step 12:

[1046] The generative model takes into account the feedback and emotional information to generate a new childcare curriculum and sends it back to the server, which then receives it and sends it back to the device in JSON format.

[1047] Step 13:

[1048] The terminal displays the received new curriculum, and the user (childcare worker) checks and applies the contents.

[1049] Specifically, a childcare worker inputs basic information such as "3-year-old child, sunny day, interest in animals," and the emotion engine recognizes that the childcare worker is in a "very good mood." The generative model then generates a curriculum of "10:00 - 11:00 outdoor animal observation" and recommends activities that reflect the childcare worker's good mood. Similarly, if a parent inputs feedback such as "my child wants to go to the zoo this weekend" and recognizes that the child is in a happy mood, this information will be taken into account when generating the next curriculum, and "zoo-related activities" will be recommended.

[1050] This provides a more personalized childcare curriculum that takes into account the user's emotions.

[1051] Example 2

[1052] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1053] Conventional childcare curriculum generation systems were unable to consider the emotions of childcare workers or the feedback of parents, and instead created a uniform curriculum. This placed a heavy burden on childcare workers and made communication with parents difficult. Furthermore, because the curriculum did not reflect the interests and emotions of individual children, it was difficult to improve the quality of childcare.

[1054] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1055] In this invention, the server includes a means for using a terminal equipped with an emotion engine that recognizes the emotions of childcare workers, a means for recognizing feedback from parents and their emotions, and a means for storing the feedback from parents and emotion information in a database. This makes it possible to generate an individually optimized childcare curriculum that takes into account the emotions of childcare workers and the feedback and emotion information from parents.

[1056] "Basic information" refers to data entered by childcare workers, such as children's ages, interests, weather, and seasons.

[1057] A "generative model" refers to an artificial intelligence algorithm that automatically generates a childcare curriculum based on input basic information and emotional information.

[1058] "Emotion engine" refers to software or a device that recognizes and analyzes the emotions of childcare workers and parents.

[1059] "Devices" refers to electronic devices such as PCs, tablets, and smartphones used by childcare workers and parents.

[1060] "Feedback" refers to opinions, requests, and impressions from parents.

[1061] "Database" refers to an electronic information storage system for storing feedback, emotional information, etc.

[1062] A "prompt" refers to input data that provides basic and emotional information to a generative model.

[1063] "JSON format" refers to a text-based data exchange format that expresses data concisely and in a highly readable manner.

[1064] This invention is a system that automatically generates an optimal childcare curriculum based on basic information and emotional information entered by childcare workers. The purpose of this system is to reduce the burden on childcare workers, facilitate communication with parents, and provide individually optimized childcare curricula.

[1065] Enter basic information

[1066] Users (childcare workers) enter basic information using devices such as PCs or tablets. For example, they can open a dedicated application or web form and enter information such as the children's ages, interests, weather, and season. Once the information is complete, they click the "Generate" button, and the information is saved on the device.

[1067] Emotion recognition

[1068] The device is equipped with an emotion engine that recognizes the emotions of the childcare worker. This engine uses sensor devices such as cameras and microphones to analyze emotions from the childcare worker's facial expressions and tone of voice. For example, if the childcare worker's facial expression is smiling, the emotion engine will determine that the childcare worker is in a "very good mood." This emotion information is sent to the server along with basic information.

[1069] Request curriculum generation

[1070] The device sends basic information and emotional information to the server in JSON format. The device uses a web framework such as Flask to send this data to the server as an HTTP request. Specific examples of transmitted data include the following formats:

[1071] {

[1072] "age": "3 years old",

[1073] "Interests": "Animals",

[1074] "Weather": "Sunny",

[1075] "season": "spring",

[1076] "Childcare worker's feelings": "I feel very good"

[1077] }

[1078] Using generative models

[1079] The server analyzes the received basic information and emotional information and sends it as prompts to the generative AI model. The generative AI model automatically generates a childcare curriculum based on this information. For example, given prompts such as "The childcare worker is in a good mood," "For 3-year-olds," "It's a sunny day," and "Interested in animals," the generative AI model generates a curriculum such as "10:00 - 11:00 Outdoor animal observation."

[1080] Return and view curriculum

[1081] The generated childcare curriculum is sent back to the device in JSON format from the server. The device's dedicated application or web application parses this JSON data and displays the curriculum content on the user interface. Childcare workers can check the content and adjust it as necessary. For example, the following display content is possible:

[1082] 10:00 - 11:00 Outdoor animal observation

[1083] 11:00 - 12:00 Indoor animal picture book reading

[1084] Gathering feedback from parents

[1085] Users (parents) input feedback using a dedicated app or chatbot. During this input process, the emotion engine analyzes the parent's emotions. For example, if a parent inputs "My child wants to go to the zoo this weekend" and looks happy while doing so, the emotion engine will recognize this as "feeling happy."

[1086] Send and save feedback

[1087] The device sends parental feedback and emotional information in JSON format to the server. The server receives the data and stores it in a database such as Firestore. Once the data is saved, a notification of success is displayed on the device.

[1088] Next curriculum generation

[1089] When generating a new childcare curriculum, the server retrieves previously saved feedback and emotional information from the database and supplies it to the generative AI model. This makes it possible to generate a more optimal childcare curriculum that takes past feedback and emotions into account. The generative AI model generates a new curriculum based on this information and sends the results back to the server. The server receives this and sends it back to the device in JSON format, which then displays it.

[1090] As described above, the system of the present invention effectively utilizes the emotions of childcare workers and feedback from parents to provide individually optimized childcare curricula, thereby improving the work efficiency of childcare workers and the quality of childcare.

[1091] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1092] Step 1:

[1093] The user (childcare worker) uses a device such as a PC or tablet to enter basic information. This basic information includes the children's ages, interests, weather, season, etc. This basic information is entered through a dedicated application or web form. Once the entry is complete, the user clicks the "Generate" button, and the basic information is sent to the device. Specific data is entered using text boxes and drop-down menus, and the basic information is saved on the device as output.

[1094] Step 2:

[1095] The device's emotion engine recognizes the emotions of the childcare worker through sensor devices such as cameras and microphones. For example, if a childcare worker is smiling while entering information, the emotion engine will analyze this and recognize it as a "very good mood." This emotional information is then stored directly on the device.

[1096] Step 3:

[1097] The device sends the basic information entered by the childcare worker and the recognized emotional information to the server in JSON format. The device uses a web framework such as Flask to send this data to the server as an HTTP request. The following JSON format is used as an example of specific data to be sent. The basic information and emotional information are used as input, and the output is sent to the server in JSON format.

[1098] {

[1099] "age": "3 years old",

[1100] "Interests": "Animals",

[1101] "Weather": "Sunny",

[1102] "season": "spring",

[1103] "Childcare worker's feelings": "I feel very good"

[1104] }

[1105] Step 4:

[1106] The server analyzes the received basic information and emotional information and sends it as a prompt to the generative AI model. The generative AI model automatically generates a childcare curriculum based on this information. For example, given prompts such as "The childcare worker is in a good mood," "For 3-year-olds," "It's a sunny day," and "Interested in animals," the generative AI model generates a curriculum such as "10:00 - 11:00 Outdoor animal observation." In this step, the server receives the basic information and emotional information as input and obtains an output that sends a prompt to the generative AI model.

[1107] Step 5:

[1108] The generated childcare curriculum is sent from the server to the device again in JSON format. A dedicated application or web application on the device parses this JSON data and displays the curriculum content on the user interface. For example, a curriculum such as "10:00 - 11:00 Outdoor animal observation" is displayed, allowing childcare workers to review the content and adjust it as necessary. In this step, the output of the generative AI model (childcare curriculum) is sent to the device in JSON format, where it is parsed and displayed.

