System

Abstract

A system is provided.SOLUTION: A system for presenting a waste sorting method, the system comprising: an image acquisition unit configured to take a photograph of waste by a user and generate image data of the photograph; a communication unit configured to transmit the image data to a server; an image analysis unit configured to receive the image data and identify a type of the waste; a sorting method specification unit configured to search a database for a sorting rule corresponding to the type of the waste and specify a sorting method corresponding to the sorting rule; and a presentation unit configured to present the specified sorting method to the user.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] In many households, garbage sorting methods vary from one municipality to another, and individually researching these methods is time-consuming and laborious. Furthermore, incorrect sorting results in waste not being collected, leading to the hassle and confusion of re-sorting. This places a heavy burden on users. Furthermore, with environmental awareness on the rise, accurate garbage sorting has become a social issue. The present invention aims to solve these problems by providing a system that significantly reduces the user's time and effort and enables accurate garbage sorting. [Means for solving the problem]

[0005] The present invention is a system including an image acquisition means for a user to take a photo of garbage and generate image data of the photo, a communication means for transmitting the image data to a server, an image analysis means for analyzing the received image data and identifying the type of garbage, a sorting method identification means for searching a database for sorting rules corresponding to the type of garbage and identifying an appropriate sorting method, and a presentation means for presenting the identified sorting method to the user. Furthermore, a series of problems are solved by the sorting method identification means searching for the sorting rules for the relevant area based on the user's residential area, and the image analysis means identifying the type of garbage using a model using deep learning.

[0006] The "image acquisition means" is a device or function that allows a user to take a photo of the garbage and generate image data of the photo.

[0007] "Communication means" refers to a device or function for transmitting image data to a server.

[0008] "Image analysis means" refers to a device or function that analyzes received image data and identifies the type of dust.

[0009] The "sorting method specifying means" is a device or function that searches a database for sorting rules corresponding to the type of garbage and specifies the corresponding sorting method.

[0010] The "presentation means" is a device or function that presents the identified sorting method to the user. [Brief explanation of the drawings]

[0011] [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

[0012] 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.

[0013] First, the terms used in the following description will be explained.

[0014] 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).

[0015] 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.

[0016] 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.

[0017] 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.

[0018] 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."

[0019] [First embodiment]

[0020] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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."

[0032] The present invention is a system for enabling a user to learn how to separate garbage, and this system is composed of a plurality of means. Hereinafter, an embodiment of the present invention will be described in detail.

[0033] System configuration

[0034] Image Acquisition Method

[0035] The user takes a photo of the trash using the camera on their smartphone or other device. The captured image data is saved in the device's internal storage. The user can then view the captured image data within the application and proceed to the next processing step.

[0036] communication means

[0037] The smartphone is equipped with a communication method for sending captured image data to a server. Specifically, it uses an HTTP POST request from the smartphone to the server. The image data is sent as part of this request.

[0038] Image analysis methods

[0039] The server analyzes the received image data using deep learning models (e.g., ResNet-50 and VGG-16), which automatically identifies the type of garbage (bottles, cans, plastic, etc.).

[0040] Separation method identification means

[0041] The server searches a database for sorting rules that correspond to the user's area based on the identified type of garbage, and uses the search results to identify specific methods for sorting garbage.

[0042] Presentation means

[0043] The identified sorting method is sent to the user's device in real time, and the device displays the received information on the user interface, allowing the user to instantly confirm the correct method for sorting their garbage.

[0044] Specific examples

[0045] For example, consider the case where a user takes a picture of a beer bottle.

[0046] 1. User: Take a photo of a beer bottle with your smartphone camera.

[0047] 2. Device: The captured image data is stored in the internal storage and then sent to the server.

[0048] 3. Server: Receives the image data and performs image analysis using a deep learning model. This analysis identifies it as a beer bottle.

[0049] 4. Server: Based on the user's address data, the server searches the database for the relevant municipality's sorting rules and identifies specific sorting methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[0050] 5. Server: The identified sorting method is formatted in JSON format and sent to the device.

[0051] 6. Terminal: The received sorting method is displayed on the user interface.

[0052] 7. User: Check the displayed sorting method and sort the beer bottles in the correct way.

[0053] The system of the present invention allows users to easily and accurately learn how to separate their garbage, enabling them to separate their garbage appropriately and efficiently. As a result, users can dispose of their garbage in accordance with local government rules, which also contributes to environmental protection.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] A user takes a photo of trash (e.g., a beer bottle) with their smartphone camera. The device stores the captured image data in its internal storage.

[0057] Step 2:

[0058] The application on the device displays a screen for the user to check the image they have taken. When the user taps the "Confirm" button, the device prepares to send the image data to the server.

[0059] Step 3:

[0060] The device sends the image data that is ready to be sent to the server as an HTTP POST request. This request includes the image data.

[0061] Step 4:

[0062] The server receives the HTTP POST request sent from the device, extracts the image data from the request, and passes it to the image analysis module.

[0063] Step 5:

[0064] The server's image analysis module processes the received image data. It uses a deep learning model (e.g., ResNet-50 or VGG-16) to analyze the image and identify the type of debris contained in the image. In this case, the image analysis module detects that it is a beer bottle.

[0065] Step 6:

[0066] Based on the analysis results, the server references the user's residential area information and queries the database for the sorting rules for that area, searching for the appropriate sorting method.

[0067] Step 7:

[0068] The server then uses the query results to identify specific separation methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[0069] Step 8:

[0070] The server formats the generated sorting instructions in JSON format and sends them to the terminal as an HTTP response.

[0071] Step 9:

[0072] The device receives the HTTP response from the server, analyzes the received JSON data, and extracts the sorting instructions.

[0073] Step 10:

[0074] The device displays the analyzed sorting instructions on the app's user interface. The user confirms the displayed instructions and then performs the actual garbage sorting work.

[0075] This series of processes allows users to easily and accurately learn how to separate their garbage, enabling them to dispose of their garbage appropriately in accordance with local garbage separation rules.

[0076] Example 1

[0077] 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."

[0078] Conventional systems providing information on garbage sorting methods are cumbersome, requiring users to manually identify the type of garbage and look up the corresponding sorting rules. Furthermore, there is no flexible system to reflect the different sorting rules of each specific municipality, which can lead to users sorting incorrectly.

[0079] 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.

[0080] In this invention, the server includes an image acquisition means for allowing a user to take a photo of waste and generate image data of the photo, a communication means for transmitting the image data to a remote server, an image analysis means for receiving the image data and identifying the type of waste using a deep learning model, a sorting method identification means for searching a database for sorting rules corresponding to the type of waste and identifying an appropriate sorting method, and a presentation means for presenting the identified sorting method to the user. This allows the user to easily obtain an accurate sorting method and efficiently sort their waste appropriately.

[0081] The "image acquisition means" is a device or system that allows a user to take a photograph of waste and generate image data thereof.

[0082] "Communication means" is a network interface or protocol for transmitting the image data to a remote server.

[0083] "Image analysis means" refers to a processing device or software that receives the image data and uses a deep learning model to identify the type of waste.

[0084] The "sorting method specifying means" is an algorithm or system for searching a database for sorting rules corresponding to the type of waste and specifying the corresponding sorting method.

[0085] The "presentation means" refers to a display or application user interface for presenting the identified sorting method to the user.

[0086] "Waste" is a general term for garbage and unwanted items.

[0087] A "remote server" is a computer system installed remotely for communicating with a user's terminal via a network.

[0088] A "deep learning model" is a part of artificial intelligence, and is an algorithm that uses a multi-layer neural network to automatically extract features from large amounts of data and perform classification and prediction.

[0089] A "database" is an information management system for systematically storing and searching information on sorting rules and types of waste.

[0090] MODE FOR CARRYING OUT THE INVENTION

[0091] This invention is a system that allows users to learn how to separate waste materials. The system is composed of multiple means. Users take photos of waste materials using a device such as a smartphone and send the image data to a server. The server analyzes the image data, identifies the type of waste material, and then provides the user with specific separation methods based on the separation rules for the relevant area.

[0092] (composition)

[0093] Image Acquisition Method

[0094] The user takes a photo of the waste using the smartphone camera, and the image data is saved in the smartphone's internal storage. The user can then review the image data within the application and proceed to the next processing step.

[0095] communication means

[0096] The smartphone is provided with a communication means for transmitting the image data to the server. Specifically, the image data is transmitted from the smartphone terminal to the remote server using an HTTP POST request.

[0097] Image analysis methods

[0098] The server analyzes the image data received from the device using a deep learning model (e.g., ResNet-50 or VGG-16). The deep learning model identifies the type of waste (e.g., bottles, cans, plastic, etc.).

[0099] Separation method identification means

[0100] Based on the identified waste type, the server searches a database for sorting rules that correspond to the user's area of ​​residence, and uses the search results to identify specific methods for sorting waste.

[0101] Presentation means

[0102] The identified waste separation method is sent in real time to the user's device, which then displays the received information on the user interface, allowing the user to instantly confirm the correct waste separation method.

[0103] (Example)

[0104] For example, a case where a user photographs a beer bottle will be described.

[0105] 1. User: Take a photo of a beer bottle with your smartphone camera.

[0106] 2. Device: The captured image data is stored in the internal storage and sent to the server.

[0107] 3. Server: Receives the image data and performs image analysis using a deep learning model. The analysis identifies it as a beer bottle.

[0108] 4. Server: Based on the user's address information, the server searches the database for the relevant municipality's sorting rules and identifies specific sorting methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[0109] 5. Server: The identified sorting method is formatted in JSON format and sent to the device.

[0110] 6. Terminal: The received sorting method is displayed on the user interface.

[0111] 7. User: Check the displayed sorting method and sort the beer bottles in the correct way.

[0112] This allows users to easily obtain accurate waste separation methods, enabling them to efficiently separate waste appropriately. As a result, waste can be disposed of in accordance with local government rules, contributing to environmental protection.

[0113] (Example of a prompt)

[0114] "Please create a program that uses ResNet-50 to identify waste categories (bottles, cans, plastic, etc.) and searches for the municipality's waste separation rules based on the user's address. The user takes a picture of the waste with their smartphone camera and sends it to the server. Please explain in natural language the entire process, from image analysis and search on the server to displaying the separation instructions on the device."

[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0116] Step 1:

[0117] Users take photos of waste using their smartphone camera by tapping the "Take Photo" button in the application. The input is the physical presence of the waste, and the output is image data stored on the smartphone.

[0118] Step 2:

[0119] The device saves the captured image data in its internal storage. The input is the photo data from the camera application, and the output is an image file saved in the device's internal storage. Also, if the user taps the "Send" button in this step, processing for the next communication method will begin.

[0120] Step 3:

[0121] The device sends the stored image data to the server. Specifically, it generates an HTTP POST request, includes the image data in the request body, and sends it to the specified API endpoint of the remote server. The input is the image data stored inside the device, and the output is the HTTP request sent to the remote server.

[0122] Step 4:

[0123] The server receives the image data sent from the device and analyzes it using a deep learning model. Specifically, the received image data is input into a deep learning model such as ResNet-50, and image analysis is performed using the model. The input is the image data extracted from the HTTP request, and the output is the type of waste (e.g., bottle, can, plastic, etc.) as the analysis result.

[0124] Step 5:

[0125] Based on the analysis results, the server searches a database for sorting rules that correspond to the user's residential area. The input is the waste type obtained by the analysis and the user's address information, and the output is the corresponding sorting rules obtained from the database. Specifically, the server generates a database query and executes a search to obtain the sorting rules.

[0126] Step 6:

[0127] The server analyzes the obtained sorting rules and identifies the specific sorting method. The input is the sorting rules obtained from the database, and the output is the specific sorting method identified. This identified sorting method is formatted in JSON format or similar.

[0128] Step 7:

[0129] The server sends the formatted sorting method to the terminal. The input is the sorting method data in JSON format, and the output is the HTTP response sent to the terminal. This prepares the terminal for reception.

[0130] Step 8:

[0131] The device analyzes the sorting method data received from the server and displays it on the user interface. The input is the JSON data received from the server, and the output is sorting method information that is visually presented to the user. Specifically, the information is appropriately laid out on the application screen and displayed in a way that is easy for the user to understand.

[0132] Step 9:

[0133] The user checks the displayed sorting instructions and actually sorts the waste correctly. The input is the sorting information displayed on the device, and the output is the actual waste sorting behavior. The user follows the instructions and places the waste in the appropriate garbage bag or recycling container.

[0134] (Application example 1)

[0135] 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."

[0136] Until now, it has been difficult for employees to accurately and efficiently separate the wide variety of waste generated within physical stores. In particular, due to complex sorting rules and regional differences, it took a lot of time and effort for employees to understand how to separate waste. Therefore, there was a strong demand for a system that would allow employees to easily and accurately learn how to separate waste, thereby improving work efficiency.

[0137] 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.

[0138] In this invention, the server includes an image acquisition means for allowing a user to take a photo of trash and generate image data of the photo, a communication means for transmitting the image data to the server, an image analysis means for receiving the image data and identifying the type of trash, a sorting method identification means for searching a database for sorting rules corresponding to the type of trash and identifying an appropriate sorting method, a presentation means for presenting the identified sorting method to the user, and a means for presenting the trash sorting method to employees in the physical store in real time using a smart device or a robot. This enables accurate and efficient trash sorting in the physical store, reducing the burden on employees and improving work efficiency.

[0139] "Waste sorting method" is a procedure for separating waste into different categories according to material and disposal method.

[0140] A "system" refers to a device or group of devices in which multiple elements work together to achieve a specific function.

[0141] The "image acquisition means" is a function that allows a user to take a photo of the garbage using a device such as a camera and acquire the image data.

[0142] "Communication means" refers to the communication protocol and infrastructure for transmitting image data acquired on the terminal to the server.

[0143] "Image analysis means" refers to an analytical technology for identifying the type of garbage based on the image data received by the server, and includes deep learning models, etc.

[0144] The "sorting method identification means" is a function that searches a database for the sorting rules for the relevant area based on the identified type of garbage, and identifies the specific sorting method.

[0145] The "presentation means" is a function for displaying the identified waste separation method to the user and encouraging them to separate their garbage appropriately.

[0146] A "smart device" is a portable or stationary electronic device that has internet connectivity, a touchscreen, and advanced computing capabilities.

[0147] A "robot" refers to a mechanical device that operates autonomously according to programmed instructions.

[0148] "Physical store" refers to a physical store for selling goods or providing services.

[0149] A "deep learning model" is a technology that uses an artificial neural network to learn specific patterns and features from large amounts of data, enabling advanced discrimination and prediction.

[0150] MODE FOR CARRYING OUT THE INVENTION

[0151] System Configuration

[0152] A system embodying the invention includes the following major hardware and software components:

[0153] 1. Image acquisition method

[0154] Users take a photo of the trash using a smartphone, tablet, or in-store smart robot. The captured image data is stored in the device's internal storage, and the user can view the image data within the app before it moves on to the next processing step.

[0155] 2. Means of communication

[0156] The captured image data is sent to the server via Wi-Fi or a mobile network using an HTTP POST request.

[0157] 3. Image analysis methods

[0158] The server analyzes the received image data using a deep learning model (e.g., ResNet-50 or VGG-16), which automatically identifies the type of garbage (bottles, cans, plastic, etc.).

[0159] 4. Means for specifying separation method

[0160] Based on the identified type of waste, the server searches a database for sorting rules that correspond to the specific store and its location, and then determines the specific method for sorting the waste.

[0161] 5. Presentation means

[0162] The identified sorting method is sent in real time to the user's device, which then displays the received information on the user interface, allowing store employees to quickly understand the correct method for sorting waste.

[0163] 6. In-store support

[0164] Smart devices or robots will provide real-time guidance to store employees on how to separate waste, improving employee efficiency and encouraging accurate waste separation.

[0165] Examples of concrete examples and prompts

[0166] Specific examples

[0167] For example, here's the procedure for employees at a cafe to dispose of used plastic containers:

[0168] 1. User (employee): Take a photo of a plastic container with the camera on their smartphone or tablet.

[0169] 2. Device: The captured image data is stored in the internal storage and then sent to the server.

[0170] 3. Server: Analyzes the received image data using a deep learning model and identifies it as a plastic container.

[0171] 4. Server: Based on the store's location, search the database for the relevant sorting rules and identify that "plastic containers should be disposed of as plastic waste."

[0172] 5. Server: The identified sorting method is formatted in JSON format and sent to the device.

[0173] 6. Terminal: The received sorting method is displayed on the user interface, and employees sort the garbage appropriately.

[0174] Prompt Sentence Examples

[0175] Write an application program that allows users to take pictures of trash with their smartphone camera, send them to a server, and use a deep learning model to identify the type of trash. Then, based on the user's location, determine how to sort the trash and display the results on the device in real time.

[0176] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0177] Step 1:

[0178] The user takes a photo of the trash and generates image data. Specifically, the image is taken using a smartphone, tablet, or the camera of a smart robot installed in the store. This image data is then stored in the internal storage.

[0179] Input: Physical image of the trash

[0180] Output: Image data stored in internal storage

[0181] Step 2:

[0182] The device sends the captured image data to the server using an HTTP POST request via Wi-Fi or a mobile network.

[0183] Input: Image data stored in the internal storage

[0184] Output: Image data sent to the server

[0185] Step 3:

[0186] The image data received by the server is analyzed using a deep learning model. Specifically, deep learning models such as ResNet-50 and VGG-16 are used to identify the type of garbage. This analysis allows for identification of, for example, "plastic containers" or "bottles."

[0187] Input: Image data sent to the server

[0188] Output: Identified trash type (e.g. plastic container)

[0189] Step 4:

[0190] The server searches the database for the local sorting rules based on the identified type of garbage. Since the local sorting rules are identified based on the user's location information, the server also refers to the user's location data.

[0191] Input: Identified garbage type, user location information

[0192] Output: Sorting method according to type of garbage

[0193] Step 5:

[0194] Based on the search results, the server formats the identified sorting methods in JSON format and sends them to the device. The formatted data is presented to the user in a format that is easy to view.

[0195] Input: Identified separation method

[0196] Output: JSON formatted sorting method data

[0197] Step 6:

[0198] The terminal displays the received sorting method data on the user interface, allowing users (employees) to check the correct garbage sorting method in real time and sort their garbage appropriately.

