system

Abstract

We provide the system. [Solution] Using natural language processing techniques, we analyze user questions. By referring to regional waste classification rules, A means of instructing users on the proper method of sorting waste, Using image recognition technology, we analyze images of waste taken by the user. A means of proposing a waste classification method to the user based on the analysis results, These means are integrated to enable users to easily classify waste, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Due to different waste classification rules in each region, residents cannot correctly classify waste, resulting in a decrease in recycling efficiency and an increase in environmental load. Also, with the increasing number of residents using diverse languages, confusion and misunderstandings due to language barriers are also problematic. Furthermore, due to the increasing number of products made of complex structures and composite materials, it has become difficult for individuals to manually and accurately classify waste. Technical support is required to efficiently solve these problems

Means for Solving the Problems

[0005] This invention provides a means for instructing users on the appropriate waste classification method by analyzing user questions using natural language processing technology and referring to regional waste classification rules. Furthermore, by constructing a means for analyzing images of waste taken by users using image recognition technology and proposing the optimal waste classification method to the user based on the analysis results, it achieves multilingual support and high accuracy analysis. In addition, by having users send questions and images, the system can provide appropriate classification guidance in real time, enabling residents to classify waste easily and accurately. This makes it possible to improve the efficiency of waste disposal and reduce the environmental burden.

[0006] "Natural language processing technology" refers to the technology of analyzing, understanding, and generating human language using computers, and it involves analyzing text data using machine learning and rule-based algorithms.

[0007] "Regional waste classification regulations" are rules established in each region regarding waste sorting methods, and compliance is required for recycling and waste disposal.

[0008] "Image recognition technology" is a technology that uses computer vision to analyze image data and identify or classify objects.

[0009] A "composite material" is a material made by combining different substances or materials, and it may possess superior properties compared to a single material.

[0010] A "user" refers to a person or organization that uses a system or application to obtain information or utilize its functions. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

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

[0021] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0028] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] This invention is implemented as an AI assistant system for users to accurately classify household waste. The system mainly consists of a 24 / 7 AI chatbot and a smartphone application, which work together to provide users with appropriate waste classification instructions.

[0033] Users submit questions about waste classification to the system via an AI chatbot using their smartphone or PC. These questions are analyzed by the server using natural language processing technology, and specific keywords and regional information are extracted. Based on this information, the server refers to regional waste classification regulations and instructs the user on the most appropriate classification method.

[0034] For example, if a user asks, "How should I dispose of this plastic?", the server detects the keyword "plastic," queries the local database, and returns instructions such as "Put it in the combustible waste bin."

[0035] Additionally, when a user takes a picture of composite material waste using a smartphone app, the device sends the image data to a server. The server analyzes the image using image recognition technology to identify the material and shape of the waste. Based on the analysis results, the server provides the user with instructions such as, "Please separate this packaging into paper and plastic before disposal."

[0036] In this way, the system provides immediate answers to user questions and can meet the needs of a wide range of residents through multilingual support. This reduces the effort required for traditional manual waste sorting and promotes proper recycling.

[0037] The following describes the processing flow.

[0038] Step 1:

[0039] Users use their smartphones or PCs to input and submit questions about waste classification to an AI chatbot.

[0040] Step 2:

[0041] The server receives questions submitted by users and analyzes the text data that makes up those questions using natural language processing techniques. Specifically, this involves language identification, keyword extraction, and contextual understanding.

[0042] Step 3:

[0043] Based on the analysis results, the server references the corresponding waste classification rules from the database along with regional information to identify the type of waste and the appropriate disposal method.

[0044] Step 4:

[0045] Based on the classification method identified by the server, it generates instructions for the user and creates responses such as, "This plastic is classified as combustible waste."

[0046] Step 5:

[0047] The server generates a response and sends it to the user in real time, displaying the answer on the chatbot interface.

[0048] Step 6:

[0049] Users use a smartphone app to take pictures of waste and send them to a server via the app.

[0050] Step 7:

[0051] The server receives the transmitted image data and performs preprocessing to make it ready for analysis. This includes adjusting the resolution and removing noise.

[0052] Step 8:

[0053] The server analyzes the processed images using image recognition technology to identify the material and components of the waste.

[0054] Step 9:

[0055] Based on the analysis results, the server determines the optimal waste classification method and generates suggestions such as, "Please separate this packaging into paper and plastic before disposal."

[0056] Step 10:

[0057] The server generates suggestions, which are then sent to the user's terminal and visualized on the application interface for the user to see.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] In modern society, improper classification of materials leads to environmental problems and waste of resources. This problem is difficult for users to address appropriately because different rules and information exist in different regions. Furthermore, manual classification of composite materials is particularly difficult, requiring an efficient and accurate solution.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for an information processing device to analyze queries using natural language processing technology and instruct the user on an appropriate method of classifying materials by referring to rules based on geographical information, and means for analyzing visual information of materials acquired by the device using image recognition technology and means for enabling the user to easily classify the materials. As a result, users can accurately classify materials based on the rules of their local area, reducing adverse environmental impacts and enabling efficient resource utilization.

[0063] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[0064] The term "information processing device" refers to any device that has the function of inputting, processing, and outputting data.

[0065] "Inquiry" refers to a question or request that a user makes to an information processing device.

[0066] "Geographical information" refers to data and knowledge about a specific region, and this information includes the rules and systems specific to that region.

[0067] A "rule" is a set of rules or guidelines established for a specific purpose.

[0068] "User" refers to an individual or organization that uses this system.

[0069] "Materials" refers to all objects that contain information or data, including waste.

[0070] "Image recognition technology" is a technology in which a computer analyzes image data, extracts information, and recognizes it.

[0071] "Visual information" refers to information that is structured as image data.

[0072] "Analysis results" refer to conclusions and knowledge derived from the input data.

[0073] A "composite material" refers to a material composed of multiple materials with different properties combined together.

[0074] This invention is an information processing system for users to accurately classify materials. This system mainly includes an AI conversation program that can operate continuously and application software for mobile devices, which work together to provide users with appropriate instructions for classifying materials.

[0075] Users can use their mobile phones or computers to make inquiries about document classification via an AI conversational program. These inquiries are analyzed by the server using natural language processing technology, extracting specific keywords and geographical information. Based on this extracted information, the server consults geographical rules and instructs the user on the most appropriate classification method.

[0076] For example, if a user asks, "How should I dispose of this plastic?", the server can identify the keyword "plastic," look up local information, and return instructions such as "classify it as combustible waste."

[0077] Furthermore, when a user uses a mobile device application to capture visual information of a composite material, that visual data is sent from the device to the server. The server uses image recognition technology to analyze this visual data and identify the material and shape of the material. Based on this, the server can provide instructions to the user, such as "Please separate this packaging into paper and plastic before disposal."

[0078] This system can meet the needs of many users by supporting multiple languages. By utilizing a generative AI model, the system can quickly analyze prompt sentences and efficiently perform information processing and classification instructions.

[0079] A possible example of a specific prompt message would be, "How should I dispose of metal products?" In response to this inquiry, the server would instruct the user on the appropriate disposal method based on geographical regulations. This would enable the user to accurately classify and dispose of materials in their local area.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The user enters a query into the AI ​​conversation program using a mobile device or computer. For example, they might enter a query like, "How should I dispose of this plastic?" This query is then sent to the system as input data.

[0083] Step 2:

[0084] The server receives queries sent by users and performs natural language processing using a generative AI model. Here, the query is analyzed to extract keywords such as "plastic." This data processing then outputs the extracted keywords and geographical information.

[0085] Step 3:

[0086] The server queries a geographical rules database based on the extracted keywords and geographical information. During information processing, it refers to relevant waste classification rules to identify the optimal classification method. As a result, output data is generated to provide instructions to the user.

[0087] Step 4:

[0088] The server uses the obtained output data to send waste classification instructions to the user. Specifically, it sends clear instructions, such as "classify as combustible resources," as text messages to the user's terminal.

[0089] Step 5:

[0090] When a user provides details of a document using images, they take a picture of the document using the camera function of their mobile device. This visual information is then sent to the server via the device as input data.