[1109] Step 6:

[1110] The user (parent) inputs feedback using a dedicated app or chatbot. During this input process, the emotion engine analyzes the parent's emotions. For example, if the parent inputs "My child wants to go to the zoo this weekend" and has a happy expression while doing so, the emotion engine will recognize this as "a happy feeling." In this step, feedback and emotional information are input and saved as output on the device.

[1111] Step 7:

[1112] The device sends the parent's feedback and emotion information in JSON format to the server. The server receives this and stores it in a database such as Firestore. Once the storage is complete, a notification of successful storage is displayed on the device. In this step, the input feedback and emotion information are sent to the server, and the output is stored in a database.

[1113] Step 8:

[1114] When generating a new childcare curriculum, the server retrieves previously saved feedback and emotional information from the database and supplies it to the generative AI model. This allows for the generation of a more optimal childcare curriculum that takes past feedback and emotions into account. For example, a childcare curriculum that suggests "zoo-related activities" based on parental feedback may be generated. In this step, past feedback and emotional information are input, and the generative AI model outputs a newly generated childcare curriculum.

[1115] (Application example 2)

[1116] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1117] In childcare operations such as automatically generating childcare curricula and collecting feedback, there are issues related to reducing the burden on childcare workers and smooth communication with parents.In addition, there is a need to improve the efficiency of sales promotion activities and customer satisfaction by making optimal product suggestions based on basic information and emotional information of customers in physical stores.

[1118] The specific processing 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 means for using a generative model to automatically generate a childcare curriculum based on basic information input by a childcare worker, means for displaying the childcare curriculum generated by the generative model on the childcare worker's terminal, means for collecting feedback from parents, means for storing the feedback in a database, means for generating the next childcare curriculum taking the feedback into consideration, means for using a generative model to generate optimal product proposals based on basic information and emotional information of customers, and means for displaying the generated product proposals on the salesperson's terminal. This reduces the workload of childcare workers, facilitates communication with parents, and further enables more efficient sales promotion activities in physical stores and improved customer satisfaction.

[1119] A "childcare worker" refers to a person whose occupation is to specialize in caring for infants and children.

[1120] "Basic information" refers to basic information about the user or subject that is entered into the system, such as age, interests, weather, and season.

[1121] A "generative model" refers to an artificial intelligence model that automatically generates outputs suitable for a specific purpose based on input data.

[1122] "Terminal" refers to an electronic device for inputting, outputting, and processing information, and includes smartphones, tablets, PCs, etc.

[1123] "Feedback" refers to opinions expressed by users of the system, such as their impressions after using it and areas for improvement.

[1124] A "database" refers to a collection of data that is systematically organized and stored so that it can be searched and used as needed.

[1125] A "server" refers to a computer system that provides services to clients over a network.

[1126] "Childcare curriculum" refers to programs and schedules for systematically carrying out childcare activities for infants and young children.

[1127] "Salesperson" refers to the staff in charge of selling products in physical stores, etc.

[1128] "Basic information and emotional information" refers to basic data about the customer as well as information that indicates their emotional state at the time.

[1129] "Product Recommendations" refers to products or services recommended based on a customer's interests and needs.

[1130] "JSON format" is a data exchange format, an abbreviation for JavaScript Object Notation, and refers to a method of expressing data in text format.

[1131] This system combines a generative model that automatically generates a childcare curriculum based on basic information entered by childcare workers with an emotion engine that recognizes feedback from parents and the user's emotions. It can also be applied to a system in brick-and-mortar stores that allows sales staff to recommend optimal products to customers based on their basic and emotional information.

[1132] The system's program exchanges information between the server and the device, and generates childcare curriculum and product proposals using a generative model and emotion engine. The main hardware used includes the server, smartphones, tablets, PCs, and other devices. The main software used includes web frameworks such as Flask, emotion engines, and generative models.

[1133] The server receives the basic information and emotional information entered by the nursery teacher, or the basic information and emotional information of the customer entered by the salesperson. This information is sent from the device in JSON format and stored in a database on the server. The database can be something like Firestore.

[1134] The server sends a prompt to the generative model based on the received basic information and emotion information. This prompt includes specific input data and instructions based on that data. For example, the following prompt sentence could be considered:

[1135] "Customer basic information: Interests - Healthy foods, Previous purchases - Protein bars, Product viewed in store - Vitamin supplements. Currently, the customer is smiling. Generate optimal product suggestions based on this."

[1136] The generative model generates optimal childcare curriculum and product recommendations based on the input prompts and sends the results back to the server. This information is then sent back to the device in JSON format and displayed on the device screen.

[1137] As a specific example, if a nursery teacher inputs basic information such as "3-year-old child, sunny day, interest in animals" and the emotion engine recognizes that the nursery teacher is in a good mood, the generative model will generate a nursery curriculum of "10:00 - 11:00 outdoor animal observation." Similarly, if a salesperson inputs basic information such as "interests: health foods, past purchases: protein bars, products viewed in the store: vitamin supplements" and the generative model recognizes that the customer is smiling, the generative model will generate suggestions such as "introduction to vitamin supplements" and "suggestion for new protein bar products."

[1138] The childcare curriculum and product proposals generated in this way are displayed on the devices of childcare workers and sales staff, allowing users to check and adapt them. Feedback from parents and customers is also sent from the devices to the server and used for the next generation. This system reduces the workload of childcare workers, facilitates communication with parents, and also makes sales promotion activities in physical stores more efficient and improves customer satisfaction.

[1139] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1140] Step 1:

[1141] The user (childcare worker or salesperson) enters basic information using a device (smartphone, tablet, PC, etc.). For childcare workers, basic information includes the child's age, interests, weather, season, etc. For salespeople, basic information includes the customer's interests, past purchase history, current situation, etc. The entered basic information is temporarily saved on the device.

[1142] Step 2:

[1143] The device uses a camera and microphone to capture the facial expressions and voice of the user or customer. The emotion engine analyzes this captured data and recognizes the user's emotions. The recognized emotion information is collected on the device along with basic information.

[1144] Step 3:

[1145] The device converts the collected basic information and emotional information into JSON format and sends it to the server. For example, JSON format data might include "Age: 3 years old, Interests: Animals, Weather: Sunny, Emotion: Good." The sent data is then received by the server.

[1146] Step 4:

[1147] The server generates a prompt based on the received basic information and emotion information and sends it to the generative model. For example, the prompt may contain information such as "3-year-old child, sunny day, interest in animals, and good emotion of the caregiver." The prompt is sent in a format that the generative model can understand.

[1148] Step 5:

[1149] The generative model calculates data based on the input prompts and generates optimal childcare curriculum and product suggestions. For example, it generates a childcare curriculum of "10:00 - 11:00 Outdoor animal observation" and a product suggestion of "Introduction to vitamin supplements." This generated information is sent back to the server.

[1150] Step 6:

[1151] The server receives the childcare curriculum and product suggestions returned by the generative model and converts them into JSON format. The converted data is then sent to the device, which parses the received JSON data and displays it on the user interface.

[1152] Step 7:

[1153] The user (childcare worker or salesperson) checks the childcare curriculum and product suggestions displayed on the terminal, implements them, and inputs any feedback they may have about the implementation through the terminal.

[1154] Step 8:

[1155] The device converts the user feedback back into JSON format and sends it to the server, which stores the received feedback in a database. This stored feedback is used as information for generating the next curriculum and product proposals.