[0199] Input: JSON formatted separation method data

[0200] Output: The sorting method displayed in the user interface

[0201] Step 7:

[0202] Smart devices or robots in physical stores provide real-time guidance to employees on how to separate waste, allowing them to see how to do so without having to take their hands off the device.

[0203] Input: The sorting method displayed in the user interface

[0204] Output: Garbage sorting method presented to store employees

[0205] Through these steps, waste sorting in physical stores is carried out accurately and efficiently.

[0206] 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.

[0207] The present invention provides a system that improves the user experience by combining a system for helping users learn how to separate their garbage with an emotion engine that recognizes the user's emotional state. This system is comprised of the following means.

[0208] System configuration

[0209] Image Acquisition Method

[0210] The user takes a photo of the trash using the camera on their smartphone or other device. The captured image data is saved in the device's internal storage, and the user can view the captured image data within the application and proceed to the next processing step.

[0211] communication means

[0212] The smartphone is equipped with a communication method for sending captured image data to a server. Specifically, it uses an HTTP POST request from the smartphone to the server. The image data is sent as part of this request.

[0213] Image analysis methods

[0214] The server analyzes the received image data using deep learning models (e.g., ResNet-50 and VGG-16), which automatically identifies the type of garbage (bottles, cans, plastic, etc.).

[0215] Separation method identification means

[0216] The server searches a database for sorting rules that correspond to the user's area based on the identified type of garbage, and uses the search results to identify specific methods for sorting garbage.

[0217] Presentation means

[0218] The identified sorting method is sent to the user's device in real time, and the device displays the received information on the user interface, allowing the user to instantly confirm the correct method for sorting their garbage.

[0219] Emotion Engine

[0220] The emotion engine recognizes the user's emotional state and optimizes the interface display and presentation methods accordingly. In this invention, the emotional state can be recognized by analyzing the user's voice input and facial expressions. Furthermore, the recognized emotional state can be logged and used to improve the user experience in subsequent interactions.

[0221] Specific examples

[0222] For example, consider the case where a user takes a picture of a beer bottle.

[0223] 1. User: Take a photo of a beer bottle with your smartphone camera.

[0224] 2. Device: The captured image data is stored in the internal storage and then sent to the server.

[0225] 3. Server: Receives the image data and performs image analysis using a deep learning model. This analysis identifies it as a beer bottle.

[0226] 4. Server: Based on the user's address data, the server searches the database for the relevant municipality's sorting rules and identifies specific sorting methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[0227] 5. Server: The identified sorting method is formatted in JSON format and sent to the device.

[0228] 6. Terminal: The received sorting method is displayed on the user interface.

[0229] 7. Emotion Engine: The emotion engine analyzes the user's voice and facial expressions, and if it determines that the user is confused, it provides more specific instructions or additional support information.

[0230] 8. User: Check the displayed sorting instructions and sort the beer bottles in the correct way. The additional information from the emotion engine improves the user experience.

[0231] The system of this invention not only allows users to easily learn accurate garbage sorting methods, but also enables smoother, stress-free garbage sorting with the support of the emotion engine. This allows users to dispose of garbage appropriately in accordance with local garbage sorting rules, thereby contributing to environmental protection.

[0232] The processing flow will be explained below.

[0233] Step 1:

[0234] A user takes a photo of trash (e.g., a beer bottle) with their smartphone camera. The device stores the captured image data in its internal storage.

[0235] Step 2:

[0236] The application on the device displays a screen for the user to check the image they have taken. When the user taps the "Confirm" button, the device prepares to send the image data to the server.

[0237] Step 3:

[0238] The device sends the image data that is ready to be sent to the server as an HTTP POST request. This request includes the image data.

[0239] Step 4:

[0240] The server receives the HTTP POST request sent from the device, extracts the image data from the request, and passes it to the image analysis module.

[0241] Step 5:

[0242] The server's image analysis module processes the received image data. It uses a deep learning model (e.g., ResNet-50 or VGG-16) to analyze the image and identify the type of debris contained in the image. In this case, the image analysis module detects that it is a beer bottle.

[0243] Step 6:

[0244] Based on the analysis results, the server references the user's residential area information and queries the database for the sorting rules for that area, searching for the appropriate sorting method.

[0245] Step 7:

[0246] The server then uses the query results to identify specific separation methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[0247] Step 8:

[0248] The server formats the generated sorting instructions in JSON format and sends them to the terminal as an HTTP response.

[0249] Step 9:

[0250] The device receives the HTTP response from the server, analyzes the received JSON data, and extracts the sorting instructions.

[0251] Step 10:

[0252] The device displays the analyzed sorting instructions on the app's user interface, and the user confirms the displayed instructions.

[0253] Step 11:

[0254] The emotion engine analyzes the user's voice input and facial expressions, and in the process determines whether the user is stressed or confused.

[0255] Step 12:

[0256] If the emotion engine determines that the user is confused, it will provide more detailed explanations and additional support information in addition to the identified sorting method, such as "Please dispose of beer bottles as recyclable waste. If this bottle is broken, please wrap it in protective material using these steps."

[0257] Step 13:

[0258] The terminal displays additional information from the emotion engine on the user interface to provide appropriate assistance to the user.

[0259] Step 14:

[0260] The user checks the displayed sorting method and additional information and sorts the garbage correctly accordingly.

[0261] This process allows users to easily and accurately learn how to separate their trash. Furthermore, with the support of the emotion engine, the user experience is improved, allowing them to separate their trash without feeling stressed or confused.

[0262] Example 2

[0263] 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."

[0264] While existing technologies provide users with accurate and prompt guidance on how to separate their trash, there is a lack of technology that provides optimal guidance based on the user's emotional state. In particular, there is a need for technology that can improve situations where users become confused or stressed about how to separate their trash.

[0265] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an image acquisition means for allowing a user to take a photo of garbage and generate image data thereof, a communication means for transmitting the image data to the server, an image analysis means for receiving the image data and identifying the type of garbage using a model based on deep learning, a sorting method identification means for searching a database for sorting rules corresponding to the type of garbage and identifying an appropriate sorting method, a presentation means for presenting the identified sorting method to the user, an emotion engine means for analyzing the user's voice input and facial expressions to recognize the user's emotional state, and a means for optimizing the presentation method based on the recognized emotional state. This not only enables the user to accurately understand how to sort garbage, but also improves the user's usage experience according to the user's emotional state.

[0266] text

[0267] The "image acquisition means" is a device that allows a user to take a photograph of the garbage and generate image data of the photograph.

[0268] The "communication means" is a device or function for transmitting the image data to the server.

[0269] The "image analysis means" is a device or function that receives the image data and identifies the type of dust using a model that uses deep learning.

[0270] The "sorting method specifying means" is a device or function that searches a database for sorting rules that correspond to the type of waste and specifies the corresponding sorting method.

[0271] The "presentation means" is a device or function for presenting the identified sorting method to the user.

[0272] The "emotion engine means" is a device or function that analyzes the user's voice input and facial expressions and recognizes the user's emotional state.

[0273] An "optimizer" is a device or function that optimizes presentation methods based on a recognized emotional state.

[0274] The present invention provides a technology for recognizing a user's emotional state and optimizing guidance based on the emotional state in a system for helping a user learn how to separate garbage. The system includes the following means.

[0275] Image Acquisition Method

[0276] The user takes a photo of the trash using the smartphone camera. For example, if the user takes a photo of a beer bottle, the image data is saved in the device's internal storage. This image acquisition method is realized by using the smartphone's camera application.

[0277] communication means

[0278] The device sends the saved image data to the server. This communication is performed using an HTTP POST request, and the image data is included in this request and sent to the server. The communication method is the smartphone's Internet connection function.

[0279] Image analysis methods

[0280] The server analyzes the received image data. A deep learning model (e.g., ResNet-50 or VGG-16) is used for this image analysis. The server uses this model to identify the type of garbage (e.g., bottles, cans, plastic, etc.). The server's processing unit uses hardware such as a GPU to perform this analysis quickly.

[0281] Separation method identification means

[0282] The server searches a database for sorting rules that correspond to the user's area of ​​residence based on the identified type of garbage. For example, it obtains a rule such as "beer bottles should be disposed of as recyclable garbage" and identifies the specific sorting method. This search process uses a relational database management system (RDBMS).

[0283] Presentation means

[0284] The server sends the identified sorting method to the user's device in real time. The device displays the received information on the user interface. For example, the screen might say, "Please dispose of beer bottles as recyclable waste."

[0285] Emotion Engine Means

[0286] The device analyzes the user's voice input and facial expressions to recognize the user's emotional state. This analysis is performed using voice recognition software and facial expression analysis algorithms. For example, if the device recognizes that the user is confused, it may display more specific instructions or additional support information. The emotion engine means transmits the results to a server, which uses them to improve the user experience in subsequent interactions.

[0287] Specific examples

[0288] The series of processes will be explained using a specific example. For example, if a user takes a photo of a beer bottle, the following prompt sentence can be input to the generative AI model:

[0289] Prompt Sentence Examples

[0290] "Tell me how to separate beer bottles into trash. If the user is confused, how would the emotion engine respond?"

[0291] This system not only allows users to easily obtain accurate garbage sorting instructions, but also enhances the user experience with its emotion engine. Specifically, if users are confused, the system can provide more detailed explanations and additional support information, enabling a smoother garbage sorting process. This promotes proper garbage disposal in accordance with local garbage sorting rules and contributes to environmental protection.

[0292] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0293] text

[0294] Step 1: Acquire and save image data

[0295] A user takes a photo of trash using the smartphone camera. For example, they take a photo of a beer bottle by tapping the camera button on the camera app. The input is the image of the beer bottle taken by the user, and the output is the image data. The device saves the generated image data in its internal storage, and the save destination is a specific folder on the device (e.g., the application folder).

[0296] Step 2: Sending image data

[0297] The device sends the saved image data to the server. This communication uses an HTTP POST request, and the image data is included in this request. The input is the image data saved in step 1, and the output is the image data sent to the server. The device displays the progress of the communication in the status bar.

[0298] Step 3: Receiving and analyzing image data

[0299] The server receives the received image data and analyzes the image using a deep learning model (e.g., ResNet-50 or VGG-16). The input is the image data sent from the device, and the output is the identification result of the type of garbage (e.g., bottle). The server stores the data in a temporary database on the server to temporarily save the analysis results.

[0300] Step 4: Search for sorting rules

[0301] The server searches a database for sorting rules that correspond to the user's area of ​​residence based on the identified type of garbage. The input is the garbage identification result and the user's address data, and the output is the corresponding sorting rule (e.g., "Beer bottles should be disposed of as recyclable garbage"). The server performs a rapid search using a relational database management system (RDBMS).

[0302] Step 5: Identify and format the sorting method

[0303] The server identifies specific sorting methods based on the search results and formats this information in JSON format. The input is the sorting rules obtained in step 4, and the output is the formatted sorting method data. The server prepares this data to send as a response.

[0304] Step 6: Present the sorting method

[0305] The server sends the formatted sorting method data to the terminal. The terminal analyzes the received data and displays it on the user interface. For example, it might display "Please dispose of beer bottles as recyclable waste." The input is the sorting method data from the server, and the output is the content presented to the user.

[0306] Step 7: Recognizing your emotional state

[0307] The device acquires the user's voice input and facial expressions. For this purpose, it uses a camera and microphone. The input is the user's voice data and video data, and the output is input data to the emotion engine. The device sends this data to the emotion engine.

[0308] Step 8: Emotional state analysis and feedback

[0309] The device uses an emotion engine to analyze the user's emotional state. The input is audio and video data, and the output is the identification result of the user's emotional state. For example, if the device recognizes that the user is confused, it will display more specific instructions or additional support information. It will display additional detailed explanations on the screen, such as "Please dispose of beer bottles as recyclable waste. Caps are general waste."

[0310] (Application example 2)

[0311] 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."

[0312] Conventional garbage sorting systems require users to manually check the type of garbage and local sorting rules, which is often time-consuming and laborious. Furthermore, if users feel confused or stressed about how to sort their garbage, the system provides no appropriate support, making the sorting process itself a hassle. The goal of this system is to solve these issues, improve the user experience, and achieve more efficient and accurate garbage sorting.

[0313] The identification process 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 image acquisition means for allowing a user to take a photo of garbage and generate image data thereof, communication means for transmitting the image data to the server, image analysis means for receiving the image data and identifying the type of garbage, sorting method identification means for searching a database for sorting rules corresponding to the type of garbage and identifying an appropriate sorting method, presentation means for presenting the identified sorting method to the user, and emotion recognition means for recognizing the user's emotional state and optimizing the display of the interface in accordance with that state. This not only enables the user to easily and accurately acquire garbage sorting methods, but also provides optimal support in accordance with the user's emotional state, enabling smoother and more stress-free garbage sorting.

[0314] The "image acquisition means" is a device or mechanism that allows a user to take a photo of the garbage and generate image data of the photo.

[0315] The "communication means" is a network communication means for transmitting the image data to the server.

[0316] The "image analysis means" is an analysis device that receives the image data and uses a deep learning model or the like to identify the type of dust.

[0317] The "sorting method specifying means" is a device or mechanism for searching a database for sorting rules corresponding to the type of waste and specifying the corresponding sorting method.

[0318] The "presentation means" is a user interface for presenting the identified separation method to the user.

[0319] An "emotion recognition means" is a device or mechanism for recognizing the user's emotional state and optimizing the display of the interface in accordance with that state.

[0320] "Deep learning" is a machine learning technology that recognizes and predicts complex patterns by learning from large amounts of data.

[0321] A "server" is a computer system that provides services in response to requests from clients.

[0322] A "database" is a data storage device for managing and searching garbage sorting rules and other related information.

[0323] This invention provides a system called "Smart Eco Guide" that allows users to easily learn how to separate garbage. This system includes the following main components:

[0324] 1. Image acquisition method

[0325] When a user takes a photo of trash using the smartphone camera, the application controls the camera device and saves the captured image data in the internal storage.

[0326] 2. Means of communication

[0327] The smartphone is equipped with a communication method for sending captured image data to a server. Specifically, it uses an HTTP POST request from the smartphone to the server. The image data is included in this request.

[0328] 3. Image analysis methods

[0329] The server analyzes the received image data using a deep learning model (e.g., ResNet-50 or VGG-16), which automatically identifies the type of garbage (e.g., bottles, cans, plastic, etc.).

[0330] 4. Means for specifying separation method

[0331] The server searches a database for sorting rules that correspond to the user's area or specific location based on the type of garbage identified, and uses the search results to identify specific methods for sorting garbage.

[0332] 5. Presentation means

[0333] The identified sorting method is sent to the user's device in real time and displayed on the user interface, allowing the user to instantly confirm the correct method for sorting their garbage.

[0334] 6. Emotion recognition means

[0335] The emotion recognition engine analyzes the user's emotional state and optimizes the interface display and presentation accordingly. For example, if it determines that the user is confused, it will display more detailed explanations or supplementary information.

[0336] Hardware and software used

[0337] Hardware

[0338] Smartphone (with camera function)

[0339] Server (high-performance computing power required)

[0340] software

[0341] OpenCV: for image capture and pre-processing

[0342] Keras: for loading and predicting deep learning models

[0343] Requests: HTTP communication library

[0344] Sentiment Analysis API: An external service for analyzing user sentiment

[0345] Specific examples

[0346] For example, consider a case where a user wants to properly separate empty plastic bottles at a shopping mall:

[0347] 1. The user launches the app on their smartphone and takes a photo of a plastic bottle with the camera.

[0348] 2. The captured image is sent to a server, where a deep learning model analyzes the image and identifies it as a plastic bottle.

[0349] 3. The server searches the database for the mall's garbage sorting rules and identifies the correct way to sort plastic bottles.

[0350] 4. The app displays the sorting method on the user interface, helping users sort their waste correctly without hesitation.

[0351] 5. If the user is confused, the emotion recognition engine will detect this and provide more specific explanations and images.

[0352] Prompt Sentence Examples

[0353] When a user wants to know how to sort a plastic bottle they have finished drinking from, they launch the app and take a photo of the trash with their smartphone camera. The image is sent to the server, where the AI ​​analyzes it and returns the correct sorting instructions. The app also analyzes the user's emotional state and, if it determines they are confused, provides additional details and a QR code. Express this process in Python code.

[0354] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0355] Step 1:

[0356] The user takes a photo of the garbage. The user launches the app on their smartphone and takes a photo of the garbage using the camera function. The input is the actual garbage, and the output is image data. This image data is saved in the internal storage.

[0357] Step 2:

[0358] The device sends image data to the server. The device sends image data stored in its internal storage to the server via an HTTP POST request. The input is the image data, and the output is a data packet sent to the server.

[0359] Step 3:

[0360] The server analyzes the image data. The server analyzes the received image data using a deep learning model (e.g., ResNet-50 or VGG-16). The input is the image data, and the output is the identified type of garbage (e.g., PET bottle, can, plastic, etc.).

[0361] Step 4:

[0362] The server searches for the sorting rules and identifies the sorting method. Based on the identified type of garbage, the server searches for the corresponding sorting rule from the database. The input is the type of garbage, and the output is the specific sorting method. This sorting method is formatted in JSON format.

[0363] Step 5:

[0364] The server sends the specified sorting method to the terminal. The server sends the specified sorting method (JSON format) to the terminal. The input is the JSON data of the sorting method, and the output is the data packet sent to the terminal.

[0365] Step 6:

[0366] The terminal displays the sorting method on the user interface. The terminal analyzes the received data on the sorting method and displays it on the user interface. The input is the JSON data of the sorting method, and the output is the sorting method displayed on the user interface.

[0367] Step 7:

[0368] The server analyzes the user's emotional state. The server uses an emotion analysis API to analyze the user's voice data and facial expression images being captured. The input is the voice data and facial expression images, and the output is the analysis result of the user's emotional state (e.g., confusion, stress).

[0369] Step 8:

[0370] The server provides optimal support according to the user's emotional state. If the server determines that the user is confused based on the analysis results, it generates additional detailed information and a QR code and sends them to the device. The input is the emotion analysis result, and the output is the additional information and QR code data.

[0371] By clearly indicating the specific operations and inputs / outputs at each step, the overall processing flow of the system becomes clear, allowing users to smoothly and accurately learn how to separate their garbage.

[0372] 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.

