System

Abstract

A system is provided.SOLUTION: A system includes, in a waste disposal facility, means for receiving a waste image on which preprocessing has been performed by using a generated artificial intelligence model, classifying the waste into materials based on the image, means for analyzing data of the classified waste to grasp a waste sorting situation for each area, means for presenting a waste sorting situation and a tendency for each area based on an analysis result, presenting an appropriate guidance proposal, and means for proposing a new waste disposal method based on component information of the waste by using the generated artificial intelligence model.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] The waste problem has become a serious issue in modern society, with the massive generation of waste and the resulting increase in disposal costs placing a heavy burden on the environment and economy. In particular, if waste is not properly separated, recyclable resources are wasted and disposal costs increase. Furthermore, the lack of efficient waste disposal methods increases the negative impact on the environment. This invention aims to use generative AI to improve the efficiency of waste separation and disposal, thereby reducing costs and environmental impact. [Means for solving the problem]

[0005] The present invention provides a system for utilizing generative artificial intelligence models in waste disposal facilities. Specifically, the system includes a means for receiving preprocessed waste images and classifying the waste by material based on the images, a means for analyzing the classified waste data to understand the waste sorting situation in each region, a means for presenting the waste sorting situation and trends in each region based on the analysis results and providing appropriate guidance suggestions, and a means for using the generative artificial intelligence model to propose new waste disposal methods based on waste composition information. This system achieves efficient waste sorting, promotes recycling, reduces disposal costs, and reduces environmental impact.

[0006] A "waste disposal facility" is a place where waste is collected and disposed of by means of sorting, recycling, incineration, landfill, or other methods.

[0007] A "generative artificial intelligence model" is a type of artificial intelligence that uses self-learning based on large amounts of data and is trained to perform specific tasks.

[0008] "Garbage Image" refers to an image file containing visual information of garbage captured by a camera or other photographic device.

[0009] "Preprocessing" refers to the process of performing processes such as noise removal, resolution adjustment, and normalization on the received dust image to prepare the image for analysis.

[0010] "Material sorting methods" refers to the technology and devices used to identify and separate waste into different materials, such as plastic, paper, metal, and glass.

[0011] "Classified waste data" refers to digitally stored information about waste that has been classified by material using image recognition technology.

[0012] "Analysis" refers to the process of performing calculations and analysis based on the classified waste data to understand the sorting rates and trends in each region.

[0013] "Garbage sorting status by region" refers to information showing the degree and status of garbage sorting in a specific region (city, ward, town, etc.).

[0014] "Means for providing guidance and suggestions" refers to methods and devices that use the analysis results to provide advice and education to local residents about appropriate methods for sorting waste and improvement measures.

[0015] "Composition information" refers to detailed data about the composition and materials of waste.

[0016] "New waste disposal methods" refer to waste disposal processes that use new technologies and methodologies that differ from conventional methods. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The system of the present invention realizes a waste disposal facility that utilizes a generative artificial intelligence model. Specifically, it involves the process of acquiring image data of waste, classifying it by material using generative AI, analyzing the data to understand the sorting situation in each region, making appropriate guidance suggestions based on the analysis results, and even proposing new waste disposal methods.

[0039] Garbage image acquisition and preprocessing

[0040] First, the server periodically receives image data of the garbage from cameras installed inside the waste disposal facility, and then performs preprocessing such as noise reduction, resolution adjustment, and image normalization to prepare the images for the generative AI model.

[0041] Classification of garbage by material

[0042] After pre-processing, the image data is fed into a deep learning-based generative AI model on the server, which uses techniques such as convolutional neural networks (CNN) to accurately classify waste by material, such as plastic, paper, metal, glass, and other materials.

[0043] Data accumulation and analysis

[0044] The sorted waste data is stored in a database on a server. The accumulated data is aggregated over a set period and analyzed. This analysis includes calculating the sorting rate for each area, comparing it with past data, and identifying trends.

[0045] Presentation of analysis results and educational proposals

[0046] The analysis results are sent to the device, which displays the current state and trends of waste sorting in each region. The user (local government official) can use this information to plan and implement education and campaigns for local residents. For example, if plastic sorting is low in a particular region, they can take measures such as holding information sessions on plastic sorting.

[0047] Proposing a new method for disposing of garbage

[0048] The server utilizes generative AI models based on the analytical data and composition information to propose new waste disposal methods, including improvements to chemical and mechanical processes. The proposed new disposal methods are sent to the device in the form of a report, allowing the user to test them.

[0049] Specific examples

[0050] For example, for 20 images of trash received from a waste disposal facility camera at 9 a.m. each day, the server preprocesses them and then uses a generative AI model to classify them by material: on this day, eight pieces were classified as plastic, four as paper, two as metal, and six as other trash.

[0051] The server then accumulates this data and aggregates and analyzes it for one week, determining that the average plastic sorting rate in Area A is 80%. It also confirms that the sorting rate has improved compared to two months ago. Based on this information, the device proposes an educational campaign to emphasize the importance of further sorting to residents of Area A.

[0052] Additionally, the server uses a generative AI model to suggest new chemical processing methods, calculating details on how to dissolve a particular plastic in a solvent and reuse it as new raw material, and reporting this to the user via their device.

[0053] In this way, the system of the present invention realizes efficient waste separation, promotes recycling, reduces costs, and further reduces the environmental burden.

[0054] The processing flow will be explained below.

[0055] Step 1: Obtaining and preprocessing the dust image

[0056] The server receives image data of the waste from cameras inside the waste treatment facility, performs noise reduction on the received images, adjusts the resolution to a specified size, and normalizes each pixel value to prepare the image for analysis.

[0057] Step 2: Classify the images

[0058] The server then inputs the preprocessed images into a generative AI model, which uses a convolutional neural network (CNN) to classify the waste by material, including plastic, paper, metal, glass, and other categories. The classification results are then recorded as digital data.

[0059] Step 3: Accumulate data

[0060] The server stores the classification results in a database, and the data on the material classification of each piece of garbage is centrally managed and used for future analysis.

[0061] Step 4: Data analysis

[0062] The server aggregates the accumulated data every certain period (e.g., one week). Based on this aggregated data, it calculates the garbage sorting rate and analyzes the sorting situation and trends by region. The analysis results are generated in report format.

[0063] Step 5: Submitting the analysis results

[0064] The server then sends the analysis results to the local government's terminal. The report includes the current state of waste sorting in each area, a comparison with past data, sorting trends, and areas for further improvement.

[0065] Step 6: View Educational Offers

[0066] The device displays the received report, which shows local waste separation rates and trends, and includes educational suggestions for specific waste separation methods. Users can use this information to plan educational activities and campaigns for local residents.

[0067] Step 7: Generate a new processing method

[0068] The server uses the analyzed data and composition information to use generative AI models to suggest new waste disposal methods, including recycling methods and new chemical treatment technologies based on the waste's specific composition.

[0069] Step 8: Generate a report of the new processing method

[0070] The server generates a report detailing the proposed new waste disposal method, including specific steps and expected results.

[0071] Step 9: Submit and test the new process

[0072] The server sends a report of the new processing method to the terminal. The user uses this report to plan a trial of the new processing method. The test results are later fed back to the server for further improvement.

[0073] As described above, through the specific processing flow of each step, the system of the present invention efficiently realizes efficient waste separation, analysis, educational proposals, and proposals for new processing methods.

[0074] Example 1

[0075] 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."

[0076] At conventional waste treatment facilities, waste sorting was done manually, which not only took time and effort but also resulted in insufficient sorting accuracy. Furthermore, there was a lack of efficient means to grasp the waste sorting situation in each region and provide appropriate guidance, making it difficult to effectively treat waste. Furthermore, there was a lack of concrete means to propose and implement new waste treatment methods.

[0077] 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.

[0078] In this invention, the server includes means for receiving preprocessed garbage images, means for performing noise reduction, resolution adjustment, and normalization on the images, means for classifying garbage by material based on the preprocessed images, means for storing data on the classified garbage in a database, means for compiling and analyzing the stored data to grasp the garbage sorting situation in each region, means for presenting the garbage sorting situation and trends in each region based on the analysis results and providing appropriate guidance suggestions, and means for using a generative artificial intelligence model to propose new garbage disposal methods based on garbage composition information.This makes it possible to improve the efficiency and accuracy of garbage sorting work, grasp the garbage sorting situation in each region, provide appropriate guidance suggestions, and propose specific new garbage disposal methods.

[0079] A "server" is a computer system that provides data and services to clients (terminals) via a network.

[0080] A "generative artificial intelligence model" is an artificial intelligence model that has the technology to learn from large amounts of data and perform pattern recognition and prediction, and uses algorithms such as neural networks.

[0081] "Garbage images" are photographic data of garbage captured by a photographing device such as a camera.

[0082] "Preprocessing" is a process in which received dust images are subjected to noise removal, resolution adjustment, normalization, etc. to prepare them for analysis.

[0083] "Material sorting" is the process of separating waste into plastic, paper, metal, glass and other categories.

[0084] A "database" is a software system for efficiently storing, managing, and searching structured data.

[0085] "Data aggregation" is the process of statistically summarizing accumulated data, making it easier to extract information from the results.

[0086] "Analysis" is a means of analyzing the aggregated data in detail to understand the waste sorting situation and trends in each region.

[0087] "Analysis results" refer to the information and conclusions obtained through data analysis, which form the basis for subsequent actions.

[0088] "Guidance proposals" are activities that use the analysis results to educate local residents on how to separate waste and propose improvement measures.

[0089] "Waste composition information" is detailed data on the physical and chemical properties of waste.

[0090] A "new waste disposal method" is a method of waste disposal and recycling that is more efficient and environmentally friendly than conventional methods.

[0091] The system of the present invention realizes a waste treatment facility that utilizes a generative artificial intelligence model. Specific embodiments of the system are described in detail below.

[0092] Garbage image acquisition and preprocessing

[0093] The server periodically receives image data of the garbage from cameras (commonly known as camera devices) installed within the waste disposal facility. High-resolution cameras are used as camera devices. The server uses image processing libraries such as OpenCV to perform preprocessing on the received image data, such as noise removal, resolution adjustment, and image normalization. This prepares the image for the generative AI model to analyze more accurately.

[0094] Classification of garbage by material

[0095] Once pre-processed, the image data is fed into a generative AI model stored on the server, which is based on a convolutional neural network (algorithm) using deep learning libraries such as TENSORFLOW® to accurately classify waste by material, such as plastic, paper, metal, glass, and others.

[0096] Data accumulation and analysis

[0097] The data on the sorted waste is stored in a database system (commonly known as a data management system) on the server. The accumulated data is compiled over a set period of time and analyzed. This analysis uses data analysis tools such as Apache Spark (registered trademark) to calculate the sorting rate by region, compare it with past data, and identify trends.

[0098] Presentation of analysis results and educational proposals

[0099] The analysis results are sent to the device, which displays the waste sorting situation and trends for each region. The user (commonly known as the operator) uses this information to plan and implement education and campaigns for local residents. The analysis results are visualized using a data visualization tool (e.g., Tableau).

[0100] Proposing a new method for disposing of garbage

[0101] The server utilizes a generative AI model (e.g., GPT-4 (registered trademark)) based on the analysis data and component information to propose new waste disposal methods. These methods include improvements to chemical and mechanical processes. The proposed new disposal methods are sent to the terminal in the form of a report, which the user can then test.

[0102] Specific examples

[0103] For example, every day at 9 a.m., the server receives 20 images of trash from a camera at a waste disposal facility. The server uses OpenCV to remove noise and adjust the resolution, then uses a TensorFlow-based generative AI model to classify the images by material. On this day, the images were classified as 8 pieces of plastic, 4 pieces of paper, 2 pieces of metal, and 6 pieces of other trash.

[0104] The server then stores this data in a MySQL® database and aggregates and analyzes one week's worth of data, determining that the average plastic sorting rate in Area A is 80%. It also confirms that the sorting rate has improved compared to two months ago. Based on this information, the device proposes an educational campaign to emphasize the importance of further sorting to residents of Area A.

[0105] Additionally, the server uses GPT-4 to propose new chemical processing methods, calculating details on how to dissolve a particular plastic in a solvent and reuse it as new raw material, and reporting this to the user via the device.

[0106] In this way, the system of the present invention realizes efficient waste separation, promotes recycling, reduces costs, and further reduces the environmental burden.

[0107] Prompt Sentence Examples

[0108] "Please tell us some specific suggestions for increasing the garbage sorting rate in Area A."

[0109] "Please suggest a new way to dispose of plastic waste."

[0110] In this way, the system of the present invention achieves reduced environmental impact and efficient recycling through automation and advanced data analysis at waste treatment facilities.

[0111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0112] Step 1: Receiving image data

[0113] The server receives image data of the garbage from cameras installed in the waste treatment facility at 9:00 AM every day. The input data is a high-resolution image. The output is an image file of the received raw data.

[0114] Specific behavior:

[0115] 1. The server obtains image files from the camera using a protocol such as FTP.

[0116] 2. Save the image data immediately after receiving it in temporary storage.

[0117] Step 2: Image preprocessing

[0118] The server performs preprocessing on the received images, such as noise removal, resolution adjustment, and normalization. The input is the received raw image data file. The output is the preprocessed image data.

[0119] Specific behavior:

[0120] 1. The server uses the OpenCV library to remove noise using the cv2.GaussianBlur function.

[0121] 2. The server uses the cv2.resize function to adjust to a consistent resolution.

[0122] 3. The server normalizes the image pixel values ​​by dividing them by 255.

[0123] Step 3: Categorize your images by content

[0124] The preprocessed image data is input to the generative AI model on the server. The input is the preprocessed image data. The output is the image classification result (plastic, paper, metal, glass, other).

[0125] Specific behavior:

[0126] 1. The server loads the CNN model using the TensorFlow library.

[0127] 2. The preprocessed image data is input into the CNN model to obtain classification results.

[0128] Step 4: Data accumulation

[0129] The data of the classified garbage is stored in a database on the server. The input is the classified garbage data. The output is structured data stored in the database.

[0130] Specific behavior:

[0131] 1. The server connects to the MySQL database and inserts the new classification data.

[0132] 2. Verify that the data was inserted correctly.

[0133] Step 5: Data collection and analysis

[0134] The server periodically aggregates and analyzes the data in the database. The input is the accumulated database data. The output is a report of the analysis results.

[0135] Specific behavior:

[0136] 1. The server uses Apache Spark to query one week's worth of data from the database.

[0137] 2. Calculate the separation rate and trends based on the acquired data.

[0138] 3. Compile the analysis results in a report format.

[0139] Step 6: Submit and view analysis results

[0140] The analysis results are sent to a terminal, where the waste sorting situation and trends for each region are displayed. The input is the analysis result report. The output is visualized data.

[0141] Specific behavior:

[0142] 1. The server converts the analysis results into JSON format and sends them to the device via the Web API.

[0143] 2. The device displays the received data using a data visualization tool such as Tableau.

[0144] Step 7: Propose a new method of waste disposal

[0145] The server uses a generative AI model based on the composition information to propose new waste disposal methods. The input is the analysis data and composition information. The output is a report proposing a new disposal method.

[0146] Specific behavior:

[0147] 1. The server uses the GPT-4 model to generate prompts for new processing methods.

[0148] 2. The generated processing method is compiled into a report format using Microsoft® Word.

[0149] 3. The generated report is sent to the terminal and provided to the user.

[0150] This series of steps will enable efficient waste sorting, analysis, and the proposal of new waste disposal methods at waste disposal facilities.

[0151] (Application example 1)

[0152] 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."

[0153] In modern waste treatment facilities, waste sorting and processing is often done manually, limiting efficiency and accuracy. Furthermore, if waste is not properly sorted, recycling efficiency decreases and the environmental impact increases. Furthermore, similar issues exist in industrial waste and waste processing within factories. This has led to a demand for new technologies to improve waste management efficiency and reduce the environmental impact.

[0154] 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.

[0155] In this invention, the server includes means for receiving preprocessed garbage images and classifying the garbage by material based on the images, means for analyzing the classified garbage data and understanding the garbage sorting situation in each region, means for presenting the garbage sorting situation and trends in each region based on the analysis results and providing appropriate guidance suggestions, means for proposing new garbage disposal methods based on garbage composition information using a generative artificial intelligence model, means for operating a factory robot that moves the classified garbage by material into dedicated containers, and an application installed on a smartphone, smart glasses, head-mounted display, or robot that can monitor and operate the robot's operation from inside and outside the factory. This enables automated, high-precision waste sorting and efficient waste disposal.

[0156] A "server" is a computer system that provides data and services over a network.

[0157] "Preprocessing" refers to the initial processing of data to facilitate subsequent data analysis or classification in artificial intelligence models.

[0158] "Garbage image" refers to image data of waste material captured using a photographic device such as a camera.

[0159] "Material sorting" is the process of classifying a group of objects with specific attributes based on their material (e.g., plastic, paper, metal, glass, etc.).

[0160] "Data analysis" is a method of statistically processing collected data to extract usable information and patterns.

[0161] "Waste sorting status by region" is information that indicates the current state of waste sorting within a specific region.

[0162] A "trend" is a widespread pattern of change in a particular phenomenon or practice over time.

[0163] "Guidance proposal" means specific advice or plans to promote improvement in a specific problem.

[0164] A "generative artificial intelligence model" is an artificial intelligence algorithm that is automatically generated to perform a specific task based on training data.

[0165] "Ingredient information" refers to detailed data about the composition and elements of a substance.

[0166] A "robot" is a programmed mechanical device that can perform specific tasks automatically.

[0167] A "specialized container" is a storage box or container designed for a specific material or purpose.

[0168] An "application" is a software program designed to perform a specific task or function.

[0169] The system of the present invention utilizes a generative artificial intelligence model to realize automatic classification and efficient disposal of waste within a factory. Specific embodiments for implementing this system are described below.

[0170] The system consists of a server, factory robots, mobile devices such as smartphones, smart glasses, and head-mounted displays, as well as the necessary software.

[0171] First, the server periodically receives image data of waste from cameras installed in the factory. The received image data undergoes a pre-processing process to make it suitable for the generative AI model. Pre-processing includes noise removal, resolution adjustment, and image normalization.

[0172] The pre-processed image data is then fed into a deep learning-based generative artificial intelligence model on the server, which uses a convolutional neural network (CNN) to analyze the images and accurately classify the waste into plastic, paper, metal, glass, and other materials.

[0173] The classified waste data is stored in a database on a server and analyzed. The server aggregates the accumulated data and performs analysis to understand the waste sorting situation and trends in each region. The results of this analysis are presented to users via their mobile devices and used as guidance suggestions for improving waste management. For example, if the plastic sorting rate in a particular area is low, an educational campaign for local residents will be suggested.

[0174] Furthermore, new waste disposal methods are proposed by the generative AI model and sent to the user in the form of reports via the server, allowing new chemical and mechanical methods to be tested.

[0175] The factory robots then move the classified waste into dedicated containers based on instructions from the server. The robots' operations can be remotely monitored and controlled using mobile devices such as smartphones, smart glasses, and head-mounted displays.

[0176] As a concrete example, at a waste processing line, the server preprocesses waste image data received from a camera every day at 9:00 a.m., and then uses a generative AI model to classify the data by material. During this process, eight pieces of plastic, four pieces of paper, two pieces of metal, and six pieces of other waste are identified. The analysis results are aggregated for one week, and it is found that the plastic sorting rate in a particular area is 80%. Based on this, guidance suggestions emphasizing the importance of further sorting are presented to the user.

[0177] Example prompts to input to a generative AI model:

[0178] Please perform image capture using the "capture_image" function.

[0179] Use the "preprocess_image" function for preprocessing and perform classification using a generative AI model.

[0180] Based on the classification result, use the "place_in_container" function to move the robot arm to the appropriate container.

[0181] As described above, the system of the present invention enables automated, highly accurate classification and efficient disposal of waste.

[0182] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0183] Step 1:

[0184] The server periodically receives image data of waste from cameras installed in the factory. The input data is raw image data acquired from the camera, and the output is image data suitable for preprocessing. Specifically, the image from the camera is captured and saved as an image file on the server.

[0185] Step 2:

[0186] The server performs preprocessing on the received image data, such as noise removal, resolution adjustment, and image normalization. The input is the raw image data obtained in step 1, and the output is image data that has been preprocessed into a format suitable for the generative AI model. This preprocessing improves the quality of the image and increases the accuracy of analysis by the generative AI model.

[0187] Step 3:

[0188] The server inputs the preprocessed image data into a generative AI model. The input is the preprocessed image data, and the output is waste labels classified by material. The generative AI model uses a convolutional neural network (CNN) to accurately classify each material (plastic, paper, metal, glass, etc.).

[0189] Step 4:

[0190] The server stores the classified waste data in a database. The input is the classification result from the generative AI model, and the output is the waste data stored in the database. This data is used for data analysis, which is useful for future analysis and trend identification.