[1156] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1157] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1158] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1159] [Fourth embodiment]

[1160] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1161] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1162] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1163] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1164] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1165] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1166] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1167] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1168] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1169] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1170] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1171] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1172] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1173] This invention is a system that automatically generates a childcare curriculum based on basic information entered by childcare workers. This system uses a generative model to reduce the burden on childcare workers and achieve smooth communication with parents.

[1174] System configuration and processing flow

[1175] 1. Enter basic information

[1176] Users (childcare workers) use devices such as PCs and tablets to input basic information, such as the children's ages, interests, weather, and season. This information is entered through a web form or dedicated application on the device.

[1177] 2. Request for curriculum generation

[1178] The device sends the basic information entered in JSON format to the server, which is built using a web framework such as Flask and receives the request.

[1179] 3. Use of generative models

[1180] The server receives the request and sends basic information as a prompt to the generative model. Based on the content of this prompt, the generative model generates a childcare curriculum. For example, GPT, a generative AI, is used as the generative model.

[1181] 4. Return and display of curriculum

[1182] The generated curriculum is sent back to the device in JSON format from the server. The device analyzes the curriculum and displays it on a user interface for childcare workers. This allows the childcare workers to check and adapt the generated curriculum.

[1183] 5. Gathering feedback from parents

[1184] Users (parents) use communication tools (such as dedicated apps or chatbots) to input feedback, which includes the parents' opinions and insights about their children.

[1185] 6. Sending and Saving Feedback

[1186] The device sends feedback in JSON format to the server, which receives the feedback, stores it in a database such as Firestore, and takes it into account when generating the next curriculum.

[1187] 7. Next curriculum generation

[1188] When generating a new childcare curriculum, the server retrieves relevant feedback from the database and provides it to the generative model, allowing for the generation of a more customized childcare curriculum based on this information and other information.

[1189] Specific examples

[1190] 1. The user (childcare worker) enters basic information such as "3-year-old child, sunny day, interest in animals" and requests curriculum generation.

[1191] 2. The generative model generates a curriculum such as "10:00 - 11:00 Outdoor animal observation."

[1192] 3. This curriculum is displayed on the terminal, and the nursery school teacher confirms and adopts the contents.

[1193] 4. The user (parent) enters feedback such as "My child wants to go to the zoo this weekend," which is saved in the database.

[1194] 5. The next time the curriculum is generated, the generative model will take the stored feedback into account and suggest zoo-related activities.

[1195] This system will provide a curriculum that is closer to the interests of children and will also allow childcare to be provided in a way that reflects the opinions of parents, thereby improving the quality of childcare and streamlining the work of childcare workers.

[1196] The processing flow will be explained below.

[1197] Step 1:

[1198] The user (childcare worker) enters basic information about the children (age, interests, weather, season, etc.) through a web form or dedicated application on their device (PC or tablet) and clicks the "Generate" button.

[1199] Step 2:

[1200] The device sends the entered basic information to the server in JSON format using the HTTP POST method.

[1201] Step 3:

[1202] The server receives the request using a web framework such as Flask, which includes basic information entered by the childcare worker.

[1203] Step 4:

[1204] The server then sends the received basic information to a generative AI model (e.g., GPT) as a prompt. This prompt contains the basic information and instructs the generation of a curriculum.

[1205] Step 5:

[1206] The generative model generates a childcare curriculum based on the received prompts, and the generated curriculum is sent back to the server in text format.

[1207] Step 6:

[1208] The server converts the childcare curriculum returned from the generative model into JSON format and returns it to the device using an HTTP response.

[1209] Step 7:

[1210] The device receives the JSON data returned from the server and displays it on the user interface, allowing childcare workers to check the generated curriculum.

[1211] Step 8:

[1212] Users (parents) input and send feedback (e.g., "My child wants to go to the zoo") via a dedicated app or chatbot.

[1213] Step 9:

[1214] The device sends the input feedback in JSON format to the server, and this request is also made using the HTTP POST method.

[1215] Step 10:

[1216] The server saves the received feedback in a database such as Firestore, and notifies the device that the saving is complete.

[1217] Step 11:

[1218] The next time a curriculum is generated, the server retrieves the relevant feedback from the database and again sends a prompt to the generative model, this time containing the new basic information and the previous feedback.

[1219] Step 12:

[1220] The generative model generates a new childcare curriculum that takes the feedback into account and sends it back to the server, which then receives it and sends it back to the device in JSON format.

[1221] Step 13:

[1222] The terminal displays the received new curriculum, and the user (childcare worker) checks and adapts the content.

[1223] Example 1

[1224] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1225] Childcare workers spend a lot of time and effort creating daily childcare curricula. Furthermore, there is no efficient way to incorporate parental feedback into the curriculum, making it difficult to improve the quality of childcare. Furthermore, when automatically generating childcare curricula, it is difficult to appropriately reflect the latest childcare information and children's interests.

[1226] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1227] In this invention, the server includes means for using a generative model to automatically generate a childcare curriculum based on basic information input by a childcare worker, means for displaying the childcare curriculum generated by the generative model on the childcare worker's terminal, means for collecting feedback from parents, means for saving the feedback in a database, means for generating the next childcare curriculum taking the feedback into consideration, means for inputting basic information through a user interface, means for converting the basic information into JSON format and sending it to the server, means for returning the generated curriculum in JSON format to the terminal, means for parents to input feedback using a communication tool, and means for sending the feedback to the server in JSON format. This enables childcare workers to efficiently create curricula and provide high-quality childcare that reflects parental feedback.

[1228] A "childcare worker" is a professional who is responsible for caring for and educating children in a childcare facility.

[1229] "Basic information" refers to information necessary for creating a curriculum, such as the children's ages, interests, weather, and season.

[1230] A "childcare curriculum" is a plan of activities and education that childcare workers provide to children.

[1231] A "generative model" is an AI technique that generates new text or plans based on input prompts.

[1232] A "terminal" is a device, such as a computer or tablet, that a user uses to enter information or view results.

[1233] A "server" is a computer system that provides services to client terminals over a network.

[1234] "Feedback" refers to opinions and thoughts about their children provided by parents.

[1235] A "database" is a system for storing and managing information efficiently and safely.

[1236] A "user interface" is a component such as a screen, menu, or form that allows a user to access and operate a system.

[1237] A "prompt" is text that is input as an instruction or question to a generative model.

[1238] "JSON format" is a format for describing data in a structured text format.

[1239] "Communication means" refers to technologies and systems for sending and receiving information and data.

[1240] This invention is a system that automatically generates a childcare curriculum based on basic information entered by childcare workers, and by using a generative model, it reduces the burden on childcare workers and realizes smooth communication with parents. This system is composed of users (childcare workers and parents), terminals, a server, and a generative AI model.

[1241] Enter basic information

[1242] Users (childcare workers) use devices such as PCs and tablets to enter basic information, such as the child's age, interests, weather, and season. This basic information is entered through a web form displayed on the device or a dedicated app.

[1243] Request curriculum generation

[1244] The terminal converts the basic information entered by the user into JSON format data and sends it to the server using an HTTP request, which is built with a web framework such as Flask.

[1245] Using generative models

[1246] The server sends the received basic information in JSON format as prompts to a generative AI model (e.g., GPT-3), which then generates a new childcare curriculum based on the prompts.

[1247] Return and view curriculum

[1248] After the generative AI model generates the childcare curriculum, the generated results are sent back to the server in JSON format, which is then sent to the device, which then displays the curriculum on the user interface.