[0373] 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.

[0374] 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.

[0375] [Second embodiment]

[0376] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0377] 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.

[0378] 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).

[0379] 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.

[0380] 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.

[0381] 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).

[0382] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0383] 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.

[0384] 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.

[0385] 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.

[0386] 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.

[0387] 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."

[0388] The present invention is a system for enabling a user to learn how to separate garbage, and this system is composed of a plurality of means. Hereinafter, an embodiment of the present invention will be described in detail.

[0389] System configuration

[0390] Image Acquisition Method

[0391] The user takes a photo of the trash using the camera on their smartphone or other device. The captured image data is saved in the device's internal storage. The user can then view the captured image data within the application and proceed to the next processing step.

[0392] communication means

[0393] The smartphone is equipped with a communication method for sending captured image data to a server. Specifically, it uses an HTTP POST request from the smartphone to the server. The image data is sent as part of this request.

[0394] Image analysis methods

[0395] The server analyzes the received image data using deep learning models (e.g., ResNet-50 and VGG-16), which automatically identifies the type of garbage (bottles, cans, plastic, etc.).

[0396] Separation method identification means

[0397] The server searches a database for sorting rules that correspond to the user's area based on the identified type of garbage, and uses the search results to identify specific methods for sorting garbage.

[0398] Presentation means

[0399] The identified sorting method is sent to the user's device in real time, and the device displays the received information on the user interface, allowing the user to instantly confirm the correct method for sorting their garbage.

[0400] Specific examples

[0401] For example, consider the case where a user takes a picture of a beer bottle.

[0402] 1. User: Take a photo of a beer bottle with your smartphone camera.

[0403] 2. Device: The captured image data is stored in the internal storage and then sent to the server.

[0404] 3. Server: Receives the image data and performs image analysis using a deep learning model. This analysis identifies it as a beer bottle.

[0405] 4. Server: Based on the user's address data, the server searches the database for the relevant municipality's sorting rules and identifies specific sorting methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[0406] 5. Server: The identified sorting method is formatted in JSON format and sent to the device.

[0407] 6. Terminal: The received sorting method is displayed on the user interface.

[0408] 7. User: Check the displayed sorting method and sort the beer bottles in the correct way.

[0409] The system of the present invention allows users to easily and accurately learn how to separate their garbage, enabling them to separate their garbage appropriately and efficiently. As a result, users can dispose of their garbage in accordance with local government rules, which also contributes to environmental protection.

[0410] The processing flow will be explained below.

[0411] Step 1:

[0412] A user takes a photo of trash (e.g., a beer bottle) with their smartphone camera. The device stores the captured image data in its internal storage.

[0413] Step 2:

[0414] The application on the device displays a screen for the user to check the image they have taken. When the user taps the "Confirm" button, the device prepares to send the image data to the server.

[0415] Step 3:

[0416] The device sends the image data that is ready to be sent to the server as an HTTP POST request. This request includes the image data.

[0417] Step 4:

[0418] The server receives the HTTP POST request sent from the device, extracts the image data from the request, and passes it to the image analysis module.

[0419] Step 5:

[0420] The server's image analysis module processes the received image data. It uses a deep learning model (e.g., ResNet-50 or VGG-16) to analyze the image and identify the type of debris contained in the image. In this case, the image analysis module detects that it is a beer bottle.

[0421] Step 6:

[0422] Based on the analysis results, the server references the user's residential area information and queries the database for the sorting rules for that area, searching for the appropriate sorting method.

[0423] Step 7:

[0424] The server then uses the query results to identify specific separation methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[0425] Step 8:

[0426] The server formats the generated sorting instructions in JSON format and sends them to the terminal as an HTTP response.

[0427] Step 9:

[0428] The device receives the HTTP response from the server, analyzes the received JSON data, and extracts the sorting instructions.

[0429] Step 10:

[0430] The device displays the analyzed sorting instructions on the app's user interface. The user confirms the displayed instructions and then performs the actual garbage sorting work.

[0431] This series of processes allows users to easily and accurately learn how to separate their garbage, enabling them to dispose of their garbage appropriately in accordance with local garbage separation rules.

[0432] Example 1

[0433] 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."

[0434] Conventional systems providing information on garbage sorting methods are cumbersome, requiring users to manually identify the type of garbage and look up the corresponding sorting rules. Furthermore, there is no flexible system to reflect the different sorting rules of each specific municipality, which can lead to users sorting incorrectly.

[0435] 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.

[0436] In this invention, the server includes an image acquisition means for allowing a user to take a photo of waste and generate image data of the photo, a communication means for transmitting the image data to a remote server, an image analysis means for receiving the image data and identifying the type of waste using a deep learning model, a sorting method identification means for searching a database for sorting rules corresponding to the type of waste and identifying an appropriate sorting method, and a presentation means for presenting the identified sorting method to the user. This allows the user to easily obtain an accurate sorting method and efficiently sort their waste appropriately.

[0437] The "image acquisition means" is a device or system that allows a user to take a photograph of waste and generate image data thereof.

[0438] "Communication means" is a network interface or protocol for transmitting the image data to a remote server.

[0439] "Image analysis means" refers to a processing device or software that receives the image data and uses a deep learning model to identify the type of waste.

[0440] The "sorting method specifying means" is an algorithm or system for searching a database for sorting rules corresponding to the type of waste and specifying the corresponding sorting method.

[0441] The "presentation means" refers to a display or application user interface for presenting the identified sorting method to the user.

[0442] "Waste" is a general term for garbage and unwanted items.

[0443] A "remote server" is a computer system installed remotely for communicating with a user's terminal via a network.

[0444] A "deep learning model" is a part of artificial intelligence, and is an algorithm that uses a multi-layer neural network to automatically extract features from large amounts of data and perform classification and prediction.

[0445] A "database" is an information management system for systematically storing and searching information on sorting rules and types of waste.

[0446] MODE FOR CARRYING OUT THE INVENTION

[0447] This invention is a system that allows users to learn how to separate waste materials. The system is composed of multiple means. Users take photos of waste materials using a device such as a smartphone and send the image data to a server. The server analyzes the image data, identifies the type of waste material, and then provides the user with specific separation methods based on the separation rules for the relevant area.

[0448] (composition)

[0449] Image Acquisition Method

[0450] The user takes a photo of the waste using the smartphone camera, and the image data is saved in the smartphone's internal storage. The user can then review the image data within the application and proceed to the next processing step.

[0451] communication means

[0452] The smartphone is provided with a communication means for transmitting the image data to the server. Specifically, the image data is transmitted from the smartphone terminal to the remote server using an HTTP POST request.

[0453] Image analysis methods

[0454] The server analyzes the image data received from the device using a deep learning model (e.g., ResNet-50 or VGG-16). The deep learning model identifies the type of waste (e.g., bottles, cans, plastic, etc.).

[0455] Separation method identification means

[0456] Based on the identified waste type, the server searches a database for sorting rules that correspond to the user's area of ​​residence, and uses the search results to identify specific methods for sorting waste.

[0457] Presentation means

[0458] The identified waste separation method is sent in real time to the user's device, which then displays the received information on the user interface, allowing the user to instantly confirm the correct waste separation method.

[0459] (Example)

[0460] For example, a case where a user photographs a beer bottle will be described.

[0461] 1. User: Take a photo of a beer bottle with your smartphone camera.

[0462] 2. Device: The captured image data is stored in the internal storage and sent to the server.

[0463] 3. Server: Receives the image data and performs image analysis using a deep learning model. The analysis identifies it as a beer bottle.

[0464] 4. Server: Based on the user's address information, the server searches the database for the relevant municipality's sorting rules and identifies specific sorting methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[0465] 5. Server: The identified sorting method is formatted in JSON format and sent to the device.

[0466] 6. Terminal: The received sorting method is displayed on the user interface.

[0467] 7. User: Check the displayed sorting method and sort the beer bottles in the correct way.

[0468] This allows users to easily obtain accurate waste separation methods, enabling them to efficiently separate waste appropriately. As a result, waste can be disposed of in accordance with local government rules, contributing to environmental protection.

[0469] (Example of a prompt)

[0470] "Please create a program that uses ResNet-50 to identify waste categories (bottles, cans, plastic, etc.) and searches for the municipality's waste separation rules based on the user's address. The user takes a picture of the waste with their smartphone camera and sends it to the server. Please explain in natural language the entire process, from image analysis and search on the server to displaying the separation instructions on the device."

[0471] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0472] Step 1:

[0473] Users take photos of waste using their smartphone camera by tapping the "Take Photo" button in the application. The input is the physical presence of the waste, and the output is image data stored on the smartphone.

[0474] Step 2:

[0475] The device saves the captured image data in its internal storage. The input is the photo data from the camera application, and the output is an image file saved in the device's internal storage. Also, if the user taps the "Send" button in this step, processing for the next communication method will begin.

[0476] Step 3:

[0477] The device sends the stored image data to the server. Specifically, it generates an HTTP POST request, includes the image data in the request body, and sends it to the specified API endpoint of the remote server. The input is the image data stored inside the device, and the output is the HTTP request sent to the remote server.

[0478] Step 4:

[0479] The server receives the image data sent from the device and analyzes it using a deep learning model. Specifically, the received image data is input into a deep learning model such as ResNet-50, and image analysis is performed using the model. The input is the image data extracted from the HTTP request, and the output is the type of waste (e.g., bottle, can, plastic, etc.) as the analysis result.

[0480] Step 5:

[0481] Based on the analysis results, the server searches a database for sorting rules that correspond to the user's residential area. The input is the waste type obtained by the analysis and the user's address information, and the output is the corresponding sorting rules obtained from the database. Specifically, the server generates a database query and executes a search to obtain the sorting rules.

[0482] Step 6:

[0483] The server analyzes the obtained sorting rules and identifies the specific sorting method. The input is the sorting rules obtained from the database, and the output is the specific sorting method identified. This identified sorting method is formatted in JSON format or similar.

[0484] Step 7:

[0485] The server sends the formatted sorting method to the terminal. The input is the sorting method data in JSON format, and the output is the HTTP response sent to the terminal. This prepares the terminal for reception.

[0486] Step 8:

[0487] The device analyzes the sorting method data received from the server and displays it on the user interface. The input is the JSON data received from the server, and the output is sorting method information that is visually presented to the user. Specifically, the information is appropriately laid out on the application screen and displayed in a way that is easy for the user to understand.

[0488] Step 9:

[0489] The user checks the displayed sorting instructions and actually sorts the waste correctly. The input is the sorting information displayed on the device, and the output is the actual waste sorting behavior. The user follows the instructions and places the waste in the appropriate garbage bag or recycling container.

[0490] (Application example 1)

[0491] 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."

[0492] Until now, it has been difficult for employees to accurately and efficiently separate the wide variety of waste generated within physical stores. In particular, due to complex sorting rules and regional differences, it took a lot of time and effort for employees to understand how to separate waste. Therefore, there was a strong demand for a system that would allow employees to easily and accurately learn how to separate waste, thereby improving work efficiency.

[0493] 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.

[0494] In this invention, the server includes an image acquisition means for allowing a user to take a photo of trash and generate image data of the photo, a communication means for transmitting the image data to the server, an image analysis means for receiving the image data and identifying the type of trash, a sorting method identification means for searching a database for sorting rules corresponding to the type of trash and identifying an appropriate sorting method, a presentation means for presenting the identified sorting method to the user, and a means for presenting the trash sorting method to employees in the physical store in real time using a smart device or a robot. This enables accurate and efficient trash sorting in the physical store, reducing the burden on employees and improving work efficiency.

[0495] "Waste sorting method" is a procedure for separating waste into different categories according to material and disposal method.

[0496] A "system" refers to a device or group of devices in which multiple elements work together to achieve a specific function.

[0497] The "image acquisition means" is a function that allows a user to take a photo of the garbage using a device such as a camera and acquire the image data.

[0498] "Communication means" refers to the communication protocol and infrastructure for transmitting image data acquired on the terminal to the server.

[0499] "Image analysis means" refers to an analytical technology for identifying the type of garbage based on the image data received by the server, and includes deep learning models, etc.

[0500] The "sorting method identification means" is a function that searches a database for the sorting rules for the relevant area based on the identified type of garbage, and identifies the specific sorting method.

[0501] The "presentation means" is a function for displaying the identified waste separation method to the user and encouraging them to separate their garbage appropriately.

[0502] A "smart device" is a portable or stationary electronic device that has internet connectivity, a touchscreen, and advanced computing capabilities.

[0503] A "robot" refers to a mechanical device that operates autonomously according to programmed instructions.

[0504] "Physical store" refers to a physical store for selling goods or providing services.

[0505] A "deep learning model" is a technology that uses an artificial neural network to learn specific patterns and features from large amounts of data, enabling advanced discrimination and prediction.

[0506] MODE FOR CARRYING OUT THE INVENTION

[0507] System Configuration

[0508] A system embodying the invention includes the following major hardware and software components:

[0509] 1. Image acquisition method

[0510] Users take a photo of the trash using a smartphone, tablet, or in-store smart robot. The captured image data is stored in the device's internal storage, and the user can view the image data within the app before it moves on to the next processing step.

[0511] 2. Means of communication

[0512] The captured image data is sent to the server via Wi-Fi or a mobile network using an HTTP POST request.

[0513] 3. Image analysis methods

[0514] The server analyzes the received image data using a deep learning model (e.g., ResNet-50 or VGG-16), which automatically identifies the type of garbage (bottles, cans, plastic, etc.).

[0515] 4. Means for specifying separation method

[0516] Based on the identified type of waste, the server searches a database for sorting rules that correspond to the specific store and its location, and then determines the specific method for sorting the waste.

[0517] 5. Presentation means

[0518] The identified sorting method is sent in real time to the user's device, which then displays the received information on the user interface, allowing store employees to quickly understand the correct method for sorting waste.

[0519] 6. In-store support

[0520] Smart devices or robots will provide real-time guidance to store employees on how to separate waste, improving employee efficiency and encouraging accurate waste separation.

[0521] Examples of concrete examples and prompts

[0522] Specific examples

[0523] For example, here's the procedure for employees at a cafe to dispose of used plastic containers:

[0524] 1. User (employee): Take a photo of a plastic container with the camera on their smartphone or tablet.

[0525] 2. Device: The captured image data is stored in the internal storage and then sent to the server.

[0526] 3. Server: Analyzes the received image data using a deep learning model and identifies it as a plastic container.

[0527] 4. Server: Based on the store's location, search the database for the relevant sorting rules and identify that "plastic containers should be disposed of as plastic waste."

[0528] 5. Server: The identified sorting method is formatted in JSON format and sent to the device.

[0529] 6. Terminal: The received sorting method is displayed on the user interface, and employees sort the garbage appropriately.

[0530] Prompt Sentence Examples

[0531] Write an application program that allows users to take pictures of trash with their smartphone camera, send them to a server, and use a deep learning model to identify the type of trash. Then, based on the user's location, determine how to sort the trash and display the results on the device in real time.

[0532] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0533] Step 1:

[0534] The user takes a photo of the trash and generates image data. Specifically, the image is taken using a smartphone, tablet, or the camera of a smart robot installed in the store. This image data is then stored in the internal storage.

[0535] Input: Physical image of the trash

[0536] Output: Image data stored in internal storage

[0537] Step 2:

[0538] The device sends the captured image data to the server using an HTTP POST request via Wi-Fi or a mobile network.

[0539] Input: Image data stored in the internal storage

[0540] Output: Image data sent to the server

[0541] Step 3:

[0542] The image data received by the server is analyzed using a deep learning model. Specifically, deep learning models such as ResNet-50 and VGG-16 are used to identify the type of garbage. This analysis allows for identification of, for example, "plastic containers" or "bottles."

[0543] Input: Image data sent to the server

[0544] Output: Identified trash type (e.g. plastic container)

[0545] Step 4:

[0546] The server searches the database for the local sorting rules based on the identified type of garbage. Since the local sorting rules are identified based on the user's location information, the server also refers to the user's location data.

[0547] Input: Identified garbage type, user location information

[0548] Output: Sorting method according to type of garbage

[0549] Step 5:

[0550] Based on the search results, the server formats the identified sorting methods in JSON format and sends them to the device. The formatted data is presented to the user in a format that is easy to view.

[0551] Input: Identified separation method

[0552] Output: JSON formatted sorting method data

[0553] Step 6:

[0554] The terminal displays the received sorting method data on the user interface, allowing users (employees) to check the correct garbage sorting method in real time and sort their garbage appropriately.

[0555] Input: JSON formatted separation method data

[0556] Output: The sorting method displayed in the user interface

[0557] Step 7:

[0558] Smart devices or robots in physical stores provide real-time guidance to employees on how to separate waste, allowing them to see how to do so without having to take their hands off the device.

[0559] Input: The sorting method displayed in the user interface

[0560] Output: Garbage sorting method presented to store employees

[0561] Through these steps, waste sorting in physical stores is carried out accurately and efficiently.

[0562] 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.

[0563] The present invention provides a system that improves the user experience by combining a system for helping users learn how to separate their garbage with an emotion engine that recognizes the user's emotional state. This system is comprised of the following means.

[0564] System configuration

[0565] Image Acquisition Method

[0566] The user takes a photo of the trash using the camera on their smartphone or other device. The captured image data is saved in the device's internal storage, and the user can view the captured image data within the application and proceed to the next processing step.

[0567] communication means

[0568] The smartphone is equipped with a communication method for sending captured image data to a server. Specifically, it uses an HTTP POST request from the smartphone to the server. The image data is sent as part of this request.

[0569] Image analysis methods

[0570] The server analyzes the received image data using deep learning models (e.g., ResNet-50 and VGG-16), which automatically identifies the type of garbage (bottles, cans, plastic, etc.).

[0571] Separation method identification means

[0572] The server searches a database for sorting rules that correspond to the user's area based on the identified type of garbage, and uses the search results to identify specific methods for sorting garbage.

[0573] Presentation means

[0574] The identified sorting method is sent to the user's device in real time, and the device displays the received information on the user interface, allowing the user to instantly confirm the correct method for sorting their garbage.

[0575] Emotion Engine

[0576] The emotion engine recognizes the user's emotional state and optimizes the interface display and presentation methods accordingly. In this invention, the emotional state can be recognized by analyzing the user's voice input and facial expressions. Furthermore, the recognized emotional state can be logged and used to improve the user experience in subsequent interactions.