[0091] Step 6:

[0092] The server analyzes the received visual information using image recognition technology. It processes the image data to identify the material and shape of the object. This analysis generates output data regarding the type of material.

[0093] Step 7:

[0094] Based on the results of image analysis, the server provides the user with instructions for appropriate waste classification. For example, it sends the user specific instructions such as, "Please separate this packaging into paper and plastic before disposal." This information is output to the user's terminal, enabling accurate classification of the materials.

[0095] (Application Example 1)

[0096] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0097] In modern living environments, the diversification of waste necessitates its proper classification. However, the increasing complexity of waste types and differing regulations in various regions make it difficult for individual users to accurately classify their waste. Furthermore, in industrial environments, manual waste classification is inefficient, and addressing labor shortages is desirable. Therefore, systems and methods for accurately and efficiently classifying waste are needed in both personal and industrial settings.

[0098] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0099] In this invention, the server includes means for analyzing user inquiries using natural language processing technology, means for instructing the user on the correct method of waste classification by referring to regional waste sorting regulations, means for analyzing images of waste taken by the user using image recognition technology, and means for controlling automated machinery in an industrial environment to physically classify the waste. This enables efficient and accurate waste classification in both personal and industrial settings.

[0100] "Natural language processing technology" is a technology that allows computers to analyze human language and understand its meaning.

[0101] "Regional waste sorting regulations" are rules concerning the classification and disposal of waste that are enforced in a specific region.

[0102] "Image recognition technology" is a technique in which a computer analyzes image data and identifies the objects and features contained within it.

[0103] "User" refers to an individual or legal entity that operates or utilizes this system.

[0104] "Industrial environment" refers to environments related to manufacturing, such as factories and production lines.

[0105] "Controlling automated machinery" refers to operating a machine based on a program to perform a specific task.

[0106] A description of the embodiment for carrying out the invention will be provided.

[0107] This invention is a system that assists users in accurately classifying household waste. The system efficiently responds to user inquiries by combining natural language processing and image recognition technologies. It also enables the physical classification of waste in industrial environments by controlling automated machinery.

[0108] The server first analyzes the text data sent from the user's terminal using natural language processing technology (specifically, advanced natural language processing models) to extract key information. This information includes regional waste sorting rules, which serve as a basis for the user to determine how to classify their waste. The server also analyzes the waste images received from the user's terminal using image recognition technology (specifically, state-of-the-art image processing libraries) to identify the material and shape. This allows the server to provide the user with specific instructions for waste classification.

[0109] In industrial settings, servers transmit control signals to automated machinery to classify recognized waste into appropriate categories. This includes identifying the type of waste material and operating the machinery accordingly to perform the classification process.

[0110] For example, when a user sends an image of a plastic bottle using their smartphone, the server recognizes the material and provides instructions to classify it as "plastic waste" based on local regulations. These instructions are then transmitted to the user or industrial robots, enabling accurate waste classification. Generative AI models can also be utilized with prompts such as, "Explain a system where a factory robot recognizes waste and automatically classifies it based on local regulations."

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The user uses a terminal to input and submit a question about waste. The input is natural language text. The server receives this text data and analyzes it using natural language processing techniques. Specifically, it extracts keywords from the user's question and compares them with regional waste sorting regulations. The output is basic information necessary for waste classification.

[0114] Step 2:

[0115] The user takes a picture of the waste using a device and sends it to the server. The server analyzes the image data using image recognition technology to identify the material and characteristics of the waste. This analysis processes the data to recognize the material and shape of the objects in the image. The output is the identified material information.

[0116] Step 3:

[0117] The server combines the keywords obtained in Step 1 with the material information identified in Step 2, consults regional waste sorting regulations, and determines the most appropriate disposal method. In this step, the server queries the regulations database internally and generates specific instructions from the matched results. The output is specific disposal instructions for the user or industrial machinery.

[0118] Step 4:

[0119] The server sends and displays the generated instructions in text format to the user's terminal. When used in an industrial environment, the instructions are also sent as control signals to automated machinery, initiating the physical sorting of waste. This ensures the automated machinery operates in a way that properly sorts the waste. The output consists of the instructions displayed to the user and the start of the automated machinery's operation.

[0120] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0121] This invention is an AI assistant system that combines natural language processing technology, image recognition technology, and an emotion engine to help users accurately and efficiently sort household waste. The system functions at the core of a 24 / 7 AI chatbot and smartphone application, supporting various user interactions.

[0122] Users can ask the AI ​​chatbot questions about waste classification via their smartphone or PC. The server analyzes these questions using natural language processing technology to understand relevant keywords and context. The analyzed information is then cross-referenced with a database of regional waste classification rules. The server then utilizes an emotion engine to detect the emotions expressed in the text accompanying the user's question. For example, if the user appears confused, the AI ​​chatbot adjusts its tone to provide additional information in a gentler manner.

[0123] As a concrete example, suppose a user expresses anxiety, saying, "I don't know what to do with this bottle cap." The server extracts "bottle cap" as a keyword using natural language processing, and the emotion engine recognizes the user's anxiety. In this case, the server generates a response that includes encouraging information such as, "Please calm down. Bottle caps are usually classified as recyclable waste."

[0124] Furthermore, users can take pictures of waste materials via a smartphone app and send them to a server. The server preprocesses the image data and analyzes it using image recognition technology. This analysis identifies the material and composition of the waste. Based on the analysis results, the server suggests an appropriate classification method for the waste and sends it to the user. User reactions are also monitored by an emotion engine, and the interaction is adjusted as needed.

[0125] By using such a system, users can easily learn the correct way to classify waste and reduce emotional frustration during the process. This invention has the effect of improving the user experience, increasing recycling efficiency, and reducing environmental impact.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] Users use their smartphones or PCs to input and submit questions about waste management to an AI chatbot.

[0129] Step 2:

[0130] The server receives text sent by the user and analyzes it using natural language processing techniques. This analysis extracts keywords from the text and understands the intent of the question.

[0131] Step 3:

[0132] Based on the extracted keywords and intent, the server accesses a regional waste classification rules database to search for information regarding appropriate classification.

[0133] Step 4:

[0134] The server uses an emotion engine to recognize the user's emotional state from their questions and statements. For example, if the user is showing signs of confusion or anxiety, the server will capture those emotions.

[0135] Step 5:

[0136] The server generates responses based on regional classification information and the results of the emotion engine's analysis. If necessary, it considers the user's emotional state and adds words of encouragement or additional explanations.

[0137] Step 6:

[0138] The server sends the generated response to the user in real time, and it is displayed on the chatbot interface.

[0139] Step 7:

[0140] Users use a smartphone app to take pictures of the waste they want to classify and send them to the server through the application.

[0141] Step 8:

[0142] The server verifies the received image data, performs necessary preprocessing, and prepares the image for analysis. This preprocessing includes adjusting the image resolution and denoising.

[0143] Step 9:

[0144] The server analyzes the pre-processed images using image recognition technology to identify the material and components of the waste.

[0145] Step 10:

[0146] Based on the image analysis results, the server determines the appropriate waste classification method and generates specific suggestions. The emotion engine is then used again to confirm the user's emotions and adjust the suggestions based on that feedback.

[0147] Step 11:

[0148] The server sends the generated classification method to the terminal, and the application visually displays the method to the user. It uses diagrams and user-friendly language to guide the user in an easy-to-understand manner.

[0149] (Example 2)

[0150] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0151] The classification of household waste is subject to different rules depending on the region, which can be complex and difficult for users to understand. Furthermore, standard waste classification support systems often fail to consider the user's feelings, leading to frustration. In addition, the lack of multilingual support and the inability to classify composite material waste are also challenges.

[0152] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0153] In this invention, the server includes means for analyzing user questions using natural language processing technology, means for analyzing images of waste using image recognition technology, and emotion engine means for detecting the user's emotional state and adjusting the response content. This makes it possible for the user to classify waste accurately and easily while taking their emotions into consideration.

[0154] "Natural language processing technology" refers to the technology that enables computers to analyze, understand, and generate human language.