[1249] Gathering feedback from parents

[1250] Users (parents) can use a dedicated app or chatbot to input feedback, which includes opinions and reactions about their children.

[1251] Send and save feedback

[1252] The device sends the input feedback in JSON format to the server, which stores it in a database such as Firestore, so that it can take this feedback into account when generating the next curriculum.

[1253] Next curriculum generation

[1254] When generating a new curriculum, the server retrieves the stored feedback from the database and provides it to the generative model. By providing the generative model with information including the feedback as prompts, the next generated curriculum can be further customized.

[1255] Specific examples

[1256] For example, suppose a user (a nursery teacher) enters basic information such as "3-year-old child, sunny day, interest in animals." Based on this information, the prompt sent to the generative model is as follows:

[1257] Child's age: 3 years old

[1258] Weather: Sunny

[1259] Interests: Animals

[1260] Based on this prompt, the generative model generates a curriculum such as "10:00 - 11:00 Outdoor animal observation." This curriculum is displayed on the device, and the nursery teacher can review and adopt the content.

[1261] In addition, the user (parent) can input feedback such as "My child wants to go to the zoo this weekend," and this feedback is saved in the database. By providing this feedback to the generative model the next time a curriculum is generated, it will be more likely to suggest zoo-related activities.

[1262] This system allows childcare workers to create curriculums more efficiently, improving the quality of childcare. In addition, by incorporating parents' opinions into the curriculum, more individualized childcare can be achieved.

[1263] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1264] Step 1:

[1265] The user (childcare worker) uses a device such as a PC or tablet to enter basic information into a web form or dedicated app. For example, information such as "3-year-old child, sunny day, interest in animals." This input data is stored as is in the device's memory. Input: Basic information. Output: Input data in the device.

[1266] Step 2:

[1267] The terminal converts the basic information entered in step 1 into JSON format. This data conversion process uses a serialization library within the program. The converted JSON data is sent to the server as an HTTP POST request. Input: Basic information. Output: Basic information in JSON format.

[1268] Step 3:

[1269] The server receives an HTTP POST request and obtains the JSON data within it. This data is processed by an API endpoint within the server. The server parses the received basic information and sends it as a prompt to the generative AI model (e.g., GPT-3). Input: Basic information in JSON format. Output: Prompt to the generative AI model.

[1270] Step 4:

[1271] The generative AI model generates a childcare curriculum based on the prompts it receives. During this generation process, the model uses its internal neural network to analyze and generate data. The generated curriculum is sent back to the server in JSON format. Input: Prompt. Output: Childcare curriculum in JSON format.

[1272] Step 5:

[1273] The server receives the childcare curriculum in JSON format returned from the generative AI model. This data is parsed again and sent back to the device. The server sends the data as an HTTP response. Input: Childcare curriculum in JSON format. Output: HTTP response to the device.

[1274] Step 6:

[1275] The terminal analyzes the JSON formatted childcare curriculum received from the server and displays it on the user interface. This display process uses a front-end library to render the analysis results on the screen. Input: Childcare curriculum in JSON format. Output: Data displayed on the user interface.

[1276] Step 7:

[1277] The user (parent) enters feedback using a dedicated app or chatbot. The feedback includes the child's reactions and opinions. This input data is stored in the device's memory. Input: Feedback. Output: Input data in the device.

[1278] Step 8:

[1279] The terminal converts the feedback entered in step 7 into JSON format. A serialization library is used for this conversion process. The converted JSON data is sent to the server as an HTTP POST request. Input: Feedback. Output: Feedback in JSON format.

[1280] Step 9:

[1281] The server receives an HTTP POST request and retrieves JSON data within it. This data is processed by an API endpoint on the server and saved in a database such as Firestore. Input: Feedback in JSON format. Output: Data saved in the database.

[1282] Step 10:

[1283] The server retrieves the stored feedback from the database when generating a new curriculum. This retrieved data is included in the prompts provided to the generative model. Input: Feedback data from the database. Output: Updated prompts to the generative model.

[1284] Through specific operations that take into account input and output, this system can improve the work efficiency of childcare workers and effectively reflect parental feedback in the curriculum.

[1285] (Application example 1)

[1286] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1287] Efficiently and flexibly managing robot task schedules in factories requires consideration of a vast amount of work information and operating status. However, this requires a great deal of time and effort, which increases the burden on workers and managers and reduces production efficiency. In addition, it is difficult to generate an optimal schedule that takes into account real-time factors such as environmental conditions and task priorities. To solve these issues, a system that efficiently and automatically generates work schedules is needed.

[1288] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1289] In this invention, the server includes means for using a generative model to automatically generate a work schedule based on basic information entered by a manager, means for displaying the work schedule generated by the generative model on the manager's terminal, means for collecting feedback from workers, means for saving the feedback in a database, and means for generating the next work schedule taking the feedback into consideration. This reduces the burden on workers and managers and makes it possible to efficiently generate and apply optimal work schedules in real time.

[1290] An "administrator" is a person who is responsible for managing and supervising the task schedules of robots and workers in factory operations.

[1291] "Basic information" refers to data such as the type of work, priority, operating status, and work environment that must be entered by the administrator.

[1292] A "work schedule" is a specific work plan for factory robots and workers that is automatically generated based on a generative model.

[1293] A "generative model" is a system that includes an algorithm that generates an optimal work schedule based on input basic information.

[1294] A "terminal" is a device such as a computer or tablet that allows an administrator to enter basic information and check the generated work schedule.

[1295] "Feedback" refers to evaluations and opinions provided by workers and other stakeholders regarding the actual work situation and robot performance.

[1296] A "server" is a central processing unit for running generative models, processing requests from terminals, and storing feedback in a database.

[1297] A "database" is an information storage system for storing and managing feedback, basic information, etc.

[1298] A "prompt" is an instruction containing basic information entered that the generative model uses to generate a work schedule.

[1299] The "JSON format" is a text format for structuring, storing, and transmitting data, and is commonly used when exchanging data between programs.

[1300] This invention is a system for efficiently and automatically generating work schedules for robots in a factory, reducing the burden on managers and improving production efficiency. The configuration and operation of this system are described below.

[1301] 1. System Configuration

[1302] The system consists of an administrator's terminal, a server, a generative model, and a database. The hardware used includes factory PCs and tablets, as well as industrial robots. The software uses a Flask web framework, generative AI (e.g., GPT), and Firestore (Google's NoSQL database).

[1303] 2. Program processing flow and explanation

[1304] Enter basic information

[1305] Managers use terminals to enter basic information such as product type, work priority, operating status, and work environment information, etc. The information is entered through a web form or a dedicated application.

[1306] Request to generate a task schedule

[1307] The terminal converts the input basic information into JSON format and sends it to the server, which uses Flask to receive the request and begin processing.

[1308] Using generative models

[1309] The server receives the request and sends basic information as prompts to a generative model (e.g., GPT), which then generates an optimal work schedule based on the content of the prompts.

[1310] Return and view schedules

[1311] The generated schedule is sent back to the administrator's terminal in JSON format from the server. The terminal parses the returned schedule and displays it in the administrator's user interface. This allows the administrator to check and apply the generated schedule.

[1312] Feedback collection

[1313] Workers use communication tools to input feedback, which includes information about actual work results and robot performance.

[1314] Send and save feedback

[1315] The device sends feedback in JSON format to the server, which receives this feedback, stores it in Firestore, and takes this feedback into account when generating the next schedule.