[0191] Step 5:

[0192] The server aggregates and analyzes waste data over a set period of time to understand the waste separation situation and trends for each region. The input is the accumulated waste data, and the output is information on the separation situation and trends for each region based on the analysis results. Statistical analysis and machine learning techniques are used for the analysis method.

[0193] Step 6:

[0194] The server uses the analysis results to present the user with information on the current state and trends of waste separation in each region and makes appropriate guidance suggestions. The input is the analysis results, and the output is a report of guidance suggestions for the user. The user can use this report to plan and implement educational campaigns and improvement measures.

[0195] Step 7:

[0196] The server uses a generative artificial intelligence model to propose new waste treatment methods. The input is composition information and analytical data, and the output is a report of the new treatment method, leading to more efficient and environmentally friendly treatment methods.

[0197] Step 8:

[0198] Based on commands from the server, factory robots move the classified waste into dedicated containers. The input is the command to move the waste from the server, and the output is the result of the waste being moved to the appropriate container. This operation automates the proper disposal of waste.

[0199] Step 9:

[0200] Users use mobile devices such as smartphones, smart glasses, and head-mounted displays to remotely monitor and operate factory robots. The input is operation commands from the mobile device, and the output is the robot's operating status and monitoring report. Specifically, the current status of the robot can be checked through the application, and manual operation can be performed as needed.

[0201] Through the above processing steps, the system of the present invention enables automated, highly accurate classification and efficient processing of waste.

[0202] 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.

[0203] The system of this invention utilizes a generative artificial intelligence model and combines it with an emotion engine that recognizes user emotions to realize a waste disposal facility. This allows for efficient waste sorting, analysis, educational proposals, and proposals for new disposal methods, while also enabling flexible responses that take into account user emotion data.

[0204] Garbage image acquisition and preprocessing

[0205] First, the server receives image data of the waste from cameras inside the waste treatment facility, and then performs preprocessing such as noise reduction, resolution adjustment, and image normalization.

[0206] Classification of garbage by material

[0207] After preprocessing, the image data is input into a deep learning-based generative AI model stored on the server. The generative AI model uses techniques such as convolutional neural networks (CNN) to classify the waste by material. The classification results are recorded as digital data.

[0208] Data accumulation and analysis

[0209] The classified waste data is stored in a server database. The accumulated data is aggregated over a set period of time, and the sorting rate and trends by region are analyzed. The analysis results are generated in report format and sent to a designated device.

[0210] Presentation of analysis results and educational proposals

[0211] The device receives the analysis results sent from the server and displays the status and trends of waste sorting for each region. Here, the emotion engine recognizes the emotions of the user (local government official) and adjusts the way the analysis results are presented. For example, if the sorting rate is improving, it can display positive feedback.

[0212] Educational proposals using emotion engines

[0213] Based on the analysis results and information from the emotion engine, the device provides local residents with appropriate methods for educating them about waste separation. Users can use this information to plan and implement educational activities for residents. The emotion engine can analyze residents' reactions in real time during educational activities and provide feedback.

[0214] Proposing a new method for disposing of garbage

[0215] The server uses generative AI models based on the analyzed data and composition information to propose new waste disposal methods, including improvements to chemical and mechanical processes. The proposed new disposal methods are sent to the device in the form of a report, allowing users to plan trials at their waste disposal facilities.

[0216] Specific examples

[0217] For example, when a local government device receives a weekly report, the emotion engine analyzes the user's emotional state and adjusts the report display accordingly. If the sorting rate is low, a presentation highlighting areas for improvement will be presented and feedback to motivate the user. Similarly, if the plastic sorting rate in Region A improves by 5% compared to the previous year, positive comments and visual highlights will be provided.

[0218] Furthermore, during the educational campaign, the devices collect participants' emotional data and adjust the educational content in real time. For example, if residents' reactions are positive, the device will continue to explain in detail how to separate trash, but if they are negative, it will switch to a brief explanation of the main points.

[0219] In this way, the system of the present invention realizes efficient waste separation, analysis, educational suggestions, and proposals for new disposal methods, all in combination with user emotion recognition.

[0220] The processing flow will be explained below.

[0221] Step 1: Obtaining and preprocessing the dust image

[0222] The server receives image data of the waste from cameras inside the waste treatment facility. It then performs noise reduction on the received images, adjusts the resolution to a specified size, and normalizes the pixel values ​​of the images to make them suitable for analysis.

[0223] Step 2: Sort the waste by material

[0224] The server then inputs the pre-processed images into a generative AI model, which uses a convolutional neural network (CNN) to classify the waste material into categories such as plastic, paper, metal, glass, and other. The classification results are recorded as digital data and used in the next processing step.

[0225] Step 3: Accumulate data

[0226] The server stores the classified garbage data in a database, which is continuously accumulated and used for future analysis.

[0227] Step 4: Data analysis

[0228] The server collects and analyzes the data at regular intervals (e.g., weekly). This analysis includes calculating the waste separation rate by region, comparing it with past data, and analyzing trends in waste separation. The analysis results are generated in report format and sent to the specified device.

[0229] Step 5: Adjusting the analysis results by the emotion engine

[0230] The device receives the analysis results sent from the server and uses an emotion engine to recognize the user's (local government official's) emotions before displaying them on the screen. The emotion engine adjusts the way the analysis results are displayed depending on the user's reaction. For example, it may display positive emotions or add detailed explanations if necessary.

[0231] Step 6: Displaying educational suggestions and sentiment analysis

[0232] Based on the received data, the device displays the current state of waste sorting in each region and educational suggestions based on that data. The emotion engine analyzes the user's emotional state and dynamically adjusts appropriate educational methods and suggestions. Users can refer to the emotion engine's analysis to plan and implement more effective educational activities.

[0233] Step 7: Generate a new garbage disposal method

[0234] The server uses a generative AI model based on the analyzed data and composition information to propose new waste disposal methods, including improving chemical and mechanical processes and optimizing recycling technologies. The proposals are compiled into a report and sent to the device.

[0235] Step 8: Submit and feedback your new process

[0236] The device receives a report on the new waste disposal method and displays it to the user. The user then tests the new method based on the results and feeds the results back to the server. The feedback data is used to improve the accuracy of future proposals.

[0237] Step 9: Longitudinal analysis of sentiment data

[0238] The devices store emotional data collected during educational activities and the implementation of new waste disposal methods. Using this data, the server performs long-term data analysis and provides optimal educational approaches and waste disposal methods for each region.

[0239] In this way, the system of the present invention realizes efficient waste separation, analysis, educational suggestions, and suggestions for new disposal methods by combining them with user emotion recognition.

[0240] Example 2

[0241] 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."

[0242] At conventional waste disposal facilities, waste separation and disposal method proposals were sometimes inefficient, making it difficult to improve the local waste separation rate or implement appropriate educational activities.In addition, because it was not possible to consider the emotions and reactions of staff and residents in real time, it was difficult to respond individually, making it difficult to carry out effective educational activities or propose disposal methods.

[0243] 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.

[0244] In this invention, the server includes means for receiving preprocessed garbage images and classifying garbage by material based on the images, means for analyzing the classified garbage data and grasping the garbage sorting situation in each region, means for presenting the garbage sorting situation and trends in each region based on the analysis results and making appropriate instruction suggestions, means for proposing new garbage disposal methods based on garbage component information using a generative AI model, means for adjusting the display of the analysis results based on the user's emotional state, and means for collecting user emotional data and adjusting the content of educational activities in real time. This enables efficient garbage sorting, analysis, educational suggestions, and new disposal method suggestions, and enables flexible responses that take into account the user's emotions and reactions.

[0245] "Garbage images" are photographic data of garbage taken by cameras installed in garbage disposal facilities.

[0246] "Preprocessing" refers to image processing such as noise removal, resolution adjustment, and normalization that is performed on the received dust image.

[0247] A "generative AI model" is a generative artificial intelligence model, a trained neural network model that uses deep learning technology to classify garbage by material.

[0248] "Material sorting" is the process of separating garbage into different materials such as plastic, paper, and metal.

[0249] "Database" means an information system for storing and managing data on classified waste.

[0250] "Analysis" refers to analyzing accumulated garbage data using statistical methods and machine learning techniques.

[0251] A "report" is a report summarizing the analysis results in document and graph format.

[0252] "Terminal" refers to an electronic device for displaying analysis results and educational suggestions, including smartphones, PCs, tablets, etc.

[0253] The "emotion engine" is software that analyzes the emotional data of users and residents and adjusts the display content and educational suggestions.

[0254] "Educational activities" are efforts to educate local residents about the importance of sorting garbage and the correct way to do it.

[0255] "New waste disposal methods" are waste disposal technologies or methods that are more efficient or environmentally friendly than conventional methods, proposed using generative AI models.

[0256] "Real-time" means that data and information are processed and reflected immediately.

[0257] The system of the present invention utilizes a generative artificial intelligence model and combines it with an emotion engine that recognizes user emotions to realize a waste disposal facility. This system enables efficient waste sorting, analysis, educational proposals, and proposals for new disposal methods, and enables flexible responses that take into account user emotion data.

[0258] Garbage image acquisition and preprocessing

[0259] First, the server receives image data of the garbage from a camera inside the waste disposal facility. This camera is equipped with a high-resolution image sensor, which can capture even the smallest details of the garbage. The received image data is denoised using the OpenCV library. Next, the resolution is adjusted, for example, to 1024x768 pixels. Finally, the image is normalized using the numpy library, scaling the pixel values ​​to the range 0 to 1.

[0260] Classification of garbage by material

[0261] After preprocessing, the image data is input into a deep learning-based generative AI model stored on the server. This generative AI model utilizes frameworks such as TensorFlow and PyTorch and employs a convolutional neural network (CNN). The model analyzes the received image data and classifies the waste by material, such as plastic, paper, and metal. This makes it possible to select the appropriate disposal method for each type of waste.

[0262] Data accumulation and analysis

[0263] The sorted waste data is stored in a database on the server. This database uses MySQL and MongoDB. Every week, the accumulated data is compiled using a Python script, and the sorting rate and trends by region are analyzed. Statistical analysis and machine learning techniques are used for this analysis. The analysis results are formatted into a report and sent to a designated device.

[0264] Presentation of analysis results and educational proposals

[0265] The device receives the analysis results sent from the server and displays them to the user using intuitive graphs and charts. An emotion engine recognizes the user's (local government official's) emotions and adjusts the presentation of the analysis results accordingly. For example, software that generates text containing positive feedback and displays it on the screen includes an API for emotion analysis (e.g., Microsoft Azure's Emotion API).

[0266] Educational proposals using emotion engines

[0267] Based on the analysis results and information from the emotion engine, the device provides local residents with appropriate methods for educating them on how to sort their garbage. Users can view educational content, including videos and infographics, through a web application or mobile app. The emotion engine analyzes residents' reactions in real time during the education session and can adjust the content and progress of the education on the spot.

[0268] Proposing a new method for disposing of garbage

[0269] Based on the accumulated waste data and analysis results, the server uses a generative AI model to propose new waste disposal methods, including improving the reuse of specific materials and increasing the efficiency of processing equipment. These proposals are formatted into a report containing detailed technical specifications and cost-benefit analysis and sent to a designated device. Users can then try out new waste disposal methods to achieve even more efficient waste disposal.

[0270] Specific examples

[0271] For example, when a local government device receives a weekly report, the emotion engine analyzes the user's emotional state and adjusts the report display accordingly. If the sorting rate is low, a presentation highlighting areas for improvement will be presented, providing feedback to motivate the user. Conversely, if Region A's plastic sorting rate improves by 5% compared to the previous year, positive comments and visual highlights will be provided, allowing users to visually confirm concrete results.

[0272] Furthermore, during the education campaign, the devices collect participants' emotional data and adjust the educational content in real time. For example, if residents' reactions are positive, the device will continue to explain in detail how to separate trash, but if they are negative, it will briefly explain the main points. In this way, the effectiveness of the education can be maximized.

[0273] The above is a specific implementation method of the system of the present invention.

[0274] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0275] Step 1:

[0276] Garbage image acquisition and preprocessing

[0277] The server receives real-time image data of garbage from high-resolution cameras in the waste treatment facility. The image data received as input is first subjected to a noise reduction filter using the OpenCV library. Then, the image resolution is adjusted to 1024x768 pixels and pixel values ​​are scaled to the range of 0 to 1 using the numpy library. As an output, preprocessed image data is obtained. This preprocessed image data is used in the next step.

[0278] Specific behavior:

[0279] The server periodically polls the image data from the camera, calls functions in OpenCV to remove noise and adjust the resolution, and performs normalization with numpy.

[0280] Step 2:

[0281] Classification of garbage by material

[0282] The preprocessed image data is input into a generative AI model on the server. The generative AI model is a convolutional neural network (CNN) implemented in the TensorFlow framework, which classifies the waste into materials such as plastic, paper, and metal. The input data is the preprocessed image data, and the output is a probability value for each material classification. The most appropriate material label is assigned based on this probability value.

[0283] Specific behavior:

[0284] The server inputs the preprocessed image data into the model and receives the probability values ​​for each material returned as the model's inference results. Based on this, the server determines the classification results and stores them in a database.

[0285] Step 3:

[0286] Data accumulation and analysis

[0287] The classified waste data is stored in a database on the server. The input data is the classification results, and the output data is the data in the format stored in the database. The data is aggregated at regular intervals using a Python script, and the sorting rate and trends by region are analyzed. Statistical analysis methods and machine learning algorithms are used for the analysis. The output is a report on the sorting rate and trends by region.

[0288] Specific behavior:

[0289] The server periodically accesses the database and runs a batch script to aggregate the classification data, and then reports the analysis results in JSON and PDF format for the next step.

[0290] Step 4:

[0291] Presentation of analysis results and educational proposals

[0292] The device receives the analysis results sent from the server and displays them to the user using intuitive graphs and charts. The input data is the analysis results sent from the server, and the output is data in the form of graphs and charts displayed on the screen. The emotion engine recognizes the user's emotions and adjusts the display method. Specifically, it provides positive feedback and emphasizes points of caution depending on the user's emotional state.

[0293] Specific behavior:

[0294] The device receives the analysis results and uses libraries such as D3.js and Chart.js to draw graphs and charts. Based on the output of the emotion engine, it generates auxiliary text to adjust the display content.

[0295] Step 5:

[0296] Educational proposals using emotion engines

[0297] Based on the analysis results and information from the emotion engine, the device provides local residents with appropriate methods for educating them on how to separate waste. The input data are the analysis results and the output of the emotion engine, and the output data is educational content. Users view the educational content through a web application or mobile app. The emotion engine analyzes the emotional reactions of residents during the education in real time and adjusts the educational content as needed.

[0298] Specific behavior:

[0299] While playing educational content, the device transmits the residents' emotional data obtained from cameras and sensors to an emotion engine, which then displays supplementary explanations and encouraging messages based on the output of the emotion engine.

[0300] Step 6:

[0301] Proposing a new method for disposing of garbage

[0302] The server uses a generative AI model to propose new waste disposal methods based on the accumulated waste data and analysis results. The input data is the waste data and analysis results, and the output data is a report describing the new waste disposal method. The proposals include ways to reuse specific materials and improvements to the disposal equipment.

[0303] Specific behavior:

[0304] The server runs the generative AI model to generate a proposal for a new waste disposal method, converts the proposal into a PDF format, and sends it to the device via HTTP. The report includes technical specifications, cost-effectiveness, and specific implementation steps.

[0305] The above are the specific processing steps in the system of the present invention. In this way, it is possible to realize efficient waste separation, analysis, educational suggestions, and proposals for new waste disposal methods in combination with user emotion recognition.

[0306] (Application example 2)

[0307] 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."

[0308] In modern waste treatment facilities, efficient waste sorting, analysis, training, and new treatment methods are key challenges. To improve employee motivation and efficiency, it is also necessary to recognize user emotions in real time and provide appropriate feedback. However, existing systems lack dynamic feedback based on user emotions, resulting in insufficient optimization of waste treatment. Accurate waste classification and training are particularly important in large-scale facilities such as logistics centers, and new technologies with efficient feedback systems are needed.

[0309] The identification processing by the identification 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 utilizing a generative AI model to receive preprocessed garbage images and classify the garbage by material based on the images; means for analyzing the classified garbage data and understanding the garbage sorting situation in each region; means for presenting the garbage sorting situation and trends in each region based on the analysis results and providing appropriate guidance; means for using the generative AI model to propose a new garbage disposal method based on garbage composition information; and means for recognizing the user's emotions and providing feedback in real time. This enables efficient garbage sorting and analysis and allows the user to receive appropriate feedback based on their emotions, thereby improving the garbage disposal efficiency in the logistics center and increasing employee motivation.

[0310] A "generative artificial intelligence model" is an artificial intelligence technology that learns complex patterns and features based on data and makes predictions and classifications.

[0311] A "waste disposal facility" is a place where collected waste is processed and separated into reusable materials and non-combustible materials.

[0312] "Garbage images" are photographs or videos that visually record the type and condition of waste.

[0313] An "emotion engine" is a technology that analyzes data such as a user's facial expressions and voice to recognize their emotional state.

[0314] "Regional waste separation status" refers to how accurately waste is separated in a particular region.

[0315] "Guidance suggestions" are the act of suggesting improvements or new methods based on specific results or situations.

[0316] "Real-time feedback" is a technology that provides immediate responses and suggestions for improvement based on the current state or situation.

[0317] "Preprocessing" refers to the initial processing and adjustment work carried out to improve the quality of data.

[0318] "Material sorting" is the process of separating waste based on its material (paper, plastic, glass, etc.).

[0319] A "new garbage disposal method" is a newly proposed method of waste disposal that differs from conventional methods.

[0320] This invention is a waste disposal facility system incorporating an emotion engine that utilizes a generative AI model. Specifically, the system uses an application on smartphones and head-mounted displays in logistics centers to make it easier for employees to sort waste.

[0321] The server receives garbage image data acquired from cameras installed in the logistics center. This image data undergoes preprocessing such as noise removal, resolution adjustment, and image normalization before being input into a generative AI model. The generative AI model uses a convolutional neural network (CNN) to classify the garbage by material. The classification results are stored as digital data in a database on the server.

[0322] The data on the sorted waste is compiled periodically, and the status and trends of waste sorting in each region are analyzed. The analysis results are generated in report format and sent to a designated device. The device displays the analysis results and makes appropriate guidance suggestions. In addition, an emotion engine recognizes the emotions of the user (local government officials or logistics center staff) and adjusts the way the analysis results are presented. For example, if the waste sorting rate has improved, a display containing positive feedback will be displayed.

[0323] Furthermore, the server uses a generative AI model based on the analyzed data and composition information to propose new waste disposal methods, which are then sent to the device in the form of a report, allowing users to plan tests at their waste disposal facilities.

[0324] To give a specific example, employees working in a logistics center wear head-mounted displays and sort trash. Images of trash taken by the employees are sent to a server, where a generative AI model classifies them as "plastic." At the same time, if the emotion engine analyzes the employee's face and recognizes the emotion of "fatigue," the system provides positive feedback, saying, "Let's concentrate a little and do our best. Trash is plastic." This leads to efficient trash sorting and improved employee motivation.

[0325] An example of a prompt is as follows:

[0326] "You will take a picture of the garbage and input it into a generative AI model to classify the type of garbage. Then, write a program to analyze the user's emotions and provide appropriate feedback."

[0327] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0328] Step 1:

[0329] The server receives image data of dust particles from cameras installed in the logistics center. The received image data undergoes preprocessing such as noise removal, resolution adjustment, and image normalization. This improves the quality of the image data and provides input data for effective subsequent processing.

[0330] Step 2:

[0331] The server inputs the pre-processed garbage image data into a generative AI model. The generative AI model uses a convolutional neural network (CNN) to classify the garbage by material. Data analysis and calculations based on the input image data result in a classification such as "plastic" or "paper."

[0332] Step 3:

[0333] The generated classification results are stored in a database on the server, which accumulates data including information on the type and quantity of waste, ensuring data consistency and reusability.

[0334] Step 4:

[0335] The server periodically compiles the classification data stored in the database and analyzes the waste sorting situation and trends for each region. The analysis results are generated as digital data and output in report format. This analysis process involves statistically evaluating the input data and calculating data to identify trends.

[0336] Step 5:

[0337] The device receives the analysis results sent in report format from the server and displays the status and trends of waste sorting by region. An emotion engine runs simultaneously to recognize the user's emotional data. Based on this emotional data, the device adjusts the presentation method of the report and the content of the feedback. For example, if a positive emotion is recognized, a praising comment is displayed.

[0338] Step 6:

[0339] The server utilizes a generative AI model to propose new waste disposal methods based on additional analysis data and waste composition information. This proposal is sent to the device in the form of a report. The new waste disposal method is output as the result of data analysis and creative proposals based on the input composition information.