[0155] "Regional waste classification regulations" are rules that specify the waste classification methods and related regulations applicable to a particular region.

[0156] "Image recognition technology" is a technology that uses computers to analyze image data and identify or classify its content.

[0157] An "emotion engine" is a technology that analyzes and detects emotions from input text and other data, and reflects them in the output.

[0158] A "generative AI model" is an algorithm that uses machine learning to automatically generate natural-sounding text and responses for specific tasks, similar to those produced by humans.

[0159] This invention is implemented as an AI system combining natural language processing technology, image recognition technology, and an emotion engine. This system is designed to allow users to understand the correct way to classify waste by sending questions and images related to waste via a smartphone or PC.

[0160] Users can use their smartphones or PCs (devices) to ask questions about waste classification through an AI chatbot. The device provides an interface for sending questions and images of waste to the server.

[0161] The server analyzes received questions using natural language processing techniques. This analysis utilizes generative AI models (e.g., BERT and GPT) to extract keywords and context from user questions and compare them with a regional waste classification rules database. This process allows the server to understand the user's intent and derive appropriate classification information. Furthermore, an emotion engine can be used to detect the user's emotional state and adjust the response accordingly.

[0162] Furthermore, the server analyzes the images of waste submitted by the user using image recognition technology. The image data is preprocessed to identify the material and composition of the waste. Based on the analysis results, an appropriate classification method for the waste is then generated and sent to the user in an appropriate tone through an emotion engine.

[0163] As a concrete example of using this system, consider a scenario where a user sends a text message asking, "Can this plastic be recycled?" The server analyzes the question using natural language processing technology, compares it to local classification rules, and provides the user with appropriate classification information. Furthermore, if the user takes a picture and sends it, the server can suggest the correct classification method through image recognition technology.

[0164] These factors enable users to sort waste accurately and quickly in an emotionally sensitive manner, thereby improving the efficiency of recycling.

[0165] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0166] Step 1:

[0167] Users use their smartphones or PCs (devices) to send questions about waste classification and images of waste to an AI chatbot. Questions are sent as text input, and images are sent in standard image file formats. The device then forwards this data to the server. The server processes the received data as wireless output.

[0168] Step 2:

[0169] The server analyzes the received text data using natural language processing techniques. Specifically, it uses a generative AI model to extract keywords and key context from the input text. Through this data processing, the server understands the gist of the question and identifies keywords related to waste (e.g., "bottle caps"). The output generates a list of analyzed keywords and contextual information.

[0170] Step 3:

[0171] The server compares the results of natural language processing with a regional waste classification rules database. This step searches for appropriate classification rules based on the analyzed keywords. As a data calculation, it derives optimal waste classification information based on the matching results. As output, it prepares a waste classification guide for the user.

[0172] Step 4:

[0173] The server uses an emotion engine to analyze the user's emotional state. Specifically, it performs emotion analysis on the text sent by the user to detect emotional elements such as anxiety and reassurance. This data processing prepares the server to generate a response in an appropriate tone based on the user's emotions. The output is a determined response tone based on emotion.

[0174] Step 5:

[0175] The server preprocesses the image data submitted by the user and analyzes its content using image recognition technology. The image data is first converted to the required format and then applied to an object recognition algorithm. This identifies the material and composition of the waste. The output generates the analyzed material information.

[0176] Step 6:

[0177] The server generates responses to the user using a generative AI model based on natural language processing, image recognition, and sentiment analysis. Specifically, the response content is optimized and constructed in a tone that corresponds to the user's emotions. As output, a final response message is prepared for sending to the user.

[0178] Step 7:

[0179] The server sends the generated response message to the terminal. The terminal displays this message to the user, allowing the user to immediately learn the proper way to classify waste. The output provides organized information that is displayed in the user interface.

[0180] (Application Example 2)

[0181] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0182] In logistics and factory settings, proper waste classification is crucial, but incorrect classification can occur if employees are not familiar with waste types or local regulations. Furthermore, waste classification can be stressful, increasing the burden on employees. In addition, in environments where multiple languages ​​are used, language barriers hinder communication, highlighting the need to overcome these challenges.

[0183] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0184] In this invention, the server includes means for analyzing user inquiries using natural language processing technology and referring to regional waste classification rules, means for analyzing images of waste taken by the user using image recognition technology, and means for detecting the user's emotional state using emotion recognition technology and providing information in an appropriate tone. This enables users to easily and accurately classify waste, overcoming language and emotional barriers.

[0185] "Natural language processing technology" is a technology that enables computers to understand and interpret human language.

[0186] "Waste classification regulations" are standards established for each region to properly classify waste.

[0187] "Image recognition technology" is a technology that uses computers to analyze image data and recognize objects and features.

[0188] "Emotion recognition technology" is a technology that detects human emotions from voice or text.

[0189] A "user" is an individual or organization that uses the system to classify waste.

[0190] A "device" is an electronic device that allows users to visually confirm information.

[0191] A "parsable format" is a data format optimized for computers to process data effectively.

[0192] This invention provides an AI assistant system that helps users accurately classify waste. The system includes a server, a user terminal (a visual device such as smart glasses), and a communication network.

[0193] The server processes input from each user using natural language processing, image recognition, and emotion recognition technologies. When a user scans waste using smart glasses or a smartphone, the image is sent to the server. The server analyzes the image using image recognition technology to identify the type of waste. Furthermore, the server uses natural language processing to analyze questions entered by the user via voice and generates answers based on regional waste classification rules.

[0194] Furthermore, emotion recognition technology determines the emotions a user expresses in questions and responses, and adjusts the information provided in an appropriate tone to reduce user stress. This allows users to understand and implement proper waste sorting methods without feeling stressed.

[0195] As a concrete example, in a logistics center, when a user scans a cardboard box using smart glasses, the system immediately notifies the user that the cardboard is recyclable. If the user asks, "How should I dispose of it?", the system provides persuasive guidance in a gentle, empathetic tone.

[0196] An example of a prompt when using a generative AI model to generate responses that respond to user emotions is as follows: "Generate a gentle-toned AI response to a frequently asked question from employees regarding waste classification for smart glasses at a logistics center."

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] The user wears smart glasses and places the waste object in their field of vision. The smart glasses use a built-in camera to capture an image of the waste object. The captured image data is transmitted to a server via wireless communication. In this case, the input is the image data of the waste object, and the output is the image data transmitted to the server.

[0200] Step 2:

[0201] The server receives the image data and uses image recognition technology to analyze the material and shape of the waste. This analysis process compares patterns and features in the image with a database to identify the type of waste. The input is the transmitted image data, and the output is the waste classification result. The server's specific actions involve image processing using an analysis library and the application of specific algorithms.

[0202] Step 3:

[0203] The user sends a question to the server using the voice input function. The question is sent to the server as audio data from the smart glasses. The server receives this audio data, converts it to text using natural language processing techniques, and analyzes the intent of the question. The input is audio data, and the output is an appropriate answer to the question. The specific operation involves the use of speech recognition software.

[0204] Step 4:

[0205] The server uses emotion recognition technology to detect the user's emotional state. This is a process that analyzes voice and text data to evaluate the user's emotions. Through this process, it determines whether the user is experiencing stress and adjusts the tone of its response accordingly. The input is the user's text data, and the output is the emotion evaluation result. The specific operation involves data analysis by the emotion recognition engine.

[0206] Step 5:

[0207] The server uses a generative AI model to generate waste classification instruction messages for the user, taking into account the sentiment assessment results. These messages are tailored to a gentle tone and are generated using prompts. The input is the sentiment assessment results and data related to the question, and the output is a notification message for the user.

[0208] Step 6:

[0209] Ultimately, the server sends the generated instruction message to the smart glasses, displaying it directly in the user's field of view. The user can then use this information to properly classify waste. The input is the generated instruction message, and the output is the visual information displayed on the smart glasses. Specific operations include data transmission via a communication protocol and information display on the device.

[0210] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0211] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0212] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0213] [Second Embodiment]

[0214] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0215] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0216] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0217] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0218] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0219] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0220] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0221] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0222] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0223] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0224] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0225] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0226] This invention is implemented as an AI assistant system for users to accurately classify household waste. The system mainly consists of a 24 / 7 AI chatbot and a smartphone application, which work together to provide users with appropriate waste classification instructions.