[1316] Next schedule generation

[1317] When generating a new work schedule, the server retrieves relevant feedback from the database and feeds it into the generative model, which then generates a more customized schedule based on this information.

[1318] Examples of concrete examples and prompts

[1319] Specific examples

[1320] Suppose a manager inputs basic information such as "Production of Product A, high priority, machine 1, humidity 70%" and requests schedule generation. The generative model generates a task schedule such as "10:00 - 11:00 Product A Line 1, production speed 120%." This schedule is displayed on the manager's terminal, and the manager can confirm and adopt the contents.

[1321] The worker provides feedback such as "the robot's speed was appropriate" or "the operating time was short," which is then stored in Firestore. The next time the schedule is generated, the generative model takes this feedback into account and proposes an optimal task schedule.

[1322] Prompt Sentence Examples

[1323] Factory task schedule generation:

[1324] Product name: Product A

[1325] Work priority: High

[1326] Operation status: Machine 1

[1327] Working environment: 70% humidity

[1328] Feedback Consideration:

[1329] Speed: 120%

[1330] Feedback: Good

[1331] In this way, this system reduces the burden on managers and workers and enables them to efficiently manage and operate work schedules.

[1332] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1333] Step 1:

[1334] Administrator enters basic information

[1335] The administrator uses the terminal to enter basic information such as the product type, work priority, operating status, and work environment information. This information is entered through the terminal's web form or a dedicated application, and the entered information is converted into JSON format.

[1336] Input: Product type, work priority, operation status, work environment information

[1337] Output: Basic information in JSON format

[1338] Step 2:

[1339] Send basic information

[1340] The device sends the basic information entered in JSON format to the server, which uses Flask to receive the request and begin processing.

[1341] Input: Basic information in JSON format

[1342] Output: The request received by the server

[1343] Step 3:

[1344] Using generative models

[1345] The server sends the received basic information to the generative model as prompts, which the generative model (e.g., GPT) uses to generate an optimal work schedule.

[1346] Input: Basic information in JSON format, prompt statement

[1347] Output: Generated work schedule

[1348] Specific working example:

[1349] Factory task schedule generation:

[1350] Product name: Product A

[1351] Work priority: High

[1352] Operation status: Machine 1

[1353] Working environment: 70% humidity

[1354] Step 4:

[1355] Return and view schedules

[1356] The server returns the generated work schedule in JSON format to the terminal, which then analyzes the returned schedule and displays it in a user interface for administrators, allowing them to check and apply the generated schedule.

[1357] Input: Generated work schedule (JSON format)

[1358] Output: Schedule displayed on the administrator's terminal

[1359] Step 5:

[1360] Enter your feedback

[1361] Workers use communication tools to provide feedback, including evaluations and opinions on the actual work results and the robot's performance.

[1362] Input: Work results, robot performance

[1363] Output: Feedback information

[1364] Step 6:

[1365] Send and save feedback

[1366] The device sends the collected feedback in JSON format to the server, which receives this feedback and stores it in Firestore, so that it can take this feedback into account when generating the next schedule.

[1367] Input: Feedback information (JSON format)

[1368] Output: Feedback stored in Firestore

[1369] Step 7:

[1370] Next schedule generation

[1371] When generating a new work schedule, the server retrieves relevant feedback from the database (Firestore) and feeds it into the generative model, which then generates a more customized schedule based on this information.

[1372] Input: Feedback information, Basic information

[1373] Output: Next best schedule

[1374] This reduces the burden on managers and workers and makes it possible to efficiently generate and apply optimal work schedules in real time.

[1375] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1376] This system combines a generative model that automatically generates a childcare curriculum based on basic information entered by childcare workers with an emotion engine that recognizes feedback from parents and the user's emotions. This reduces the burden on childcare workers, enables smooth communication with parents, and enables the generation of an optimal childcare curriculum based on emotions.

[1377] System configuration and processing flow

[1378] 1. Enter basic information

[1379] Users (childcare workers) use devices such as PCs and tablets to enter basic information, including the children's ages, interests, weather, and seasons. Input is done through a web form or a dedicated application, and is completed by clicking the "Generate" button.

[1380] 2. Emotional Recognition

[1381] The emotion engine installed in the device recognizes the emotions of the childcare worker, and this emotion information is sent to the server along with basic information.

[1382] 3. Request for curriculum generation

[1383] The device sends basic information and emotional information in JSON format to the server, which receives the request using a web framework such as Flask.

[1384] 4. Using Generative Models

[1385] The server receives basic information and emotion information and sends it to the generative model as a prompt. This prompt takes into account the emotions of the childcare worker. The generative model generates a childcare curriculum based on the prompt and sends the result back to the server.

[1386] 5. Return and display of curriculum

[1387] The generated curriculum is sent back to the device in JSON format from the server. The device displays the curriculum on the user interface, allowing the childcare worker to review and adapt it.

[1388] 6. Gathering feedback from parents

[1389] The user (parent) enters feedback through a dedicated app or chatbot. At this time, the emotion engine also recognizes the parent's emotions. The feedback, along with the emotional information, is sent from the device to the server.

[1390] 7. Sending and Saving Feedback

[1391] The device sends the input feedback and emotion information in JSON format to the server. The server receives it, stores it in a database such as Firestore, and notifies the device that the saving is complete.

[1392] 8. Next curriculum generation

[1393] When generating a new childcare curriculum, the server retrieves relevant feedback and emotional information from the database and supplies it to the generative model. The generative model generates a new childcare curriculum that takes the feedback and emotional information into account and sends the results back to the server. The server receives this and sends it back to the device in JSON format.

[1394] Specific examples

[1395] 1. The user (childcare worker) enters basic information such as "3-year-old child, sunny day, interest in animals," and the emotion engine recognizes that the user is in a very good mood.

[1396] 2. The generative model generates a childcare curriculum such as "10:00 - 11:00 Outdoor animal observation" and recommends activities that also reflect the positive emotions of the childcare workers.

[1397] 3. This curriculum is displayed on the terminal, and the nursery school teacher confirms and adopts the contents.

[1398] 4. The user (parent) inputs feedback such as "My child wants to go to the zoo this weekend," and the emotion engine recognizes the parent's happy feelings.

[1399] 5. The feedback and parental sentiment information will be stored in a database and taken into consideration when generating the next curriculum.

[1400] 6. Next time, the generative model will take into account parents’ feedback and emotions to generate a new curriculum and recommend “zoo-related activities.”

[1401] This will provide a more personalized childcare curriculum that takes into account the user's emotions, improving the quality of childcare and increasing the work efficiency of childcare workers.

[1402] The processing flow will be explained below.

[1403] Step 1:

[1404] The user (childcare worker) uses a device such as a PC or tablet to enter basic information (child's age, interests, weather, season, etc.) into a web form or dedicated application and clicks the "Generate" button.

[1405] Step 2:

[1406] The device converts the input basic information into JSON format and simultaneously recognizes the childcare worker's emotions using an emotion engine. This emotional information is also compiled in JSON format and sent to the server.

[1407] Step 3:

[1408] The server receives basic information and emotional information from the device through a web framework such as Flask.

[1409] Step 4:

[1410] The server sends the received basic information and emotional information to the generative model as a prompt, which includes the emotional state of the caregiver (e.g., "I feel very good").

[1411] Step 5:

[1412] The generative model generates a childcare curriculum based on the prompts. The generative model analyzes the information and creates an optimal childcare curriculum based on the feelings of the childcare workers.

[1413] Step 6:

[1414] The generated childcare curriculum returned from the generative model is sent back to the server, which then sends it back to the device in JSON format.