[0340] Step 7:

[0341] Users can check the analysis results and new waste disposal method proposals displayed on their devices and plan tests at their waste disposal facilities as needed. Furthermore, the emotion engine recognizes real-time emotional data of residents and employees, and provides training suggestions and work instructions to improve the accuracy and efficiency of waste sorting.

[0342] 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.

[0343] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0344] 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.

[0345] [Second embodiment]

[0346] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0347] 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.

[0348] 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).

[0349] 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.

[0350] 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.

[0351] 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).

[0352] 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. 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.

[0353] 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.

[0354] 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.

[0355] 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.

[0356] 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.

[0357] 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."

[0358] The system of the present invention realizes a waste disposal facility that utilizes a generative artificial intelligence model. Specifically, it involves the process of acquiring image data of waste, classifying it by material using generative AI, analyzing the data to understand the sorting situation in each region, making appropriate guidance suggestions based on the analysis results, and even proposing new waste disposal methods.

[0359] Garbage image acquisition and preprocessing

[0360] First, the server periodically receives image data of the garbage from cameras installed inside the waste disposal facility, and then performs preprocessing such as noise reduction, resolution adjustment, and image normalization to prepare the images for the generative AI model.

[0361] Classification of garbage by material

[0362] After pre-processing, the image data is fed into a deep learning-based generative AI model on the server, which uses techniques such as convolutional neural networks (CNN) to accurately classify waste by material, such as plastic, paper, metal, glass, and other materials.

[0363] Data accumulation and analysis

[0364] The sorted waste data is stored in a database on a server. The accumulated data is aggregated over a set period and analyzed. This analysis includes calculating the sorting rate for each area, comparing it with past data, and identifying trends.

[0365] Presentation of analysis results and educational proposals

[0366] The analysis results are sent to the device, which displays the current state and trends of waste sorting in each region. The user (local government official) can use this information to plan and implement education and campaigns for local residents. For example, if plastic sorting is low in a particular region, they can take measures such as holding information sessions on plastic sorting.

[0367] Proposing a new method for disposing of garbage

[0368] The server utilizes generative AI models based on the analytical data and composition information to propose new waste disposal methods, including improvements to chemical and mechanical processes. The proposed new disposal methods are sent to the device in the form of a report, allowing the user to test them.

[0369] Specific examples

[0370] For example, for 20 images of trash received from a waste disposal facility camera at 9 a.m. each day, the server preprocesses them and then uses a generative AI model to classify them by material: on this day, eight pieces were classified as plastic, four as paper, two as metal, and six as other trash.

[0371] The server then accumulates this data and aggregates and analyzes it for one week, determining that the average plastic sorting rate in Area A is 80%. It also confirms that the sorting rate has improved compared to two months ago. Based on this information, the device proposes an educational campaign to emphasize the importance of further sorting to residents of Area A.

[0372] Additionally, the server uses a generative AI model to suggest new chemical processing methods, calculating details on how to dissolve a particular plastic in a solvent and reuse it as new raw material, and reporting this to the user via their device.

[0373] In this way, the system of the present invention realizes efficient waste separation, promotes recycling, reduces costs, and further reduces the environmental burden.

[0374] The processing flow will be explained below.

[0375] Step 1: Obtaining and preprocessing the dust image

[0376] The server receives image data of the waste from cameras inside the waste treatment facility, performs noise reduction on the received images, adjusts the resolution to a specified size, and normalizes each pixel value to prepare the image for analysis.

[0377] Step 2: Classify the images

[0378] The server then inputs the preprocessed images into a generative AI model, which uses a convolutional neural network (CNN) to classify the waste by material, including plastic, paper, metal, glass, and other categories. The classification results are then recorded as digital data.

[0379] Step 3: Accumulate data

[0380] The server stores the classification results in a database, and the data on the material classification of each piece of garbage is centrally managed and used for future analysis.

[0381] Step 4: Data analysis

[0382] The server aggregates the accumulated data every certain period (e.g., one week). Based on this aggregated data, it calculates the garbage sorting rate and analyzes the sorting situation and trends by region. The analysis results are generated in report format.

[0383] Step 5: Submitting the analysis results

[0384] The server then sends the analysis results to the local government's terminal. The report includes the current state of waste sorting in each area, a comparison with past data, sorting trends, and areas for further improvement.

[0385] Step 6: View Educational Offers

[0386] The device displays the received report, which shows local waste separation rates and trends, and includes educational suggestions for specific waste separation methods. Users can use this information to plan educational activities and campaigns for local residents.

[0387] Step 7: Generate a new processing method

[0388] The server uses the analyzed data and composition information to use generative AI models to suggest new waste disposal methods, including recycling methods and new chemical treatment technologies based on the waste's specific composition.

[0389] Step 8: Generate a report of the new processing method

[0390] The server generates a report detailing the proposed new waste disposal method, including specific steps and expected results.

[0391] Step 9: Submit and test the new process

[0392] The server sends a report of the new processing method to the terminal. The user uses this report to plan a trial of the new processing method. The test results are later fed back to the server for further improvement.

[0393] As described above, through the specific processing flow of each step, the system of the present invention efficiently realizes efficient waste separation, analysis, educational proposals, and proposals for new processing methods.

[0394] Example 1

[0395] 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."

[0396] At conventional waste treatment facilities, waste sorting was done manually, which not only took time and effort but also resulted in insufficient sorting accuracy. Furthermore, there was a lack of efficient means to grasp the waste sorting situation in each region and provide appropriate guidance, making it difficult to effectively treat waste. Furthermore, there was a lack of concrete means to propose and implement new waste treatment methods.

[0397] 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.

[0398] In this invention, the server includes means for receiving preprocessed garbage images, means for performing noise reduction, resolution adjustment, and normalization on the images, means for classifying garbage by material based on the preprocessed images, means for storing data on the classified garbage in a database, means for compiling and analyzing the stored data to grasp the garbage sorting situation in each region, means for presenting the garbage sorting situation and trends in each region based on the analysis results and providing appropriate guidance suggestions, and means for using a generative artificial intelligence model to propose new garbage disposal methods based on garbage composition information.This makes it possible to improve the efficiency and accuracy of garbage sorting work, grasp the garbage sorting situation in each region, provide appropriate guidance suggestions, and propose specific new garbage disposal methods.

[0399] A "server" is a computer system that provides data and services to clients (terminals) via a network.

[0400] A "generative artificial intelligence model" is an artificial intelligence model that has the technology to learn from large amounts of data and perform pattern recognition and prediction, and uses algorithms such as neural networks.

[0401] "Garbage images" are photographic data of garbage captured by a photographing device such as a camera.

[0402] "Preprocessing" is a process in which received dust images are subjected to noise removal, resolution adjustment, normalization, etc. to prepare them for analysis.

[0403] "Material sorting" is the process of separating waste into plastic, paper, metal, glass and other categories.

[0404] A "database" is a software system for efficiently storing, managing, and searching structured data.

[0405] "Data aggregation" is the process of statistically summarizing accumulated data, making it easier to extract information from the results.

[0406] "Analysis" is a means of analyzing the aggregated data in detail to understand the waste sorting situation and trends in each region.

[0407] "Analysis results" refer to the information and conclusions obtained through data analysis, which form the basis for subsequent actions.

[0408] "Guidance proposals" are activities that use the analysis results to educate local residents on how to separate waste and propose improvement measures.

[0409] "Waste composition information" is detailed data on the physical and chemical properties of waste.

[0410] A "new waste disposal method" is a method of waste disposal and recycling that is more efficient and environmentally friendly than conventional methods.

[0411] The system of the present invention realizes a waste treatment facility that utilizes a generative artificial intelligence model. Specific embodiments of the system are described in detail below.

[0412] Garbage image acquisition and preprocessing

[0413] The server periodically receives image data of the garbage from cameras (commonly known as camera devices) installed within the waste disposal facility. High-resolution cameras are used as camera devices. The server uses image processing libraries such as OpenCV to perform preprocessing on the received image data, such as noise removal, resolution adjustment, and image normalization. This prepares the image for the generative AI model to analyze more accurately.

[0414] Classification of garbage by material

[0415] Once preprocessed, the image data is fed into a generative AI model on the server, which is based on a convolutional neural network (a common name for an algorithm) using deep learning libraries such as TensorFlow, and accurately classifies the waste by material, such as plastic, paper, metal, glass, and other materials.

[0416] Data accumulation and analysis

[0417] The data on the sorted waste is stored in a database system (commonly known as a data management system) on the server. The accumulated data is aggregated over a set period and analyzed. This analysis involves using data analysis tools such as Apache Spark to calculate the sorting rate by region, compare it with past data, and identify trends.

[0418] Presentation of analysis results and educational proposals

[0419] The analysis results are sent to the device, which displays the waste sorting situation and trends for each region. The user (commonly known as the operator) uses this information to plan and implement education and campaigns for local residents. The analysis results are visualized using a data visualization tool (e.g., Tableau).

[0420] Proposing a new method for disposing of garbage

[0421] The server uses generative AI models (e.g., GPT-4) based on the analysis data and component information to propose new waste disposal methods. These methods include improvements to chemical and mechanical processes. The proposed new disposal methods are sent to the terminal in the form of a report, which the user can then test.

[0422] Specific examples

[0423] For example, every day at 9 a.m., the server receives 20 images of trash from a camera at a waste disposal facility. The server uses OpenCV to remove noise and adjust the resolution, then uses a TensorFlow-based generative AI model to classify the images by material. On this day, the images were classified as 8 pieces of plastic, 4 pieces of paper, 2 pieces of metal, and 6 pieces of other trash.

[0424] The server then stores this data in a MySQL database and aggregates and analyzes one week's worth of data, determining that the average plastic sorting rate in Area A is 80%. It also confirms that the sorting rate has improved compared to two months ago. Using this information, the device proposes an educational campaign to emphasize the importance of further sorting to residents of Area A.

[0425] Additionally, the server uses GPT-4 to propose new chemical processing methods, calculating details on how to dissolve a particular plastic in a solvent and reuse it as new raw material, and reporting this to the user via the device.

[0426] In this way, the system of the present invention realizes efficient waste separation, promotes recycling, reduces costs, and further reduces the environmental burden.

[0427] Prompt Sentence Examples

[0428] "Please tell us some specific suggestions for increasing the garbage sorting rate in Area A."

[0429] "Please suggest a new way to dispose of plastic waste."

[0430] In this way, the system of the present invention achieves reduced environmental impact and efficient recycling through automation and advanced data analysis at waste treatment facilities.

[0431] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0432] Step 1: Receiving image data

[0433] The server receives image data of the garbage from cameras installed in the waste treatment facility at 9:00 AM every day. The input data is a high-resolution image. The output is an image file of the received raw data.

[0434] Specific behavior:

[0435] 1. The server obtains image files from the camera using a protocol such as FTP.

[0436] 2. Save the image data immediately after receiving it in temporary storage.

[0437] Step 2: Image preprocessing

[0438] The server performs preprocessing on the received images, such as noise removal, resolution adjustment, and normalization. The input is the received raw image data file. The output is the preprocessed image data.

[0439] Specific behavior:

[0440] 1. The server uses the OpenCV library to remove noise using the cv2.GaussianBlur function.

[0441] 2. The server uses the cv2.resize function to adjust to a consistent resolution.

[0442] 3. The server normalizes the image pixel values ​​by dividing them by 255.

[0443] Step 3: Categorize your images by content

[0444] The preprocessed image data is input to the generative AI model on the server. The input is the preprocessed image data. The output is the image classification result (plastic, paper, metal, glass, other).

[0445] Specific behavior:

[0446] 1. The server loads the CNN model using the TensorFlow library.

[0447] 2. The preprocessed image data is input into the CNN model to obtain classification results.

[0448] Step 4: Data accumulation

[0449] The data of the classified garbage is stored in a database on the server. The input is the classified garbage data. The output is structured data stored in the database.

[0450] Specific behavior:

[0451] 1. The server connects to the MySQL database and inserts the new classification data.

[0452] 2. Verify that the data was inserted correctly.

[0453] Step 5: Data collection and analysis

[0454] The server periodically aggregates and analyzes the data in the database. The input is the accumulated database data. The output is a report of the analysis results.

[0455] Specific behavior:

[0456] 1. The server uses Apache Spark to query one week's worth of data from the database.

[0457] 2. Calculate the separation rate and trends based on the acquired data.

[0458] 3. Compile the analysis results in a report format.

[0459] Step 6: Submit and view analysis results

[0460] The analysis results are sent to a terminal, where the waste sorting situation and trends for each region are displayed. The input is the analysis result report. The output is visualized data.

[0461] Specific behavior:

[0462] 1. The server converts the analysis results into JSON format and sends them to the device via the Web API.

[0463] 2. The device displays the received data using a data visualization tool such as Tableau.

[0464] Step 7: Propose a new method of waste disposal

[0465] The server uses a generative AI model based on the composition information to propose new waste disposal methods. The input is the analysis data and composition information. The output is a report proposing a new disposal method.

[0466] Specific behavior:

[0467] 1. The server uses the GPT-4 model to generate prompts for new processing methods.

[0468] 2. The generated processing method is compiled into a report format in Microsoft Word.

[0469] 3. The generated report is sent to the terminal and provided to the user.

[0470] This series of steps will enable efficient waste sorting, analysis, and the proposal of new waste disposal methods at waste disposal facilities.

[0471] (Application example 1)

[0472] 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."

[0473] In modern waste treatment facilities, waste sorting and processing is often done manually, limiting efficiency and accuracy. Furthermore, if waste is not properly sorted, recycling efficiency decreases and the environmental impact increases. Furthermore, similar issues exist in industrial waste and waste processing within factories. This has led to a demand for new technologies to improve waste management efficiency and reduce the environmental impact.

[0474] 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.

[0475] In this invention, the server includes means for receiving preprocessed garbage images and classifying the garbage by material based on the images, means for analyzing the classified garbage data and understanding the garbage sorting situation in each region, means for presenting the garbage sorting situation and trends in each region based on the analysis results and providing appropriate guidance suggestions, means for proposing new garbage disposal methods based on garbage composition information using a generative artificial intelligence model, means for operating a factory robot that moves the classified garbage by material into dedicated containers, and an application installed on a smartphone, smart glasses, head-mounted display, or robot that can monitor and operate the robot's operation from inside and outside the factory. This enables automated, high-precision waste sorting and efficient waste disposal.

[0476] A "server" is a computer system that provides data and services over a network.

[0477] "Preprocessing" refers to the initial processing of data to facilitate subsequent data analysis or classification in artificial intelligence models.

[0478] "Garbage image" refers to image data of waste material captured using a photographic device such as a camera.

[0479] "Material sorting" is the process of classifying a group of objects with specific attributes based on their material (e.g., plastic, paper, metal, glass, etc.).

[0480] "Data analysis" is a method of statistically processing collected data to extract usable information and patterns.

[0481] "Waste sorting status by region" is information that indicates the current state of waste sorting within a specific region.

[0482] A "trend" is a widespread pattern of change in a particular phenomenon or practice over time.

[0483] "Guidance proposal" means specific advice or plans to promote improvement in a specific problem.

[0484] A "generative artificial intelligence model" is an artificial intelligence algorithm that is automatically generated to perform a specific task based on training data.

[0485] "Ingredient information" refers to detailed data about the composition and elements of a substance.

[0486] A "robot" is a programmed mechanical device that can perform specific tasks automatically.

[0487] A "specialized container" is a storage box or container designed for a specific material or purpose.

[0488] An "application" is a software program designed to perform a specific task or function.

[0489] The system of the present invention utilizes a generative artificial intelligence model to realize automatic classification and efficient disposal of waste within a factory. Specific embodiments for implementing this system are described below.

[0490] The system consists of a server, factory robots, mobile devices such as smartphones, smart glasses, and head-mounted displays, as well as the necessary software.

[0491] First, the server periodically receives image data of waste from cameras installed in the factory. The received image data undergoes a pre-processing process to make it suitable for the generative AI model. Pre-processing includes noise removal, resolution adjustment, and image normalization.

[0492] The pre-processed image data is then fed into a deep learning-based generative artificial intelligence model on the server, which uses a convolutional neural network (CNN) to analyze the images and accurately classify the waste into plastic, paper, metal, glass, and other materials.

[0493] The classified waste data is stored in a database on a server and analyzed. The server aggregates the accumulated data and performs analysis to understand the waste sorting situation and trends in each region. The results of this analysis are presented to users via their mobile devices and used as guidance suggestions for improving waste management. For example, if the plastic sorting rate in a particular area is low, an educational campaign for local residents will be suggested.

[0494] Furthermore, new waste disposal methods are proposed by the generative AI model and sent to the user in the form of reports via the server, allowing new chemical and mechanical methods to be tested.

[0495] The factory robots then move the classified waste into dedicated containers based on instructions from the server. The robots' operations can be remotely monitored and controlled using mobile devices such as smartphones, smart glasses, and head-mounted displays.

[0496] As a concrete example, at a waste processing line, the server preprocesses waste image data received from a camera every day at 9:00 a.m., and then uses a generative AI model to classify the data by material. During this process, eight pieces of plastic, four pieces of paper, two pieces of metal, and six pieces of other waste are identified. The analysis results are aggregated for one week, and it is found that the plastic sorting rate in a particular area is 80%. Based on this, guidance suggestions emphasizing the importance of further sorting are presented to the user.

[0497] Example prompts to input to a generative AI model:

[0498] Please perform image capture using the "capture_image" function.

[0499] Use the "preprocess_image" function for preprocessing and perform classification using a generative AI model.

[0500] Based on the classification result, use the "place_in_container" function to move the robot arm to the appropriate container.

[0501] As described above, the system of the present invention enables automated, highly accurate classification and efficient disposal of waste.

[0502] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0503] Step 1:

[0504] The server periodically receives image data of waste from cameras installed in the factory. The input data is raw image data acquired from the camera, and the output is image data suitable for preprocessing. Specifically, the image from the camera is captured and saved as an image file on the server.

[0505] Step 2:

[0506] The server performs preprocessing on the received image data, such as noise removal, resolution adjustment, and image normalization. The input is the raw image data obtained in step 1, and the output is image data that has been preprocessed into a format suitable for the generative AI model. This preprocessing improves the quality of the image and increases the accuracy of analysis by the generative AI model.

[0507] Step 3:

[0508] The server inputs the preprocessed image data into a generative AI model. The input is the preprocessed image data, and the output is waste labels classified by material. The generative AI model uses a convolutional neural network (CNN) to accurately classify each material (plastic, paper, metal, glass, etc.).

[0509] Step 4:

[0510] The server stores the classified waste data in a database. The input is the classification result from the generative AI model, and the output is the waste data stored in the database. This data is used for data analysis, which is useful for future analysis and trend identification.

[0511] Step 5:

[0512] The server aggregates and analyzes waste data over a set period of time to understand the waste separation situation and trends for each region. The input is the accumulated waste data, and the output is information on the separation situation and trends for each region based on the analysis results. Statistical analysis and machine learning techniques are used for the analysis method.

[0513] Step 6:

[0514] The server uses the analysis results to present the user with information on the current state and trends of waste separation in each region and makes appropriate guidance suggestions. The input is the analysis results, and the output is a report of guidance suggestions for the user. The user can use this report to plan and implement educational campaigns and improvement measures.

[0515] Step 7:

[0516] The server uses a generative artificial intelligence model to propose new waste treatment methods. The input is composition information and analytical data, and the output is a report of the new treatment method, leading to more efficient and environmentally friendly treatment methods.

[0517] Step 8:

[0518] Based on commands from the server, factory robots move the classified waste into dedicated containers. The input is the command to move the waste from the server, and the output is the result of the waste being moved to the appropriate container. This operation automates the proper disposal of waste.

[0519] Step 9:

[0520] Users use mobile devices such as smartphones, smart glasses, and head-mounted displays to remotely monitor and operate factory robots. The input is operation commands from the mobile device, and the output is the robot's operating status and monitoring report. Specifically, the current status of the robot can be checked through the application, and manual operation can be performed as needed.

[0521] Through the above processing steps, the system of the present invention enables automated, highly accurate classification and efficient processing of waste.

[0522] 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.

[0523] The system of this invention utilizes a generative artificial intelligence model and combines it with an emotion engine that recognizes user emotions to realize a waste disposal facility. This allows for efficient waste sorting, analysis, educational proposals, and proposals for new disposal methods, while also enabling flexible responses that take into account user emotion data.

[0524] Garbage image acquisition and preprocessing

[0525] First, the server receives image data of the waste from cameras inside the waste treatment facility, and then performs preprocessing such as noise reduction, resolution adjustment, and image normalization.

[0526] Classification of garbage by material

[0527] After preprocessing, the image data is input into a deep learning-based generative AI model stored on the server. The generative AI model uses techniques such as convolutional neural networks (CNN) to classify the waste by material. The classification results are recorded as digital data.