[0227] Users submit questions about waste classification to the system via an AI chatbot using their smartphone or PC. These questions are analyzed by the server using natural language processing technology, and specific keywords and regional information are extracted. Based on this information, the server refers to regional waste classification regulations and instructs the user on the most appropriate classification method.

[0228] For example, if a user asks, "How should I dispose of this plastic?", the server detects the keyword "plastic," queries the local database, and returns instructions such as "Put it in the combustible waste bin."

[0229] Additionally, when a user takes a picture of composite material waste using a smartphone app, the device sends the image data to a server. The server analyzes the image using image recognition technology to identify the material and shape of the waste. Based on the analysis results, the server provides the user with instructions such as, "Please separate this packaging into paper and plastic before disposal."

[0230] In this way, the system provides immediate answers to user questions and can meet the needs of a wide range of residents through multilingual support. This reduces the effort required for traditional manual waste sorting and promotes proper recycling.

[0231] The following describes the processing flow.

[0232] Step 1:

[0233] Users use their smartphones or PCs to input and submit questions about waste classification to an AI chatbot.

[0234] Step 2:

[0235] The server receives questions submitted by users and analyzes the text data that makes up those questions using natural language processing techniques. Specifically, this involves language identification, keyword extraction, and contextual understanding.

[0236] Step 3:

[0237] Based on the analysis results, the server references the corresponding waste classification rules from the database along with regional information to identify the type of waste and the appropriate disposal method.

[0238] Step 4:

[0239] Based on the classification method identified by the server, it generates instructions for the user and creates responses such as, "This plastic is classified as combustible waste."

[0240] Step 5:

[0241] The server generates a response and sends it to the user in real time, displaying the answer on the chatbot interface.

[0242] Step 6:

[0243] Users use a smartphone app to take pictures of waste and send them to a server via the app.

[0244] Step 7:

[0245] The server receives the transmitted image data and performs preprocessing to make it ready for analysis. This includes adjusting the resolution and removing noise.

[0246] Step 8:

[0247] The server analyzes the processed images using image recognition technology to identify the material and components of the waste.

[0248] Step 9:

[0249] Based on the analysis results, the server determines the optimal waste classification method and generates suggestions such as, "Please separate this packaging into paper and plastic before disposal."

[0250] Step 10:

[0251] The server generates suggestions, which are then sent to the user's terminal and visualized on the application interface for the user to see.

[0252] (Example 1)

[0253] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0254] In modern society, improper classification of materials leads to environmental problems and waste of resources. This problem is difficult for users to address appropriately because different rules and information exist in different regions. Furthermore, manual classification of composite materials is particularly difficult, requiring an efficient and accurate solution.

[0255] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0256] In this invention, the server includes means for an information processing device to analyze queries using natural language processing technology and instruct the user on an appropriate method of classifying materials by referring to rules based on geographical information, and means for analyzing visual information of materials acquired by the device using image recognition technology and means for enabling the user to easily classify the materials. As a result, users can accurately classify materials based on the rules of their local area, reducing adverse environmental impacts and enabling efficient resource utilization.

[0257] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[0258] The term "information processing device" refers to any device that has the function of inputting, processing, and outputting data.

[0259] "Inquiry" refers to a question or request that a user makes to an information processing device.

[0260] "Geographical information" refers to data and knowledge about a specific region, and this information includes the rules and systems specific to that region.

[0261] A "rule" is a set of rules or guidelines established for a specific purpose.

[0262] "User" refers to an individual or organization that uses this system.

[0263] "Materials" refers to all objects that contain information or data, including waste.

[0264] "Image recognition technology" is a technology in which a computer analyzes image data, extracts information, and recognizes it.

[0265] "Visual information" refers to information that is structured as image data.

[0266] "Analysis results" refer to conclusions and knowledge derived from the input data.

[0267] A "composite material" refers to a material composed of multiple materials with different properties combined together.

[0268] This invention is an information processing system for users to accurately classify materials. This system mainly includes an AI conversation program that can operate continuously and application software for mobile devices, which work together to provide users with appropriate instructions for classifying materials.

[0269] Users can use their mobile phones or computers to make inquiries about document classification via an AI conversational program. These inquiries are analyzed by the server using natural language processing technology, extracting specific keywords and geographical information. Based on this extracted information, the server consults geographical rules and instructs the user on the most appropriate classification method.

[0270] For example, if a user asks, "How should I dispose of this plastic?", the server can identify the keyword "plastic," look up local information, and return instructions such as "classify it as combustible waste."

[0271] Furthermore, when a user uses a mobile device application to capture visual information of a composite material, that visual data is sent from the device to the server. The server uses image recognition technology to analyze this visual data and identify the material and shape of the material. Based on this, the server can provide instructions to the user, such as "Please separate this packaging into paper and plastic before disposal."

[0272] This system can meet the needs of many users by supporting multiple languages. By utilizing a generative AI model, the system can quickly analyze prompt sentences and efficiently perform information processing and classification instructions.

[0273] A possible example of a specific prompt message would be, "How should I dispose of metal products?" In response to this inquiry, the server would instruct the user on the appropriate disposal method based on geographical regulations. This would enable the user to accurately classify and dispose of materials in their local area.

[0274] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0275] Step 1:

[0276] The user enters a query into the AI ​​conversation program using a mobile device or computer. For example, they might enter a query like, "How should I dispose of this plastic?" This query is then sent to the system as input data.

[0277] Step 2:

[0278] The server receives the query sent by the user and performs natural language processing using the generative AI model. Here, the question text is analyzed to extract keywords such as "plastic". Through this data processing, the extracted keywords and geographical information are output.

[0279] Step 3:

[0280] The server queries the geographical rule database based on the extracted keywords and geographical information. In information processing, relevant waste classification rules are referred to identify the optimal classification method. As a result, output data for instructing the user is generated.

[0281] Step 4:

[0282] The server uses the obtained output data to send a waste classification instruction to the user. Specifically, a clear instruction such as "classify as combustible resources" is delivered as a text message to the user's terminal.

[0283] Step 5:

[0284] When the user provides details of the document with an image, the camera function of the mobile terminal is used to take a photo of the document. This visual information is sent to the server via the terminal as input data.

[0285] Step 6:

[0286] The server analyzes the received visual information using image recognition technology. Here, the image data is processed to identify the material and shape of the document. Through this analysis, output data regarding the type of material is generated.

[0287] Step 7:

[0288] Based on the results of image analysis, the server provides the user with instructions for appropriate waste classification. For example, it sends the user specific instructions such as, "Please separate this packaging into paper and plastic before disposal." This information is output to the user's terminal, enabling accurate classification of the materials.

[0289] (Application Example 1)

[0290] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0291] In modern living environments, the diversification of waste necessitates its proper classification. However, the increasing complexity of waste types and differing regulations in various regions make it difficult for individual users to accurately classify their waste. Furthermore, in industrial environments, manual waste classification is inefficient, and addressing labor shortages is desirable. Therefore, systems and methods for accurately and efficiently classifying waste are needed in both personal and industrial settings.

[0292] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0293] In this invention, the server includes means for analyzing user inquiries using natural language processing technology, means for instructing the user on the correct method of waste classification by referring to regional waste sorting regulations, means for analyzing images of waste taken by the user using image recognition technology, and means for controlling automated machinery in an industrial environment to physically classify the waste. This enables efficient and accurate waste classification in both personal and industrial settings.

[0294] "Natural language processing technology" is a technology that allows computers to analyze human language and understand its meaning.

[0295] "Regional waste sorting regulations" are rules concerning the classification and disposal of waste that are enforced in a specific region.

[0296] "Image recognition technology" is a technique in which a computer analyzes image data and identifies the objects and features contained within it.

[0297] "User" refers to an individual or legal entity that operates or utilizes this system.

[0298] "Industrial environment" refers to environments related to manufacturing, such as factories and production lines.