[1415] Step 7:

[1416] The device receives the JSON data returned from the server and displays the generated curriculum on the user interface. The childcare worker can check and apply the content.

[1417] Step 8:

[1418] Users (parents) input feedback through a dedicated app or chatbot, and this feedback is recognized by the emotion engine, including the parent's emotions (e.g., happy feelings).

[1419] Step 9:

[1420] The device converts the input feedback and emotion information into JSON format and sends it to the server using the HTTP POST method.

[1421] Step 10:

[1422] The server receives the feedback and emotion information, stores it in a database such as Firestore, and notifies the device once the storage is complete.

[1423] Step 11:

[1424] When generating the next curriculum, the server retrieves the relevant feedback and emotion information from the database and sends it to the generative model as a prompt, which includes the new basic information, the previous feedback, and the parent's emotion information.

[1425] Step 12:

[1426] The generative model takes into account the feedback and emotional information to generate a new childcare curriculum and sends it back to the server, which then receives it and sends it back to the device in JSON format.

[1427] Step 13:

[1428] The terminal displays the received new curriculum, and the user (childcare worker) checks and applies the contents.

[1429] Specifically, a childcare worker inputs basic information such as "3-year-old child, sunny day, interest in animals," and the emotion engine recognizes that the childcare worker is in a "very good mood." The generative model then generates a curriculum of "10:00 - 11:00 outdoor animal observation" and recommends activities that reflect the childcare worker's good mood. Similarly, if a parent inputs feedback such as "my child wants to go to the zoo this weekend" and recognizes that the child is in a happy mood, this information will be taken into account when generating the next curriculum, and "zoo-related activities" will be recommended.

[1430] This provides a more personalized childcare curriculum that takes into account the user's emotions.

[1431] Example 2

[1432] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1433] Conventional childcare curriculum generation systems were unable to consider the emotions of childcare workers or the feedback of parents, and instead created a uniform curriculum. This placed a heavy burden on childcare workers and made communication with parents difficult. Furthermore, because the curriculum did not reflect the interests and emotions of individual children, it was difficult to improve the quality of childcare.

[1434] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1435] In this invention, the server includes a means for using a terminal equipped with an emotion engine that recognizes the emotions of childcare workers, a means for recognizing feedback from parents and their emotions, and a means for storing the feedback from parents and emotion information in a database. This makes it possible to generate an individually optimized childcare curriculum that takes into account the emotions of childcare workers and the feedback and emotion information from parents.

[1436] "Basic information" refers to data entered by childcare workers, such as children's ages, interests, weather, and seasons.

[1437] A "generative model" refers to an artificial intelligence algorithm that automatically generates a childcare curriculum based on input basic information and emotional information.

[1438] "Emotion engine" refers to software or a device that recognizes and analyzes the emotions of childcare workers and parents.

[1439] "Devices" refers to electronic devices such as PCs, tablets, and smartphones used by childcare workers and parents.

[1440] "Feedback" refers to opinions, requests, and impressions from parents.

[1441] "Database" refers to an electronic information storage system for storing feedback, emotional information, etc.

[1442] A "prompt" refers to input data that provides basic and emotional information to a generative model.

[1443] "JSON format" refers to a text-based data exchange format that expresses data concisely and in a highly readable manner.

[1444] This invention is a system that automatically generates an optimal childcare curriculum based on basic information and emotional information entered by childcare workers. The purpose of this system is to reduce the burden on childcare workers, facilitate communication with parents, and provide individually optimized childcare curricula.

[1445] Enter basic information

[1446] Users (childcare workers) enter basic information using devices such as PCs or tablets. For example, they can open a dedicated application or web form and enter information such as the children's ages, interests, weather, and season. Once the information is complete, they click the "Generate" button, and the information is saved on the device.

[1447] Emotion recognition

[1448] The device is equipped with an emotion engine that recognizes the emotions of the childcare worker. This engine uses sensor devices such as cameras and microphones to analyze emotions from the childcare worker's facial expressions and tone of voice. For example, if the childcare worker's facial expression is smiling, the emotion engine will determine that the childcare worker is in a "very good mood." This emotion information is sent to the server along with basic information.

[1449] Request curriculum generation

[1450] The device sends basic information and emotional information to the server in JSON format. The device uses a web framework such as Flask to send this data to the server as an HTTP request. Specific examples of transmitted data include the following formats:

[1451] {

[1452] "age": "3 years old",

[1453] "Interests": "Animals",

[1454] "Weather": "Sunny",

[1455] "season": "spring",

[1456] "Childcare worker's feelings": "I feel very good"

[1457] }

[1458] Using generative models

[1459] The server analyzes the received basic information and emotional information and sends it as prompts to the generative AI model. The generative AI model automatically generates a childcare curriculum based on this information. For example, given prompts such as "The childcare worker is in a good mood," "For 3-year-olds," "It's a sunny day," and "Interested in animals," the generative AI model generates a curriculum such as "10:00 - 11:00 Outdoor animal observation."

[1460] Return and view curriculum

[1461] The generated childcare curriculum is sent back to the device in JSON format from the server. The device's dedicated application or web application parses this JSON data and displays the curriculum content on the user interface. Childcare workers can check the content and adjust it as necessary. For example, the following display content is possible:

[1462] 10:00 - 11:00 Outdoor animal observation

[1463] 11:00 - 12:00 Indoor animal picture book reading

[1464] Gathering feedback from parents

[1465] Users (parents) input feedback using a dedicated app or chatbot. During this input process, the emotion engine analyzes the parent's emotions. For example, if a parent inputs "My child wants to go to the zoo this weekend" and looks happy while doing so, the emotion engine will recognize this as "feeling happy."

[1466] Send and save feedback

[1467] The device sends parental feedback and emotional information in JSON format to the server. The server receives the data and stores it in a database such as Firestore. Once the data is saved, a notification of success is displayed on the device.

[1468] Next curriculum generation

[1469] When generating a new childcare curriculum, the server retrieves previously saved feedback and emotional information from the database and supplies it to the generative AI model. This makes it possible to generate a more optimal childcare curriculum that takes past feedback and emotions into account. The generative AI model generates a new curriculum based on this information and sends the results back to the server. The server receives this and sends it back to the device in JSON format, which then displays it.

[1470] As described above, the system of the present invention effectively utilizes the emotions of childcare workers and feedback from parents to provide individually optimized childcare curricula, thereby improving the work efficiency of childcare workers and the quality of childcare.

[1471] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1472] Step 1:

[1473] The user (childcare worker) uses a device such as a PC or tablet to enter basic information. This basic information includes the children's ages, interests, weather, season, etc. This basic information is entered through a dedicated application or web form. Once the entry is complete, the user clicks the "Generate" button, and the basic information is sent to the device. Specific data is entered using text boxes and drop-down menus, and the basic information is saved on the device as output.

[1474] Step 2:

[1475] The device's emotion engine recognizes the emotions of the childcare worker through sensor devices such as cameras and microphones. For example, if a childcare worker is smiling while entering information, the emotion engine will analyze this and recognize it as a "very good mood." This emotional information is then stored directly on the device.

[1476] Step 3:

[1477] The device sends the basic information entered by the childcare worker and the recognized emotional information to the server in JSON format. The device uses a web framework such as Flask to send this data to the server as an HTTP request. The following JSON format is used as an example of specific data to be sent. The basic information and emotional information are used as input, and the output is sent to the server in JSON format.