[0577] Specific examples

[0578] For example, consider the case where a user takes a picture of a beer bottle.

[0579] 1. User: Take a photo of a beer bottle with your smartphone camera.

[0580] 2. Device: The captured image data is stored in the internal storage and then sent to the server.

[0581] 3. Server: Receives the image data and performs image analysis using a deep learning model. This analysis identifies it as a beer bottle.

[0582] 4. Server: Based on the user's address data, the server searches the database for the relevant municipality's sorting rules and identifies specific sorting methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[0583] 5. Server: The identified sorting method is formatted in JSON format and sent to the device.

[0584] 6. Terminal: The received sorting method is displayed on the user interface.

[0585] 7. Emotion Engine: The emotion engine analyzes the user's voice and facial expressions, and if it determines that the user is confused, it provides more specific instructions or additional support information.

[0586] 8. User: Check the displayed sorting instructions and sort the beer bottles in the correct way. The additional information from the emotion engine improves the user experience.

[0587] The system of this invention not only allows users to easily learn accurate garbage sorting methods, but also enables smoother, stress-free garbage sorting with the support of the emotion engine. This allows users to dispose of garbage appropriately in accordance with local garbage sorting rules, thereby contributing to environmental protection.

[0588] The processing flow will be explained below.

[0589] Step 1:

[0590] A user takes a photo of trash (e.g., a beer bottle) with their smartphone camera. The device stores the captured image data in its internal storage.

[0591] Step 2:

[0592] The application on the device displays a screen for the user to check the image they have taken. When the user taps the "Confirm" button, the device prepares to send the image data to the server.

[0593] Step 3:

[0594] The device sends the image data that is ready to be sent to the server as an HTTP POST request. This request includes the image data.

[0595] Step 4:

[0596] The server receives the HTTP POST request sent from the device, extracts the image data from the request, and passes it to the image analysis module.

[0597] Step 5:

[0598] The server's image analysis module processes the received image data. It uses a deep learning model (e.g., ResNet-50 or VGG-16) to analyze the image and identify the type of debris contained in the image. In this case, the image analysis module detects that it is a beer bottle.

[0599] Step 6:

[0600] Based on the analysis results, the server references the user's residential area information and queries the database for the sorting rules for that area, searching for the appropriate sorting method.

[0601] Step 7:

[0602] The server then uses the query results to identify specific separation methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[0603] Step 8:

[0604] The server formats the generated sorting instructions in JSON format and sends them to the terminal as an HTTP response.

[0605] Step 9:

[0606] The device receives the HTTP response from the server, analyzes the received JSON data, and extracts the sorting instructions.

[0607] Step 10:

[0608] The device displays the analyzed sorting instructions on the app's user interface, and the user confirms the displayed instructions.

[0609] Step 11:

[0610] The emotion engine analyzes the user's voice input and facial expressions, and in the process determines whether the user is stressed or confused.

[0611] Step 12:

[0612] If the emotion engine determines that the user is confused, it will provide more detailed explanations and additional support information in addition to the identified sorting method, such as "Please dispose of beer bottles as recyclable waste. If this bottle is broken, please wrap it in protective material using these steps."

[0613] Step 13:

[0614] The terminal displays additional information from the emotion engine on the user interface to provide appropriate assistance to the user.

[0615] Step 14:

[0616] The user checks the displayed sorting method and additional information and sorts the garbage correctly accordingly.

[0617] This process allows users to easily and accurately learn how to separate their trash. Furthermore, with the support of the emotion engine, the user experience is improved, allowing them to separate their trash without feeling stressed or confused.

[0618] Example 2

[0619] 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."

[0620] While existing technologies provide users with accurate and prompt guidance on how to separate their trash, there is a lack of technology that provides optimal guidance based on the user's emotional state. In particular, there is a need for technology that can improve situations where users become confused or stressed about how to separate their trash.

[0621] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an image acquisition means for allowing a user to take a photo of garbage and generate image data thereof, a communication means for transmitting the image data to the server, an image analysis means for receiving the image data and identifying the type of garbage using a model based on deep learning, a sorting method identification means for searching a database for sorting rules corresponding to the type of garbage and identifying an appropriate sorting method, a presentation means for presenting the identified sorting method to the user, an emotion engine means for analyzing the user's voice input and facial expressions to recognize the user's emotional state, and a means for optimizing the presentation method based on the recognized emotional state. This not only enables the user to accurately understand how to sort garbage, but also improves the user's usage experience according to the user's emotional state.

[0622] text

[0623] The "image acquisition means" is a device that allows a user to take a photograph of the garbage and generate image data of the photograph.

[0624] The "communication means" is a device or function for transmitting the image data to the server.

[0625] The "image analysis means" is a device or function that receives the image data and identifies the type of dust using a model that uses deep learning.

[0626] The "sorting method specifying means" is a device or function that searches a database for sorting rules that correspond to the type of waste and specifies the corresponding sorting method.

[0627] The "presentation means" is a device or function for presenting the identified sorting method to the user.

[0628] The "emotion engine means" is a device or function that analyzes the user's voice input and facial expressions and recognizes the user's emotional state.

[0629] An "optimizer" is a device or function that optimizes presentation methods based on a recognized emotional state.

[0630] The present invention provides a technology for recognizing a user's emotional state and optimizing guidance based on the emotional state in a system for helping a user learn how to separate garbage. The system includes the following means.

[0631] Image Acquisition Method

[0632] The user takes a photo of the trash using the smartphone camera. For example, if the user takes a photo of a beer bottle, the image data is saved in the device's internal storage. This image acquisition method is realized by using the smartphone's camera application.

[0633] communication means

[0634] The device sends the saved image data to the server. This communication is performed using an HTTP POST request, and the image data is included in this request and sent to the server. The communication method is the smartphone's Internet connection function.

[0635] Image analysis methods

[0636] The server analyzes the received image data. A deep learning model (e.g., ResNet-50 or VGG-16) is used for this image analysis. The server uses this model to identify the type of garbage (e.g., bottles, cans, plastic, etc.). The server's processing unit uses hardware such as a GPU to perform this analysis quickly.

[0637] Separation method identification means

[0638] The server searches a database for sorting rules that correspond to the user's area of ​​residence based on the identified type of garbage. For example, it obtains a rule such as "beer bottles should be disposed of as recyclable garbage" and identifies the specific sorting method. This search process uses a relational database management system (RDBMS).

[0639] Presentation means

[0640] The server sends the identified sorting method to the user's device in real time. The device displays the received information on the user interface. For example, the screen might say, "Please dispose of beer bottles as recyclable waste."

[0641] Emotion Engine Means

[0642] The device analyzes the user's voice input and facial expressions to recognize the user's emotional state. This analysis is performed using voice recognition software and facial expression analysis algorithms. For example, if the device recognizes that the user is confused, it may display more specific instructions or additional support information. The emotion engine means transmits the results to a server, which uses them to improve the user experience in subsequent interactions.

[0643] Specific examples

[0644] The series of processes will be explained using a specific example. For example, if a user takes a photo of a beer bottle, the following prompt sentence can be input to the generative AI model:

[0645] Prompt Sentence Examples

[0646] "Tell me how to separate beer bottles into trash. If the user is confused, how would the emotion engine respond?"

[0647] This system not only allows users to easily obtain accurate garbage sorting instructions, but also enhances the user experience with its emotion engine. Specifically, if users are confused, the system can provide more detailed explanations and additional support information, enabling a smoother garbage sorting process. This promotes proper garbage disposal in accordance with local garbage sorting rules and contributes to environmental protection.

[0648] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0649] text

[0650] Step 1: Acquire and save image data

[0651] A user takes a photo of trash using the smartphone camera. For example, they take a photo of a beer bottle by tapping the camera button on the camera app. The input is the image of the beer bottle taken by the user, and the output is the image data. The device saves the generated image data in its internal storage, and the save destination is a specific folder on the device (e.g., the application folder).

[0652] Step 2: Sending image data

[0653] The device sends the saved image data to the server. This communication uses an HTTP POST request, and the image data is included in this request. The input is the image data saved in step 1, and the output is the image data sent to the server. The device displays the progress of the communication in the status bar.

[0654] Step 3: Receiving and analyzing image data

[0655] The server receives the received image data and analyzes the image using a deep learning model (e.g., ResNet-50 or VGG-16). The input is the image data sent from the device, and the output is the identification result of the type of garbage (e.g., bottle). The server stores the data in a temporary database on the server to temporarily save the analysis results.

[0656] Step 4: Search for sorting rules

[0657] The server searches a database for sorting rules that correspond to the user's area of ​​residence based on the identified type of garbage. The input is the garbage identification result and the user's address data, and the output is the corresponding sorting rule (e.g., "Beer bottles should be disposed of as recyclable garbage"). The server performs a rapid search using a relational database management system (RDBMS).

[0658] Step 5: Identify and format the sorting method

[0659] The server identifies specific sorting methods based on the search results and formats this information in JSON format. The input is the sorting rules obtained in step 4, and the output is the formatted sorting method data. The server prepares this data to send as a response.

[0660] Step 6: Present the sorting method

[0661] The server sends the formatted sorting method data to the terminal. The terminal analyzes the received data and displays it on the user interface. For example, it might display "Please dispose of beer bottles as recyclable waste." The input is the sorting method data from the server, and the output is the content presented to the user.

[0662] Step 7: Recognizing your emotional state

[0663] The device acquires the user's voice input and facial expressions. For this purpose, it uses a camera and microphone. The input is the user's voice data and video data, and the output is input data to the emotion engine. The device sends this data to the emotion engine.

[0664] Step 8: Emotional state analysis and feedback

[0665] The device uses an emotion engine to analyze the user's emotional state. The input is audio and video data, and the output is the identification result of the user's emotional state. For example, if the device recognizes that the user is confused, it will display more specific instructions or additional support information. It will display additional detailed explanations on the screen, such as "Please dispose of beer bottles as recyclable waste. Caps are general waste."

[0666] (Application example 2)

[0667] 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."

[0668] Conventional garbage sorting systems require users to manually check the type of garbage and local sorting rules, which is often time-consuming and laborious. Furthermore, if users feel confused or stressed about how to sort their garbage, the system provides no appropriate support, making the sorting process itself a hassle. The goal of this system is to solve these issues, improve the user experience, and achieve more efficient and accurate garbage sorting.

[0669] The identification process 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 image acquisition means for allowing a user to take a photo of garbage and generate image data thereof, communication means for transmitting the image data to the server, image analysis means for receiving the image data and identifying the type of garbage, sorting method identification means for searching a database for sorting rules corresponding to the type of garbage and identifying an appropriate sorting method, presentation means for presenting the identified sorting method to the user, and emotion recognition means for recognizing the user's emotional state and optimizing the display of the interface in accordance with that state. This not only enables the user to easily and accurately acquire garbage sorting methods, but also provides optimal support in accordance with the user's emotional state, enabling smoother and more stress-free garbage sorting.

[0670] The "image acquisition means" is a device or mechanism that allows a user to take a photo of the garbage and generate image data of the photo.

[0671] The "communication means" is a network communication means for transmitting the image data to the server.

[0672] The "image analysis means" is an analysis device that receives the image data and uses a deep learning model or the like to identify the type of dust.

[0673] The "sorting method specifying means" is a device or mechanism for searching a database for sorting rules corresponding to the type of waste and specifying the corresponding sorting method.

[0674] The "presentation means" is a user interface for presenting the identified separation method to the user.

[0675] An "emotion recognition means" is a device or mechanism for recognizing the user's emotional state and optimizing the display of the interface in accordance with that state.

[0676] "Deep learning" is a machine learning technology that recognizes and predicts complex patterns by learning from large amounts of data.

[0677] A "server" is a computer system that provides services in response to requests from clients.

[0678] A "database" is a data storage device for managing and searching garbage sorting rules and other related information.

[0679] This invention provides a system called "Smart Eco Guide" that allows users to easily learn how to separate garbage. This system includes the following main components:

[0680] 1. Image acquisition method

[0681] When a user takes a photo of trash using the smartphone camera, the application controls the camera device and saves the captured image data in the internal storage.

[0682] 2. Means of communication

[0683] The smartphone is equipped with a communication method for sending captured image data to a server. Specifically, it uses an HTTP POST request from the smartphone to the server. The image data is included in this request.

[0684] 3. Image analysis methods

[0685] The server analyzes the received image data using a deep learning model (e.g., ResNet-50 or VGG-16), which automatically identifies the type of garbage (e.g., bottles, cans, plastic, etc.).

[0686] 4. Means for specifying separation method

[0687] The server searches a database for sorting rules that correspond to the user's area or specific location based on the type of garbage identified, and uses the search results to identify specific methods for sorting garbage.

[0688] 5. Presentation means

[0689] The identified sorting method is sent to the user's device in real time and displayed on the user interface, allowing the user to instantly confirm the correct method for sorting their garbage.

[0690] 6. Emotion recognition means

[0691] The emotion recognition engine analyzes the user's emotional state and optimizes the interface display and presentation accordingly. For example, if it determines that the user is confused, it will display more detailed explanations or supplementary information.

[0692] Hardware and software used

[0693] Hardware

[0694] Smartphone (with camera function)

[0695] Server (high-performance computing power required)

[0696] software

[0697] OpenCV: for image capture and pre-processing

[0698] Keras: for loading and predicting deep learning models

[0699] Requests: HTTP communication library

[0700] Sentiment Analysis API: An external service for analyzing user sentiment

[0701] Specific examples

[0702] For example, consider a case where a user wants to properly separate empty plastic bottles at a shopping mall:

[0703] 1. The user launches the app on their smartphone and takes a photo of a plastic bottle with the camera.

[0704] 2. The captured image is sent to a server, where a deep learning model analyzes the image and identifies it as a plastic bottle.

[0705] 3. The server searches the database for the mall's garbage sorting rules and identifies the correct way to sort plastic bottles.

[0706] 4. The app displays the sorting method on the user interface, helping users sort their waste correctly without hesitation.

[0707] 5. If the user is confused, the emotion recognition engine will detect this and provide more specific explanations and images.

[0708] Prompt Sentence Examples

[0709] When a user wants to know how to sort a plastic bottle they have finished drinking from, they launch the app and take a photo of the trash with their smartphone camera. The image is sent to the server, where the AI ​​analyzes it and returns the correct sorting instructions. The app also analyzes the user's emotional state and, if it determines they are confused, provides additional details and a QR code. Express this process in Python code.

[0710] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0711] Step 1:

[0712] The user takes a photo of the garbage. The user launches the app on their smartphone and takes a photo of the garbage using the camera function. The input is the actual garbage, and the output is image data. This image data is saved in the internal storage.

[0713] Step 2:

[0714] The device sends image data to the server. The device sends image data stored in its internal storage to the server via an HTTP POST request. The input is the image data, and the output is a data packet sent to the server.

[0715] Step 3:

[0716] The server analyzes the image data. The server analyzes the received image data using a deep learning model (e.g., ResNet-50 or VGG-16). The input is the image data, and the output is the identified type of garbage (e.g., PET bottle, can, plastic, etc.).

[0717] Step 4:

[0718] The server searches for the sorting rules and identifies the sorting method. Based on the identified type of garbage, the server searches for the corresponding sorting rule from the database. The input is the type of garbage, and the output is the specific sorting method. This sorting method is formatted in JSON format.

[0719] Step 5:

[0720] The server sends the specified sorting method to the terminal. The server sends the specified sorting method (JSON format) to the terminal. The input is the JSON data of the sorting method, and the output is the data packet sent to the terminal.

[0721] Step 6:

[0722] The terminal displays the sorting method on the user interface. The terminal analyzes the received data on the sorting method and displays it on the user interface. The input is the JSON data of the sorting method, and the output is the sorting method displayed on the user interface.

[0723] Step 7:

[0724] The server analyzes the user's emotional state. The server uses an emotion analysis API to analyze the user's voice data and facial expression images being captured. The input is the voice data and facial expression images, and the output is the analysis result of the user's emotional state (e.g., confusion, stress).

[0725] Step 8:

[0726] The server provides optimal support according to the user's emotional state. If the server determines that the user is confused based on the analysis results, it generates additional detailed information and a QR code and sends them to the device. The input is the emotion analysis result, and the output is the additional information and QR code data.

[0727] By clearly indicating the specific operations and inputs / outputs at each step, the overall processing flow of the system becomes clear, allowing users to smoothly and accurately learn how to separate their garbage.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] [Third embodiment]

[0732] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0733] 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.

[0734] 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).

[0735] 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.

[0736] 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.

[0737] 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).

[0738] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0739] 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.

[0740] 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.

[0741] 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.

[0742] 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.

[0743] 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."

[0744] The present invention is a system for enabling a user to learn how to separate garbage, and this system is composed of a plurality of means. Hereinafter, an embodiment of the present invention will be described in detail.

[0745] System configuration

[0746] Image Acquisition Method

[0747] The user takes a photo of the trash using the camera on their smartphone or other device. The captured image data is saved in the device's internal storage. The user can then view the captured image data within the application and proceed to the next processing step.

[0748] communication means

[0749] The smartphone is equipped with a communication method for sending captured image data to a server. Specifically, it uses an HTTP POST request from the smartphone to the server. The image data is sent as part of this request.

[0750] Image analysis methods

[0751] The server analyzes the received image data using deep learning models (e.g., ResNet-50 and VGG-16), which automatically identifies the type of garbage (bottles, cans, plastic, etc.).

[0752] Separation method identification means

[0753] The server searches a database for sorting rules that correspond to the user's area based on the identified type of garbage, and uses the search results to identify specific methods for sorting garbage.

[0754] Presentation means

[0755] The identified sorting method is sent to the user's device in real time, and the device displays the received information on the user interface, allowing the user to instantly confirm the correct method for sorting their garbage.

[0756] Specific examples

[0757] For example, consider the case where a user takes a picture of a beer bottle.

[0758] 1. User: Take a photo of a beer bottle with your smartphone camera.

[0759] 2. Device: The captured image data is stored in the internal storage and then sent to the server.

[0760] 3. Server: Receives the image data and performs image analysis using a deep learning model. This analysis identifies it as a beer bottle.

[0761] 4. Server: Based on the user's address data, the server searches the database for the relevant municipality's sorting rules and identifies specific sorting methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[0762] 5. Server: The identified sorting method is formatted in JSON format and sent to the device.