[0299] "Controlling automated machinery" refers to operating a machine based on a program to perform a specific task.

[0300] A description of the embodiment for carrying out the invention will be provided.

[0301] This invention is a system that assists users in accurately classifying household waste. The system efficiently responds to user inquiries by combining natural language processing and image recognition technologies. It also enables the physical classification of waste in industrial environments by controlling automated machinery.

[0302] The server first analyzes the text data sent from the user's terminal using natural language processing technology (specifically, advanced natural language processing models) to extract key information. This information includes regional waste sorting rules, which serve as a basis for the user to determine how to classify their waste. The server also analyzes the waste images received from the user's terminal using image recognition technology (specifically, state-of-the-art image processing libraries) to identify the material and shape. This allows the server to provide the user with specific instructions for waste classification.

[0303] In industrial settings, servers transmit control signals to automated machinery to classify recognized waste into appropriate categories. This includes identifying the type of waste material and operating the machinery accordingly to perform the classification process.

[0304] As a specific example, when a user uses a smartphone to send an image of a PET bottle, the server recognizes the material and provides an instruction to classify it as "plastic waste" based on local regulations. When this instruction is conveyed to the user or an industrial robot, accurate waste classification is achieved. It is also possible to utilize a generative AI model with a prompt sentence such as "Explain a system where a factory robot recognizes waste and automatically classifies it based on local regulations."

[0305] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0306] Step 1:

[0307] The user uses a terminal to input and send a question about the waste. The input is text in natural language. The server receives this text data and analyzes it using natural language processing technology. Specifically, keywords included in the question sentence from the user are extracted and compared with waste sorting rules by region. The output is the basic information necessary for waste classification.

[0308] Step 2:

[0309] The user uses a terminal to take a picture of the waste and send it to the server. The server analyzes the image data using image recognition technology to identify the material and characteristics of the waste. Through this analysis, data processing is performed to recognize the material and shape of the object shown in the image. The output is the identified material information.

[0310] Step 3:

[0311] The server combines the keywords obtained in Step 1 and the material information identified in Step 2, refers to the waste sorting rules by region, and determines the most appropriate waste disposal method. In this step, a query is made to the rule database inside the server, and a specific instruction is generated from the matched results. The output is a specific instruction on the waste disposal method for the user or industrial machinery.

[0312] Step 4:

[0313] The server sends and displays the generated instructions in text format to the user's terminal. When used in an industrial environment, the instructions are also sent as control signals to automated machinery, initiating the physical sorting of waste. This ensures the automated machinery operates in a way that properly sorts the waste. The output consists of the instructions displayed to the user and the start of the automated machinery's operation.

[0314] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0315] This invention is an AI assistant system that combines natural language processing technology, image recognition technology, and an emotion engine to help users accurately and efficiently sort household waste. The system functions at the core of a 24 / 7 AI chatbot and smartphone application, supporting various user interactions.

[0316] Users can ask the AI ​​chatbot questions about waste classification via their smartphone or PC. The server analyzes these questions using natural language processing technology to understand relevant keywords and context. The analyzed information is then cross-referenced with a database of regional waste classification rules. The server then utilizes an emotion engine to detect the emotions expressed in the text accompanying the user's question. For example, if the user appears confused, the AI ​​chatbot adjusts its tone to provide additional information in a gentler manner.

[0317] As a concrete example, suppose a user expresses anxiety, saying, "I don't know what to do with this bottle cap." The server extracts "bottle cap" as a keyword using natural language processing, and the emotion engine recognizes the user's anxiety. In this case, the server generates a response that includes encouraging information such as, "Please calm down. Bottle caps are usually classified as recyclable waste."

[0318] Furthermore, users can take pictures of waste materials via a smartphone app and send them to a server. The server preprocesses the image data and analyzes it using image recognition technology. This analysis identifies the material and composition of the waste. Based on the analysis results, the server suggests an appropriate classification method for the waste and sends it to the user. User reactions are also monitored by an emotion engine, and the interaction is adjusted as needed.

[0319] By using such a system, users can easily learn the correct way to classify waste and reduce emotional frustration during the process. This invention has the effect of improving the user experience, increasing recycling efficiency, and reducing environmental impact.

[0320] The following describes the processing flow.

[0321] Step 1:

[0322] Users use their smartphones or PCs to input and submit questions about waste management to an AI chatbot.

[0323] Step 2:

[0324] The server receives text sent by the user and analyzes it using natural language processing techniques. This analysis extracts keywords from the text and understands the intent of the question.

[0325] Step 3:

[0326] Based on the extracted keywords and intent, the server accesses a regional waste classification rules database to search for information regarding appropriate classification.

[0327] Step 4:

[0328] The server uses an emotion engine to recognize the user's emotional state from their questions and statements. For example, if the user is showing signs of confusion or anxiety, the server will capture those emotions.

[0329] Step 5:

[0330] The server generates responses based on regional classification information and the results of the emotion engine's analysis. If necessary, it considers the user's emotional state and adds words of encouragement or additional explanations.

[0331] Step 6:

[0332] The server sends the generated response to the user in real time, and it is displayed on the chatbot interface.

[0333] Step 7:

[0334] Users use a smartphone app to take pictures of the waste they want to classify and send them to the server through the application.

[0335] Step 8:

[0336] The server verifies the received image data, performs necessary preprocessing, and prepares the image for analysis. This preprocessing includes adjusting the image resolution and denoising.

[0337] Step 9:

[0338] The server analyzes the pre-processed images using image recognition technology to identify the material and components of the waste.

[0339] Step 10:

[0340] Based on the image analysis results, the server determines the appropriate waste classification method and generates specific suggestions. The emotion engine is then used again to confirm the user's emotions and adjust the suggestions based on that feedback.

[0341] Step 11:

[0342] The server sends the generated classification method to the terminal, and the application visually displays the method to the user. It uses diagrams and user-friendly language to guide the user in an easy-to-understand manner.

[0343] (Example 2)

[0344] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0345] The classification of household waste is subject to different rules depending on the region, which can be complex and difficult for users to understand. Furthermore, standard waste classification support systems often fail to consider the user's feelings, leading to frustration. In addition, the lack of multilingual support and the inability to classify composite material waste are also challenges.

[0346] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0347] In this invention, the server includes means for analyzing user questions using natural language processing technology, means for analyzing images of waste using image recognition technology, and emotion engine means for detecting the user's emotional state and adjusting the response content. This makes it possible for the user to classify waste accurately and easily while taking their emotions into consideration.

[0348] "Natural language processing technology" refers to the technology that enables computers to analyze, understand, and generate human language.

[0349] "Regional waste classification regulations" are rules that specify the waste classification methods and related regulations applicable to a particular region.

[0350] "Image recognition technology" is a technology that uses computers to analyze image data and identify or classify its content.

[0351] An "emotion engine" is a technology that analyzes and detects emotions from input text and other data, and reflects them in the output.

[0352] A "generative AI model" is an algorithm that uses machine learning to automatically generate natural-sounding text and responses for specific tasks, similar to those produced by humans.

[0353] This invention is implemented as an AI system combining natural language processing technology, image recognition technology, and an emotion engine. This system is designed to allow users to understand the correct way to classify waste by sending questions and images related to waste via a smartphone or PC.

[0354] Users can use their smartphones or PCs (devices) to ask questions about waste classification through an AI chatbot. The device provides an interface for sending questions and images of waste to the server.

[0355] The server analyzes received questions using natural language processing techniques. This analysis utilizes generative AI models (e.g., BERT and GPT) to extract keywords and context from user questions and compare them with a regional waste classification rules database. This process allows the server to understand the user's intent and derive appropriate classification information. Furthermore, an emotion engine can be used to detect the user's emotional state and adjust the response accordingly.

[0356] Furthermore, the server analyzes the images of waste submitted by the user using image recognition technology. The image data is preprocessed to identify the material and composition of the waste. Based on the analysis results, an appropriate classification method for the waste is then generated and sent to the user in an appropriate tone through an emotion engine.