[1478] {

[1479] "age": "3 years old",

[1480] "Interests": "Animals",

[1481] "Weather": "Sunny",

[1482] "season": "spring",

[1483] "Childcare worker's feelings": "I feel very good"

[1484] }

[1485] Step 4:

[1486] The server analyzes the received basic information and emotional information and sends it as a prompt to the generative AI model. The generative AI model automatically generates a childcare curriculum based on this information. For example, given prompts such as "The childcare worker is in a good mood," "For 3-year-olds," "It's a sunny day," and "Interested in animals," the generative AI model generates a curriculum such as "10:00 - 11:00 Outdoor animal observation." In this step, the server receives the basic information and emotional information as input and obtains an output that sends a prompt to the generative AI model.

[1487] Step 5:

[1488] The generated childcare curriculum is sent from the server to the device again in JSON format. A dedicated application or web application on the device parses this JSON data and displays the curriculum content on the user interface. For example, a curriculum such as "10:00 - 11:00 Outdoor animal observation" is displayed, allowing childcare workers to review the content and adjust it as necessary. In this step, the output of the generative AI model (childcare curriculum) is sent to the device in JSON format, where it is parsed and displayed.

[1489] Step 6:

[1490] The user (parent) inputs feedback using a dedicated app or chatbot. During this input process, the emotion engine analyzes the parent's emotions. For example, if the parent inputs "My child wants to go to the zoo this weekend" and has a happy expression while doing so, the emotion engine will recognize this as "a happy feeling." In this step, feedback and emotional information are input and saved as output on the device.

[1491] Step 7:

[1492] The device sends the parent's feedback and emotion information in JSON format to the server. The server receives this and stores it in a database such as Firestore. Once the storage is complete, a notification of successful storage is displayed on the device. In this step, the input feedback and emotion information are sent to the server, and the output is stored in a database.

[1493] Step 8:

[1494] When generating a new childcare curriculum, the server retrieves previously saved feedback and emotional information from the database and supplies it to the generative AI model. This allows for the generation of a more optimal childcare curriculum that takes past feedback and emotions into account. For example, a childcare curriculum that suggests "zoo-related activities" based on parental feedback may be generated. In this step, past feedback and emotional information are input, and the generative AI model outputs a newly generated childcare curriculum.

[1495] (Application example 2)

[1496] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1497] In childcare operations such as automatically generating childcare curricula and collecting feedback, there are issues related to reducing the burden on childcare workers and smooth communication with parents.In addition, there is a need to improve the efficiency of sales promotion activities and customer satisfaction by making optimal product suggestions based on basic information and emotional information of customers in physical stores.

[1498] The specific processing 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 means for using a generative model to automatically generate a childcare curriculum based on basic information input by a childcare worker, means for displaying the childcare curriculum generated by the generative model on the childcare worker's terminal, means for collecting feedback from parents, means for storing the feedback in a database, means for generating the next childcare curriculum taking the feedback into consideration, means for using a generative model to generate optimal product proposals based on basic information and emotional information of customers, and means for displaying the generated product proposals on the salesperson's terminal. This reduces the workload of childcare workers, facilitates communication with parents, and further enables more efficient sales promotion activities in physical stores and improved customer satisfaction.

[1499] A "childcare worker" refers to a person whose occupation is to specialize in caring for infants and children.

[1500] "Basic information" refers to basic information about the user or subject that is entered into the system, such as age, interests, weather, and season.

[1501] A "generative model" refers to an artificial intelligence model that automatically generates outputs suitable for a specific purpose based on input data.

[1502] "Terminal" refers to an electronic device for inputting, outputting, and processing information, and includes smartphones, tablets, PCs, etc.

[1503] "Feedback" refers to opinions expressed by users of the system, such as their impressions after using it and areas for improvement.

[1504] A "database" refers to a collection of data that is systematically organized and stored so that it can be searched and used as needed.

[1505] A "server" refers to a computer system that provides services to clients over a network.

[1506] "Childcare curriculum" refers to programs and schedules for systematically carrying out childcare activities for infants and young children.

[1507] "Salesperson" refers to the staff in charge of selling products in physical stores, etc.

[1508] "Basic information and emotional information" refers to basic data about the customer as well as information that indicates their emotional state at the time.

[1509] "Product Recommendations" refers to products or services recommended based on a customer's interests and needs.

[1510] "JSON format" is a data exchange format, an abbreviation for JavaScript Object Notation, and refers to a method of expressing data in text format.

[1511] This system combines a generative model that automatically generates a childcare curriculum based on basic information entered by childcare workers with an emotion engine that recognizes feedback from parents and the user's emotions. It can also be applied to a system in brick-and-mortar stores that allows sales staff to recommend optimal products to customers based on their basic and emotional information.

[1512] The system's program exchanges information between the server and the device, and generates childcare curriculum and product proposals using a generative model and emotion engine. The main hardware used includes the server, smartphones, tablets, PCs, and other devices. The main software used includes web frameworks such as Flask, emotion engines, and generative models.

[1513] The server receives the basic information and emotional information entered by the nursery teacher, or the basic information and emotional information of the customer entered by the salesperson. This information is sent from the device in JSON format and stored in a database on the server. The database can be something like Firestore.

[1514] The server sends a prompt to the generative model based on the received basic information and emotion information. This prompt includes specific input data and instructions based on that data. For example, the following prompt sentence could be considered:

[1515] "Customer basic information: Interests - Healthy foods, Previous purchases - Protein bars, Product viewed in store - Vitamin supplements. Currently, the customer is smiling. Generate optimal product suggestions based on this."

[1516] The generative model generates optimal childcare curriculum and product recommendations based on the input prompts and sends the results back to the server. This information is then sent back to the device in JSON format and displayed on the device screen.

[1517] As a specific example, if a nursery teacher inputs basic information such as "3-year-old child, sunny day, interest in animals" and the emotion engine recognizes that the nursery teacher is in a good mood, the generative model will generate a nursery curriculum of "10:00 - 11:00 outdoor animal observation." Similarly, if a salesperson inputs basic information such as "interests: health foods, past purchases: protein bars, products viewed in the store: vitamin supplements" and the generative model recognizes that the customer is smiling, the generative model will generate suggestions such as "introduction to vitamin supplements" and "suggestion for new protein bar products."

[1518] The childcare curriculum and product proposals generated in this way are displayed on the devices of childcare workers and sales staff, allowing users to check and adapt them. Feedback from parents and customers is also sent from the devices to the server and used for the next generation. This system reduces the workload of childcare workers, facilitates communication with parents, and also makes sales promotion activities in physical stores more efficient and improves customer satisfaction.

[1519] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1520] Step 1:

[1521] The user (childcare worker or salesperson) enters basic information using a device (smartphone, tablet, PC, etc.). For childcare workers, basic information includes the child's age, interests, weather, season, etc. For salespeople, basic information includes the customer's interests, past purchase history, current situation, etc. The entered basic information is temporarily saved on the device.

[1522] Step 2:

[1523] The device uses a camera and microphone to capture the facial expressions and voice of the user or customer. The emotion engine analyzes this captured data and recognizes the user's emotions. The recognized emotion information is collected on the device along with basic information.

[1524] Step 3:

[1525] The device converts the collected basic information and emotional information into JSON format and sends it to the server. For example, JSON format data might include "Age: 3 years old, Interests: Animals, Weather: Sunny, Emotion: Good." The sent data is then received by the server.

[1526] Step 4:

[1527] The server generates a prompt based on the received basic information and emotion information and sends it to the generative model. For example, the prompt may contain information such as "3-year-old child, sunny day, interest in animals, and good emotion of the caregiver." The prompt is sent in a format that the generative model can understand.