[0528] Data accumulation and analysis

[0529] The classified waste data is stored in a server database. The accumulated data is aggregated over a set period of time, and the sorting rate and trends by region are analyzed. The analysis results are generated in report format and sent to a designated device.

[0530] Presentation of analysis results and educational proposals

[0531] The device receives the analysis results sent from the server and displays the status and trends of waste sorting for each region. Here, the emotion engine recognizes the emotions of the user (local government official) and adjusts the way the analysis results are presented. For example, if the sorting rate is improving, it can display positive feedback.

[0532] Educational proposals using emotion engines

[0533] Based on the analysis results and information from the emotion engine, the device provides local residents with appropriate methods for educating them about waste separation. Users can use this information to plan and implement educational activities for residents. The emotion engine can analyze residents' reactions in real time during educational activities and provide feedback.

[0534] Proposing a new method for disposing of garbage

[0535] The server uses generative AI models based on the analyzed data and composition information to propose new waste disposal methods, including improvements to chemical and mechanical processes. The proposed new disposal methods are sent to the device in the form of a report, allowing users to plan trials at their waste disposal facilities.

[0536] Specific examples

[0537] For example, when a local government device receives a weekly report, the emotion engine analyzes the user's emotional state and adjusts the report display accordingly. If the sorting rate is low, a presentation highlighting areas for improvement will be presented and feedback to motivate the user. Similarly, if the plastic sorting rate in Region A improves by 5% compared to the previous year, positive comments and visual highlights will be provided.

[0538] Furthermore, during the educational campaign, the devices collect participants' emotional data and adjust the educational content in real time. For example, if residents' reactions are positive, the device will continue to explain in detail how to separate trash, but if they are negative, it will switch to a brief explanation of the main points.

[0539] In this way, the system of the present invention realizes efficient waste separation, analysis, educational suggestions, and proposals for new disposal methods, all in combination with user emotion recognition.

[0540] The processing flow will be explained below.

[0541] Step 1: Obtaining and preprocessing the dust image

[0542] The server receives image data of the waste from cameras inside the waste treatment facility. It then performs noise reduction on the received images, adjusts the resolution to a specified size, and normalizes the pixel values ​​of the images to make them suitable for analysis.

[0543] Step 2: Sort the waste by material

[0544] The server then inputs the pre-processed images into a generative AI model, which uses a convolutional neural network (CNN) to classify the waste material into categories such as plastic, paper, metal, glass, and other. The classification results are recorded as digital data and used in the next processing step.

[0545] Step 3: Accumulate data

[0546] The server stores the classified garbage data in a database, which is continuously accumulated and used for future analysis.

[0547] Step 4: Data analysis

[0548] The server collects and analyzes the data at regular intervals (e.g., weekly). This analysis includes calculating the waste separation rate by region, comparing it with past data, and analyzing trends in waste separation. The analysis results are generated in report format and sent to the specified device.

[0549] Step 5: Adjusting the analysis results by the emotion engine

[0550] The device receives the analysis results sent from the server and uses an emotion engine to recognize the user's (local government official's) emotions before displaying them on the screen. The emotion engine adjusts the way the analysis results are displayed depending on the user's reaction. For example, it may display positive emotions or add detailed explanations if necessary.

[0551] Step 6: Displaying educational suggestions and sentiment analysis

[0552] Based on the received data, the device displays the current state of waste sorting in each region and educational suggestions based on that data. The emotion engine analyzes the user's emotional state and dynamically adjusts appropriate educational methods and suggestions. Users can refer to the emotion engine's analysis to plan and implement more effective educational activities.

[0553] Step 7: Generate a new garbage disposal method

[0554] The server uses a generative AI model based on the analyzed data and composition information to propose new waste disposal methods, including improving chemical and mechanical processes and optimizing recycling technologies. The proposals are compiled into a report and sent to the device.

[0555] Step 8: Submit and feedback your new process

[0556] The device receives a report on the new waste disposal method and displays it to the user. The user then tests the new method based on the results and feeds the results back to the server. The feedback data is used to improve the accuracy of future proposals.

[0557] Step 9: Longitudinal analysis of sentiment data

[0558] The devices store emotional data collected during educational activities and the implementation of new waste disposal methods. Using this data, the server performs long-term data analysis and provides optimal educational approaches and waste disposal methods for each region.

[0559] In this way, the system of the present invention realizes efficient waste separation, analysis, educational suggestions, and suggestions for new disposal methods by combining them with user emotion recognition.

[0560] Example 2

[0561] 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."

[0562] At conventional waste disposal facilities, waste separation and disposal method proposals were sometimes inefficient, making it difficult to improve the local waste separation rate or implement appropriate educational activities.In addition, because it was not possible to consider the emotions and reactions of staff and residents in real time, it was difficult to respond individually, making it difficult to carry out effective educational activities or propose disposal methods.

[0563] 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.

[0564] In this invention, the server includes means for receiving preprocessed garbage images and classifying garbage by material based on the images, means for analyzing the classified garbage data and grasping the garbage sorting situation in each region, means for presenting the garbage sorting situation and trends in each region based on the analysis results and making appropriate instruction suggestions, means for proposing new garbage disposal methods based on garbage component information using a generative AI model, means for adjusting the display of the analysis results based on the user's emotional state, and means for collecting user emotional data and adjusting the content of educational activities in real time. This enables efficient garbage sorting, analysis, educational suggestions, and new disposal method suggestions, and enables flexible responses that take into account the user's emotions and reactions.

[0565] "Garbage images" are photographic data of garbage taken by cameras installed in garbage disposal facilities.

[0566] "Preprocessing" refers to image processing such as noise removal, resolution adjustment, and normalization that is performed on the received dust image.

[0567] A "generative AI model" is a generative artificial intelligence model, a trained neural network model that uses deep learning technology to classify garbage by material.

[0568] "Material sorting" is the process of separating garbage into different materials such as plastic, paper, and metal.

[0569] "Database" means an information system for storing and managing data on classified waste.

[0570] "Analysis" refers to analyzing accumulated garbage data using statistical methods and machine learning techniques.

[0571] A "report" is a report summarizing the analysis results in document and graph format.

[0572] "Terminal" refers to an electronic device for displaying analysis results and educational suggestions, including smartphones, PCs, tablets, etc.

[0573] The "emotion engine" is software that analyzes the emotional data of users and residents and adjusts the display content and educational suggestions.

[0574] "Educational activities" are efforts to educate local residents about the importance of sorting garbage and the correct way to do it.

[0575] "New waste disposal methods" are waste disposal technologies or methods that are more efficient or environmentally friendly than conventional methods, proposed using generative AI models.

[0576] "Real-time" means that data and information are processed and reflected immediately.

[0577] The system of the present invention utilizes a generative artificial intelligence model and combines it with an emotion engine that recognizes user emotions to realize a waste disposal facility. This system enables efficient waste sorting, analysis, educational proposals, and proposals for new disposal methods, and enables flexible responses that take into account user emotion data.

[0578] Garbage image acquisition and preprocessing

[0579] First, the server receives image data of the garbage from a camera inside the waste disposal facility. This camera is equipped with a high-resolution image sensor, which can capture even the smallest details of the garbage. The received image data is denoised using the OpenCV library. Next, the resolution is adjusted, for example, to 1024x768 pixels. Finally, the image is normalized using the numpy library, scaling the pixel values ​​to the range 0 to 1.

[0580] Classification of garbage by material

[0581] After preprocessing, the image data is input into a deep learning-based generative AI model stored on the server. This generative AI model utilizes frameworks such as TensorFlow and PyTorch and employs a convolutional neural network (CNN). The model analyzes the received image data and classifies the waste by material, such as plastic, paper, and metal. This makes it possible to select the appropriate disposal method for each type of waste.

[0582] Data accumulation and analysis

[0583] The sorted waste data is stored in a database on the server. This database uses MySQL and MongoDB. Every week, the accumulated data is compiled using a Python script, and the sorting rate and trends by region are analyzed. Statistical analysis and machine learning techniques are used for this analysis. The analysis results are formatted into a report and sent to a designated device.

[0584] Presentation of analysis results and educational proposals

[0585] The device receives the analysis results sent from the server and displays them to the user using intuitive graphs and charts. An emotion engine recognizes the user's (local government official's) emotions and adjusts the presentation of the analysis results accordingly. For example, the software generates text containing positive feedback and displays it on the screen, incorporating an API for emotion analysis (e.g., Microsoft Azure's Emotion API).

[0586] Educational proposals using emotion engines

[0587] Based on the analysis results and information from the emotion engine, the device provides local residents with appropriate methods for educating them on how to sort their garbage. Users can view educational content, including videos and infographics, through a web application or mobile app. The emotion engine analyzes residents' reactions in real time during the education session and can adjust the content and progress of the education on the spot.

[0588] Proposing a new method for disposing of garbage

[0589] Based on the accumulated waste data and analysis results, the server uses a generative AI model to propose new waste disposal methods, including improving the reuse of specific materials and increasing the efficiency of processing equipment. These proposals are formatted into a report containing detailed technical specifications and cost-benefit analysis and sent to a designated device. Users can then try out new waste disposal methods to achieve even more efficient waste disposal.

[0590] Specific examples

[0591] For example, when a local government device receives a weekly report, the emotion engine analyzes the user's emotional state and adjusts the report display accordingly. If the sorting rate is low, a presentation highlighting areas for improvement will be presented, providing feedback to motivate the user. Conversely, if Region A's plastic sorting rate improves by 5% compared to the previous year, positive comments and visual highlights will be provided, allowing users to visually confirm concrete results.

[0592] Furthermore, during the education campaign, the devices collect participants' emotional data and adjust the educational content in real time. For example, if residents' reactions are positive, the device will continue to explain in detail how to separate trash, but if they are negative, it will briefly explain the main points. In this way, the effectiveness of the education can be maximized.

[0593] The above is a specific implementation method of the system of the present invention.

[0594] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0595] Step 1:

[0596] Garbage image acquisition and preprocessing

[0597] The server receives real-time image data of garbage from high-resolution cameras in the waste treatment facility. The image data received as input is first subjected to a noise reduction filter using the OpenCV library. Then, the image resolution is adjusted to 1024x768 pixels and pixel values ​​are scaled to the range of 0 to 1 using the numpy library. As an output, preprocessed image data is obtained. This preprocessed image data is used in the next step.

[0598] Specific behavior:

[0599] The server periodically polls the image data from the camera, calls functions in OpenCV to remove noise and adjust the resolution, and performs normalization with numpy.

[0600] Step 2:

[0601] Classification of garbage by material

[0602] The preprocessed image data is input into a generative AI model on the server. The generative AI model is a convolutional neural network (CNN) implemented in the TensorFlow framework, which classifies the waste into materials such as plastic, paper, and metal. The input data is the preprocessed image data, and the output is a probability value for each material classification. The most appropriate material label is assigned based on this probability value.

[0603] Specific behavior:

[0604] The server inputs the preprocessed image data into the model and receives the probability values ​​for each material returned as the model's inference results. Based on this, the server determines the classification results and stores them in a database.

[0605] Step 3:

[0606] Data accumulation and analysis

[0607] The classified waste data is stored in a database on the server. The input data is the classification results, and the output data is the data in the format stored in the database. The data is aggregated at regular intervals using a Python script, and the sorting rate and trends by region are analyzed. Statistical analysis methods and machine learning algorithms are used for the analysis. The output is a report on the sorting rate and trends by region.

[0608] Specific behavior:

[0609] The server periodically accesses the database and runs a batch script to aggregate the classification data, and then reports the analysis results in JSON and PDF format for the next step.

[0610] Step 4:

[0611] Presentation of analysis results and educational proposals

[0612] The device receives the analysis results sent from the server and displays them to the user using intuitive graphs and charts. The input data is the analysis results sent from the server, and the output is data in the form of graphs and charts displayed on the screen. The emotion engine recognizes the user's emotions and adjusts the display method. Specifically, it provides positive feedback and emphasizes points of caution depending on the user's emotional state.

[0613] Specific behavior:

[0614] The device receives the analysis results and uses libraries such as D3.js and Chart.js to draw graphs and charts. Based on the output of the emotion engine, it generates auxiliary text to adjust the display content.

[0615] Step 5:

[0616] Educational proposals using emotion engines

[0617] Based on the analysis results and information from the emotion engine, the device provides local residents with appropriate methods for educating them on how to separate waste. The input data are the analysis results and the output of the emotion engine, and the output data is educational content. Users view the educational content through a web application or mobile app. The emotion engine analyzes the emotional reactions of residents during the education in real time and adjusts the educational content as needed.

[0618] Specific behavior:

[0619] While playing educational content, the device transmits the residents' emotional data obtained from cameras and sensors to an emotion engine, which then displays supplementary explanations and encouraging messages based on the output of the emotion engine.

[0620] Step 6:

[0621] Proposing a new method for disposing of garbage

[0622] The server uses a generative AI model to propose new waste disposal methods based on the accumulated waste data and analysis results. The input data is the waste data and analysis results, and the output data is a report describing the new waste disposal method. The proposals include ways to reuse specific materials and improvements to the disposal equipment.

[0623] Specific behavior:

[0624] The server runs the generative AI model to generate a proposal for a new waste disposal method, converts the proposal into a PDF format, and sends it to the device via HTTP. The report includes technical specifications, cost-effectiveness, and specific implementation steps.

[0625] The above are the specific processing steps in the system of the present invention. In this way, it is possible to realize efficient waste separation, analysis, educational suggestions, and proposals for new waste disposal methods in combination with user emotion recognition.

[0626] (Application example 2)

[0627] 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."

[0628] In modern waste treatment facilities, efficient waste sorting, analysis, training, and new treatment methods are key challenges. To improve employee motivation and efficiency, it is also necessary to recognize user emotions in real time and provide appropriate feedback. However, existing systems lack dynamic feedback based on user emotions, resulting in insufficient optimization of waste treatment. Accurate waste classification and training are particularly important in large-scale facilities such as logistics centers, and new technologies with efficient feedback systems are needed.

[0629] The identification processing by the identification 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 utilizing a generative AI model to receive preprocessed garbage images and classify the garbage by material based on the images; means for analyzing the classified garbage data and understanding the garbage sorting situation in each region; means for presenting the garbage sorting situation and trends in each region based on the analysis results and providing appropriate guidance; means for using the generative AI model to propose a new garbage disposal method based on garbage composition information; and means for recognizing the user's emotions and providing feedback in real time. This enables efficient garbage sorting and analysis and allows the user to receive appropriate feedback based on their emotions, thereby improving the garbage disposal efficiency in the logistics center and increasing employee motivation.

[0630] A "generative artificial intelligence model" is an artificial intelligence technology that learns complex patterns and features based on data and makes predictions and classifications.

[0631] A "waste disposal facility" is a place where collected waste is processed and separated into reusable materials and non-combustible materials.

[0632] "Garbage images" are photographs or videos that visually record the type and condition of waste.

[0633] An "emotion engine" is a technology that analyzes data such as a user's facial expressions and voice to recognize their emotional state.

[0634] "Regional waste separation status" refers to how accurately waste is separated in a particular region.

[0635] "Guidance suggestions" are the act of suggesting improvements or new methods based on specific results or situations.

[0636] "Real-time feedback" is a technology that provides immediate responses and suggestions for improvement based on the current state or situation.

[0637] "Preprocessing" refers to the initial processing and adjustment work carried out to improve the quality of data.

[0638] "Material sorting" is the process of separating waste based on its material (paper, plastic, glass, etc.).

[0639] A "new garbage disposal method" is a newly proposed method of waste disposal that differs from conventional methods.

[0640] This invention is a waste disposal facility system incorporating an emotion engine that utilizes a generative AI model. Specifically, the system uses an application on smartphones and head-mounted displays in logistics centers to make it easier for employees to sort waste.

[0641] The server receives garbage image data acquired from cameras installed in the logistics center. This image data undergoes preprocessing such as noise removal, resolution adjustment, and image normalization before being input into a generative AI model. The generative AI model uses a convolutional neural network (CNN) to classify the garbage by material. The classification results are stored as digital data in a database on the server.

[0642] The data on the sorted waste is compiled periodically, and the status and trends of waste sorting in each region are analyzed. The analysis results are generated in report format and sent to a designated device. The device displays the analysis results and makes appropriate guidance suggestions. In addition, an emotion engine recognizes the emotions of the user (local government officials or logistics center staff) and adjusts the way the analysis results are presented. For example, if the waste sorting rate has improved, a display containing positive feedback will be displayed.

[0643] Furthermore, the server uses a generative AI model based on the analyzed data and composition information to propose new waste disposal methods, which are then sent to the device in the form of a report, allowing users to plan tests at their waste disposal facilities.

[0644] To give a specific example, employees working in a logistics center wear head-mounted displays and sort trash. Images of trash taken by the employees are sent to a server, where a generative AI model classifies them as "plastic." At the same time, if the emotion engine analyzes the employee's face and recognizes the emotion of "fatigue," the system provides positive feedback, saying, "Let's concentrate a little and do our best. Trash is plastic." This leads to efficient trash sorting and improved employee motivation.

[0645] An example of a prompt is as follows:

[0646] "You will take a picture of the garbage and input it into a generative AI model to classify the type of garbage. Then, write a program to analyze the user's emotions and provide appropriate feedback."

[0647] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0648] Step 1:

[0649] The server receives image data of dust particles from cameras installed in the logistics center. The received image data undergoes preprocessing such as noise removal, resolution adjustment, and image normalization. This improves the quality of the image data and provides input data for effective subsequent processing.

[0650] Step 2:

[0651] The server inputs the pre-processed garbage image data into a generative AI model. The generative AI model uses a convolutional neural network (CNN) to classify the garbage by material. Data analysis and calculations based on the input image data result in a classification such as "plastic" or "paper."

[0652] Step 3:

[0653] The generated classification results are stored in a database on the server, which accumulates data including information on the type and quantity of waste, ensuring data consistency and reusability.

[0654] Step 4:

[0655] The server periodically compiles the classification data stored in the database and analyzes the waste sorting situation and trends for each region. The analysis results are generated as digital data and output in report format. This analysis process involves statistically evaluating the input data and calculating data to identify trends.

[0656] Step 5:

[0657] The device receives the analysis results sent in report format from the server and displays the status and trends of waste sorting by region. An emotion engine runs simultaneously to recognize the user's emotional data. Based on this emotional data, the device adjusts the presentation method of the report and the content of the feedback. For example, if a positive emotion is recognized, a praising comment is displayed.

[0658] Step 6:

[0659] The server utilizes a generative AI model to propose new waste disposal methods based on additional analysis data and waste composition information. This proposal is sent to the device in the form of a report. The new waste disposal method is output as the result of data analysis and creative proposals based on the input composition information.

[0660] Step 7:

[0661] Users can check the analysis results and new waste disposal method proposals displayed on their devices and plan tests at their waste disposal facilities as needed. Furthermore, the emotion engine recognizes real-time emotional data of residents and employees, and provides training suggestions and work instructions to improve the accuracy and efficiency of waste sorting.

[0662] 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.

[0663] 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.

[0664] 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.

[0665] [Third embodiment]

[0666] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0667] 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.

[0668] 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).

[0669] 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.

[0670] 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.

[0671] 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).

[0672] 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. 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.

[0673] 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.

[0674] 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.

[0675] 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.

[0676] 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.

[0677] 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."

[0678] The system of the present invention realizes a waste disposal facility that utilizes a generative artificial intelligence model. Specifically, it involves the process of acquiring image data of waste, classifying it by material using generative AI, analyzing the data to understand the sorting situation in each region, making appropriate guidance suggestions based on the analysis results, and even proposing new waste disposal methods.

[0679] Garbage image acquisition and preprocessing

[0680] First, the server periodically receives image data of the garbage from cameras installed inside the waste disposal facility, and then performs preprocessing such as noise reduction, resolution adjustment, and image normalization to prepare the images for the generative AI model.

[0681] Classification of garbage by material

[0682] After pre-processing, the image data is fed into a deep learning-based generative AI model on the server, which uses techniques such as convolutional neural networks (CNN) to accurately classify waste by material, such as plastic, paper, metal, glass, and other materials.

[0683] Data accumulation and analysis

[0684] The sorted waste data is stored in a database on a server. The accumulated data is aggregated over a set period and analyzed. This analysis includes calculating the sorting rate for each area, comparing it with past data, and identifying trends.

[0685] Presentation of analysis results and educational proposals

[0686] The analysis results are sent to the device, which displays the current state and trends of waste sorting in each region. The user (local government official) can use this information to plan and implement education and campaigns for local residents. For example, if plastic sorting is low in a particular region, they can take measures such as holding information sessions on plastic sorting.