[0357] As a concrete example of using this system, consider a scenario where a user sends a text message asking, "Can this plastic be recycled?" The server analyzes the question using natural language processing technology, compares it to local classification rules, and provides the user with appropriate classification information. Furthermore, if the user takes a picture and sends it, the server can suggest the correct classification method through image recognition technology.

[0358] These factors enable users to sort waste accurately and quickly in an emotionally sensitive manner, thereby improving the efficiency of recycling.

[0359] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0360] Step 1:

[0361] Users use their smartphones or PCs (devices) to send questions about waste classification and images of waste to an AI chatbot. Questions are sent as text input, and images are sent in standard image file formats. The device then forwards this data to the server. The server processes the received data as wireless output.

[0362] Step 2:

[0363] The server analyzes the received text data using natural language processing techniques. Specifically, it uses a generative AI model to extract keywords and key context from the input text. Through this data processing, the server understands the gist of the question and identifies keywords related to waste (e.g., "bottle caps"). The output generates a list of analyzed keywords and contextual information.

[0364] Step 3:

[0365] The server compares the results of natural language processing with a regional waste classification rules database. This step searches for appropriate classification rules based on the analyzed keywords. As a data calculation, it derives optimal waste classification information based on the matching results. As output, it prepares a waste classification guide for the user.

[0366] Step 4:

[0367] The server uses an emotion engine to analyze the user's emotional state. Specifically, it performs emotion analysis on the text sent by the user to detect emotional elements such as anxiety and reassurance. This data processing prepares the server to generate a response in an appropriate tone based on the user's emotions. The output is a determined response tone based on emotion.

[0368] Step 5:

[0369] The server preprocesses the image data submitted by the user and analyzes its content using image recognition technology. The image data is first converted to the required format and then applied to an object recognition algorithm. This identifies the material and composition of the waste. The output generates the analyzed material information.

[0370] Step 6:

[0371] The server generates responses to the user using a generative AI model based on natural language processing, image recognition, and sentiment analysis. Specifically, the response content is optimized and constructed in a tone that corresponds to the user's emotions. As output, a final response message is prepared for sending to the user.

[0372] Step 7:

[0373] The server sends the generated response message to the terminal. The terminal displays this message to the user, allowing the user to immediately learn the proper way to classify waste. The output provides organized information that is displayed in the user interface.

[0374] (Application Example 2)

[0375] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0376] In logistics and factory settings, proper waste classification is crucial, but incorrect classification can occur if employees are not familiar with waste types or local regulations. Furthermore, waste classification can be stressful, increasing the burden on employees. In addition, in environments where multiple languages ​​are used, language barriers hinder communication, highlighting the need to overcome these challenges.

[0377] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0378] In this invention, the server includes means for analyzing user inquiries using natural language processing technology and referring to regional waste classification rules, means for analyzing images of waste taken by the user using image recognition technology, and means for detecting the user's emotional state using emotion recognition technology and providing information in an appropriate tone. This enables users to easily and accurately classify waste, overcoming language and emotional barriers.

[0379] "Natural language processing technology" is a technology that enables computers to understand and interpret human language.

[0380] "Waste classification regulations" are standards established for each region to properly classify waste.

[0381] "Image recognition technology" is a technology that uses computers to analyze image data and recognize objects and features.

[0382] "Emotion recognition technology" is a technology that detects human emotions from voice or text.

[0383] A "user" is an individual or organization that uses the system to classify waste.

[0384] A "device" is an electronic device that allows users to visually confirm information.

[0385] A "parsable format" is a data format optimized for computers to process data effectively.

[0386] This invention provides an AI assistant system that helps users accurately classify waste. The system includes a server, a user terminal (a visual device such as smart glasses), and a communication network.

[0387] The server processes input from each user using natural language processing, image recognition, and emotion recognition technologies. When a user scans waste using smart glasses or a smartphone, the image is sent to the server. The server analyzes the image using image recognition technology to identify the type of waste. Furthermore, the server uses natural language processing to analyze questions entered by the user via voice and generates answers based on regional waste classification rules.

[0388] Furthermore, emotion recognition technology determines the emotions a user expresses in questions and responses, and adjusts the information provided in an appropriate tone to reduce user stress. This allows users to understand and implement proper waste sorting methods without feeling stressed.

[0389] As a concrete example, in a logistics center, when a user scans a cardboard box using smart glasses, the system immediately notifies the user that the cardboard is recyclable. If the user asks, "How should I dispose of it?", the system provides persuasive guidance in a gentle, empathetic tone.

[0390] An example of a prompt when using a generative AI model to generate responses that respond to user emotions is as follows: "Generate a gentle-toned AI response to a frequently asked question from employees regarding waste classification for smart glasses at a logistics center."

[0391] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0392] Step 1:

[0393] The user wears smart glasses and places the waste object in their field of vision. The smart glasses use a built-in camera to capture an image of the waste object. The captured image data is transmitted to a server via wireless communication. In this case, the input is the image data of the waste object, and the output is the image data transmitted to the server.

[0394] Step 2:

[0395] The server receives the image data and uses image recognition technology to analyze the material and shape of the waste. This analysis process compares patterns and features in the image with a database to identify the type of waste. The input is the transmitted image data, and the output is the waste classification result. The server's specific actions involve image processing using an analysis library and the application of specific algorithms.

[0396] Step 3:

[0397] The user sends a question to the server using the voice input function. The question is sent to the server as audio data from the smart glasses. The server receives this audio data, converts it to text using natural language processing techniques, and analyzes the intent of the question. The input is audio data, and the output is an appropriate answer to the question. The specific operation involves the use of speech recognition software.

[0398] Step 4:

[0399] The server uses emotion recognition technology to detect the user's emotional state. This is a process that analyzes voice and text data to evaluate the user's emotions. Through this process, it determines whether the user is experiencing stress and adjusts the tone of its response accordingly. The input is the user's text data, and the output is the emotion evaluation result. The specific operation involves data analysis by the emotion recognition engine.

[0400] Step 5:

[0401] The server uses a generative AI model to generate waste classification instruction messages for the user, taking into account the sentiment assessment results. These messages are tailored to a gentle tone and are generated using prompts. The input is the sentiment assessment results and data related to the question, and the output is a notification message for the user.

[0402] Step 6:

[0403] Ultimately, the server sends the generated instruction message to the smart glasses, displaying it directly in the user's field of view. The user can then use this information to properly classify waste. The input is the generated instruction message, and the output is the visual information displayed on the smart glasses. Specific operations include data transmission via a communication protocol and information display on the device.

[0404] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0405] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0406] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0407] [Third Embodiment]

[0408] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0409] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0410] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0411] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0412] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0413] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0414] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0415] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0416] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0417] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0418] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0419] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0420] This invention is implemented as an AI assistant system for users to accurately classify household waste. The system mainly consists of a 24 / 7 AI chatbot and a smartphone application, which work together to provide users with appropriate waste classification instructions.

[0421] Users submit questions about waste classification to the system via an AI chatbot using their smartphone or PC. These questions are analyzed by the server using natural language processing technology, and specific keywords and regional information are extracted. Based on this information, the server refers to regional waste classification regulations and instructs the user on the most appropriate classification method.

[0422] For example, if a user asks, "How should I dispose of this plastic?", the server detects the keyword "plastic," queries the local database, and returns instructions such as "Put it in the combustible waste bin."

[0423] Additionally, when a user takes a picture of composite material waste using a smartphone app, the device sends the image data to a server. The server analyzes the image using image recognition technology to identify the material and shape of the waste. Based on the analysis results, the server provides the user with instructions such as, "Please separate this packaging into paper and plastic before disposal."

[0424] In this way, the system provides immediate answers to user questions and can meet the needs of a wide range of residents through multilingual support. This reduces the effort required for traditional manual waste sorting and promotes proper recycling.

[0425] The following describes the processing flow.

[0426] Step 1:

[0427] Users use their smartphones or PCs to input and submit questions about waste classification to an AI chatbot.

[0428] Step 2:

[0429] The server receives questions submitted by users and analyzes the text data that makes up those questions using natural language processing techniques. Specifically, this involves language identification, keyword extraction, and contextual understanding.