[0763] 6. Terminal: The received sorting method is displayed on the user interface.

[0764] 7. User: Check the displayed sorting method and sort the beer bottles in the correct way.

[0765] The system of the present invention allows users to easily and accurately learn how to separate their garbage, enabling them to separate their garbage appropriately and efficiently. As a result, users can dispose of their garbage in accordance with local government rules, which also contributes to environmental protection.

[0766] The processing flow will be explained below.

[0767] Step 1:

[0768] A user takes a photo of trash (e.g., a beer bottle) with their smartphone camera. The device stores the captured image data in its internal storage.

[0769] Step 2:

[0770] The application on the device displays a screen for the user to check the image they have taken. When the user taps the "Confirm" button, the device prepares to send the image data to the server.

[0771] Step 3:

[0772] The device sends the image data that is ready to be sent to the server as an HTTP POST request. This request includes the image data.

[0773] Step 4:

[0774] The server receives the HTTP POST request sent from the device, extracts the image data from the request, and passes it to the image analysis module.

[0775] Step 5:

[0776] The server's image analysis module processes the received image data. It uses a deep learning model (e.g., ResNet-50 or VGG-16) to analyze the image and identify the type of debris contained in the image. In this case, the image analysis module detects that it is a beer bottle.

[0777] Step 6:

[0778] Based on the analysis results, the server references the user's residential area information and queries the database for the sorting rules for that area, searching for the appropriate sorting method.

[0779] Step 7:

[0780] The server then uses the query results to identify specific separation methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[0781] Step 8:

[0782] The server formats the generated sorting instructions in JSON format and sends them to the terminal as an HTTP response.

[0783] Step 9:

[0784] The device receives the HTTP response from the server, analyzes the received JSON data, and extracts the sorting instructions.

[0785] Step 10:

[0786] The device displays the analyzed sorting instructions on the app's user interface. The user confirms the displayed instructions and then performs the actual garbage sorting work.

[0787] This series of processes allows users to easily and accurately learn how to separate their garbage, enabling them to dispose of their garbage appropriately in accordance with local garbage separation rules.

[0788] Example 1

[0789] 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."

[0790] Conventional systems providing information on garbage sorting methods are cumbersome, requiring users to manually identify the type of garbage and look up the corresponding sorting rules. Furthermore, there is no flexible system to reflect the different sorting rules of each specific municipality, which can lead to users sorting incorrectly.

[0791] 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.

[0792] In this invention, the server includes an image acquisition means for allowing a user to take a photo of waste and generate image data of the photo, a communication means for transmitting the image data to a remote server, an image analysis means for receiving the image data and identifying the type of waste using a deep learning model, a sorting method identification means for searching a database for sorting rules corresponding to the type of waste and identifying an appropriate sorting method, and a presentation means for presenting the identified sorting method to the user. This allows the user to easily obtain an accurate sorting method and efficiently sort their waste appropriately.

[0793] The "image acquisition means" is a device or system that allows a user to take a photograph of waste and generate image data thereof.

[0794] "Communication means" is a network interface or protocol for transmitting the image data to a remote server.

[0795] "Image analysis means" refers to a processing device or software that receives the image data and uses a deep learning model to identify the type of waste.

[0796] The "sorting method specifying means" is an algorithm or system for searching a database for sorting rules corresponding to the type of waste and specifying the corresponding sorting method.

[0797] The "presentation means" refers to a display or application user interface for presenting the identified sorting method to the user.

[0798] "Waste" is a general term for garbage and unwanted items.

[0799] A "remote server" is a computer system installed remotely for communicating with a user's terminal via a network.

[0800] A "deep learning model" is a part of artificial intelligence, and is an algorithm that uses a multi-layer neural network to automatically extract features from large amounts of data and perform classification and prediction.

[0801] A "database" is an information management system for systematically storing and searching information on sorting rules and types of waste.

[0802] MODE FOR CARRYING OUT THE INVENTION

[0803] This invention is a system that allows users to learn how to separate waste materials. The system is composed of multiple means. Users take photos of waste materials using a device such as a smartphone and send the image data to a server. The server analyzes the image data, identifies the type of waste material, and then provides the user with specific separation methods based on the separation rules for the relevant area.

[0804] (composition)

[0805] Image Acquisition Method

[0806] The user takes a photo of the waste using the smartphone camera, and the image data is saved in the smartphone's internal storage. The user can then review the image data within the application and proceed to the next processing step.

[0807] communication means

[0808] The smartphone is provided with a communication means for transmitting the image data to the server. Specifically, the image data is transmitted from the smartphone terminal to the remote server using an HTTP POST request.

[0809] Image analysis methods

[0810] The server analyzes the image data received from the device using a deep learning model (e.g., ResNet-50 or VGG-16). The deep learning model identifies the type of waste (e.g., bottles, cans, plastic, etc.).

[0811] Separation method identification means

[0812] Based on the identified waste type, the server searches a database for sorting rules that correspond to the user's area of ​​residence, and uses the search results to identify specific methods for sorting waste.

[0813] Presentation means

[0814] The identified waste separation method is sent in real time to the user's device, which then displays the received information on the user interface, allowing the user to instantly confirm the correct waste separation method.

[0815] (Example)

[0816] For example, a case where a user photographs a beer bottle will be described.

[0817] 1. User: Take a photo of a beer bottle with your smartphone camera.

[0818] 2. Device: The captured image data is stored in the internal storage and sent to the server.

[0819] 3. Server: Receives the image data and performs image analysis using a deep learning model. The analysis identifies it as a beer bottle.

[0820] 4. Server: Based on the user's address information, the server searches the database for the relevant municipality's sorting rules and identifies specific sorting methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[0821] 5. Server: The identified sorting method is formatted in JSON format and sent to the device.

[0822] 6. Terminal: The received sorting method is displayed on the user interface.

[0823] 7. User: Check the displayed sorting method and sort the beer bottles in the correct way.

[0824] This allows users to easily obtain accurate waste separation methods, enabling them to efficiently separate waste appropriately. As a result, waste can be disposed of in accordance with local government rules, contributing to environmental protection.

[0825] (Example of a prompt)

[0826] "Please create a program that uses ResNet-50 to identify waste categories (bottles, cans, plastic, etc.) and searches for the municipality's waste separation rules based on the user's address. The user takes a picture of the waste with their smartphone camera and sends it to the server. Please explain in natural language the entire process, from image analysis and search on the server to displaying the separation instructions on the device."

[0827] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0828] Step 1:

[0829] Users take photos of waste using their smartphone camera by tapping the "Take Photo" button in the application. The input is the physical presence of the waste, and the output is image data stored on the smartphone.

[0830] Step 2:

[0831] The device saves the captured image data in its internal storage. The input is the photo data from the camera application, and the output is an image file saved in the device's internal storage. Also, if the user taps the "Send" button in this step, processing for the next communication method will begin.

[0832] Step 3:

[0833] The device sends the stored image data to the server. Specifically, it generates an HTTP POST request, includes the image data in the request body, and sends it to the specified API endpoint of the remote server. The input is the image data stored inside the device, and the output is the HTTP request sent to the remote server.

[0834] Step 4:

[0835] The server receives the image data sent from the device and analyzes it using a deep learning model. Specifically, the received image data is input into a deep learning model such as ResNet-50, and image analysis is performed using the model. The input is the image data extracted from the HTTP request, and the output is the type of waste (e.g., bottle, can, plastic, etc.) as the analysis result.

[0836] Step 5:

[0837] Based on the analysis results, the server searches a database for sorting rules that correspond to the user's residential area. The input is the waste type obtained by the analysis and the user's address information, and the output is the corresponding sorting rules obtained from the database. Specifically, the server generates a database query and executes a search to obtain the sorting rules.

[0838] Step 6:

[0839] The server analyzes the obtained sorting rules and identifies the specific sorting method. The input is the sorting rules obtained from the database, and the output is the specific sorting method identified. This identified sorting method is formatted in JSON format or similar.

[0840] Step 7:

[0841] The server sends the formatted sorting method to the terminal. The input is the sorting method data in JSON format, and the output is the HTTP response sent to the terminal. This prepares the terminal for reception.

[0842] Step 8:

[0843] The device analyzes the sorting method data received from the server and displays it on the user interface. The input is the JSON data received from the server, and the output is sorting method information that is visually presented to the user. Specifically, the information is appropriately laid out on the application screen and displayed in a way that is easy for the user to understand.

[0844] Step 9:

[0845] The user checks the displayed sorting instructions and actually sorts the waste correctly. The input is the sorting information displayed on the device, and the output is the actual waste sorting behavior. The user follows the instructions and places the waste in the appropriate garbage bag or recycling container.

[0846] (Application example 1)

[0847] 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."

[0848] Until now, it has been difficult for employees to accurately and efficiently separate the wide variety of waste generated within physical stores. In particular, due to complex sorting rules and regional differences, it took a lot of time and effort for employees to understand how to separate waste. Therefore, there was a strong demand for a system that would allow employees to easily and accurately learn how to separate waste, thereby improving work efficiency.

[0849] 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.

[0850] In this invention, the server includes an image acquisition means for allowing a user to take a photo of trash and generate image data of the photo, a communication means for transmitting the image data to the server, an image analysis means for receiving the image data and identifying the type of trash, a sorting method identification means for searching a database for sorting rules corresponding to the type of trash and identifying an appropriate sorting method, a presentation means for presenting the identified sorting method to the user, and a means for presenting the trash sorting method to employees in the physical store in real time using a smart device or a robot. This enables accurate and efficient trash sorting in the physical store, reducing the burden on employees and improving work efficiency.

[0851] "Waste sorting method" is a procedure for separating waste into different categories according to material and disposal method.

[0852] A "system" refers to a device or group of devices in which multiple elements work together to achieve a specific function.

[0853] The "image acquisition means" is a function that allows a user to take a photo of the garbage using a device such as a camera and acquire the image data.

[0854] "Communication means" refers to the communication protocol and infrastructure for transmitting image data acquired on the terminal to the server.

[0855] "Image analysis means" refers to an analytical technology for identifying the type of garbage based on the image data received by the server, and includes deep learning models, etc.

[0856] The "sorting method identification means" is a function that searches a database for the sorting rules for the relevant area based on the identified type of garbage, and identifies the specific sorting method.

[0857] The "presentation means" is a function for displaying the identified waste separation method to the user and encouraging them to separate their garbage appropriately.

[0858] A "smart device" is a portable or stationary electronic device that has internet connectivity, a touchscreen, and advanced computing capabilities.

[0859] A "robot" refers to a mechanical device that operates autonomously according to programmed instructions.

[0860] "Physical store" refers to a physical store for selling goods or providing services.

[0861] A "deep learning model" is a technology that uses an artificial neural network to learn specific patterns and features from large amounts of data, enabling advanced discrimination and prediction.

[0862] MODE FOR CARRYING OUT THE INVENTION

[0863] System Configuration

[0864] A system embodying the invention includes the following major hardware and software components:

[0865] 1. Image acquisition method

[0866] Users take a photo of the trash using a smartphone, tablet, or in-store smart robot. The captured image data is stored in the device's internal storage, and the user can view the image data within the app before it moves on to the next processing step.

[0867] 2. Means of communication

[0868] The captured image data is sent to the server via Wi-Fi or a mobile network using an HTTP POST request.

[0869] 3. Image analysis methods

[0870] The server analyzes the received image data using a deep learning model (e.g., ResNet-50 or VGG-16), which automatically identifies the type of garbage (bottles, cans, plastic, etc.).

[0871] 4. Means for specifying separation method

[0872] Based on the identified type of waste, the server searches a database for sorting rules that correspond to the specific store and its location, and then determines the specific method for sorting the waste.

[0873] 5. Presentation means

[0874] The identified sorting method is sent in real time to the user's device, which then displays the received information on the user interface, allowing store employees to quickly understand the correct method for sorting waste.

[0875] 6. In-store support

[0876] Smart devices or robots will provide real-time guidance to store employees on how to separate waste, improving employee efficiency and encouraging accurate waste separation.

[0877] Examples of concrete examples and prompts

[0878] Specific examples

[0879] For example, here's the procedure for employees at a cafe to dispose of used plastic containers:

[0880] 1. User (employee): Take a photo of a plastic container with the camera on their smartphone or tablet.

[0881] 2. Device: The captured image data is stored in the internal storage and then sent to the server.

[0882] 3. Server: Analyzes the received image data using a deep learning model and identifies it as a plastic container.

[0883] 4. Server: Based on the store's location, search the database for the relevant sorting rules and identify that "plastic containers should be disposed of as plastic waste."

[0884] 5. Server: The identified sorting method is formatted in JSON format and sent to the device.

[0885] 6. Terminal: The received sorting method is displayed on the user interface, and employees sort the garbage appropriately.

[0886] Prompt Sentence Examples

[0887] Write an application program that allows users to take pictures of trash with their smartphone camera, send them to a server, and use a deep learning model to identify the type of trash. Then, based on the user's location, determine how to sort the trash and display the results on the device in real time.

[0888] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0889] Step 1:

[0890] The user takes a photo of the trash and generates image data. Specifically, the image is taken using a smartphone, tablet, or the camera of a smart robot installed in the store. This image data is then stored in the internal storage.

[0891] Input: Physical image of the trash

[0892] Output: Image data stored in internal storage

[0893] Step 2:

[0894] The device sends the captured image data to the server using an HTTP POST request via Wi-Fi or a mobile network.

[0895] Input: Image data stored in the internal storage

[0896] Output: Image data sent to the server

[0897] Step 3:

[0898] The image data received by the server is analyzed using a deep learning model. Specifically, deep learning models such as ResNet-50 and VGG-16 are used to identify the type of garbage. This analysis allows for identification of, for example, "plastic containers" or "bottles."

[0899] Input: Image data sent to the server

[0900] Output: Identified trash type (e.g. plastic container)

[0901] Step 4:

[0902] The server searches the database for the local sorting rules based on the identified type of garbage. Since the local sorting rules are identified based on the user's location information, the server also refers to the user's location data.

[0903] Input: Identified garbage type, user location information

[0904] Output: Sorting method according to type of garbage

[0905] Step 5:

[0906] Based on the search results, the server formats the identified sorting methods in JSON format and sends them to the device. The formatted data is presented to the user in a format that is easy to view.

[0907] Input: Identified separation method

[0908] Output: JSON formatted sorting method data

[0909] Step 6:

[0910] The terminal displays the received sorting method data on the user interface, allowing users (employees) to check the correct garbage sorting method in real time and sort their garbage appropriately.

[0911] Input: JSON formatted separation method data

[0912] Output: The sorting method displayed in the user interface

[0913] Step 7:

[0914] Smart devices or robots in physical stores provide real-time guidance to employees on how to separate waste, allowing them to see how to do so without having to take their hands off the device.

[0915] Input: The sorting method displayed in the user interface

[0916] Output: Garbage sorting method presented to store employees

[0917] Through these steps, waste sorting in physical stores is carried out accurately and efficiently.

[0918] 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.

[0919] The present invention provides a system that improves the user experience by combining a system for helping users learn how to separate their garbage with an emotion engine that recognizes the user's emotional state. This system is comprised of the following means.

[0920] System configuration

[0921] Image Acquisition Method

[0922] The user takes a photo of the trash using the camera on their smartphone or other device. The captured image data is saved in the device's internal storage, and the user can view the captured image data within the application and proceed to the next processing step.

[0923] communication means

[0924] The smartphone is equipped with a communication method for sending captured image data to a server. Specifically, it uses an HTTP POST request from the smartphone to the server. The image data is sent as part of this request.

[0925] Image analysis methods

[0926] The server analyzes the received image data using deep learning models (e.g., ResNet-50 and VGG-16), which automatically identifies the type of garbage (bottles, cans, plastic, etc.).

[0927] Separation method identification means

[0928] The server searches a database for sorting rules that correspond to the user's area based on the identified type of garbage, and uses the search results to identify specific methods for sorting garbage.

[0929] Presentation means

[0930] The identified sorting method is sent to the user's device in real time, and the device displays the received information on the user interface, allowing the user to instantly confirm the correct method for sorting their garbage.

[0931] Emotion Engine

[0932] The emotion engine recognizes the user's emotional state and optimizes the interface display and presentation methods accordingly. In this invention, the emotional state can be recognized by analyzing the user's voice input and facial expressions. Furthermore, the recognized emotional state can be logged and used to improve the user experience in subsequent interactions.

[0933] Specific examples

[0934] For example, consider the case where a user takes a picture of a beer bottle.

[0935] 1. User: Take a photo of a beer bottle with your smartphone camera.

[0936] 2. Device: The captured image data is stored in the internal storage and then sent to the server.

[0937] 3. Server: Receives the image data and performs image analysis using a deep learning model. This analysis identifies it as a beer bottle.

[0938] 4. Server: Based on the user's address data, the server searches the database for the relevant municipality's sorting rules and identifies specific sorting methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[0939] 5. Server: The identified sorting method is formatted in JSON format and sent to the device.

[0940] 6. Terminal: The received sorting method is displayed on the user interface.

[0941] 7. Emotion Engine: The emotion engine analyzes the user's voice and facial expressions, and if it determines that the user is confused, it provides more specific instructions or additional support information.

[0942] 8. User: Check the displayed sorting instructions and sort the beer bottles in the correct way. The additional information from the emotion engine improves the user experience.

[0943] The system of this invention not only allows users to easily learn accurate garbage sorting methods, but also enables smoother, stress-free garbage sorting with the support of the emotion engine. This allows users to dispose of garbage appropriately in accordance with local garbage sorting rules, thereby contributing to environmental protection.

[0944] The processing flow will be explained below.

[0945] Step 1:

[0946] A user takes a photo of trash (e.g., a beer bottle) with their smartphone camera. The device stores the captured image data in its internal storage.

[0947] Step 2:

[0948] The application on the device displays a screen for the user to check the image they have taken. When the user taps the "Confirm" button, the device prepares to send the image data to the server.

[0949] Step 3:

[0950] The device sends the image data that is ready to be sent to the server as an HTTP POST request. This request includes the image data.

[0951] Step 4:

[0952] The server receives the HTTP POST request sent from the device, extracts the image data from the request, and passes it to the image analysis module.