[0687] Proposing a new method for disposing of garbage

[0688] The server utilizes generative AI models based on the analytical data and composition information to propose new waste disposal methods, including improvements to chemical and mechanical processes. The proposed new disposal methods are sent to the device in the form of a report, allowing the user to test them.

[0689] Specific examples

[0690] For example, for 20 images of trash received from a waste disposal facility camera at 9 a.m. each day, the server preprocesses them and then uses a generative AI model to classify them by material: on this day, eight pieces were classified as plastic, four as paper, two as metal, and six as other trash.

[0691] The server then accumulates this data and aggregates and analyzes it for one week, determining that the average plastic sorting rate in Area A is 80%. It also confirms that the sorting rate has improved compared to two months ago. Based on this information, the device proposes an educational campaign to emphasize the importance of further sorting to residents of Area A.

[0692] Additionally, the server uses a generative AI model to suggest new chemical processing methods, calculating details on how to dissolve a particular plastic in a solvent and reuse it as new raw material, and reporting this to the user via their device.

[0693] In this way, the system of the present invention realizes efficient waste separation, promotes recycling, reduces costs, and further reduces the environmental burden.

[0694] The processing flow will be explained below.

[0695] Step 1: Obtaining and preprocessing the dust image

[0696] The server receives image data of the waste from cameras inside the waste treatment facility, performs noise reduction on the received images, adjusts the resolution to a specified size, and normalizes each pixel value to prepare the image for analysis.

[0697] Step 2: Classify the images

[0698] The server then inputs the preprocessed images into a generative AI model, which uses a convolutional neural network (CNN) to classify the waste by material, including plastic, paper, metal, glass, and other categories. The classification results are then recorded as digital data.

[0699] Step 3: Accumulate data

[0700] The server stores the classification results in a database, and the data on the material classification of each piece of garbage is centrally managed and used for future analysis.

[0701] Step 4: Data analysis

[0702] The server aggregates the accumulated data every certain period (e.g., one week). Based on this aggregated data, it calculates the garbage sorting rate and analyzes the sorting situation and trends by region. The analysis results are generated in report format.

[0703] Step 5: Submitting the analysis results

[0704] The server then sends the analysis results to the local government's terminal. The report includes the current state of waste sorting in each area, a comparison with past data, sorting trends, and areas for further improvement.

[0705] Step 6: View Educational Offers

[0706] The device displays the received report, which shows local waste separation rates and trends, and includes educational suggestions for specific waste separation methods. Users can use this information to plan educational activities and campaigns for local residents.

[0707] Step 7: Generate a new processing method

[0708] The server uses the analyzed data and composition information to use generative AI models to suggest new waste disposal methods, including recycling methods and new chemical treatment technologies based on the waste's specific composition.

[0709] Step 8: Generate a report of the new processing method

[0710] The server generates a report detailing the proposed new waste disposal method, including specific steps and expected results.

[0711] Step 9: Submit and test the new process

[0712] The server sends a report of the new processing method to the terminal. The user uses this report to plan a trial of the new processing method. The test results are later fed back to the server for further improvement.

[0713] As described above, through the specific processing flow of each step, the system of the present invention efficiently realizes efficient waste separation, analysis, educational proposals, and proposals for new processing methods.

[0714] Example 1

[0715] 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."

[0716] At conventional waste treatment facilities, waste sorting was done manually, which not only took time and effort but also resulted in insufficient sorting accuracy. Furthermore, there was a lack of efficient means to grasp the waste sorting situation in each region and provide appropriate guidance, making it difficult to effectively treat waste. Furthermore, there was a lack of concrete means to propose and implement new waste treatment methods.

[0717] 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.

[0718] In this invention, the server includes means for receiving preprocessed garbage images, means for performing noise reduction, resolution adjustment, and normalization on the images, means for classifying garbage by material based on the preprocessed images, means for storing data on the classified garbage in a database, means for compiling and analyzing the stored data to grasp the garbage sorting situation in each region, means for presenting the garbage sorting situation and trends in each region based on the analysis results and providing appropriate guidance suggestions, and means for using a generative artificial intelligence model to propose new garbage disposal methods based on garbage composition information.This makes it possible to improve the efficiency and accuracy of garbage sorting work, grasp the garbage sorting situation in each region, provide appropriate guidance suggestions, and propose specific new garbage disposal methods.

[0719] A "server" is a computer system that provides data and services to clients (terminals) via a network.

[0720] A "generative artificial intelligence model" is an artificial intelligence model that has the technology to learn from large amounts of data and perform pattern recognition and prediction, and uses algorithms such as neural networks.

[0721] "Garbage images" are photographic data of garbage captured by a photographing device such as a camera.

[0722] "Preprocessing" is a process in which received dust images are subjected to noise removal, resolution adjustment, normalization, etc. to prepare them for analysis.

[0723] "Material sorting" is the process of separating waste into plastic, paper, metal, glass and other categories.

[0724] A "database" is a software system for efficiently storing, managing, and searching structured data.

[0725] "Data aggregation" is the process of statistically summarizing accumulated data, making it easier to extract information from the results.

[0726] "Analysis" is a means of analyzing the aggregated data in detail to understand the waste sorting situation and trends in each region.

[0727] "Analysis results" refer to the information and conclusions obtained through data analysis, which form the basis for subsequent actions.

[0728] "Guidance proposals" are activities that use the analysis results to educate local residents on how to separate waste and propose improvement measures.

[0729] "Waste composition information" is detailed data on the physical and chemical properties of waste.

[0730] A "new waste disposal method" is a method of waste disposal and recycling that is more efficient and environmentally friendly than conventional methods.

[0731] The system of the present invention realizes a waste treatment facility that utilizes a generative artificial intelligence model. Specific embodiments of the system are described in detail below.

[0732] Garbage image acquisition and preprocessing

[0733] The server periodically receives image data of the garbage from cameras (commonly known as camera devices) installed within the waste disposal facility. High-resolution cameras are used as camera devices. The server uses image processing libraries such as OpenCV to perform preprocessing on the received image data, such as noise removal, resolution adjustment, and image normalization. This prepares the image for the generative AI model to analyze more accurately.

[0734] Classification of garbage by material

[0735] Once preprocessed, the image data is fed into a generative AI model on the server, which is based on a convolutional neural network (a common name for an algorithm) using deep learning libraries such as TensorFlow, and accurately classifies the waste by material, such as plastic, paper, metal, glass, and other materials.

[0736] Data accumulation and analysis

[0737] The data on the sorted waste is stored in a database system (commonly known as a data management system) on the server. The accumulated data is aggregated over a set period and analyzed. This analysis involves using data analysis tools such as Apache Spark to calculate the sorting rate by region, compare it with past data, and identify trends.

[0738] Presentation of analysis results and educational proposals

[0739] The analysis results are sent to the device, which displays the waste sorting situation and trends for each region. The user (commonly known as the operator) uses this information to plan and implement education and campaigns for local residents. The analysis results are visualized using a data visualization tool (e.g., Tableau).

[0740] Proposing a new method for disposing of garbage

[0741] The server uses generative AI models (e.g., GPT-4) based on the analysis data and component information to propose new waste disposal methods. These methods include improvements to chemical and mechanical processes. The proposed new disposal methods are sent to the terminal in the form of a report, which the user can then test.

[0742] Specific examples

[0743] For example, every day at 9 a.m., the server receives 20 images of trash from a camera at a waste disposal facility. The server uses OpenCV to remove noise and adjust the resolution, then uses a TensorFlow-based generative AI model to classify the images by material. On this day, the images were classified as 8 pieces of plastic, 4 pieces of paper, 2 pieces of metal, and 6 pieces of other trash.

[0744] The server then stores this data in a MySQL database and aggregates and analyzes one week's worth of data, determining that the average plastic sorting rate in Area A is 80%. It also confirms that the sorting rate has improved compared to two months ago. Using this information, the device proposes an educational campaign to emphasize the importance of further sorting to residents of Area A.

[0745] Additionally, the server uses GPT-4 to propose new chemical processing methods, calculating details on how to dissolve a particular plastic in a solvent and reuse it as new raw material, and reporting this to the user via the device.

[0746] In this way, the system of the present invention realizes efficient waste separation, promotes recycling, reduces costs, and further reduces the environmental burden.

[0747] Prompt Sentence Examples

[0748] "Please tell us some specific suggestions for increasing the garbage sorting rate in Area A."

[0749] "Please suggest a new way to dispose of plastic waste."

[0750] In this way, the system of the present invention achieves reduced environmental impact and efficient recycling through automation and advanced data analysis at waste treatment facilities.

[0751] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0752] Step 1: Receiving image data

[0753] The server receives image data of the garbage from cameras installed in the waste treatment facility at 9:00 AM every day. The input data is a high-resolution image. The output is an image file of the received raw data.

[0754] Specific behavior:

[0755] 1. The server obtains image files from the camera using a protocol such as FTP.

[0756] 2. Save the image data immediately after receiving it in temporary storage.

[0757] Step 2: Image preprocessing

[0758] The server performs preprocessing on the received images, such as noise removal, resolution adjustment, and normalization. The input is the received raw image data file. The output is the preprocessed image data.

[0759] Specific behavior:

[0760] 1. The server uses the OpenCV library to remove noise using the cv2.GaussianBlur function.

[0761] 2. The server uses the cv2.resize function to adjust to a consistent resolution.

[0762] 3. The server normalizes the image pixel values ​​by dividing them by 255.

[0763] Step 3: Categorize your images by content

[0764] The preprocessed image data is input to the generative AI model on the server. The input is the preprocessed image data. The output is the image classification result (plastic, paper, metal, glass, other).

[0765] Specific behavior:

[0766] 1. The server loads the CNN model using the TensorFlow library.

[0767] 2. The preprocessed image data is input into the CNN model to obtain classification results.

[0768] Step 4: Data accumulation

[0769] The data of the classified garbage is stored in a database on the server. The input is the classified garbage data. The output is structured data stored in the database.

[0770] Specific behavior:

[0771] 1. The server connects to the MySQL database and inserts the new classification data.

[0772] 2. Verify that the data was inserted correctly.

[0773] Step 5: Data collection and analysis

[0774] The server periodically aggregates and analyzes the data in the database. The input is the accumulated database data. The output is a report of the analysis results.

[0775] Specific behavior:

[0776] 1. The server uses Apache Spark to query one week's worth of data from the database.

[0777] 2. Calculate the separation rate and trends based on the acquired data.

[0778] 3. Compile the analysis results in a report format.

[0779] Step 6: Submit and view analysis results

[0780] The analysis results are sent to a terminal, where the waste sorting situation and trends for each region are displayed. The input is the analysis result report. The output is visualized data.

[0781] Specific behavior:

[0782] 1. The server converts the analysis results into JSON format and sends them to the device via the Web API.

[0783] 2. The device displays the received data using a data visualization tool such as Tableau.

[0784] Step 7: Propose a new method of waste disposal

[0785] The server uses a generative AI model based on the composition information to propose new waste disposal methods. The input is the analysis data and composition information. The output is a report proposing a new disposal method.

[0786] Specific behavior:

[0787] 1. The server uses the GPT-4 model to generate prompts for new processing methods.

[0788] 2. The generated processing method is compiled into a report format in Microsoft Word.

[0789] 3. The generated report is sent to the terminal and provided to the user.

[0790] This series of steps will enable efficient waste sorting, analysis, and the proposal of new waste disposal methods at waste disposal facilities.

[0791] (Application example 1)

[0792] 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."

[0793] In modern waste treatment facilities, waste sorting and processing is often done manually, limiting efficiency and accuracy. Furthermore, if waste is not properly sorted, recycling efficiency decreases and the environmental impact increases. Furthermore, similar issues exist in industrial waste and waste processing within factories. This has led to a demand for new technologies to improve waste management efficiency and reduce the environmental impact.

[0794] 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.

[0795] In this invention, the server includes means for receiving preprocessed garbage images and classifying the garbage by material based on the images, means for analyzing the classified garbage data and understanding the garbage sorting situation in each region, means for presenting the garbage sorting situation and trends in each region based on the analysis results and providing appropriate guidance suggestions, means for proposing new garbage disposal methods based on garbage composition information using a generative artificial intelligence model, means for operating a factory robot that moves the classified garbage by material into dedicated containers, and an application installed on a smartphone, smart glasses, head-mounted display, or robot that can monitor and operate the robot's operation from inside and outside the factory. This enables automated, high-precision waste sorting and efficient waste disposal.

[0796] A "server" is a computer system that provides data and services over a network.

[0797] "Preprocessing" refers to the initial processing of data to facilitate subsequent data analysis or classification in artificial intelligence models.

[0798] "Garbage image" refers to image data of waste material captured using a photographic device such as a camera.

[0799] "Material sorting" is the process of classifying a group of objects with specific attributes based on their material (e.g., plastic, paper, metal, glass, etc.).

[0800] "Data analysis" is a method of statistically processing collected data to extract usable information and patterns.

[0801] "Waste sorting status by region" is information that indicates the current state of waste sorting within a specific region.

[0802] A "trend" is a widespread pattern of change in a particular phenomenon or practice over time.

[0803] "Guidance proposal" means specific advice or plans to promote improvement in a specific problem.

[0804] A "generative artificial intelligence model" is an artificial intelligence algorithm that is automatically generated to perform a specific task based on training data.

[0805] "Ingredient information" refers to detailed data about the composition and elements of a substance.

[0806] A "robot" is a programmed mechanical device that can perform specific tasks automatically.

[0807] A "specialized container" is a storage box or container designed for a specific material or purpose.

[0808] An "application" is a software program designed to perform a specific task or function.

[0809] The system of the present invention utilizes a generative artificial intelligence model to realize automatic classification and efficient disposal of waste within a factory. Specific embodiments for implementing this system are described below.

[0810] The system consists of a server, factory robots, mobile devices such as smartphones, smart glasses, and head-mounted displays, as well as the necessary software.

[0811] First, the server periodically receives image data of waste from cameras installed in the factory. The received image data undergoes a pre-processing process to make it suitable for the generative AI model. Pre-processing includes noise removal, resolution adjustment, and image normalization.

[0812] The pre-processed image data is then fed into a deep learning-based generative artificial intelligence model on the server, which uses a convolutional neural network (CNN) to analyze the images and accurately classify the waste into plastic, paper, metal, glass, and other materials.

[0813] The classified waste data is stored in a database on a server and analyzed. The server aggregates the accumulated data and performs analysis to understand the waste sorting situation and trends in each region. The results of this analysis are presented to users via their mobile devices and used as guidance suggestions for improving waste management. For example, if the plastic sorting rate in a particular area is low, an educational campaign for local residents will be suggested.

[0814] Furthermore, new waste disposal methods are proposed by the generative AI model and sent to the user in the form of reports via the server, allowing new chemical and mechanical methods to be tested.

[0815] The factory robots then move the classified waste into dedicated containers based on instructions from the server. The robots' operations can be remotely monitored and controlled using mobile devices such as smartphones, smart glasses, and head-mounted displays.

[0816] As a concrete example, at a waste processing line, the server preprocesses waste image data received from a camera every day at 9:00 a.m., and then uses a generative AI model to classify the data by material. During this process, eight pieces of plastic, four pieces of paper, two pieces of metal, and six pieces of other waste are identified. The analysis results are aggregated for one week, and it is found that the plastic sorting rate in a particular area is 80%. Based on this, guidance suggestions emphasizing the importance of further sorting are presented to the user.

[0817] Example prompts to input to a generative AI model:

[0818] Please perform image capture using the "capture_image" function.

[0819] Use the "preprocess_image" function for preprocessing and perform classification using a generative AI model.

[0820] Based on the classification result, use the "place_in_container" function to move the robot arm to the appropriate container.

[0821] As described above, the system of the present invention enables automated, highly accurate classification and efficient disposal of waste.

[0822] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0823] Step 1:

[0824] The server periodically receives image data of waste from cameras installed in the factory. The input data is raw image data acquired from the camera, and the output is image data suitable for preprocessing. Specifically, the image from the camera is captured and saved as an image file on the server.

[0825] Step 2:

[0826] The server performs preprocessing on the received image data, such as noise removal, resolution adjustment, and image normalization. The input is the raw image data obtained in step 1, and the output is image data that has been preprocessed into a format suitable for the generative AI model. This preprocessing improves the quality of the image and increases the accuracy of analysis by the generative AI model.

[0827] Step 3:

[0828] The server inputs the preprocessed image data into a generative AI model. The input is the preprocessed image data, and the output is waste labels classified by material. The generative AI model uses a convolutional neural network (CNN) to accurately classify each material (plastic, paper, metal, glass, etc.).

[0829] Step 4:

[0830] The server stores the classified waste data in a database. The input is the classification result from the generative AI model, and the output is the waste data stored in the database. This data is used for data analysis, which is useful for future analysis and trend identification.

[0831] Step 5:

[0832] The server aggregates and analyzes waste data over a set period of time to understand the waste separation situation and trends for each region. The input is the accumulated waste data, and the output is information on the separation situation and trends for each region based on the analysis results. Statistical analysis and machine learning techniques are used for the analysis method.

[0833] Step 6:

[0834] The server uses the analysis results to present the user with information on the current state and trends of waste separation in each region and makes appropriate guidance suggestions. The input is the analysis results, and the output is a report of guidance suggestions for the user. The user can use this report to plan and implement educational campaigns and improvement measures.

[0835] Step 7:

[0836] The server uses a generative artificial intelligence model to propose new waste treatment methods. The input is composition information and analytical data, and the output is a report of the new treatment method, leading to more efficient and environmentally friendly treatment methods.

[0837] Step 8:

[0838] Based on commands from the server, factory robots move the classified waste into dedicated containers. The input is the command to move the waste from the server, and the output is the result of the waste being moved to the appropriate container. This operation automates the proper disposal of waste.

[0839] Step 9:

[0840] Users use mobile devices such as smartphones, smart glasses, and head-mounted displays to remotely monitor and operate factory robots. The input is operation commands from the mobile device, and the output is the robot's operating status and monitoring report. Specifically, the current status of the robot can be checked through the application, and manual operation can be performed as needed.

[0841] Through the above processing steps, the system of the present invention enables automated, highly accurate classification and efficient processing of waste.

[0842] 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.

[0843] The system of this invention utilizes a generative artificial intelligence model and combines it with an emotion engine that recognizes user emotions to realize a waste disposal facility. This allows for efficient waste sorting, analysis, educational proposals, and proposals for new disposal methods, while also enabling flexible responses that take into account user emotion data.

[0844] Garbage image acquisition and preprocessing

[0845] First, the server receives image data of the waste from cameras inside the waste treatment facility, and then performs preprocessing such as noise reduction, resolution adjustment, and image normalization.

[0846] Classification of garbage by material

[0847] After preprocessing, the image data is input into a deep learning-based generative AI model stored on the server. The generative AI model uses techniques such as convolutional neural networks (CNN) to classify the waste by material. The classification results are recorded as digital data.

[0848] Data accumulation and analysis

[0849] The classified waste data is stored in a server database. The accumulated data is aggregated over a set period of time, and the sorting rate and trends by region are analyzed. The analysis results are generated in report format and sent to a designated device.

[0850] Presentation of analysis results and educational proposals

[0851] The device receives the analysis results sent from the server and displays the status and trends of waste sorting for each region. Here, the emotion engine recognizes the emotions of the user (local government official) and adjusts the way the analysis results are presented. For example, if the sorting rate is improving, it can display positive feedback.

[0852] Educational proposals using emotion engines

[0853] Based on the analysis results and information from the emotion engine, the device provides local residents with appropriate methods for educating them about waste separation. Users can use this information to plan and implement educational activities for residents. The emotion engine can analyze residents' reactions in real time during educational activities and provide feedback.

[0854] Proposing a new method for disposing of garbage

[0855] The server uses generative AI models based on the analyzed data and composition information to propose new waste disposal methods, including improvements to chemical and mechanical processes. The proposed new disposal methods are sent to the device in the form of a report, allowing users to plan trials at their waste disposal facilities.

[0856] Specific examples

[0857] For example, when a local government device receives a weekly report, the emotion engine analyzes the user's emotional state and adjusts the report display accordingly. If the sorting rate is low, a presentation highlighting areas for improvement will be presented and feedback to motivate the user. Similarly, if the plastic sorting rate in Region A improves by 5% compared to the previous year, positive comments and visual highlights will be provided.

[0858] Furthermore, during the educational campaign, the devices collect participants' emotional data and adjust the educational content in real time. For example, if residents' reactions are positive, the device will continue to explain in detail how to separate trash, but if they are negative, it will switch to a brief explanation of the main points.

[0859] In this way, the system of the present invention realizes efficient waste separation, analysis, educational suggestions, and proposals for new disposal methods, all in combination with user emotion recognition.

[0860] The processing flow will be explained below.