[0430] Step 3:

[0431] Based on the analysis results, the server references the corresponding waste classification rules from the database along with regional information to identify the type of waste and the appropriate disposal method.

[0432] Step 4:

[0433] Based on the classification method identified by the server, it generates instructions for the user and creates responses such as, "This plastic is classified as combustible waste."

[0434] Step 5:

[0435] The server generates a response and sends it to the user in real time, displaying the answer on the chatbot interface.

[0436] Step 6:

[0437] Users use a smartphone app to take pictures of waste and send them to a server via the app.

[0438] Step 7:

[0439] The server receives the transmitted image data and performs preprocessing to make it ready for analysis. This includes adjusting the resolution and removing noise.

[0440] Step 8:

[0441] The server analyzes the processed images using image recognition technology to identify the material and components of the waste.

[0442] Step 9:

[0443] Based on the analysis results, the server determines the optimal waste classification method and generates suggestions such as, "Please separate this packaging into paper and plastic before disposal."

[0444] Step 10:

[0445] The server generates suggestions, which are then sent to the user's terminal and visualized on the application interface for the user to see.

[0446] (Example 1)

[0447] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0448] In modern society, improper classification of materials leads to environmental problems and waste of resources. This problem is difficult for users to address appropriately because different rules and information exist in different regions. Furthermore, manual classification of composite materials is particularly difficult, requiring an efficient and accurate solution.

[0449] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0450] In this invention, the server includes means for an information processing device to analyze queries using natural language processing technology and instruct the user on an appropriate method of classifying materials by referring to rules based on geographical information, and means for analyzing visual information of materials acquired by the device using image recognition technology and means for enabling the user to easily classify the materials. As a result, users can accurately classify materials based on the rules of their local area, reducing adverse environmental impacts and enabling efficient resource utilization.

[0451] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[0452] The term "information processing device" refers to any device that has the function of inputting, processing, and outputting data.

[0453] "Inquiry" refers to a question or request that a user makes to an information processing device.

[0454] "Geographical information" refers to data and knowledge about a specific region, and this information includes the rules and systems specific to that region.

[0455] A "rule" is a set of rules or guidelines established for a specific purpose.

[0456] "User" refers to an individual or organization that uses this system.

[0457] "Materials" refers to all objects that contain information or data, including waste.

[0458] "Image recognition technology" is a technology in which a computer analyzes image data, extracts information, and recognizes it.

[0459] "Visual information" refers to information that is structured as image data.

[0460] "Analysis results" refer to conclusions and knowledge derived from the input data.

[0461] A "composite material" refers to a material composed of multiple materials with different properties combined together.

[0462] This invention is an information processing system for users to accurately classify materials. This system mainly includes an AI conversation program that can operate continuously and application software for mobile devices, which work together to provide users with appropriate instructions for classifying materials.

[0463] Users can use their mobile phones or computers to make inquiries about document classification via an AI conversational program. These inquiries are analyzed by the server using natural language processing technology, extracting specific keywords and geographical information. Based on this extracted information, the server consults geographical rules and instructs the user on the most appropriate classification method.

[0464] For example, if a user asks, "How should I dispose of this plastic?", the server can identify the keyword "plastic," look up local information, and return instructions such as "classify it as combustible waste."

[0465] Furthermore, when a user uses a mobile device application to capture visual information of a composite material, that visual data is sent from the device to the server. The server uses image recognition technology to analyze this visual data and identify the material and shape of the material. Based on this, the server can provide instructions to the user, such as "Please separate this packaging into paper and plastic before disposal."

[0466] This system can meet the needs of many users by supporting multiple languages. By utilizing a generative AI model, the system can quickly analyze prompt sentences and efficiently perform information processing and classification instructions.

[0467] A possible example of a specific prompt message would be, "How should I dispose of metal products?" In response to this inquiry, the server would instruct the user on the appropriate disposal method based on geographical regulations. This would enable the user to accurately classify and dispose of materials in their local area.

[0468] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0469] Step 1:

[0470] The user enters a query into the AI ​​conversation program using a mobile device or computer. For example, they might enter a query like, "How should I dispose of this plastic?" This query is then sent to the system as input data.

[0471] Step 2:

[0472] The server receives queries sent by users and performs natural language processing using a generative AI model. Here, the query is analyzed to extract keywords such as "plastic." This data processing then outputs the extracted keywords and geographical information.

[0473] Step 3:

[0474] The server queries a geographical rules database based on the extracted keywords and geographical information. During information processing, it refers to relevant waste classification rules to identify the optimal classification method. As a result, output data is generated to provide instructions to the user.

[0475] Step 4:

[0476] The server uses the obtained output data to send waste classification instructions to the user. Specifically, it sends clear instructions, such as "classify as combustible resources," as text messages to the user's terminal.

[0477] Step 5:

[0478] When a user provides details of a document using images, they take a picture of the document using the camera function of their mobile device. This visual information is then sent to the server via the device as input data.

[0479] Step 6:

[0480] The server analyzes the received visual information using image recognition technology. It processes the image data to identify the material and shape of the object. This analysis generates output data regarding the type of material.

[0481] Step 7:

[0482] Based on the results of image analysis, the server provides the user with instructions for appropriate waste classification. For example, it sends the user specific instructions such as, "Please separate this packaging into paper and plastic before disposal." This information is output to the user's terminal, enabling accurate classification of the materials.

[0483] (Application Example 1)

[0484] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0485] In modern living environments, the diversification of waste necessitates its proper classification. However, the increasing complexity of waste types and differing regulations in various regions make it difficult for individual users to accurately classify their waste. Furthermore, in industrial environments, manual waste classification is inefficient, and addressing labor shortages is desirable. Therefore, systems and methods for accurately and efficiently classifying waste are needed in both personal and industrial settings.

[0486] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0487] In this invention, the server includes means for analyzing user inquiries using natural language processing technology, means for instructing the user on the correct method of waste classification by referring to regional waste sorting regulations, means for analyzing images of waste taken by the user using image recognition technology, and means for controlling automated machinery in an industrial environment to physically classify the waste. This enables efficient and accurate waste classification in both personal and industrial settings.

[0488] "Natural language processing technology" is a technology that allows computers to analyze human language and understand its meaning.

[0489] "Regional waste sorting regulations" are rules concerning the classification and disposal of waste that are enforced in a specific region.

[0490] "Image recognition technology" is a technique in which a computer analyzes image data and identifies the objects and features contained within it.

[0491] "User" refers to an individual or legal entity that operates or utilizes this system.

[0492] "Industrial environment" refers to environments related to manufacturing, such as factories and production lines.

[0493] "Controlling automated machinery" refers to operating a machine based on a program to perform a specific task.

[0494] A description of the embodiment for carrying out the invention will be provided.

[0495] This invention is a system that assists users in accurately classifying household waste. The system efficiently responds to user inquiries by combining natural language processing and image recognition technologies. It also enables the physical classification of waste in industrial environments by controlling automated machinery.

[0496] The server first analyzes the text data sent from the user's terminal using natural language processing technology (specifically, advanced natural language processing models) to extract key information. This information includes regional waste sorting rules, which serve as a basis for the user to determine how to classify their waste. The server also analyzes the waste images received from the user's terminal using image recognition technology (specifically, state-of-the-art image processing libraries) to identify the material and shape. This allows the server to provide the user with specific instructions for waste classification.

[0497] In industrial settings, servers transmit control signals to automated machinery to classify recognized waste into appropriate categories. This includes identifying the type of waste material and operating the machinery accordingly to perform the classification process.

[0498] For example, when a user sends an image of a plastic bottle using their smartphone, the server recognizes the material and provides instructions to classify it as "plastic waste" based on local regulations. These instructions are then transmitted to the user or industrial robots, enabling accurate waste classification. Generative AI models can also be utilized with prompts such as, "Explain a system where a factory robot recognizes waste and automatically classifies it based on local regulations."

[0499] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0500] Step 1:

[0501] The user uses a terminal to input and submit a question about waste. The input is natural language text. The server receives this text data and analyzes it using natural language processing techniques. Specifically, it extracts keywords from the user's question and compares them with regional waste sorting regulations. The output is basic information necessary for waste classification.