[0953] Step 5:

[0954] The server's image analysis module processes the received image data. It uses a deep learning model (e.g., ResNet-50 or VGG-16) to analyze the image and identify the type of debris contained in the image. In this case, the image analysis module detects that it is a beer bottle.

[0955] Step 6:

[0956] Based on the analysis results, the server references the user's residential area information and queries the database for the sorting rules for that area, searching for the appropriate sorting method.

[0957] Step 7:

[0958] The server then uses the query results to identify specific separation methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[0959] Step 8:

[0960] The server formats the generated sorting instructions in JSON format and sends them to the terminal as an HTTP response.

[0961] Step 9:

[0962] The device receives the HTTP response from the server, analyzes the received JSON data, and extracts the sorting instructions.

[0963] Step 10:

[0964] The device displays the analyzed sorting instructions on the app's user interface, and the user confirms the displayed instructions.

[0965] Step 11:

[0966] The emotion engine analyzes the user's voice input and facial expressions, and in the process determines whether the user is stressed or confused.

[0967] Step 12:

[0968] If the emotion engine determines that the user is confused, it will provide more detailed explanations and additional support information in addition to the identified sorting method, such as "Please dispose of beer bottles as recyclable waste. If this bottle is broken, please wrap it in protective material using these steps."

[0969] Step 13:

[0970] The terminal displays additional information from the emotion engine on the user interface to provide appropriate assistance to the user.

[0971] Step 14:

[0972] The user checks the displayed sorting method and additional information and sorts the garbage correctly accordingly.

[0973] This process allows users to easily and accurately learn how to separate their trash. Furthermore, with the support of the emotion engine, the user experience is improved, allowing them to separate their trash without feeling stressed or confused.

[0974] Example 2

[0975] 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."

[0976] While existing technologies provide users with accurate and prompt guidance on how to separate their trash, there is a lack of technology that provides optimal guidance based on the user's emotional state. In particular, there is a need for technology that can improve situations where users become confused or stressed about how to separate their trash.

[0977] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an image acquisition means for allowing a user to take a photo of garbage and generate image data thereof, a communication means for transmitting the image data to the server, an image analysis means for receiving the image data and identifying the type of garbage using a model based on deep learning, a sorting method identification means for searching a database for sorting rules corresponding to the type of garbage and identifying an appropriate sorting method, a presentation means for presenting the identified sorting method to the user, an emotion engine means for analyzing the user's voice input and facial expressions to recognize the user's emotional state, and a means for optimizing the presentation method based on the recognized emotional state. This not only enables the user to accurately understand how to sort garbage, but also improves the user's usage experience according to the user's emotional state.

[0978] text

[0979] The "image acquisition means" is a device that allows a user to take a photograph of the garbage and generate image data of the photograph.

[0980] The "communication means" is a device or function for transmitting the image data to the server.

[0981] The "image analysis means" is a device or function that receives the image data and identifies the type of dust using a model that uses deep learning.

[0982] The "sorting method specifying means" is a device or function that searches a database for sorting rules that correspond to the type of waste and specifies the corresponding sorting method.

[0983] The "presentation means" is a device or function for presenting the identified sorting method to the user.

[0984] The "emotion engine means" is a device or function that analyzes the user's voice input and facial expressions and recognizes the user's emotional state.

[0985] An "optimizer" is a device or function that optimizes presentation methods based on a recognized emotional state.

[0986] The present invention provides a technology for recognizing a user's emotional state and optimizing guidance based on the emotional state in a system for helping a user learn how to separate garbage. The system includes the following means.

[0987] Image Acquisition Method

[0988] The user takes a photo of the trash using the smartphone camera. For example, if the user takes a photo of a beer bottle, the image data is saved in the device's internal storage. This image acquisition method is realized by using the smartphone's camera application.

[0989] communication means

[0990] The device sends the saved image data to the server. This communication is performed using an HTTP POST request, and the image data is included in this request and sent to the server. The communication method is the smartphone's Internet connection function.

[0991] Image analysis methods

[0992] The server analyzes the received image data. A deep learning model (e.g., ResNet-50 or VGG-16) is used for this image analysis. The server uses this model to identify the type of garbage (e.g., bottles, cans, plastic, etc.). The server's processing unit uses hardware such as a GPU to perform this analysis quickly.

[0993] Separation method identification means

[0994] The server searches a database for sorting rules that correspond to the user's area of ​​residence based on the identified type of garbage. For example, it obtains a rule such as "beer bottles should be disposed of as recyclable garbage" and identifies the specific sorting method. This search process uses a relational database management system (RDBMS).

[0995] Presentation means

[0996] The server sends the identified sorting method to the user's device in real time. The device displays the received information on the user interface. For example, the screen might say, "Please dispose of beer bottles as recyclable waste."

[0997] Emotion Engine Means

[0998] The device analyzes the user's voice input and facial expressions to recognize the user's emotional state. This analysis is performed using voice recognition software and facial expression analysis algorithms. For example, if the device recognizes that the user is confused, it may display more specific instructions or additional support information. The emotion engine means transmits the results to a server, which uses them to improve the user experience in subsequent interactions.

[0999] Specific examples

[1000] The series of processes will be explained using a specific example. For example, if a user takes a photo of a beer bottle, the following prompt sentence can be input to the generative AI model:

[1001] Prompt Sentence Examples

[1002] "Tell me how to separate beer bottles into trash. If the user is confused, how would the emotion engine respond?"

[1003] This system not only allows users to easily obtain accurate garbage sorting instructions, but also enhances the user experience with its emotion engine. Specifically, if users are confused, the system can provide more detailed explanations and additional support information, enabling a smoother garbage sorting process. This promotes proper garbage disposal in accordance with local garbage sorting rules and contributes to environmental protection.

[1004] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1005] text

[1006] Step 1: Acquire and save image data

[1007] A user takes a photo of trash using the smartphone camera. For example, they take a photo of a beer bottle by tapping the camera button on the camera app. The input is the image of the beer bottle taken by the user, and the output is the image data. The device saves the generated image data in its internal storage, and the save destination is a specific folder on the device (e.g., the application folder).

[1008] Step 2: Sending image data

[1009] The device sends the saved image data to the server. This communication uses an HTTP POST request, and the image data is included in this request. The input is the image data saved in step 1, and the output is the image data sent to the server. The device displays the progress of the communication in the status bar.

[1010] Step 3: Receiving and analyzing image data

[1011] The server receives the received image data and analyzes the image using a deep learning model (e.g., ResNet-50 or VGG-16). The input is the image data sent from the device, and the output is the identification result of the type of garbage (e.g., bottle). The server stores the data in a temporary database on the server to temporarily save the analysis results.

[1012] Step 4: Search for sorting rules

[1013] The server searches a database for sorting rules that correspond to the user's area of ​​residence based on the identified type of garbage. The input is the garbage identification result and the user's address data, and the output is the corresponding sorting rule (e.g., "Beer bottles should be disposed of as recyclable garbage"). The server performs a rapid search using a relational database management system (RDBMS).

[1014] Step 5: Identify and format the sorting method

[1015] The server identifies specific sorting methods based on the search results and formats this information in JSON format. The input is the sorting rules obtained in step 4, and the output is the formatted sorting method data. The server prepares this data to send as a response.

[1016] Step 6: Present the sorting method

[1017] The server sends the formatted sorting method data to the terminal. The terminal analyzes the received data and displays it on the user interface. For example, it might display "Please dispose of beer bottles as recyclable waste." The input is the sorting method data from the server, and the output is the content presented to the user.

[1018] Step 7: Recognizing your emotional state

[1019] The device acquires the user's voice input and facial expressions. For this purpose, it uses a camera and microphone. The input is the user's voice data and video data, and the output is input data to the emotion engine. The device sends this data to the emotion engine.

[1020] Step 8: Emotional state analysis and feedback

[1021] The device uses an emotion engine to analyze the user's emotional state. The input is audio and video data, and the output is the identification result of the user's emotional state. For example, if the device recognizes that the user is confused, it will display more specific instructions or additional support information. It will display additional detailed explanations on the screen, such as "Please dispose of beer bottles as recyclable waste. Caps are general waste."

[1022] (Application example 2)

[1023] 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."

[1024] Conventional garbage sorting systems require users to manually check the type of garbage and local sorting rules, which is often time-consuming and laborious. Furthermore, if users feel confused or stressed about how to sort their garbage, the system provides no appropriate support, making the sorting process itself a hassle. The goal of this system is to solve these issues, improve the user experience, and achieve more efficient and accurate garbage sorting.

[1025] The identification process 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 image acquisition means for allowing a user to take a photo of garbage and generate image data thereof, communication means for transmitting the image data to the server, image analysis means for receiving the image data and identifying the type of garbage, sorting method identification means for searching a database for sorting rules corresponding to the type of garbage and identifying an appropriate sorting method, presentation means for presenting the identified sorting method to the user, and emotion recognition means for recognizing the user's emotional state and optimizing the display of the interface in accordance with that state. This not only enables the user to easily and accurately acquire garbage sorting methods, but also provides optimal support in accordance with the user's emotional state, enabling smoother and more stress-free garbage sorting.

[1026] The "image acquisition means" is a device or mechanism that allows a user to take a photo of the garbage and generate image data of the photo.

[1027] The "communication means" is a network communication means for transmitting the image data to the server.

[1028] The "image analysis means" is an analysis device that receives the image data and uses a deep learning model or the like to identify the type of dust.

[1029] The "sorting method specifying means" is a device or mechanism for searching a database for sorting rules corresponding to the type of waste and specifying the corresponding sorting method.

[1030] The "presentation means" is a user interface for presenting the identified separation method to the user.

[1031] An "emotion recognition means" is a device or mechanism for recognizing the user's emotional state and optimizing the display of the interface in accordance with that state.

[1032] "Deep learning" is a machine learning technology that recognizes and predicts complex patterns by learning from large amounts of data.

[1033] A "server" is a computer system that provides services in response to requests from clients.

[1034] A "database" is a data storage device for managing and searching garbage sorting rules and other related information.

[1035] This invention provides a system called "Smart Eco Guide" that allows users to easily learn how to separate garbage. This system includes the following main components:

[1036] 1. Image acquisition method

[1037] When a user takes a photo of trash using the smartphone camera, the application controls the camera device and saves the captured image data in the internal storage.

[1038] 2. Means of communication

[1039] The smartphone is equipped with a communication method for sending captured image data to a server. Specifically, it uses an HTTP POST request from the smartphone to the server. The image data is included in this request.

[1040] 3. Image analysis methods

[1041] The server analyzes the received image data using a deep learning model (e.g., ResNet-50 or VGG-16), which automatically identifies the type of garbage (e.g., bottles, cans, plastic, etc.).

[1042] 4. Means for specifying separation method

[1043] The server searches a database for sorting rules that correspond to the user's area or specific location based on the type of garbage identified, and uses the search results to identify specific methods for sorting garbage.

[1044] 5. Presentation means

[1045] The identified sorting method is sent to the user's device in real time and displayed on the user interface, allowing the user to instantly confirm the correct method for sorting their garbage.

[1046] 6. Emotion recognition means

[1047] The emotion recognition engine analyzes the user's emotional state and optimizes the interface display and presentation accordingly. For example, if it determines that the user is confused, it will display more detailed explanations or supplementary information.

[1048] Hardware and software used

[1049] Hardware

[1050] Smartphone (with camera function)

[1051] Server (high-performance computing power required)

[1052] software

[1053] OpenCV: for image capture and pre-processing

[1054] Keras: for loading and predicting deep learning models

[1055] Requests: HTTP communication library

[1056] Sentiment Analysis API: An external service for analyzing user sentiment

[1057] Specific examples

[1058] For example, consider a case where a user wants to properly separate empty plastic bottles at a shopping mall:

[1059] 1. The user launches the app on their smartphone and takes a photo of a plastic bottle with the camera.

[1060] 2. The captured image is sent to a server, where a deep learning model analyzes the image and identifies it as a plastic bottle.

[1061] 3. The server searches the database for the mall's garbage sorting rules and identifies the correct way to sort plastic bottles.

[1062] 4. The app displays the sorting method on the user interface, helping users sort their waste correctly without hesitation.

[1063] 5. If the user is confused, the emotion recognition engine will detect this and provide more specific explanations and images.

[1064] Prompt Sentence Examples

[1065] When a user wants to know how to sort a plastic bottle they have finished drinking from, they launch the app and take a photo of the trash with their smartphone camera. The image is sent to the server, where the AI ​​analyzes it and returns the correct sorting instructions. The app also analyzes the user's emotional state and, if it determines they are confused, provides additional details and a QR code. Express this process in Python code.

[1066] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1067] Step 1:

[1068] The user takes a photo of the garbage. The user launches the app on their smartphone and takes a photo of the garbage using the camera function. The input is the actual garbage, and the output is image data. This image data is saved in the internal storage.

[1069] Step 2:

[1070] The device sends image data to the server. The device sends image data stored in its internal storage to the server via an HTTP POST request. The input is the image data, and the output is a data packet sent to the server.

[1071] Step 3:

[1072] The server analyzes the image data. The server analyzes the received image data using a deep learning model (e.g., ResNet-50 or VGG-16). The input is the image data, and the output is the identified type of garbage (e.g., PET bottle, can, plastic, etc.).

[1073] Step 4:

[1074] The server searches for the sorting rules and identifies the sorting method. Based on the identified type of garbage, the server searches for the corresponding sorting rule from the database. The input is the type of garbage, and the output is the specific sorting method. This sorting method is formatted in JSON format.

[1075] Step 5:

[1076] The server sends the specified sorting method to the terminal. The server sends the specified sorting method (JSON format) to the terminal. The input is the JSON data of the sorting method, and the output is the data packet sent to the terminal.

[1077] Step 6:

[1078] The terminal displays the sorting method on the user interface. The terminal analyzes the received data on the sorting method and displays it on the user interface. The input is the JSON data of the sorting method, and the output is the sorting method displayed on the user interface.

[1079] Step 7:

[1080] The server analyzes the user's emotional state. The server uses an emotion analysis API to analyze the user's voice data and facial expression images being captured. The input is the voice data and facial expression images, and the output is the analysis result of the user's emotional state (e.g., confusion, stress).

[1081] Step 8:

[1082] The server provides optimal support according to the user's emotional state. If the server determines that the user is confused based on the analysis results, it generates additional detailed information and a QR code and sends them to the device. The input is the emotion analysis result, and the output is the additional information and QR code data.

[1083] By clearly indicating the specific operations and inputs / outputs at each step, the overall processing flow of the system becomes clear, allowing users to smoothly and accurately learn how to separate their garbage.

[1084] 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.

[1085] 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.

[1086] 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.

[1087] [Fourth embodiment]

[1088] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1089] 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.

[1090] 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).

[1091] 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.

[1092] 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.

[1093] 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).

[1094] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1095] 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.

[1096] 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.

[1097] 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.

[1098] 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.

[1099] 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.

[1100] 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."

[1101] The present invention is a system for enabling a user to learn how to separate garbage, and this system is composed of a plurality of means. Hereinafter, an embodiment of the present invention will be described in detail.

[1102] System configuration

[1103] Image Acquisition Method

[1104] The user takes a photo of the trash using the camera on their smartphone or other device. The captured image data is saved in the device's internal storage. The user can then view the captured image data within the application and proceed to the next processing step.

[1105] communication means

[1106] The smartphone is equipped with a communication method for sending captured image data to a server. Specifically, it uses an HTTP POST request from the smartphone to the server. The image data is sent as part of this request.

[1107] Image analysis methods

[1108] The server analyzes the received image data using deep learning models (e.g., ResNet-50 and VGG-16), which automatically identifies the type of garbage (bottles, cans, plastic, etc.).

[1109] Separation method identification means

[1110] The server searches a database for sorting rules that correspond to the user's area based on the identified type of garbage, and uses the search results to identify specific methods for sorting garbage.

[1111] Presentation means

[1112] The identified sorting method is sent to the user's device in real time, and the device displays the received information on the user interface, allowing the user to instantly confirm the correct method for sorting their garbage.

[1113] Specific examples

[1114] For example, consider the case where a user takes a picture of a beer bottle.

[1115] 1. User: Take a photo of a beer bottle with your smartphone camera.

[1116] 2. Device: The captured image data is stored in the internal storage and then sent to the server.

[1117] 3. Server: Receives the image data and performs image analysis using a deep learning model. This analysis identifies it as a beer bottle.

[1118] 4. Server: Based on the user's address data, the server searches the database for the relevant municipality's sorting rules and identifies specific sorting methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[1119] 5. Server: The identified sorting method is formatted in JSON format and sent to the device.

[1120] 6. Terminal: The received sorting method is displayed on the user interface.

[1121] 7. User: Check the displayed sorting method and sort the beer bottles in the correct way.

[1122] The system of the present invention allows users to easily and accurately learn how to separate their garbage, enabling them to separate their garbage appropriately and efficiently. As a result, users can dispose of their garbage in accordance with local government rules, which also contributes to environmental protection.

[1123] The processing flow will be explained below.

[1124] Step 1:

[1125] A user takes a photo of trash (e.g., a beer bottle) with their smartphone camera. The device stores the captured image data in its internal storage.

[1126] Step 2:

[1127] The application on the device displays a screen for the user to check the image they have taken. When the user taps the "Confirm" button, the device prepares to send the image data to the server.

[1128] Step 3:

[1129] The device sends the image data that is ready to be sent to the server as an HTTP POST request. This request includes the image data.

[1130] Step 4:

[1131] The server receives the HTTP POST request sent from the device, extracts the image data from the request, and passes it to the image analysis module.

[1132] Step 5:

[1133] The server's image analysis module processes the received image data. It uses a deep learning model (e.g., ResNet-50 or VGG-16) to analyze the image and identify the type of debris contained in the image. In this case, the image analysis module detects that it is a beer bottle.

[1134] Step 6:

[1135] Based on the analysis results, the server references the user's residential area information and queries the database for the sorting rules for that area, searching for the appropriate sorting method.

[1136] Step 7:

[1137] The server then uses the query results to identify specific separation methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[1138] Step 8:

[1139] The server formats the generated sorting instructions in JSON format and sends them to the terminal as an HTTP response.

[1140] Step 9:

[1141] The device receives the HTTP response from the server, analyzes the received JSON data, and extracts the sorting instructions.