[0861] Step 1: Obtaining and preprocessing the dust image

[0862] The server receives image data of the waste from cameras inside the waste treatment facility. It then performs noise reduction on the received images, adjusts the resolution to a specified size, and normalizes the pixel values ​​of the images to make them suitable for analysis.

[0863] Step 2: Sort the waste by material

[0864] The server then inputs the pre-processed images into a generative AI model, which uses a convolutional neural network (CNN) to classify the waste material into categories such as plastic, paper, metal, glass, and other. The classification results are recorded as digital data and used in the next processing step.

[0865] Step 3: Accumulate data

[0866] The server stores the classified garbage data in a database, which is continuously accumulated and used for future analysis.

[0867] Step 4: Data analysis

[0868] The server collects and analyzes the data at regular intervals (e.g., weekly). This analysis includes calculating the waste separation rate by region, comparing it with past data, and analyzing trends in waste separation. The analysis results are generated in report format and sent to the specified device.

[0869] Step 5: Adjusting the analysis results by the emotion engine

[0870] The device receives the analysis results sent from the server and uses an emotion engine to recognize the user's (local government official's) emotions before displaying them on the screen. The emotion engine adjusts the way the analysis results are displayed depending on the user's reaction. For example, it may display positive emotions or add detailed explanations if necessary.

[0871] Step 6: Displaying educational suggestions and sentiment analysis

[0872] Based on the received data, the device displays the current state of waste sorting in each region and educational suggestions based on that data. The emotion engine analyzes the user's emotional state and dynamically adjusts appropriate educational methods and suggestions. Users can refer to the emotion engine's analysis to plan and implement more effective educational activities.

[0873] Step 7: Generate a new garbage disposal method

[0874] The server uses a generative AI model based on the analyzed data and composition information to propose new waste disposal methods, including improving chemical and mechanical processes and optimizing recycling technologies. The proposals are compiled into a report and sent to the device.

[0875] Step 8: Submit and feedback your new process

[0876] The device receives a report on the new waste disposal method and displays it to the user. The user then tests the new method based on the results and feeds the results back to the server. The feedback data is used to improve the accuracy of future proposals.

[0877] Step 9: Longitudinal analysis of sentiment data

[0878] The devices store emotional data collected during educational activities and the implementation of new waste disposal methods. Using this data, the server performs long-term data analysis and provides optimal educational approaches and waste disposal methods for each region.

[0879] In this way, the system of the present invention realizes efficient waste separation, analysis, educational suggestions, and suggestions for new disposal methods by combining them with user emotion recognition.

[0880] Example 2

[0881] 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."

[0882] At conventional waste disposal facilities, waste separation and disposal method proposals were sometimes inefficient, making it difficult to improve the local waste separation rate or implement appropriate educational activities.In addition, because it was not possible to consider the emotions and reactions of staff and residents in real time, it was difficult to respond individually, making it difficult to carry out effective educational activities or propose disposal methods.

[0883] 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.

[0884] In this invention, the server includes means for receiving preprocessed garbage images and classifying garbage by material based on the images, means for analyzing the classified garbage data and grasping the garbage sorting situation in each region, means for presenting the garbage sorting situation and trends in each region based on the analysis results and making appropriate instruction suggestions, means for proposing new garbage disposal methods based on garbage component information using a generative AI model, means for adjusting the display of the analysis results based on the user's emotional state, and means for collecting user emotional data and adjusting the content of educational activities in real time. This enables efficient garbage sorting, analysis, educational suggestions, and new disposal method suggestions, and enables flexible responses that take into account the user's emotions and reactions.

[0885] "Garbage images" are photographic data of garbage taken by cameras installed in garbage disposal facilities.

[0886] "Preprocessing" refers to image processing such as noise removal, resolution adjustment, and normalization that is performed on the received dust image.

[0887] A "generative AI model" is a generative artificial intelligence model, a trained neural network model that uses deep learning technology to classify garbage by material.

[0888] "Material sorting" is the process of separating garbage into different materials such as plastic, paper, and metal.

[0889] "Database" means an information system for storing and managing data on classified waste.

[0890] "Analysis" refers to analyzing accumulated garbage data using statistical methods and machine learning techniques.

[0891] A "report" is a report summarizing the analysis results in document and graph format.

[0892] "Terminal" refers to an electronic device for displaying analysis results and educational suggestions, including smartphones, PCs, tablets, etc.

[0893] The "emotion engine" is software that analyzes the emotional data of users and residents and adjusts the display content and educational suggestions.

[0894] "Educational activities" are efforts to educate local residents about the importance of sorting garbage and the correct way to do it.

[0895] "New waste disposal methods" are waste disposal technologies or methods that are more efficient or environmentally friendly than conventional methods, proposed using generative AI models.

[0896] "Real-time" means that data and information are processed and reflected immediately.

[0897] The system of the present invention utilizes a generative artificial intelligence model and combines it with an emotion engine that recognizes user emotions to realize a waste disposal facility. This system enables efficient waste sorting, analysis, educational proposals, and proposals for new disposal methods, and enables flexible responses that take into account user emotion data.

[0898] Garbage image acquisition and preprocessing

[0899] First, the server receives image data of the garbage from a camera inside the waste disposal facility. This camera is equipped with a high-resolution image sensor, which can capture even the smallest details of the garbage. The received image data is denoised using the OpenCV library. Next, the resolution is adjusted, for example, to 1024x768 pixels. Finally, the image is normalized using the numpy library, scaling the pixel values ​​to the range 0 to 1.

[0900] Classification of garbage by material

[0901] After preprocessing, the image data is input into a deep learning-based generative AI model stored on the server. This generative AI model utilizes frameworks such as TensorFlow and PyTorch and employs a convolutional neural network (CNN). The model analyzes the received image data and classifies the waste by material, such as plastic, paper, and metal. This makes it possible to select the appropriate disposal method for each type of waste.

[0902] Data accumulation and analysis

[0903] The sorted waste data is stored in a database on the server. This database uses MySQL and MongoDB. Every week, the accumulated data is compiled using a Python script, and the sorting rate and trends by region are analyzed. Statistical analysis and machine learning techniques are used for this analysis. The analysis results are formatted into a report and sent to a designated device.

[0904] Presentation of analysis results and educational proposals

[0905] The device receives the analysis results sent from the server and displays them to the user using intuitive graphs and charts. An emotion engine recognizes the user's (local government official's) emotions and adjusts the presentation of the analysis results accordingly. For example, the software generates text containing positive feedback and displays it on the screen, incorporating an API for emotion analysis (e.g., Microsoft Azure's Emotion API).

[0906] Educational proposals using emotion engines

[0907] Based on the analysis results and information from the emotion engine, the device provides local residents with appropriate methods for educating them on how to sort their garbage. Users can view educational content, including videos and infographics, through a web application or mobile app. The emotion engine analyzes residents' reactions in real time during the education session and can adjust the content and progress of the education on the spot.

[0908] Proposing a new method for disposing of garbage

[0909] Based on the accumulated waste data and analysis results, the server uses a generative AI model to propose new waste disposal methods, including improving the reuse of specific materials and increasing the efficiency of processing equipment. These proposals are formatted into a report containing detailed technical specifications and cost-benefit analysis and sent to a designated device. Users can then try out new waste disposal methods to achieve even more efficient waste disposal.

[0910] Specific examples

[0911] For example, when a local government device receives a weekly report, the emotion engine analyzes the user's emotional state and adjusts the report display accordingly. If the sorting rate is low, a presentation highlighting areas for improvement will be presented, providing feedback to motivate the user. Conversely, if Region A's plastic sorting rate improves by 5% compared to the previous year, positive comments and visual highlights will be provided, allowing users to visually confirm concrete results.

[0912] Furthermore, during the education campaign, the devices collect participants' emotional data and adjust the educational content in real time. For example, if residents' reactions are positive, the device will continue to explain in detail how to separate trash, but if they are negative, it will briefly explain the main points. In this way, the effectiveness of the education can be maximized.

[0913] The above is a specific implementation method of the system of the present invention.

[0914] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0915] Step 1:

[0916] Garbage image acquisition and preprocessing

[0917] The server receives real-time image data of garbage from high-resolution cameras in the waste treatment facility. The image data received as input is first subjected to a noise reduction filter using the OpenCV library. Then, the image resolution is adjusted to 1024x768 pixels and pixel values ​​are scaled to the range of 0 to 1 using the numpy library. As an output, preprocessed image data is obtained. This preprocessed image data is used in the next step.

[0918] Specific behavior:

[0919] The server periodically polls the image data from the camera, calls functions in OpenCV to remove noise and adjust the resolution, and performs normalization with numpy.

[0920] Step 2:

[0921] Classification of garbage by material

[0922] The preprocessed image data is input into a generative AI model on the server. The generative AI model is a convolutional neural network (CNN) implemented in the TensorFlow framework, which classifies the waste into materials such as plastic, paper, and metal. The input data is the preprocessed image data, and the output is a probability value for each material classification. The most appropriate material label is assigned based on this probability value.

[0923] Specific behavior:

[0924] The server inputs the preprocessed image data into the model and receives the probability values ​​for each material returned as the model's inference results. Based on this, the server determines the classification results and stores them in a database.

[0925] Step 3:

[0926] Data accumulation and analysis

[0927] The classified waste data is stored in a database on the server. The input data is the classification results, and the output data is the data in the format stored in the database. The data is aggregated at regular intervals using a Python script, and the sorting rate and trends by region are analyzed. Statistical analysis methods and machine learning algorithms are used for the analysis. The output is a report on the sorting rate and trends by region.

[0928] Specific behavior:

[0929] The server periodically accesses the database and runs a batch script to aggregate the classification data, and then reports the analysis results in JSON and PDF format for the next step.

[0930] Step 4:

[0931] Presentation of analysis results and educational proposals

[0932] The device receives the analysis results sent from the server and displays them to the user using intuitive graphs and charts. The input data is the analysis results sent from the server, and the output is data in the form of graphs and charts displayed on the screen. The emotion engine recognizes the user's emotions and adjusts the display method. Specifically, it provides positive feedback and emphasizes points of caution depending on the user's emotional state.

[0933] Specific behavior:

[0934] The device receives the analysis results and uses libraries such as D3.js and Chart.js to draw graphs and charts. Based on the output of the emotion engine, it generates auxiliary text to adjust the display content.

[0935] Step 5:

[0936] Educational proposals using emotion engines

[0937] Based on the analysis results and information from the emotion engine, the device provides local residents with appropriate methods for educating them on how to separate waste. The input data are the analysis results and the output of the emotion engine, and the output data is educational content. Users view the educational content through a web application or mobile app. The emotion engine analyzes the emotional reactions of residents during the education in real time and adjusts the educational content as needed.

[0938] Specific behavior:

[0939] While playing educational content, the device transmits the residents' emotional data obtained from cameras and sensors to an emotion engine, which then displays supplementary explanations and encouraging messages based on the output of the emotion engine.

[0940] Step 6:

[0941] Proposing a new method for disposing of garbage

[0942] The server uses a generative AI model to propose new waste disposal methods based on the accumulated waste data and analysis results. The input data is the waste data and analysis results, and the output data is a report describing the new waste disposal method. The proposals include ways to reuse specific materials and improvements to the disposal equipment.

[0943] Specific behavior:

[0944] The server runs the generative AI model to generate a proposal for a new waste disposal method, converts the proposal into a PDF format, and sends it to the device via HTTP. The report includes technical specifications, cost-effectiveness, and specific implementation steps.

[0945] The above are the specific processing steps in the system of the present invention. In this way, it is possible to realize efficient waste separation, analysis, educational suggestions, and proposals for new waste disposal methods in combination with user emotion recognition.

[0946] (Application example 2)

[0947] 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."

[0948] In modern waste treatment facilities, efficient waste sorting, analysis, training, and new treatment methods are key challenges. To improve employee motivation and efficiency, it is also necessary to recognize user emotions in real time and provide appropriate feedback. However, existing systems lack dynamic feedback based on user emotions, resulting in insufficient optimization of waste treatment. Accurate waste classification and training are particularly important in large-scale facilities such as logistics centers, and new technologies with efficient feedback systems are needed.

[0949] The identification processing by the identification 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 utilizing a generative AI model to receive preprocessed garbage images and classify the garbage by material based on the images; means for analyzing the classified garbage data and understanding the garbage sorting situation in each region; means for presenting the garbage sorting situation and trends in each region based on the analysis results and providing appropriate guidance; means for using the generative AI model to propose a new garbage disposal method based on garbage composition information; and means for recognizing the user's emotions and providing feedback in real time. This enables efficient garbage sorting and analysis and allows the user to receive appropriate feedback based on their emotions, thereby improving the garbage disposal efficiency in the logistics center and increasing employee motivation.

[0950] A "generative artificial intelligence model" is an artificial intelligence technology that learns complex patterns and features based on data and makes predictions and classifications.

[0951] A "waste disposal facility" is a place where collected waste is processed and separated into reusable materials and non-combustible materials.

[0952] "Garbage images" are photographs or videos that visually record the type and condition of waste.

[0953] An "emotion engine" is a technology that analyzes data such as a user's facial expressions and voice to recognize their emotional state.

[0954] "Regional waste separation status" refers to how accurately waste is separated in a particular region.

[0955] "Guidance suggestions" are the act of suggesting improvements or new methods based on specific results or situations.

[0956] "Real-time feedback" is a technology that provides immediate responses and suggestions for improvement based on the current state or situation.

[0957] "Preprocessing" refers to the initial processing and adjustment work carried out to improve the quality of data.

[0958] "Material sorting" is the process of separating waste based on its material (paper, plastic, glass, etc.).

[0959] A "new garbage disposal method" is a newly proposed method of waste disposal that differs from conventional methods.

[0960] This invention is a waste disposal facility system incorporating an emotion engine that utilizes a generative AI model. Specifically, the system uses an application on smartphones and head-mounted displays in logistics centers to make it easier for employees to sort waste.

[0961] The server receives garbage image data acquired from cameras installed in the logistics center. This image data undergoes preprocessing such as noise removal, resolution adjustment, and image normalization before being input into a generative AI model. The generative AI model uses a convolutional neural network (CNN) to classify the garbage by material. The classification results are stored as digital data in a database on the server.

[0962] The data on the sorted waste is compiled periodically, and the status and trends of waste sorting in each region are analyzed. The analysis results are generated in report format and sent to a designated device. The device displays the analysis results and makes appropriate guidance suggestions. In addition, an emotion engine recognizes the emotions of the user (local government officials or logistics center staff) and adjusts the way the analysis results are presented. For example, if the waste sorting rate has improved, a display containing positive feedback will be displayed.

[0963] Furthermore, the server uses a generative AI model based on the analyzed data and composition information to propose new waste disposal methods, which are then sent to the device in the form of a report, allowing users to plan tests at their waste disposal facilities.

[0964] To give a specific example, employees working in a logistics center wear head-mounted displays and sort trash. Images of trash taken by the employees are sent to a server, where a generative AI model classifies them as "plastic." At the same time, if the emotion engine analyzes the employee's face and recognizes the emotion of "fatigue," the system provides positive feedback, saying, "Let's concentrate a little and do our best. Trash is plastic." This leads to efficient trash sorting and improved employee motivation.

[0965] An example of a prompt is as follows:

[0966] "You will take a picture of the garbage and input it into a generative AI model to classify the type of garbage. Then, write a program to analyze the user's emotions and provide appropriate feedback."

[0967] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0968] Step 1:

[0969] The server receives image data of dust particles from cameras installed in the logistics center. The received image data undergoes preprocessing such as noise removal, resolution adjustment, and image normalization. This improves the quality of the image data and provides input data for effective subsequent processing.

[0970] Step 2:

[0971] The server inputs the pre-processed garbage image data into a generative AI model. The generative AI model uses a convolutional neural network (CNN) to classify the garbage by material. Data analysis and calculations based on the input image data result in a classification such as "plastic" or "paper."

[0972] Step 3:

[0973] The generated classification results are stored in a database on the server, which accumulates data including information on the type and quantity of waste, ensuring data consistency and reusability.

[0974] Step 4:

[0975] The server periodically compiles the classification data stored in the database and analyzes the waste sorting situation and trends for each region. The analysis results are generated as digital data and output in report format. This analysis process involves statistically evaluating the input data and calculating data to identify trends.

[0976] Step 5:

[0977] The device receives the analysis results sent in report format from the server and displays the status and trends of waste sorting by region. An emotion engine runs simultaneously to recognize the user's emotional data. Based on this emotional data, the device adjusts the presentation method of the report and the content of the feedback. For example, if a positive emotion is recognized, a praising comment is displayed.

[0978] Step 6:

[0979] The server utilizes a generative AI model to propose new waste disposal methods based on additional analysis data and waste composition information. This proposal is sent to the device in the form of a report. The new waste disposal method is output as the result of data analysis and creative proposals based on the input composition information.

[0980] Step 7:

[0981] Users can check the analysis results and new waste disposal method proposals displayed on their devices and plan tests at their waste disposal facilities as needed. Furthermore, the emotion engine recognizes real-time emotional data of residents and employees, and provides training suggestions and work instructions to improve the accuracy and efficiency of waste sorting.

[0982] 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.

[0983] 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.

[0984] 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.

[0985] [Fourth embodiment]

[0986] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0987] 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.

[0988] 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).

[0989] 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.

[0990] 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.

[0991] 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).

[0992] 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. 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.

[0993] 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.

[0994] 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.

[0995] 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.

[0996] 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.

[0997] 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.

[0998] 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."

[0999] The system of the present invention realizes a waste disposal facility that utilizes a generative artificial intelligence model. Specifically, it involves the process of acquiring image data of waste, classifying it by material using generative AI, analyzing the data to understand the sorting situation in each region, making appropriate guidance suggestions based on the analysis results, and even proposing new waste disposal methods.

[1000] Garbage image acquisition and preprocessing

[1001] First, the server periodically receives image data of the garbage from cameras installed inside the waste disposal facility, and then performs preprocessing such as noise reduction, resolution adjustment, and image normalization to prepare the images for the generative AI model.

[1002] Classification of garbage by material

[1003] After pre-processing, the image data is fed into a deep learning-based generative AI model on the server, which uses techniques such as convolutional neural networks (CNN) to accurately classify waste by material, such as plastic, paper, metal, glass, and other materials.

[1004] Data accumulation and analysis

[1005] The sorted waste data is stored in a database on a server. The accumulated data is aggregated over a set period and analyzed. This analysis includes calculating the sorting rate for each area, comparing it with past data, and identifying trends.

[1006] Presentation of analysis results and educational proposals

[1007] The analysis results are sent to the device, which displays the current state and trends of waste sorting in each region. The user (local government official) can use this information to plan and implement education and campaigns for local residents. For example, if plastic sorting is low in a particular region, they can take measures such as holding information sessions on plastic sorting.

[1008] Proposing a new method for disposing of garbage

[1009] The server utilizes generative AI models based on the analytical data and composition information to propose new waste disposal methods, including improvements to chemical and mechanical processes. The proposed new disposal methods are sent to the device in the form of a report, allowing the user to test them.

[1010] Specific examples

[1011] For example, for 20 images of trash received from a waste disposal facility camera at 9 a.m. each day, the server preprocesses them and then uses a generative AI model to classify them by material: on this day, eight pieces were classified as plastic, four as paper, two as metal, and six as other trash.

[1012] The server then accumulates this data and aggregates and analyzes it for one week, determining that the average plastic sorting rate in Area A is 80%. It also confirms that the sorting rate has improved compared to two months ago. Based on this information, the device proposes an educational campaign to emphasize the importance of further sorting to residents of Area A.

[1013] Additionally, the server uses a generative AI model to suggest new chemical processing methods, calculating details on how to dissolve a particular plastic in a solvent and reuse it as new raw material, and reporting this to the user via their device.

[1014] In this way, the system of the present invention realizes efficient waste separation, promotes recycling, reduces costs, and further reduces the environmental burden.

[1015] The processing flow will be explained below.

[1016] Step 1: Obtaining and preprocessing the dust image

[1017] The server receives image data of the waste from cameras inside the waste treatment facility, performs noise reduction on the received images, adjusts the resolution to a specified size, and normalizes each pixel value to prepare the image for analysis.

[1018] Step 2: Classify the images

[1019] The server then inputs the preprocessed images into a generative AI model, which uses a convolutional neural network (CNN) to classify the waste by material, including plastic, paper, metal, glass, and other categories. The classification results are then recorded as digital data.

[1020] Step 3: Accumulate data

[1021] The server stores the classification results in a database, and the data on the material classification of each piece of garbage is centrally managed and used for future analysis.

[1022] Step 4: Data analysis

[1023] The server aggregates the accumulated data every certain period (e.g., one week). Based on this aggregated data, it calculates the garbage sorting rate and analyzes the sorting situation and trends by region. The analysis results are generated in report format.