[1528] Step 5:

[1529] The generative model calculates data based on the input prompts and generates optimal childcare curriculum and product suggestions. For example, it generates a childcare curriculum of "10:00 - 11:00 Outdoor animal observation" and a product suggestion of "Introduction to vitamin supplements." This generated information is sent back to the server.

[1530] Step 6:

[1531] The server receives the childcare curriculum and product suggestions returned by the generative model and converts them into JSON format. The converted data is then sent to the device, which parses the received JSON data and displays it on the user interface.

[1532] Step 7:

[1533] The user (childcare worker or salesperson) checks the childcare curriculum and product suggestions displayed on the terminal, implements them, and inputs any feedback they may have about the implementation through the terminal.

[1534] Step 8:

[1535] The device converts the user feedback back into JSON format and sends it to the server, which stores the received feedback in a database. This stored feedback is used as information for generating the next curriculum and product proposals.

[1536] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1537] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1538] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1539] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1540] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1541] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1542] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1543] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1544] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1545] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1546] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1547] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1548] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1549] 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.

[1550] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1551] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1552] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1553] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1554] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1555] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1556] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1557] The following is further disclosed regarding the above embodiment.

[1558] (Claim 1)

[1559] A means for using a generative model to automatically generate a childcare curriculum based on basic information input by a childcare worker;

[1560] A means for displaying the childcare curriculum generated by the generative model on a terminal of a childcare worker;

[1561] a means of gathering feedback from parents;

[1562] means for storing said feedback in a database;

[1563] A means for generating the next childcare curriculum taking into consideration the feedback;

[1564] A system including:

[1565] (Claim 2)

[1566] a means for sending prompts to the generative model based on basic information entered by the caregiver;

[1567] A means for returning the childcare curriculum generated by the generative model to a childcare worker's terminal in JSON format;

[1568] The system of claim 1 further comprising:

[1569] (Claim 3)

[1570] A means of sending parent feedback in JSON format to the server,

[1571] means for ensuring that said feedback is stored in a database;

[1572] The system of claim 1 further comprising:

[1573] (Claim 4)

[1574] means for obtaining data from a database containing parental feedback and using said data when generating the next childcare curriculum;

[1575] The system of claim 1 further comprising:

[1576] "Example 1"

[1577] (Claim 1)

[1578] A means for using a generative model to automatically generate a childcare curriculum based on basic information input by a childcare worker;

[1579] A means for displaying the childcare curriculum generated by the generative model on a terminal of a childcare worker;

[1580] a means of gathering feedback from parents;

[1581] means for storing said feedback in a database;

[1582] A means for generating the next childcare curriculum taking into consideration the feedback;

[1583] a means for inputting basic information through a user interface;

[1584] A means of converting basic information into JSON format and sending it to the server,

[1585] A means to return the generated curriculum to the device in JSON format;

[1586] A means for parents to provide feedback using communication tools;

[1587] A means of sending feedback to the server in JSON format;

[1588] A system including:

[1589] (Claim 2)

[1590] a means for sending prompts to the generative model based on basic information entered by the caregiver;

[1591] A means for returning the childcare curriculum generated by the generative model to a childcare worker's terminal in JSON format;

[1592] The system of claim 1 further comprising:

[1593] (Claim 3)

[1594] A means of sending parent feedback in JSON format to the server,

[1595] means for ensuring that said feedback is stored in a database;

[1596] The system of claim 1 further comprising:

[1597] "Application Example 1"

[1598] (Claim 1)

[1599] A means for using a generative model to automatically generate a work schedule based on basic information input by an administrator;

[1600] a means for displaying the work schedule generated by the generative model on a terminal of a manager;

[1601] a means of collecting feedback from workers; and

[1602] means for storing said feedback in a database;

[1603] means for generating a next work schedule taking said feedback into account;

[1604] A system including:

[1605] (Claim 2)

[1606] a means for sending prompts to the generative model based on basic information entered by the administrator;

[1607] A means for returning the work schedule generated by the generative model to an administrator's terminal in JSON format;

[1608] The system of claim 1 further comprising:

[1609] (Claim 3)

[1610] A means of sending feedback from workers in JSON format to the server;

[1611] means for ensuring that said feedback is stored in a database;

[1612] The system of claim 1 further comprising:

[1613] "Example 2: Combining Emotion Engines"

[1614] (Claim 1)

[1615] A means for using a generative model to automatically generate a childcare curriculum based on basic information input by a childcare worker;

[1616] A means for using a device equipped with an emotion engine that recognizes the emotions of the childcare worker;

[1617] A means for displaying the childcare curriculum generated by the generative model on a terminal of a childcare worker;

[1618] a means of recognizing parental feedback and parental emotions;

[1619] means for storing said feedback and emotion information in a database;

[1620] a means for generating a next childcare curriculum taking into consideration the feedback and emotional information;

[1621] A system including:

[1622] (Claim 2)

[1623] a means for sending prompts to the generative model based on basic information and emotion information input by the childcare worker;

[1624] A means for returning the childcare curriculum generated by the generative model to a childcare worker's terminal in JSON format;

[1625] The system of claim 1 further comprising:

[1626] (Claim 3)

[1627] a means for sending parental feedback and emotional information in JSON format to a server;

[1628] means for ensuring that said feedback and emotion information is stored in a database;

[1629] The system of claim 1 further comprising:

[1630] "Application example 2 when combining emotion engines"

[1631] (Claim 1)

[1632] A means for using a generative model to automatically generate a childcare curriculum based on basic information input by a childcare worker;

[1633] A means for displaying the childcare curriculum generated by the generative model on a terminal of a childcare worker;

[1634] a means of gathering feedback from parents;

[1635] means for storing said feedback in a database;

[1636] A means for generating the next childcare curriculum taking into consideration the feedback;

[1637] A means for using a generative model to generate optimal product proposals based on basic information and emotional information of customers;

[1638] means for displaying the generated product proposal on a salesperson's terminal;

[1639] A system including:

[1640] (Claim 2)

[1641] a means for sending prompts to the generative model based on basic information entered by the caregiver;

[1642] A means for returning the childcare curriculum generated by the generative model to a childcare worker's terminal in JSON format;

[1643] means for sending prompts to the generative model based on basic customer information and sentiment information;

[1644] means for returning the product proposals generated by the generative model to a salesperson's terminal in JSON format;

[1645] The system of claim 1 further comprising:

[1646] (Claim 3)

[1647] A means of sending parent feedback in JSON format to the server,

[1648] means for ensuring that said feedback is stored in a database;

[1649] A means of sending feedback from salespeople in JSON format to the server;

[1650] means for ensuring that said feedback is stored in a database;

[1651] The system of claim 1 further comprising: [Explanation of symbols]

[1652] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for using a generative model to automatically generate a childcare curriculum based on basic information input by a childcare worker; A means for displaying the childcare curriculum generated by the generative model on a terminal of a childcare worker; a means of gathering feedback from parents; means for storing said feedback in a database; A means for generating the next childcare curriculum taking into consideration the feedback; A system including:

2. a means for sending prompts to the generative model based on basic information entered by the caregiver; A means for returning the childcare curriculum generated by the generative model to a childcare worker's terminal in JSON format; The system of claim 1 further comprising:

3. A means of sending parent feedback in JSON format to the server, means for ensuring that said feedback is stored in a database; The system of claim 1 further comprising:

4. means for obtaining data from a database containing parental feedback and using said data when generating the next childcare curriculum; The system of claim 1 further comprising:

Images