[1142] Step 10:

[1143] The device displays the analyzed sorting instructions on the app's user interface. The user confirms the displayed instructions and then performs the actual garbage sorting work.

[1144] This series of processes allows users to easily and accurately learn how to separate their garbage, enabling them to dispose of their garbage appropriately in accordance with local garbage separation rules.

[1145] Example 1

[1146] 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."

[1147] Conventional systems providing information on garbage sorting methods are cumbersome, requiring users to manually identify the type of garbage and look up the corresponding sorting rules. Furthermore, there is no flexible system to reflect the different sorting rules of each specific municipality, which can lead to users sorting incorrectly.

[1148] 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.

[1149] In this invention, the server includes an image acquisition means for allowing a user to take a photo of waste and generate image data of the photo, a communication means for transmitting the image data to a remote server, an image analysis means for receiving the image data and identifying the type of waste using a deep learning model, a sorting method identification means for searching a database for sorting rules corresponding to the type of waste and identifying an appropriate sorting method, and a presentation means for presenting the identified sorting method to the user. This allows the user to easily obtain an accurate sorting method and efficiently sort their waste appropriately.

[1150] The "image acquisition means" is a device or system that allows a user to take a photograph of waste and generate image data thereof.

[1151] "Communication means" is a network interface or protocol for transmitting the image data to a remote server.

[1152] "Image analysis means" refers to a processing device or software that receives the image data and uses a deep learning model to identify the type of waste.

[1153] The "sorting method specifying means" is an algorithm or system for searching a database for sorting rules corresponding to the type of waste and specifying the corresponding sorting method.

[1154] The "presentation means" refers to a display or application user interface for presenting the identified sorting method to the user.

[1155] "Waste" is a general term for garbage and unwanted items.

[1156] A "remote server" is a computer system installed remotely for communicating with a user's terminal via a network.

[1157] A "deep learning model" is a part of artificial intelligence, and is an algorithm that uses a multi-layer neural network to automatically extract features from large amounts of data and perform classification and prediction.

[1158] A "database" is an information management system for systematically storing and searching information on sorting rules and types of waste.

[1159] MODE FOR CARRYING OUT THE INVENTION

[1160] This invention is a system that allows users to learn how to separate waste materials. The system is composed of multiple means. Users take photos of waste materials using a device such as a smartphone and send the image data to a server. The server analyzes the image data, identifies the type of waste material, and then provides the user with specific separation methods based on the separation rules for the relevant area.

[1161] (composition)

[1162] Image Acquisition Method

[1163] The user takes a photo of the waste using the smartphone camera, and the image data is saved in the smartphone's internal storage. The user can then review the image data within the application and proceed to the next processing step.

[1164] communication means

[1165] The smartphone is provided with a communication means for transmitting the image data to the server. Specifically, the image data is transmitted from the smartphone terminal to the remote server using an HTTP POST request.

[1166] Image analysis methods

[1167] The server analyzes the image data received from the device using a deep learning model (e.g., ResNet-50 or VGG-16). The deep learning model identifies the type of waste (e.g., bottles, cans, plastic, etc.).

[1168] Separation method identification means

[1169] Based on the identified waste type, the server searches a database for sorting rules that correspond to the user's area of ​​residence, and uses the search results to identify specific methods for sorting waste.

[1170] Presentation means

[1171] The identified waste separation method is sent in real time to the user's device, which then displays the received information on the user interface, allowing the user to instantly confirm the correct waste separation method.

[1172] (Example)

[1173] For example, a case where a user photographs a beer bottle will be described.

[1174] 1. User: Take a photo of a beer bottle with your smartphone camera.

[1175] 2. Device: The captured image data is stored in the internal storage and sent to the server.

[1176] 3. Server: Receives the image data and performs image analysis using a deep learning model. The analysis identifies it as a beer bottle.

[1177] 4. Server: Based on the user's address information, the server searches the database for the relevant municipality's sorting rules and identifies specific sorting methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[1178] 5. Server: The identified sorting method is formatted in JSON format and sent to the device.

[1179] 6. Terminal: The received sorting method is displayed on the user interface.

[1180] 7. User: Check the displayed sorting method and sort the beer bottles in the correct way.

[1181] This allows users to easily obtain accurate waste separation methods, enabling them to efficiently separate waste appropriately. As a result, waste can be disposed of in accordance with local government rules, contributing to environmental protection.

[1182] (Example of a prompt)

[1183] "Please create a program that uses ResNet-50 to identify waste categories (bottles, cans, plastic, etc.) and searches for the municipality's waste separation rules based on the user's address. The user takes a picture of the waste with their smartphone camera and sends it to the server. Please explain in natural language the entire process, from image analysis and search on the server to displaying the separation instructions on the device."

[1184] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1185] Step 1:

[1186] Users take photos of waste using their smartphone camera by tapping the "Take Photo" button in the application. The input is the physical presence of the waste, and the output is image data stored on the smartphone.

[1187] Step 2:

[1188] The device saves the captured image data in its internal storage. The input is the photo data from the camera application, and the output is an image file saved in the device's internal storage. Also, if the user taps the "Send" button in this step, processing for the next communication method will begin.

[1189] Step 3:

[1190] The device sends the stored image data to the server. Specifically, it generates an HTTP POST request, includes the image data in the request body, and sends it to the specified API endpoint of the remote server. The input is the image data stored inside the device, and the output is the HTTP request sent to the remote server.

[1191] Step 4:

[1192] The server receives the image data sent from the device and analyzes it using a deep learning model. Specifically, the received image data is input into a deep learning model such as ResNet-50, and image analysis is performed using the model. The input is the image data extracted from the HTTP request, and the output is the type of waste (e.g., bottle, can, plastic, etc.) as the analysis result.

[1193] Step 5:

[1194] Based on the analysis results, the server searches a database for sorting rules that correspond to the user's residential area. The input is the waste type obtained by the analysis and the user's address information, and the output is the corresponding sorting rules obtained from the database. Specifically, the server generates a database query and executes a search to obtain the sorting rules.

[1195] Step 6:

[1196] The server analyzes the obtained sorting rules and identifies the specific sorting method. The input is the sorting rules obtained from the database, and the output is the specific sorting method identified. This identified sorting method is formatted in JSON format or similar.

[1197] Step 7:

[1198] The server sends the formatted sorting method to the terminal. The input is the sorting method data in JSON format, and the output is the HTTP response sent to the terminal. This prepares the terminal for reception.

[1199] Step 8:

[1200] The device analyzes the sorting method data received from the server and displays it on the user interface. The input is the JSON data received from the server, and the output is sorting method information that is visually presented to the user. Specifically, the information is appropriately laid out on the application screen and displayed in a way that is easy for the user to understand.

[1201] Step 9:

[1202] The user checks the displayed sorting instructions and actually sorts the waste correctly. The input is the sorting information displayed on the device, and the output is the actual waste sorting behavior. The user follows the instructions and places the waste in the appropriate garbage bag or recycling container.

[1203] (Application example 1)

[1204] 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."

[1205] Until now, it has been difficult for employees to accurately and efficiently separate the wide variety of waste generated within physical stores. In particular, due to complex sorting rules and regional differences, it took a lot of time and effort for employees to understand how to separate waste. Therefore, there was a strong demand for a system that would allow employees to easily and accurately learn how to separate waste, thereby improving work efficiency.

[1206] 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.

[1207] In this invention, the server includes an image acquisition means for allowing a user to take a photo of trash and generate image data of the photo, a communication means for transmitting the image data to the server, an image analysis means for receiving the image data and identifying the type of trash, a sorting method identification means for searching a database for sorting rules corresponding to the type of trash and identifying an appropriate sorting method, a presentation means for presenting the identified sorting method to the user, and a means for presenting the trash sorting method to employees in the physical store in real time using a smart device or a robot. This enables accurate and efficient trash sorting in the physical store, reducing the burden on employees and improving work efficiency.

[1208] "Waste sorting method" is a procedure for separating waste into different categories according to material and disposal method.

[1209] A "system" refers to a device or group of devices in which multiple elements work together to achieve a specific function.

[1210] The "image acquisition means" is a function that allows a user to take a photo of the garbage using a device such as a camera and acquire the image data.

[1211] "Communication means" refers to the communication protocol and infrastructure for transmitting image data acquired on the terminal to the server.

[1212] "Image analysis means" refers to an analytical technology for identifying the type of garbage based on the image data received by the server, and includes deep learning models, etc.

[1213] The "sorting method identification means" is a function that searches a database for the sorting rules for the relevant area based on the identified type of garbage, and identifies the specific sorting method.

[1214] The "presentation means" is a function for displaying the identified waste separation method to the user and encouraging them to separate their garbage appropriately.

[1215] A "smart device" is a portable or stationary electronic device that has internet connectivity, a touchscreen, and advanced computing capabilities.

[1216] A "robot" refers to a mechanical device that operates autonomously according to programmed instructions.

[1217] "Physical store" refers to a physical store for selling goods or providing services.

[1218] A "deep learning model" is a technology that uses an artificial neural network to learn specific patterns and features from large amounts of data, enabling advanced discrimination and prediction.

[1219] MODE FOR CARRYING OUT THE INVENTION

[1220] System Configuration

[1221] A system embodying the invention includes the following major hardware and software components:

[1222] 1. Image acquisition method

[1223] Users take a photo of the trash using a smartphone, tablet, or in-store smart robot. The captured image data is stored in the device's internal storage, and the user can view the image data within the app before it moves on to the next processing step.

[1224] 2. Means of communication

[1225] The captured image data is sent to the server via Wi-Fi or a mobile network using an HTTP POST request.

[1226] 3. Image analysis methods

[1227] The server analyzes the received image data using a deep learning model (e.g., ResNet-50 or VGG-16), which automatically identifies the type of garbage (bottles, cans, plastic, etc.).

[1228] 4. Means for specifying separation method

[1229] Based on the identified type of waste, the server searches a database for sorting rules that correspond to the specific store and its location, and then determines the specific method for sorting the waste.

[1230] 5. Presentation means

[1231] The identified sorting method is sent in real time to the user's device, which then displays the received information on the user interface, allowing store employees to quickly understand the correct method for sorting waste.

[1232] 6. In-store support

[1233] Smart devices or robots will provide real-time guidance to store employees on how to separate waste, improving employee efficiency and encouraging accurate waste separation.

[1234] Examples of concrete examples and prompts

[1235] Specific examples

[1236] For example, here's the procedure for employees at a cafe to dispose of used plastic containers:

[1237] 1. User (employee): Take a photo of a plastic container with the camera on their smartphone or tablet.

[1238] 2. Device: The captured image data is stored in the internal storage and then sent to the server.

[1239] 3. Server: Analyzes the received image data using a deep learning model and identifies it as a plastic container.

[1240] 4. Server: Based on the store's location, search the database for the relevant sorting rules and identify that "plastic containers should be disposed of as plastic waste."

[1241] 5. Server: The identified sorting method is formatted in JSON format and sent to the device.

[1242] 6. Terminal: The received sorting method is displayed on the user interface, and employees sort the garbage appropriately.

[1243] Prompt Sentence Examples

[1244] Write an application program that allows users to take pictures of trash with their smartphone camera, send them to a server, and use a deep learning model to identify the type of trash. Then, based on the user's location, determine how to sort the trash and display the results on the device in real time.

[1245] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1246] Step 1:

[1247] The user takes a photo of the trash and generates image data. Specifically, the image is taken using a smartphone, tablet, or the camera of a smart robot installed in the store. This image data is then stored in the internal storage.

[1248] Input: Physical image of the trash

[1249] Output: Image data stored in internal storage

[1250] Step 2:

[1251] The device sends the captured image data to the server using an HTTP POST request via Wi-Fi or a mobile network.

[1252] Input: Image data stored in the internal storage

[1253] Output: Image data sent to the server

[1254] Step 3:

[1255] The image data received by the server is analyzed using a deep learning model. Specifically, deep learning models such as ResNet-50 and VGG-16 are used to identify the type of garbage. This analysis allows for identification of, for example, "plastic containers" or "bottles."

[1256] Input: Image data sent to the server

[1257] Output: Identified trash type (e.g. plastic container)

[1258] Step 4:

[1259] The server searches the database for the local sorting rules based on the identified type of garbage. Since the local sorting rules are identified based on the user's location information, the server also refers to the user's location data.

[1260] Input: Identified garbage type, user location information

[1261] Output: Sorting method according to type of garbage

[1262] Step 5:

[1263] Based on the search results, the server formats the identified sorting methods in JSON format and sends them to the device. The formatted data is presented to the user in a format that is easy to view.

[1264] Input: Identified separation method

[1265] Output: JSON formatted sorting method data

[1266] Step 6:

[1267] The terminal displays the received sorting method data on the user interface, allowing users (employees) to check the correct garbage sorting method in real time and sort their garbage appropriately.

[1268] Input: JSON formatted separation method data

[1269] Output: The sorting method displayed in the user interface

[1270] Step 7:

[1271] Smart devices or robots in physical stores provide real-time guidance to employees on how to separate waste, allowing them to see how to do so without having to take their hands off the device.

[1272] Input: The sorting method displayed in the user interface

[1273] Output: Garbage sorting method presented to store employees

[1274] Through these steps, waste sorting in physical stores is carried out accurately and efficiently.

[1275] 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.

[1276] The present invention provides a system that improves the user experience by combining a system for helping users learn how to separate their garbage with an emotion engine that recognizes the user's emotional state. This system is comprised of the following means.

[1277] System configuration

[1278] Image Acquisition Method

[1279] The user takes a photo of the trash using the camera on their smartphone or other device. The captured image data is saved in the device's internal storage, and the user can view the captured image data within the application and proceed to the next processing step.

[1280] communication means

[1281] The smartphone is equipped with a communication method for sending captured image data to a server. Specifically, it uses an HTTP POST request from the smartphone to the server. The image data is sent as part of this request.

[1282] Image analysis methods

[1283] The server analyzes the received image data using deep learning models (e.g., ResNet-50 and VGG-16), which automatically identifies the type of garbage (bottles, cans, plastic, etc.).

[1284] Separation method identification means

[1285] The server searches a database for sorting rules that correspond to the user's area based on the identified type of garbage, and uses the search results to identify specific methods for sorting garbage.

[1286] Presentation means

[1287] The identified sorting method is sent to the user's device in real time, and the device displays the received information on the user interface, allowing the user to instantly confirm the correct method for sorting their garbage.

[1288] Emotion Engine

[1289] The emotion engine recognizes the user's emotional state and optimizes the interface display and presentation methods accordingly. In this invention, the emotional state can be recognized by analyzing the user's voice input and facial expressions. Furthermore, the recognized emotional state can be logged and used to improve the user experience in subsequent interactions.

[1290] Specific examples

[1291] For example, consider the case where a user takes a picture of a beer bottle.

[1292] 1. User: Take a photo of a beer bottle with your smartphone camera.

[1293] 2. Device: The captured image data is stored in the internal storage and then sent to the server.

[1294] 3. Server: Receives the image data and performs image analysis using a deep learning model. This analysis identifies it as a beer bottle.

[1295] 4. Server: Based on the user's address data, the server searches the database for the relevant municipality's sorting rules and identifies specific sorting methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[1296] 5. Server: The identified sorting method is formatted in JSON format and sent to the device.

[1297] 6. Terminal: The received sorting method is displayed on the user interface.

[1298] 7. Emotion Engine: The emotion engine analyzes the user's voice and facial expressions, and if it determines that the user is confused, it provides more specific instructions or additional support information.

[1299] 8. User: Check the displayed sorting instructions and sort the beer bottles in the correct way. The additional information from the emotion engine improves the user experience.

[1300] The system of this invention not only allows users to easily learn accurate garbage sorting methods, but also enables smoother, stress-free garbage sorting with the support of the emotion engine. This allows users to dispose of garbage appropriately in accordance with local garbage sorting rules, thereby contributing to environmental protection.

[1301] The processing flow will be explained below.

[1302] Step 1:

[1303] A user takes a photo of trash (e.g., a beer bottle) with their smartphone camera. The device stores the captured image data in its internal storage.

[1304] Step 2:

[1305] The application on the device displays a screen for the user to check the image they have taken. When the user taps the "Confirm" button, the device prepares to send the image data to the server.

[1306] Step 3:

[1307] The device sends the image data that is ready to be sent to the server as an HTTP POST request. This request includes the image data.

[1308] Step 4:

[1309] The server receives the HTTP POST request sent from the device, extracts the image data from the request, and passes it to the image analysis module.

[1310] Step 5:

[1311] The server's image analysis module processes the received image data. It uses a deep learning model (e.g., ResNet-50 or VGG-16) to analyze the image and identify the type of debris contained in the image. In this case, the image analysis module detects that it is a beer bottle.

[1312] Step 6:

[1313] Based on the analysis results, the server references the user's residential area information and queries the database for the sorting rules for that area, searching for the appropriate sorting method.

[1314] Step 7:

[1315] The server then uses the query results to identify specific separation methods, such as "put out beer bottles as recyclable waste" and "put out caps as general waste."

[1316] Step 8:

[1317] The server formats the generated sorting instructions in JSON format and sends them to the terminal as an HTTP response.

[1318] Step 9:

[1319] The device receives the HTTP response from the server, analyzes the received JSON data, and extracts the sorting instructions.

[1320] Step 10:

[1321] The device displays the analyzed sorting instructions on the app's user interface, and the user confirms the displayed instructions.

[1322] Step 11:

[1323] The emotion engine analyzes the user's voice input and facial expressions, and in the process determines whether the user is stressed or confused.

[1324] Step 12:

[1325] If the emotion engine determines that the user is confused, it will provide more detailed explanations and additional support information in addition to the identified sorting method, such as "Please dispose of beer bottles as recyclable waste. If this bottle is broken, please wrap it in protective material using these steps."

[1326] Step 13:

[1327] The terminal displays additional information from the emotion engine on the user interface to provide appropriate assistance to the user.

[1328] Step 14:

[1329] The user checks the displayed sorting method and additional information and sorts the garbage correctly accordingly.

[1330] This process allows users to easily and accurately learn how to separate their trash. Furthermore, with the support of the emotion engine, the user experience is improved, allowing them to separate their trash without feeling stressed or confused.

[1331] Example 2

[1332] 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."