[1024] Step 5: Submitting the analysis results

[1025] The server then sends the analysis results to the local government's terminal. The report includes the current state of waste sorting in each area, a comparison with past data, sorting trends, and areas for further improvement.

[1026] Step 6: View Educational Offers

[1027] The device displays the received report, which shows local waste separation rates and trends, and includes educational suggestions for specific waste separation methods. Users can use this information to plan educational activities and campaigns for local residents.

[1028] Step 7: Generate a new processing method

[1029] The server uses the analyzed data and composition information to use generative AI models to suggest new waste disposal methods, including recycling methods and new chemical treatment technologies based on the waste's specific composition.

[1030] Step 8: Generate a report of the new processing method

[1031] The server generates a report detailing the proposed new waste disposal method, including specific steps and expected results.

[1032] Step 9: Submit and test the new process

[1033] The server sends a report of the new processing method to the terminal. The user uses this report to plan a trial of the new processing method. The test results are later fed back to the server for further improvement.

[1034] As described above, through the specific processing flow of each step, the system of the present invention efficiently realizes efficient waste separation, analysis, educational proposals, and proposals for new processing methods.

[1035] Example 1

[1036] 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."

[1037] At conventional waste treatment facilities, waste sorting was done manually, which not only took time and effort but also resulted in insufficient sorting accuracy. Furthermore, there was a lack of efficient means to grasp the waste sorting situation in each region and provide appropriate guidance, making it difficult to effectively treat waste. Furthermore, there was a lack of concrete means to propose and implement new waste treatment methods.

[1038] 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.

[1039] In this invention, the server includes means for receiving preprocessed garbage images, means for performing noise reduction, resolution adjustment, and normalization on the images, means for classifying garbage by material based on the preprocessed images, means for storing data on the classified garbage in a database, means for compiling and analyzing the stored data to grasp the garbage sorting situation in each region, means for presenting the garbage sorting situation and trends in each region based on the analysis results and providing appropriate guidance suggestions, and means for using a generative artificial intelligence model to propose new garbage disposal methods based on garbage composition information.This makes it possible to improve the efficiency and accuracy of garbage sorting work, grasp the garbage sorting situation in each region, provide appropriate guidance suggestions, and propose specific new garbage disposal methods.

[1040] A "server" is a computer system that provides data and services to clients (terminals) via a network.

[1041] A "generative artificial intelligence model" is an artificial intelligence model that has the technology to learn from large amounts of data and perform pattern recognition and prediction, and uses algorithms such as neural networks.

[1042] "Garbage images" are photographic data of garbage captured by a photographing device such as a camera.

[1043] "Preprocessing" is a process in which received dust images are subjected to noise removal, resolution adjustment, normalization, etc. to prepare them for analysis.

[1044] "Material sorting" is the process of separating waste into plastic, paper, metal, glass and other categories.

[1045] A "database" is a software system for efficiently storing, managing, and searching structured data.

[1046] "Data aggregation" is the process of statistically summarizing accumulated data, making it easier to extract information from the results.

[1047] "Analysis" is a means of analyzing the aggregated data in detail to understand the waste sorting situation and trends in each region.

[1048] "Analysis results" refer to the information and conclusions obtained through data analysis, which form the basis for subsequent actions.

[1049] "Guidance proposals" are activities that use the analysis results to educate local residents on how to separate waste and propose improvement measures.

[1050] "Waste composition information" is detailed data on the physical and chemical properties of waste.

[1051] A "new waste disposal method" is a method of waste disposal and recycling that is more efficient and environmentally friendly than conventional methods.

[1052] The system of the present invention realizes a waste treatment facility that utilizes a generative artificial intelligence model. Specific embodiments of the system are described in detail below.

[1053] Garbage image acquisition and preprocessing

[1054] The server periodically receives image data of the garbage from cameras (commonly known as camera devices) installed within the waste disposal facility. High-resolution cameras are used as camera devices. The server uses image processing libraries such as OpenCV to perform preprocessing on the received image data, such as noise removal, resolution adjustment, and image normalization. This prepares the image for the generative AI model to analyze more accurately.

[1055] Classification of garbage by material

[1056] Once preprocessed, the image data is fed into a generative AI model on the server, which is based on a convolutional neural network (a common name for an algorithm) using deep learning libraries such as TensorFlow, and accurately classifies the waste by material, such as plastic, paper, metal, glass, and other materials.

[1057] Data accumulation and analysis

[1058] The data on the sorted waste is stored in a database system (commonly known as a data management system) on the server. The accumulated data is aggregated over a set period and analyzed. This analysis involves using data analysis tools such as Apache Spark to calculate the sorting rate by region, compare it with past data, and identify trends.

[1059] Presentation of analysis results and educational proposals

[1060] The analysis results are sent to the device, which displays the waste sorting situation and trends for each region. The user (commonly known as the operator) uses this information to plan and implement education and campaigns for local residents. The analysis results are visualized using a data visualization tool (e.g., Tableau).

[1061] Proposing a new method for disposing of garbage

[1062] The server uses generative AI models (e.g., GPT-4) based on the analysis data and component information to propose new waste disposal methods. These methods include improvements to chemical and mechanical processes. The proposed new disposal methods are sent to the terminal in the form of a report, which the user can then test.

[1063] Specific examples

[1064] For example, every day at 9 a.m., the server receives 20 images of trash from a camera at a waste disposal facility. The server uses OpenCV to remove noise and adjust the resolution, then uses a TensorFlow-based generative AI model to classify the images by material. On this day, the images were classified as 8 pieces of plastic, 4 pieces of paper, 2 pieces of metal, and 6 pieces of other trash.

[1065] The server then stores this data in a MySQL database and aggregates and analyzes one week's worth of data, determining that the average plastic sorting rate in Area A is 80%. It also confirms that the sorting rate has improved compared to two months ago. Using this information, the device proposes an educational campaign to emphasize the importance of further sorting to residents of Area A.

[1066] Additionally, the server uses GPT-4 to propose new chemical processing methods, calculating details on how to dissolve a particular plastic in a solvent and reuse it as new raw material, and reporting this to the user via the device.

[1067] In this way, the system of the present invention realizes efficient waste separation, promotes recycling, reduces costs, and further reduces the environmental burden.

[1068] Prompt Sentence Examples

[1069] "Please tell us some specific suggestions for increasing the garbage sorting rate in Area A."

[1070] "Please suggest a new way to dispose of plastic waste."

[1071] In this way, the system of the present invention achieves reduced environmental impact and efficient recycling through automation and advanced data analysis at waste treatment facilities.

[1072] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1073] Step 1: Receiving image data

[1074] The server receives image data of the garbage from cameras installed in the waste treatment facility at 9:00 AM every day. The input data is a high-resolution image. The output is an image file of the received raw data.

[1075] Specific behavior:

[1076] 1. The server obtains image files from the camera using a protocol such as FTP.

[1077] 2. Save the image data immediately after receiving it in temporary storage.

[1078] Step 2: Image preprocessing

[1079] The server performs preprocessing on the received images, such as noise removal, resolution adjustment, and normalization. The input is the received raw image data file. The output is the preprocessed image data.

[1080] Specific behavior:

[1081] 1. The server uses the OpenCV library to remove noise using the cv2.GaussianBlur function.

[1082] 2. The server uses the cv2.resize function to adjust to a consistent resolution.

[1083] 3. The server normalizes the image pixel values ​​by dividing them by 255.

[1084] Step 3: Categorize your images by content

[1085] The preprocessed image data is input to the generative AI model on the server. The input is the preprocessed image data. The output is the image classification result (plastic, paper, metal, glass, other).

[1086] Specific behavior:

[1087] 1. The server loads the CNN model using the TensorFlow library.

[1088] 2. The preprocessed image data is input into the CNN model to obtain classification results.

[1089] Step 4: Data accumulation

[1090] The data of the classified garbage is stored in a database on the server. The input is the classified garbage data. The output is structured data stored in the database.

[1091] Specific behavior:

[1092] 1. The server connects to the MySQL database and inserts the new classification data.

[1093] 2. Verify that the data was inserted correctly.

[1094] Step 5: Data collection and analysis

[1095] The server periodically aggregates and analyzes the data in the database. The input is the accumulated database data. The output is a report of the analysis results.

[1096] Specific behavior:

[1097] 1. The server uses Apache Spark to query one week's worth of data from the database.

[1098] 2. Calculate the separation rate and trends based on the acquired data.

[1099] 3. Compile the analysis results in a report format.

[1100] Step 6: Submit and view analysis results

[1101] The analysis results are sent to a terminal, where the waste sorting situation and trends for each region are displayed. The input is the analysis result report. The output is visualized data.

[1102] Specific behavior:

[1103] 1. The server converts the analysis results into JSON format and sends them to the device via the Web API.

[1104] 2. The device displays the received data using a data visualization tool such as Tableau.

[1105] Step 7: Propose a new method of waste disposal

[1106] The server uses a generative AI model based on the composition information to propose new waste disposal methods. The input is the analysis data and composition information. The output is a report proposing a new disposal method.

[1107] Specific behavior:

[1108] 1. The server uses the GPT-4 model to generate prompts for new processing methods.

[1109] 2. The generated processing method is compiled into a report format in Microsoft Word.

[1110] 3. The generated report is sent to the terminal and provided to the user.

[1111] This series of steps will enable efficient waste sorting, analysis, and the proposal of new waste disposal methods at waste disposal facilities.

[1112] (Application example 1)

[1113] 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."

[1114] In modern waste treatment facilities, waste sorting and processing is often done manually, limiting efficiency and accuracy. Furthermore, if waste is not properly sorted, recycling efficiency decreases and the environmental impact increases. Furthermore, similar issues exist in industrial waste and waste processing within factories. This has led to a demand for new technologies to improve waste management efficiency and reduce the environmental impact.

[1115] 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.

[1116] In this invention, the server includes means for receiving preprocessed garbage images and classifying the garbage by material based on the images, means for analyzing the classified garbage data and understanding the garbage sorting situation in each region, means for presenting the garbage sorting situation and trends in each region based on the analysis results and providing appropriate guidance suggestions, means for proposing new garbage disposal methods based on garbage composition information using a generative artificial intelligence model, means for operating a factory robot that moves the classified garbage by material into dedicated containers, and an application installed on a smartphone, smart glasses, head-mounted display, or robot that can monitor and operate the robot's operation from inside and outside the factory. This enables automated, high-precision waste sorting and efficient waste disposal.

[1117] A "server" is a computer system that provides data and services over a network.

[1118] "Preprocessing" refers to the initial processing of data to facilitate subsequent data analysis or classification in artificial intelligence models.

[1119] "Garbage image" refers to image data of waste material captured using a photographic device such as a camera.

[1120] "Material sorting" is the process of classifying a group of objects with specific attributes based on their material (e.g., plastic, paper, metal, glass, etc.).

[1121] "Data analysis" is a method of statistically processing collected data to extract usable information and patterns.

[1122] "Waste sorting status by region" is information that indicates the current state of waste sorting within a specific region.

[1123] A "trend" is a widespread pattern of change in a particular phenomenon or practice over time.

[1124] "Guidance proposal" means specific advice or plans to promote improvement in a specific problem.

[1125] A "generative artificial intelligence model" is an artificial intelligence algorithm that is automatically generated to perform a specific task based on training data.

[1126] "Ingredient information" refers to detailed data about the composition and elements of a substance.

[1127] A "robot" is a programmed mechanical device that can perform specific tasks automatically.

[1128] A "specialized container" is a storage box or container designed for a specific material or purpose.

[1129] An "application" is a software program designed to perform a specific task or function.

[1130] The system of the present invention utilizes a generative artificial intelligence model to realize automatic classification and efficient disposal of waste within a factory. Specific embodiments for implementing this system are described below.

[1131] The system consists of a server, factory robots, mobile devices such as smartphones, smart glasses, and head-mounted displays, as well as the necessary software.

[1132] First, the server periodically receives image data of waste from cameras installed in the factory. The received image data undergoes a pre-processing process to make it suitable for the generative AI model. Pre-processing includes noise removal, resolution adjustment, and image normalization.

[1133] The pre-processed image data is then fed into a deep learning-based generative artificial intelligence model on the server, which uses a convolutional neural network (CNN) to analyze the images and accurately classify the waste into plastic, paper, metal, glass, and other materials.

[1134] The classified waste data is stored in a database on a server and analyzed. The server aggregates the accumulated data and performs analysis to understand the waste sorting situation and trends in each region. The results of this analysis are presented to users via their mobile devices and used as guidance suggestions for improving waste management. For example, if the plastic sorting rate in a particular area is low, an educational campaign for local residents will be suggested.

[1135] Furthermore, new waste disposal methods are proposed by the generative AI model and sent to the user in the form of reports via the server, allowing new chemical and mechanical methods to be tested.

[1136] The factory robots then move the classified waste into dedicated containers based on instructions from the server. The robots' operations can be remotely monitored and controlled using mobile devices such as smartphones, smart glasses, and head-mounted displays.

[1137] As a concrete example, at a waste processing line, the server preprocesses waste image data received from a camera every day at 9:00 a.m., and then uses a generative AI model to classify the data by material. During this process, eight pieces of plastic, four pieces of paper, two pieces of metal, and six pieces of other waste are identified. The analysis results are aggregated for one week, and it is found that the plastic sorting rate in a particular area is 80%. Based on this, guidance suggestions emphasizing the importance of further sorting are presented to the user.

[1138] Example prompts to input to a generative AI model:

[1139] Please perform image capture using the "capture_image" function.

[1140] Use the "preprocess_image" function for preprocessing and perform classification using a generative AI model.

[1141] Based on the classification result, use the "place_in_container" function to move the robot arm to the appropriate container.

[1142] As described above, the system of the present invention enables automated, highly accurate classification and efficient disposal of waste.

[1143] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1144] Step 1:

[1145] The server periodically receives image data of waste from cameras installed in the factory. The input data is raw image data acquired from the camera, and the output is image data suitable for preprocessing. Specifically, the image from the camera is captured and saved as an image file on the server.

[1146] Step 2:

[1147] The server performs preprocessing on the received image data, such as noise removal, resolution adjustment, and image normalization. The input is the raw image data obtained in step 1, and the output is image data that has been preprocessed into a format suitable for the generative AI model. This preprocessing improves the quality of the image and increases the accuracy of analysis by the generative AI model.

[1148] Step 3:

[1149] The server inputs the preprocessed image data into a generative AI model. The input is the preprocessed image data, and the output is waste labels classified by material. The generative AI model uses a convolutional neural network (CNN) to accurately classify each material (plastic, paper, metal, glass, etc.).

[1150] Step 4:

[1151] The server stores the classified waste data in a database. The input is the classification result from the generative AI model, and the output is the waste data stored in the database. This data is used for data analysis, which is useful for future analysis and trend identification.

[1152] Step 5:

[1153] The server aggregates and analyzes waste data over a set period of time to understand the waste separation situation and trends for each region. The input is the accumulated waste data, and the output is information on the separation situation and trends for each region based on the analysis results. Statistical analysis and machine learning techniques are used for the analysis method.

[1154] Step 6:

[1155] The server uses the analysis results to present the user with information on the current state and trends of waste separation in each region and makes appropriate guidance suggestions. The input is the analysis results, and the output is a report of guidance suggestions for the user. The user can use this report to plan and implement educational campaigns and improvement measures.

[1156] Step 7:

[1157] The server uses a generative artificial intelligence model to propose new waste treatment methods. The input is composition information and analytical data, and the output is a report of the new treatment method, leading to more efficient and environmentally friendly treatment methods.

[1158] Step 8:

[1159] Based on commands from the server, factory robots move the classified waste into dedicated containers. The input is the command to move the waste from the server, and the output is the result of the waste being moved to the appropriate container. This operation automates the proper disposal of waste.

[1160] Step 9:

[1161] Users use mobile devices such as smartphones, smart glasses, and head-mounted displays to remotely monitor and operate factory robots. The input is operation commands from the mobile device, and the output is the robot's operating status and monitoring report. Specifically, the current status of the robot can be checked through the application, and manual operation can be performed as needed.

[1162] Through the above processing steps, the system of the present invention enables automated, highly accurate classification and efficient processing of waste.

[1163] 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.

[1164] The system of this invention utilizes a generative artificial intelligence model and combines it with an emotion engine that recognizes user emotions to realize a waste disposal facility. This allows for efficient waste sorting, analysis, educational proposals, and proposals for new disposal methods, while also enabling flexible responses that take into account user emotion data.

[1165] Garbage image acquisition and preprocessing

[1166] First, the server receives image data of the waste from cameras inside the waste treatment facility, and then performs preprocessing such as noise reduction, resolution adjustment, and image normalization.

[1167] Classification of garbage by material

[1168] After preprocessing, the image data is input into a deep learning-based generative AI model stored on the server. The generative AI model uses techniques such as convolutional neural networks (CNN) to classify the waste by material. The classification results are recorded as digital data.

[1169] Data accumulation and analysis

[1170] The classified waste data is stored in a server database. The accumulated data is aggregated over a set period of time, and the sorting rate and trends by region are analyzed. The analysis results are generated in report format and sent to a designated device.

[1171] Presentation of analysis results and educational proposals

[1172] The device receives the analysis results sent from the server and displays the status and trends of waste sorting for each region. Here, the emotion engine recognizes the emotions of the user (local government official) and adjusts the way the analysis results are presented. For example, if the sorting rate is improving, it can display positive feedback.

[1173] Educational proposals using emotion engines

[1174] Based on the analysis results and information from the emotion engine, the device provides local residents with appropriate methods for educating them about waste separation. Users can use this information to plan and implement educational activities for residents. The emotion engine can analyze residents' reactions in real time during educational activities and provide feedback.

[1175] Proposing a new method for disposing of garbage

[1176] The server uses generative AI models based on the analyzed data and composition information to propose new waste disposal methods, including improvements to chemical and mechanical processes. The proposed new disposal methods are sent to the device in the form of a report, allowing users to plan trials at their waste disposal facilities.

[1177] Specific examples

[1178] For example, when a local government device receives a weekly report, the emotion engine analyzes the user's emotional state and adjusts the report display accordingly. If the sorting rate is low, a presentation highlighting areas for improvement will be presented and feedback to motivate the user. Similarly, if the plastic sorting rate in Region A improves by 5% compared to the previous year, positive comments and visual highlights will be provided.

[1179] Furthermore, during the educational campaign, the devices collect participants' emotional data and adjust the educational content in real time. For example, if residents' reactions are positive, the device will continue to explain in detail how to separate trash, but if they are negative, it will switch to a brief explanation of the main points.

[1180] In this way, the system of the present invention realizes efficient waste separation, analysis, educational suggestions, and proposals for new disposal methods, all in combination with user emotion recognition.

[1181] The processing flow will be explained below.

[1182] Step 1: Obtaining and preprocessing the dust image

[1183] The server receives image data of the waste from cameras inside the waste treatment facility. It then performs noise reduction on the received images, adjusts the resolution to a specified size, and normalizes the pixel values ​​of the images to make them suitable for analysis.

[1184] Step 2: Sort the waste by material

[1185] The server then inputs the pre-processed images into a generative AI model, which uses a convolutional neural network (CNN) to classify the waste material into categories such as plastic, paper, metal, glass, and other. The classification results are recorded as digital data and used in the next processing step.

[1186] Step 3: Accumulate data

[1187] The server stores the classified garbage data in a database, which is continuously accumulated and used for future analysis.

[1188] Step 4: Data analysis

[1189] The server collects and analyzes the data at regular intervals (e.g., weekly). This analysis includes calculating the waste separation rate by region, comparing it with past data, and analyzing trends in waste separation. The analysis results are generated in report format and sent to the specified device.

[1190] Step 5: Adjusting the analysis results by the emotion engine

[1191] The device receives the analysis results sent from the server and uses an emotion engine to recognize the user's (local government official's) emotions before displaying them on the screen. The emotion engine adjusts the way the analysis results are displayed depending on the user's reaction. For example, it may display positive emotions or add detailed explanations if necessary.

[1192] Step 6: Displaying educational suggestions and sentiment analysis

[1193] Based on the received data, the device displays the current state of waste sorting in each region and educational suggestions based on that data. The emotion engine analyzes the user's emotional state and dynamically adjusts appropriate educational methods and suggestions. Users can refer to the emotion engine's analysis to plan and implement more effective educational activities.

[1194] Step 7: Generate a new garbage disposal method

[1195] The server uses a generative AI model based on the analyzed data and composition information to propose new waste disposal methods, including improving chemical and mechanical processes and optimizing recycling technologies. The proposals are compiled into a report and sent to the device.

[1196] Step 8: Submit and feedback your new process

[1197] The device receives a report on the new waste disposal method and displays it to the user. The user then tests the new method based on the results and feeds the results back to the server. The feedback data is used to improve the accuracy of future proposals.

[1198] Step 9: Longitudinal analysis of sentiment data

[1199] The devices store emotional data collected during educational activities and the implementation of new waste disposal methods. Using this data, the server performs long-term data analysis and provides optimal educational approaches and waste disposal methods for each region.

[1200] In this way, the system of the present invention realizes efficient waste separation, analysis, educational suggestions, and suggestions for new disposal methods by combining them with user emotion recognition.

[1201] Example 2

[1202] 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."

[1203] At conventional waste disposal facilities, waste separation and disposal method proposals were sometimes inefficient, making it difficult to improve the local waste separation rate or implement appropriate educational activities.In addition, because it was not possible to consider the emotions and reactions of staff and residents in real time, it was difficult to respond individually, making it difficult to carry out effective educational activities or propose disposal methods.

[1204] 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.

[1205] In this invention, the server includes means for receiving preprocessed garbage images and classifying garbage by material based on the images, means for analyzing the classified garbage data and grasping the garbage sorting situation in each region, means for presenting the garbage sorting situation and trends in each region based on the analysis results and making appropriate instruction suggestions, means for proposing new garbage disposal methods based on garbage component information using a generative AI model, means for adjusting the display of the analysis results based on the user's emotional state, and means for collecting user emotional data and adjusting the content of educational activities in real time. This enables efficient garbage sorting, analysis, educational suggestions, and new disposal method suggestions, and enables flexible responses that take into account the user's emotions and reactions.

[1206] "Garbage images" are photographic data of garbage taken by cameras installed in garbage disposal facilities.

[1207] "Preprocessing" refers to image processing such as noise removal, resolution adjustment, and normalization that is performed on the received dust image.

[1208] A "generative AI model" is a generative artificial intelligence model, a trained neural network model that uses deep learning technology to classify garbage by material.

[1209] "Material sorting" is the process of separating garbage into different materials such as plastic, paper, and metal.

[1210] "Database" means an information system for storing and managing data on classified waste.

[1211] "Analysis" refers to analyzing accumulated garbage data using statistical methods and machine learning techniques.

[1212] A "report" is a report summarizing the analysis results in document and graph format.

[1213] "Terminal" refers to an electronic device for displaying analysis results and educational suggestions, including smartphones, PCs, tablets, etc.

[1214] The "emotion engine" is software that analyzes the emotional data of users and residents and adjusts the display content and educational suggestions.

[1215] "Educational activities" are efforts to educate local residents about the importance of sorting garbage and the correct way to do it.

[1216] "New waste disposal methods" are waste disposal technologies or methods that are more efficient or environmentally friendly than conventional methods, proposed using generative AI models.

[1217] "Real-time" means that data and information are processed and reflected immediately.

[1218] The system of the present invention utilizes a generative artificial intelligence model and combines it with an emotion engine that recognizes user emotions to realize a waste disposal facility. This system enables efficient waste sorting, analysis, educational proposals, and proposals for new disposal methods, and enables flexible responses that take into account user emotion data.

[1219] Garbage image acquisition and preprocessing

[1220] First, the server receives image data of the garbage from a camera inside the waste disposal facility. This camera is equipped with a high-resolution image sensor, which can capture even the smallest details of the garbage. The received image data is denoised using the OpenCV library. Next, the resolution is adjusted, for example, to 1024x768 pixels. Finally, the image is normalized using the numpy library, scaling the pixel values ​​to the range 0 to 1.

[1221] Classification of garbage by material

[1222] After preprocessing, the image data is input into a deep learning-based generative AI model stored on the server. This generative AI model utilizes frameworks such as TensorFlow and PyTorch and employs a convolutional neural network (CNN). The model analyzes the received image data and classifies the waste by material, such as plastic, paper, and metal. This makes it possible to select the appropriate disposal method for each type of waste.

[1223] Data accumulation and analysis

[1224] The sorted waste data is stored in a database on the server. This database uses MySQL and MongoDB. Every week, the accumulated data is compiled using a Python script, and the sorting rate and trends by region are analyzed. Statistical analysis and machine learning techniques are used for this analysis. The analysis results are formatted into a report and sent to a designated device.

[1225] Presentation of analysis results and educational proposals

[1226] The device receives the analysis results sent from the server and displays them to the user using intuitive graphs and charts. An emotion engine recognizes the user's (local government official's) emotions and adjusts the presentation of the analysis results accordingly. For example, the software generates text containing positive feedback and displays it on the screen, incorporating an API for emotion analysis (e.g., Microsoft Azure's Emotion API).

[1227] Educational proposals using emotion engines

[1228] Based on the analysis results and information from the emotion engine, the device provides local residents with appropriate methods for educating them on how to sort their garbage. Users can view educational content, including videos and infographics, through a web application or mobile app. The emotion engine analyzes residents' reactions in real time during the education session and can adjust the content and progress of the education on the spot.

[1229] Proposing a new method for disposing of garbage

[1230] Based on the accumulated waste data and analysis results, the server uses a generative AI model to propose new waste disposal methods, including improving the reuse of specific materials and increasing the efficiency of processing equipment. These proposals are formatted into a report containing detailed technical specifications and cost-benefit analysis and sent to a designated device. Users can then try out new waste disposal methods to achieve even more efficient waste disposal.

[1231] Specific examples

[1232] For example, when a local government device receives a weekly report, the emotion engine analyzes the user's emotional state and adjusts the report display accordingly. If the sorting rate is low, a presentation highlighting areas for improvement will be presented, providing feedback to motivate the user. Conversely, if Region A's plastic sorting rate improves by 5% compared to the previous year, positive comments and visual highlights will be provided, allowing users to visually confirm concrete results.

[1233] Furthermore, during the education campaign, the devices collect participants' emotional data and adjust the educational content in real time. For example, if residents' reactions are positive, the device will continue to explain in detail how to separate trash, but if they are negative, it will briefly explain the main points. In this way, the effectiveness of the education can be maximized.

[1234] The above is a specific implementation method of the system of the present invention.

[1235] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1236] Step 1:

[1237] Garbage image acquisition and preprocessing

[1238] The server receives real-time image data of garbage from high-resolution cameras in the waste treatment facility. The image data received as input is first subjected to a noise reduction filter using the OpenCV library. Then, the image resolution is adjusted to 1024x768 pixels and pixel values ​​are scaled to the range of 0 to 1 using the numpy library. As an output, preprocessed image data is obtained. This preprocessed image data is used in the next step.

[1239] Specific behavior:

[1240] The server periodically polls the image data from the camera, calls functions in OpenCV to remove noise and adjust the resolution, and performs normalization with numpy.

[1241] Step 2:

[1242] Classification of garbage by material

[1243] The preprocessed image data is input into a generative AI model on the server. The generative AI model is a convolutional neural network (CNN) implemented in the TensorFlow framework, which classifies the waste into materials such as plastic, paper, and metal. The input data is the preprocessed image data, and the output is a probability value for each material classification. The most appropriate material label is assigned based on this probability value.

[1244] Specific behavior:

[1245] The server inputs the preprocessed image data into the model and receives the probability values ​​for each material returned as the model's inference results. Based on this, the server determines the classification results and stores them in a database.

[1246] Step 3:

[1247] Data accumulation and analysis

[1248] The classified waste data is stored in a database on the server. The input data is the classification results, and the output data is the data in the format stored in the database. The data is aggregated at regular intervals using a Python script, and the sorting rate and trends by region are analyzed. Statistical analysis methods and machine learning algorithms are used for the analysis. The output is a report on the sorting rate and trends by region.

[1249] Specific behavior:

[1250] The server periodically accesses the database and runs a batch script to aggregate the classification data, and then reports the analysis results in JSON and PDF format for the next step.

[1251] Step 4:

[1252] Presentation of analysis results and educational proposals

[1253] The device receives the analysis results sent from the server and displays them to the user using intuitive graphs and charts. The input data is the analysis results sent from the server, and the output is data in the form of graphs and charts displayed on the screen. The emotion engine recognizes the user's emotions and adjusts the display method. Specifically, it provides positive feedback and emphasizes points of caution depending on the user's emotional state.

[1254] Specific behavior:

[1255] The device receives the analysis results and uses libraries such as D3.js and Chart.js to draw graphs and charts. Based on the output of the emotion engine, it generates auxiliary text to adjust the display content.

[1256] Step 5:

[1257] Educational proposals using emotion engines

[1258] Based on the analysis results and information from the emotion engine, the device provides local residents with appropriate methods for educating them on how to separate waste. The input data are the analysis results and the output of the emotion engine, and the output data is educational content. Users view the educational content through a web application or mobile app. The emotion engine analyzes the emotional reactions of residents during the education in real time and adjusts the educational content as needed.

[1259] Specific behavior:

[1260] While playing educational content, the device transmits the residents' emotional data obtained from cameras and sensors to an emotion engine, which then displays supplementary explanations and encouraging messages based on the output of the emotion engine.

[1261] Step 6:

[1262] Proposing a new method for disposing of garbage

[1263] The server uses a generative AI model to propose new waste disposal methods based on the accumulated waste data and analysis results. The input data is the waste data and analysis results, and the output data is a report describing the new waste disposal method. The proposals include ways to reuse specific materials and improvements to the disposal equipment.

[1264] Specific behavior:

[1265] The server runs the generative AI model to generate a proposal for a new waste disposal method, converts the proposal into a PDF format, and sends it to the device via HTTP. The report includes technical specifications, cost-effectiveness, and specific implementation steps.

[1266] The above are the specific processing steps in the system of the present invention. In this way, it is possible to realize efficient waste separation, analysis, educational suggestions, and proposals for new waste disposal methods in combination with user emotion recognition.

[1267] (Application example 2)

[1268] 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."

[1269] In modern waste treatment facilities, efficient waste sorting, analysis, training, and new treatment methods are key challenges. To improve employee motivation and efficiency, it is also necessary to recognize user emotions in real time and provide appropriate feedback. However, existing systems lack dynamic feedback based on user emotions, resulting in insufficient optimization of waste treatment. Accurate waste classification and training are particularly important in large-scale facilities such as logistics centers, and new technologies with efficient feedback systems are needed.

[1270] The identification processing by the identification 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 utilizing a generative AI model to receive preprocessed garbage images and classify the garbage by material based on the images; means for analyzing the classified garbage data and understanding the garbage sorting situation in each region; means for presenting the garbage sorting situation and trends in each region based on the analysis results and providing appropriate guidance; means for using the generative AI model to propose a new garbage disposal method based on garbage composition information; and means for recognizing the user's emotions and providing feedback in real time. This enables efficient garbage sorting and analysis and allows the user to receive appropriate feedback based on their emotions, thereby improving the garbage disposal efficiency in the logistics center and increasing employee motivation.

[1271] A "generative artificial intelligence model" is an artificial intelligence technology that learns complex patterns and features based on data and makes predictions and classifications.

[1272] A "waste disposal facility" is a place where collected waste is processed and separated into reusable materials and non-combustible materials.

[1273] "Garbage images" are photographs or videos that visually record the type and condition of waste.

[1274] An "emotion engine" is a technology that analyzes data such as a user's facial expressions and voice to recognize their emotional state.

[1275] "Regional waste separation status" refers to how accurately waste is separated in a particular region.

[1276] "Guidance suggestions" are the act of suggesting improvements or new methods based on specific results or situations.

[1277] "Real-time feedback" is a technology that provides immediate responses and suggestions for improvement based on the current state or situation.

[1278] "Preprocessing" refers to the initial processing and adjustment work carried out to improve the quality of data.

[1279] "Material sorting" is the process of separating waste based on its material (paper, plastic, glass, etc.).

[1280] A "new garbage disposal method" is a newly proposed method of waste disposal that differs from conventional methods.

[1281] This invention is a waste disposal facility system incorporating an emotion engine that utilizes a generative AI model. Specifically, the system uses an application on smartphones and head-mounted displays in logistics centers to make it easier for employees to sort waste.

[1282] The server receives garbage image data acquired from cameras installed in the logistics center. This image data undergoes preprocessing such as noise removal, resolution adjustment, and image normalization before being input into a generative AI model. The generative AI model uses a convolutional neural network (CNN) to classify the garbage by material. The classification results are stored as digital data in a database on the server.

[1283] The data on the sorted waste is compiled periodically, and the status and trends of waste sorting in each region are analyzed. The analysis results are generated in report format and sent to a designated device. The device displays the analysis results and makes appropriate guidance suggestions. In addition, an emotion engine recognizes the emotions of the user (local government officials or logistics center staff) and adjusts the way the analysis results are presented. For example, if the waste sorting rate has improved, a display containing positive feedback will be displayed.

[1284] Furthermore, the server uses a generative AI model based on the analyzed data and composition information to propose new waste disposal methods, which are then sent to the device in the form of a report, allowing users to plan tests at their waste disposal facilities.

[1285] To give a specific example, employees working in a logistics center wear head-mounted displays and sort trash. Images of trash taken by the employees are sent to a server, where a generative AI model classifies them as "plastic." At the same time, if the emotion engine analyzes the employee's face and recognizes the emotion of "fatigue," the system provides positive feedback, saying, "Let's concentrate a little and do our best. Trash is plastic." This leads to efficient trash sorting and improved employee motivation.

[1286] An example of a prompt is as follows:

[1287] "You will take a picture of the garbage and input it into a generative AI model to classify the type of garbage. Then, write a program to analyze the user's emotions and provide appropriate feedback."

[1288] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1289] Step 1:

[1290] The server receives image data of dust particles from cameras installed in the logistics center. The received image data undergoes preprocessing such as noise removal, resolution adjustment, and image normalization. This improves the quality of the image data and provides input data for effective subsequent processing.

[1291] Step 2:

[1292] The server inputs the pre-processed garbage image data into a generative AI model. The generative AI model uses a convolutional neural network (CNN) to classify the garbage by material. Data analysis and calculations based on the input image data result in a classification such as "plastic" or "paper."

[1293] Step 3:

[1294] The generated classification results are stored in a database on the server, which accumulates data including information on the type and quantity of waste, ensuring data consistency and reusability.

[1295] Step 4:

[1296] The server periodically compiles the classification data stored in the database and analyzes the waste sorting situation and trends for each region. The analysis results are generated as digital data and output in report format. This analysis process involves statistically evaluating the input data and calculating data to identify trends.

[1297] Step 5:

[1298] The device receives the analysis results sent in report format from the server and displays the status and trends of waste sorting by region. An emotion engine runs simultaneously to recognize the user's emotional data. Based on this emotional data, the device adjusts the presentation method of the report and the content of the feedback. For example, if a positive emotion is recognized, a praising comment is displayed.

[1299] Step 6:

[1300] The server utilizes a generative AI model to propose new waste disposal methods based on additional analysis data and waste composition information. This proposal is sent to the device in the form of a report. The new waste disposal method is output as the result of data analysis and creative proposals based on the input composition information.

[1301] Step 7:

[1302] Users can check the analysis results and new waste disposal method proposals displayed on their devices and plan tests at their waste disposal facilities as needed. Furthermore, the emotion engine recognizes real-time emotional data of residents and employees, and provides training suggestions and work instructions to improve the accuracy and efficiency of waste sorting.

[1303] 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.

[1304] 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.

[1305] 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.

[1306] 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.

[1307] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion 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.

[1308] 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.

[1309] 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).

[1310] 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.

[1311] 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."

[1312] 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.

[1313] 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).

[1314] 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.

[1315] 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.

[1316] 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.

[1317] 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.

[1318] 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.

[1319] 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.

[1320] 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.

[1321] 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.

[1322] 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.

[1323] 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.

[1324] The following is further disclosed regarding the above embodiment.

[1325] (Claim 1)

[1326] Using generative artificial intelligence models in waste treatment facilities

[1327] means for receiving preprocessed dust images and classifying the dust by material based on the images;

[1328] A method for analyzing the classified garbage data and understanding the garbage sorting situation in each region,

[1329] Based on the analysis results, the system will present the current state and trends of waste sorting in each region and provide appropriate guidance and suggestions.

[1330] A means for proposing a new garbage disposal method based on garbage component information using a generative artificial intelligence model;

[1331] A system including:

[1332] (Claim 2)

[1333] 10. The system of claim 1, wherein image recognition technology is used to sort trash by material.

[1334] (Claim 3)

[1335] The system of claim 1, which uses a generative artificial intelligence model to propose new waste disposal methods based on waste composition information.

[1336] "Example 1"

[1337] (Claim 1)

[1338] Using generative artificial intelligence models in waste treatment facilities

[1339] means for receiving a preprocessed dust image;

[1340] means for performing noise reduction, resolution adjustment, and normalization on the image;

[1341] A means for classifying trash by material based on the preprocessed images;

[1342] A means for storing data on the classified waste in a database;

[1343] A method for compiling and analyzing the accumulated data to understand the waste sorting situation in each region,

[1344] Based on the analysis results, the system will present the current state and trends of waste sorting in each region and provide appropriate guidance and suggestions.

[1345] A means for proposing a new garbage disposal method based on garbage component information using a generative artificial intelligence model;

[1346] A system including:

[1347] (Claim 2)

[1348] 10. The system of claim 1, wherein image recognition technology is used to sort trash by material.

[1349] (Claim 3)

[1350] The system according to claim 1, further comprising means for transmitting the analysis results to a terminal via a server and visualizing the results.

[1351] (Claim 4)

[1352] The system of claim 1, which uses a generative artificial intelligence model to propose new waste disposal methods based on waste composition information.

[1353] "Application Example 1"

[1354] (Claim 1)

[1355] Using generative artificial intelligence models in waste treatment facilities

[1356] means for receiving preprocessed dust images and classifying the dust by material based on the images;

[1357] A method for analyzing the classified garbage data and understanding the garbage sorting situation in each region,

[1358] Based on the analysis results, the system will present the current state and trends of waste sorting in each region and provide appropriate guidance and suggestions.

[1359] A means for proposing a new garbage disposal method based on garbage component information using a generative artificial intelligence model;

[1360] A means for operating a factory robot that moves the sorted waste into designated containers;

[1361] An application that can be installed on a smartphone, smart glasses, head-mounted display, or robot to monitor and operate the robot from inside and outside the factory.

[1362] A system including:

[1363] (Claim 2)

[1364] 10. The system of claim 1, wherein image recognition technology is used to sort trash by material.

[1365] (Claim 3)

[1366] The system of claim 1, which uses a generative artificial intelligence model to propose new waste disposal methods based on waste composition information.

[1367] "Example 2: Combining Emotion Engines"

[1368] (Claim 1)

[1369] Using generative artificial intelligence models in waste treatment facilities

[1370] means for receiving preprocessed dust images and classifying the dust by material based on the images;

[1371] A method for analyzing the classified garbage data and understanding the garbage sorting situation in each region,

[1372] Based on the analysis results, the system will present the current state and trends of waste sorting in each region and provide appropriate guidance and suggestions.

[1373] A means for proposing a new garbage disposal method based on garbage component information using a generative artificial intelligence model;

[1374] means for adjusting the display of the analysis results based on the emotional state of the user;

[1375] a means for collecting user emotional data and adjusting the content of educational activities in real time;

[1376] A system including:

[1377] (Claim 2)

[1378] 10. The system of claim 1, wherein image recognition technology is used to sort trash by material.

[1379] (Claim 3)

[1380] The system of claim 1, which uses a generative artificial intelligence model to propose new waste disposal methods based on waste composition information.

[1381] "Application example 2 when combining emotion engines"

[1382] (Claim 1)

[1383] Using generative artificial intelligence models in waste treatment facilities

[1384] means for receiving preprocessed dust images and classifying the dust by material based on the images;

[1385] A method for analyzing the classified garbage data and understanding the garbage sorting situation in each region,

[1386] Based on the analysis results, the system will present the current state and trends of waste sorting in each region and provide appropriate guidance and suggestions.

[1387] A means for proposing a new garbage disposal method based on garbage component information using a generative artificial intelligence model;

[1388] a means of recognizing a user's emotions and providing feedback in real time;

[1389] A system including:

[1390] (Claim 2)

[1391] 10. The system of claim 1, wherein the system uses image recognition technology and an emotion engine to classify trash by material.

[1392] (Claim 3)

[1393] The system of claim 1, which uses a generative artificial intelligence model to suggest new garbage disposal methods based on garbage composition information and provides feedback based on the user's emotions. [Explanation of symbols]

[1394] 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. Using generative artificial intelligence models in waste treatment facilities means for receiving preprocessed dust images and classifying the dust by material based on the images; A method for analyzing the classified garbage data and understanding the garbage sorting situation in each region, Based on the analysis results, the system will present the current state and trends of waste sorting in each region and provide appropriate guidance and suggestions. A means for proposing a new garbage disposal method based on garbage component information using a generative artificial intelligence model; A system including:

2. The system of claim 1 , wherein image recognition technology is used to sort trash by material.

3. The system of claim 1 , wherein a generative artificial intelligence model is used to propose new waste disposal methods based on waste component information.

Images