[1333] While existing technologies provide users with accurate and prompt guidance on how to separate their trash, there is a lack of technology that provides optimal guidance based on the user's emotional state. In particular, there is a need for technology that can improve situations where users become confused or stressed about how to separate their trash.

[1334] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an image acquisition means for allowing a user to take a photo of garbage and generate image data thereof, a communication means for transmitting the image data to the server, an image analysis means for receiving the image data and identifying the type of garbage using a model based on deep learning, a sorting method identification means for searching a database for sorting rules corresponding to the type of garbage and identifying an appropriate sorting method, a presentation means for presenting the identified sorting method to the user, an emotion engine means for analyzing the user's voice input and facial expressions to recognize the user's emotional state, and a means for optimizing the presentation method based on the recognized emotional state. This not only enables the user to accurately understand how to sort garbage, but also improves the user's usage experience according to the user's emotional state.

[1335] text

[1336] The "image acquisition means" is a device that allows a user to take a photograph of the garbage and generate image data of the photograph.

[1337] The "communication means" is a device or function for transmitting the image data to the server.

[1338] The "image analysis means" is a device or function that receives the image data and identifies the type of dust using a model that uses deep learning.

[1339] The "sorting method specifying means" is a device or function that searches a database for sorting rules that correspond to the type of waste and specifies the corresponding sorting method.

[1340] The "presentation means" is a device or function for presenting the identified sorting method to the user.

[1341] The "emotion engine means" is a device or function that analyzes the user's voice input and facial expressions and recognizes the user's emotional state.

[1342] An "optimizer" is a device or function that optimizes presentation methods based on a recognized emotional state.

[1343] The present invention provides a technology for recognizing a user's emotional state and optimizing guidance based on the emotional state in a system for helping a user learn how to separate garbage. The system includes the following means.

[1344] Image Acquisition Method

[1345] The user takes a photo of the trash using the smartphone camera. For example, if the user takes a photo of a beer bottle, the image data is saved in the device's internal storage. This image acquisition method is realized by using the smartphone's camera application.

[1346] communication means

[1347] The device sends the saved image data to the server. This communication is performed using an HTTP POST request, and the image data is included in this request and sent to the server. The communication method is the smartphone's Internet connection function.

[1348] Image analysis methods

[1349] The server analyzes the received image data. A deep learning model (e.g., ResNet-50 or VGG-16) is used for this image analysis. The server uses this model to identify the type of garbage (e.g., bottles, cans, plastic, etc.). The server's processing unit uses hardware such as a GPU to perform this analysis quickly.

[1350] Separation method identification means

[1351] The server searches a database for sorting rules that correspond to the user's area of ​​residence based on the identified type of garbage. For example, it obtains a rule such as "beer bottles should be disposed of as recyclable garbage" and identifies the specific sorting method. This search process uses a relational database management system (RDBMS).

[1352] Presentation means

[1353] The server sends the identified sorting method to the user's device in real time. The device displays the received information on the user interface. For example, the screen might say, "Please dispose of beer bottles as recyclable waste."

[1354] Emotion Engine Means

[1355] The device analyzes the user's voice input and facial expressions to recognize the user's emotional state. This analysis is performed using voice recognition software and facial expression analysis algorithms. For example, if the device recognizes that the user is confused, it may display more specific instructions or additional support information. The emotion engine means transmits the results to a server, which uses them to improve the user experience in subsequent interactions.

[1356] Specific examples

[1357] The series of processes will be explained using a specific example. For example, if a user takes a photo of a beer bottle, the following prompt sentence can be input to the generative AI model:

[1358] Prompt Sentence Examples

[1359] "Tell me how to separate beer bottles into trash. If the user is confused, how would the emotion engine respond?"

[1360] This system not only allows users to easily obtain accurate garbage sorting instructions, but also enhances the user experience with its emotion engine. Specifically, if users are confused, the system can provide more detailed explanations and additional support information, enabling a smoother garbage sorting process. This promotes proper garbage disposal in accordance with local garbage sorting rules and contributes to environmental protection.

[1361] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1362] text

[1363] Step 1: Acquire and save image data

[1364] A user takes a photo of trash using the smartphone camera. For example, they take a photo of a beer bottle by tapping the camera button on the camera app. The input is the image of the beer bottle taken by the user, and the output is the image data. The device saves the generated image data in its internal storage, and the save destination is a specific folder on the device (e.g., the application folder).

[1365] Step 2: Sending image data

[1366] The device sends the saved image data to the server. This communication uses an HTTP POST request, and the image data is included in this request. The input is the image data saved in step 1, and the output is the image data sent to the server. The device displays the progress of the communication in the status bar.

[1367] Step 3: Receiving and analyzing image data

[1368] The server receives the received image data and analyzes the image using a deep learning model (e.g., ResNet-50 or VGG-16). The input is the image data sent from the device, and the output is the identification result of the type of garbage (e.g., bottle). The server stores the data in a temporary database on the server to temporarily save the analysis results.

[1369] Step 4: Search for sorting rules

[1370] The server searches a database for sorting rules that correspond to the user's area of ​​residence based on the identified type of garbage. The input is the garbage identification result and the user's address data, and the output is the corresponding sorting rule (e.g., "Beer bottles should be disposed of as recyclable garbage"). The server performs a rapid search using a relational database management system (RDBMS).

[1371] Step 5: Identify and format the sorting method

[1372] The server identifies specific sorting methods based on the search results and formats this information in JSON format. The input is the sorting rules obtained in step 4, and the output is the formatted sorting method data. The server prepares this data to send as a response.

[1373] Step 6: Present the sorting method

[1374] The server sends the formatted sorting method data to the terminal. The terminal analyzes the received data and displays it on the user interface. For example, it might display "Please dispose of beer bottles as recyclable waste." The input is the sorting method data from the server, and the output is the content presented to the user.

[1375] Step 7: Recognizing your emotional state

[1376] The device acquires the user's voice input and facial expressions. For this purpose, it uses a camera and microphone. The input is the user's voice data and video data, and the output is input data to the emotion engine. The device sends this data to the emotion engine.

[1377] Step 8: Emotional state analysis and feedback

[1378] The device uses an emotion engine to analyze the user's emotional state. The input is audio and video data, and the output is the identification result of the user's emotional state. For example, if the device recognizes that the user is confused, it will display more specific instructions or additional support information. It will display additional detailed explanations on the screen, such as "Please dispose of beer bottles as recyclable waste. Caps are general waste."

[1379] (Application example 2)

[1380] 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."

[1381] Conventional garbage sorting systems require users to manually check the type of garbage and local sorting rules, which is often time-consuming and laborious. Furthermore, if users feel confused or stressed about how to sort their garbage, the system provides no appropriate support, making the sorting process itself a hassle. The goal of this system is to solve these issues, improve the user experience, and achieve more efficient and accurate garbage sorting.

[1382] The identification process 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 image acquisition means for allowing a user to take a photo of garbage and generate image data thereof, communication means for transmitting the image data to the server, image analysis means for receiving the image data and identifying the type of garbage, sorting method identification means for searching a database for sorting rules corresponding to the type of garbage and identifying an appropriate sorting method, presentation means for presenting the identified sorting method to the user, and emotion recognition means for recognizing the user's emotional state and optimizing the display of the interface in accordance with that state. This not only enables the user to easily and accurately acquire garbage sorting methods, but also provides optimal support in accordance with the user's emotional state, enabling smoother and more stress-free garbage sorting.

[1383] The "image acquisition means" is a device or mechanism that allows a user to take a photo of the garbage and generate image data of the photo.

[1384] The "communication means" is a network communication means for transmitting the image data to the server.

[1385] The "image analysis means" is an analysis device that receives the image data and uses a deep learning model or the like to identify the type of dust.

[1386] The "sorting method specifying means" is a device or mechanism for searching a database for sorting rules corresponding to the type of waste and specifying the corresponding sorting method.

[1387] The "presentation means" is a user interface for presenting the identified separation method to the user.

[1388] An "emotion recognition means" is a device or mechanism for recognizing the user's emotional state and optimizing the display of the interface in accordance with that state.

[1389] "Deep learning" is a machine learning technology that recognizes and predicts complex patterns by learning from large amounts of data.

[1390] A "server" is a computer system that provides services in response to requests from clients.

[1391] A "database" is a data storage device for managing and searching garbage sorting rules and other related information.

[1392] This invention provides a system called "Smart Eco Guide" that allows users to easily learn how to separate garbage. This system includes the following main components:

[1393] 1. Image acquisition method

[1394] When a user takes a photo of trash using the smartphone camera, the application controls the camera device and saves the captured image data in the internal storage.

[1395] 2. Means of communication

[1396] The smartphone is equipped with a communication method for sending captured image data to a server. Specifically, it uses an HTTP POST request from the smartphone to the server. The image data is included in this request.

[1397] 3. Image analysis methods

[1398] The server analyzes the received image data using a deep learning model (e.g., ResNet-50 or VGG-16), which automatically identifies the type of garbage (e.g., bottles, cans, plastic, etc.).

[1399] 4. Means for specifying separation method

[1400] The server searches a database for sorting rules that correspond to the user's area or specific location based on the type of garbage identified, and uses the search results to identify specific methods for sorting garbage.

[1401] 5. Presentation means

[1402] The identified sorting method is sent to the user's device in real time and displayed on the user interface, allowing the user to instantly confirm the correct method for sorting their garbage.

[1403] 6. Emotion recognition means

[1404] The emotion recognition engine analyzes the user's emotional state and optimizes the interface display and presentation accordingly. For example, if it determines that the user is confused, it will display more detailed explanations or supplementary information.

[1405] Hardware and software used

[1406] Hardware

[1407] Smartphone (with camera function)

[1408] Server (high-performance computing power required)

[1409] software

[1410] OpenCV: for image capture and pre-processing

[1411] Keras: for loading and predicting deep learning models

[1412] Requests: HTTP communication library

[1413] Sentiment Analysis API: An external service for analyzing user sentiment

[1414] Specific examples

[1415] For example, consider a case where a user wants to properly separate empty plastic bottles at a shopping mall:

[1416] 1. The user launches the app on their smartphone and takes a photo of a plastic bottle with the camera.

[1417] 2. The captured image is sent to a server, where a deep learning model analyzes the image and identifies it as a plastic bottle.

[1418] 3. The server searches the database for the mall's garbage sorting rules and identifies the correct way to sort plastic bottles.

[1419] 4. The app displays the sorting method on the user interface, helping users sort their waste correctly without hesitation.

[1420] 5. If the user is confused, the emotion recognition engine will detect this and provide more specific explanations and images.

[1421] Prompt Sentence Examples

[1422] When a user wants to know how to sort a plastic bottle they have finished drinking from, they launch the app and take a photo of the trash with their smartphone camera. The image is sent to the server, where the AI ​​analyzes it and returns the correct sorting instructions. The app also analyzes the user's emotional state and, if it determines they are confused, provides additional details and a QR code. Express this process in Python code.

[1423] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1424] Step 1:

[1425] The user takes a photo of the garbage. The user launches the app on their smartphone and takes a photo of the garbage using the camera function. The input is the actual garbage, and the output is image data. This image data is saved in the internal storage.

[1426] Step 2:

[1427] The device sends image data to the server. The device sends image data stored in its internal storage to the server via an HTTP POST request. The input is the image data, and the output is a data packet sent to the server.

[1428] Step 3:

[1429] The server analyzes the image data. The server analyzes the received image data using a deep learning model (e.g., ResNet-50 or VGG-16). The input is the image data, and the output is the identified type of garbage (e.g., PET bottle, can, plastic, etc.).

[1430] Step 4:

[1431] The server searches for the sorting rules and identifies the sorting method. Based on the identified type of garbage, the server searches for the corresponding sorting rule from the database. The input is the type of garbage, and the output is the specific sorting method. This sorting method is formatted in JSON format.

[1432] Step 5:

[1433] The server sends the specified sorting method to the terminal. The server sends the specified sorting method (JSON format) to the terminal. The input is the JSON data of the sorting method, and the output is the data packet sent to the terminal.

[1434] Step 6:

[1435] The terminal displays the sorting method on the user interface. The terminal analyzes the received data on the sorting method and displays it on the user interface. The input is the JSON data of the sorting method, and the output is the sorting method displayed on the user interface.

[1436] Step 7:

[1437] The server analyzes the user's emotional state. The server uses an emotion analysis API to analyze the user's voice data and facial expression images being captured. The input is the voice data and facial expression images, and the output is the analysis result of the user's emotional state (e.g., confusion, stress).

[1438] Step 8:

[1439] The server provides optimal support according to the user's emotional state. If the server determines that the user is confused based on the analysis results, it generates additional detailed information and a QR code and sends them to the device. The input is the emotion analysis result, and the output is the additional information and QR code data.

[1440] By clearly indicating the specific operations and inputs / outputs at each step, the overall processing flow of the system becomes clear, allowing users to smoothly and accurately learn how to separate their garbage.

[1441] 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.

[1442] 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.

[1443] 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.

[1444] 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.

[1445] 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.

[1446] 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.

[1447] 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).

[1448] 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.

[1449] 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."

[1450] 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.

[1451] 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).

[1452] 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.

[1453] 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.

[1454] 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.

[1455] 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.

[1456] 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.

[1457] 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.

[1458] 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.

[1459] 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.

[1460] 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.

[1461] 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.

[1462] The following is further disclosed regarding the above embodiment.

[1463] (Claim 1)

[1464] A system that presents a method for separating garbage,

[1465] image acquisition means for allowing a user to take a photograph of the garbage and generate image data thereof;

[1466] a communication means for transmitting the image data to a server;

[1467] image analysis means for receiving the image data and identifying the type of dust;

[1468] a sorting method specifying means for searching a database for sorting rules corresponding to the type of waste and specifying a corresponding sorting method;

[1469] a presentation means for presenting the identified sorting method to the user;

[1470] A system including:

[1471] (Claim 2)

[1472] 2. The system according to claim 1, wherein the sorting method specifying means searches for a sorting rule for a corresponding area based on the user's residential area.

[1473] (Claim 3)

[1474] The system according to claim 1, wherein the image analysis means identifies the type of garbage using a model that uses deep learning.

[1475] "Example 1"

[1476] (Claim 1)

[1477] image acquisition means for a user to take a photograph of the waste and generate image data of the photograph;

[1478] a communication means for transmitting the image data to a remote server;

[1479] image analysis means for receiving the image data and identifying the type of waste using a deep learning model;

[1480] a sorting method specifying means for searching a database for sorting rules corresponding to the type of waste and specifying an appropriate sorting method;

[1481] a presentation means for presenting the identified sorting method to the user;

[1482] A system including:

[1483] (Claim 2)

[1484] 2. The system according to claim 1, wherein the sorting method specifying means searches for a sorting rule for a corresponding area based on the user's residential area.

[1485] (Claim 3)

[1486] The system of claim 1, wherein the image analysis means identifies the type of waste using a model that uses deep learning.

[1487] "Application Example 1"

[1488] (Claim 1)

[1489] A system that presents a method for separating garbage,

[1490] image acquisition means for allowing a user to take a photograph of the garbage and generate image data thereof;

[1491] a communication means for transmitting the image data to a server;

[1492] image analysis means for receiving the image data and identifying the type of dust;

[1493] a sorting method specifying means for searching a database for sorting rules corresponding to the type of waste and specifying a corresponding sorting method;

[1494] a presentation means for presenting the identified sorting method to the user;

[1495] A method to use smart devices or robots to provide real-time guidance to store employees on how to separate waste;

[1496] A system including:

[1497] (Claim 2)

[1498] 2. The system according to claim 1, wherein the sorting method specifying means searches for a sorting rule for a corresponding area based on the location of the user.

[1499] (Claim 3)

[1500] The system according to claim 1, wherein the image analysis means identifies the type of garbage using a model that uses deep learning.

[1501] "Example 2: Combining Emotion Engines"

[1502] text

[1503] (Claim 1)

[1504] image acquisition means for allowing a user to take a photograph of the garbage and generate image data thereof;

[1505] a communication means for transmitting the image data to a server;

[1506] an image analysis means for receiving the image data and identifying the type of dust using a model that uses deep learning;

[1507] a sorting method specifying means for searching a database for sorting rules corresponding to the type of waste and specifying a corresponding sorting method;

[1508] a presentation means for presenting the identified sorting method to the user;

[1509] an emotion engine means for analyzing a user's voice input and facial expressions to recognize the user's emotional state;

[1510] means for optimizing presentation based on the perceived emotional state;

[1511] A system including:

[1512] (Claim 2)

[1513] 2. The system according to claim 1, wherein the sorting method specifying means searches for a sorting rule for a corresponding area based on the user's residential area.

[1514] (Claim 3)

[1515] The system according to claim 1, wherein the image analysis means identifies the type of garbage using a model that uses deep learning.

[1516]

[1517] "Application example 2 when combining emotion engines"

[1518] (Claim 1)

[1519] A system that presents a method for separating garbage,

[1520] image acquisition means for allowing a user to take a photograph of the garbage and generate image data thereof;

[1521] a communication means for transmitting the image data to a server;

[1522] image analysis means for receiving the image data and identifying the type of dust;

[1523] a sorting method specifying means for searching a database for sorting rules corresponding to the type of waste and specifying a corresponding sorting method;

[1524] a presentation means for presenting the identified sorting method to the user;

[1525] emotion recognition means for recognizing the emotional state of a user and optimizing the display of the interface in accordance with the emotional state;

[1526] A system including:

[1527] (Claim 2)

[1528] 2. The system according to claim 1, wherein the sorting method specifying means searches for a sorting rule for a corresponding area based on the user's residential area.

[1529] (Claim 3)

[1530] The system according to claim 1, wherein the image analysis means identifies the type of garbage using a model that uses deep learning. [Explanation of symbols]

[1531] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A system that presents a method for separating garbage, image acquisition means for allowing a user to take a photograph of the garbage and generate image data thereof; a communication means for transmitting the image data to a server; image analysis means for receiving the image data and identifying the type of dust; a sorting method specifying means for searching a database for sorting rules corresponding to the type of waste and specifying a corresponding sorting method; a presentation means for presenting the identified sorting method to the user; A system including:

2. The system according to claim 1 , wherein the sorting method specifying means searches for a sorting rule for a corresponding area based on the user's residential area.

3. The system according to claim 1 , wherein the image analysis means identifies the type of garbage using a model that uses deep learning.

Images