[0502] Step 2:

[0503] The user takes a picture of the waste using a device and sends it to the server. The server analyzes the image data using image recognition technology to identify the material and characteristics of the waste. This analysis processes the data to recognize the material and shape of the objects in the image. The output is the identified material information.

[0504] Step 3:

[0505] The server combines the keywords obtained in Step 1 with the material information identified in Step 2, consults regional waste sorting regulations, and determines the most appropriate disposal method. In this step, the server queries the regulations database internally and generates specific instructions from the matched results. The output is specific disposal instructions for the user or industrial machinery.

[0506] Step 4:

[0507] The server sends and displays the generated instructions in text format to the user's terminal. When used in an industrial environment, the instructions are also sent as control signals to automated machinery, initiating the physical sorting of waste. This ensures the automated machinery operates in a way that properly sorts the waste. The output consists of the instructions displayed to the user and the start of the automated machinery's operation.

[0508] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0509] This invention is an AI assistant system that combines natural language processing technology, image recognition technology, and an emotion engine to help users accurately and efficiently sort household waste. The system functions at the core of a 24 / 7 AI chatbot and smartphone application, supporting various user interactions.

[0510] Users can ask the AI ​​chatbot questions about waste classification via their smartphone or PC. The server analyzes these questions using natural language processing technology to understand relevant keywords and context. The analyzed information is then cross-referenced with a database of regional waste classification rules. The server then utilizes an emotion engine to detect the emotions expressed in the text accompanying the user's question. For example, if the user appears confused, the AI ​​chatbot adjusts its tone to provide additional information in a gentler manner.

[0511] As a concrete example, suppose a user expresses anxiety, saying, "I don't know what to do with this bottle cap." The server extracts "bottle cap" as a keyword using natural language processing, and the emotion engine recognizes the user's anxiety. In this case, the server generates a response that includes encouraging information such as, "Please calm down. Bottle caps are usually classified as recyclable waste."

[0512] Furthermore, users can take pictures of waste materials via a smartphone app and send them to a server. The server preprocesses the image data and analyzes it using image recognition technology. This analysis identifies the material and composition of the waste. Based on the analysis results, the server suggests an appropriate classification method for the waste and sends it to the user. User reactions are also monitored by an emotion engine, and the interaction is adjusted as needed.

[0513] By using such a system, users can easily learn the correct way to classify waste and reduce emotional frustration during the process. This invention has the effect of improving the user experience, increasing recycling efficiency, and reducing environmental impact.

[0514] The following describes the processing flow.

[0515] Step 1:

[0516] Users use their smartphones or PCs to input and submit questions about waste management to an AI chatbot.

[0517] Step 2:

[0518] The server receives text sent by the user and analyzes it using natural language processing techniques. This analysis extracts keywords from the text and understands the intent of the question.

[0519] Step 3:

[0520] Based on the extracted keywords and intent, the server accesses a regional waste classification rules database to search for information regarding appropriate classification.

[0521] Step 4:

[0522] The server uses an emotion engine to recognize the user's emotional state from their questions and statements. For example, if the user is showing signs of confusion or anxiety, the server will capture those emotions.

[0523] Step 5:

[0524] The server generates responses based on regional classification information and the results of the emotion engine's analysis. If necessary, it considers the user's emotional state and adds words of encouragement or additional explanations.

[0525] Step 6:

[0526] The server sends the generated response to the user in real time, and it is displayed on the chatbot interface.

[0527] Step 7:

[0528] Users use a smartphone app to take pictures of the waste they want to classify and send them to the server through the application.

[0529] Step 8:

[0530] The server verifies the received image data, performs necessary preprocessing, and prepares the image for analysis. This preprocessing includes adjusting the image resolution and denoising.

[0531] Step 9:

[0532] The server analyzes the pre-processed images using image recognition technology to identify the material and components of the waste.

[0533] Step 10:

[0534] Based on the image analysis results, the server determines the appropriate waste classification method and generates specific suggestions. The emotion engine is then used again to confirm the user's emotions and adjust the suggestions based on that feedback.

[0535] Step 11:

[0536] The server sends the generated classification method to the terminal, and the application visually displays the method to the user. It uses diagrams and user-friendly language to guide the user in an easy-to-understand manner.

[0537] (Example 2)

[0538] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0539] The classification of household waste is subject to different rules depending on the region, which can be complex and difficult for users to understand. Furthermore, standard waste classification support systems often fail to consider the user's feelings, leading to frustration. In addition, the lack of multilingual support and the inability to classify composite material waste are also challenges.

[0540] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0541] In this invention, the server includes means for analyzing user questions using natural language processing technology, means for analyzing images of waste using image recognition technology, and emotion engine means for detecting the user's emotional state and adjusting the response content. This makes it possible for the user to classify waste accurately and easily while taking their emotions into consideration.

[0542] "Natural language processing technology" refers to the technology that enables computers to analyze, understand, and generate human language.

[0543] "Regional waste classification regulations" are rules that specify the waste classification methods and related regulations applicable to a particular region.

[0544] "Image recognition technology" is a technology that uses computers to analyze image data and identify or classify its content.

[0545] An "emotion engine" is a technology that analyzes and detects emotions from input text and other data, and reflects them in the output.

[0546] A "generative AI model" is an algorithm that uses machine learning to automatically generate natural-sounding text and responses for specific tasks, similar to those produced by humans.

[0547] This invention is implemented as an AI system combining natural language processing technology, image recognition technology, and an emotion engine. This system is designed to allow users to understand the correct way to classify waste by sending questions and images related to waste via a smartphone or PC.

[0548] Users can use their smartphones or PCs (devices) to ask questions about waste classification through an AI chatbot. The device provides an interface for sending questions and images of waste to the server.

[0549] The server analyzes received questions using natural language processing techniques. This analysis utilizes generative AI models (e.g., BERT and GPT) to extract keywords and context from user questions and compare them with a regional waste classification rules database. This process allows the server to understand the user's intent and derive appropriate classification information. Furthermore, an emotion engine can be used to detect the user's emotional state and adjust the response accordingly.

[0550] Furthermore, the server analyzes the images of waste submitted by the user using image recognition technology. The image data is preprocessed to identify the material and composition of the waste. Based on the analysis results, an appropriate classification method for the waste is then generated and sent to the user in an appropriate tone through an emotion engine.

[0551] As a concrete example of using this system, consider a scenario where a user sends a text message asking, "Can this plastic be recycled?" The server analyzes the question using natural language processing technology, compares it to local classification rules, and provides the user with appropriate classification information. Furthermore, if the user takes a picture and sends it, the server can suggest the correct classification method through image recognition technology.

[0552] These factors enable users to sort waste accurately and quickly in an emotionally sensitive manner, thereby improving the efficiency of recycling.

[0553] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0554] Step 1:

[0555] Users use their smartphones or PCs (devices) to send questions about waste classification and images of waste to an AI chatbot. Questions are sent as text input, and images are sent in standard image file formats. The device then forwards this data to the server. The server processes the received data as wireless output.

[0556] Step 2:

[0557] The server analyzes the received text data using natural language processing techniques. Specifically, it uses a generative AI model to extract keywords and key context from the input text. Through this data processing, the server understands the gist of the question and identifies keywords related to waste (e.g., "bottle caps"). The output generates a list of analyzed keywords and contextual information.

[0558] Step 3:

[0559] The server compares the results of natural language processing with a regional waste classification rules database. This step searches for appropriate classification rules based on the analyzed keywords. As a data calculation, it derives optimal waste classification information based on the matching results. As output, it prepares a waste classification guide for the user.

[0560] Step 4:

[0561] The server uses an emotion engine to analyze the user's emotional state. Specifically, it performs emotion analysis on the text sent by the user to detect emotional elements such as anxiety and reassurance. This data processing prepares the server to generate a response in an appropriate tone based on the user's emotions. The output is a determined response tone based on emotion.

[0562] Step 5:

[0563] The server preprocesses the image data submitted by the user and analyzes its content using image recognition technology. The image data is first converted to the required format and then applied to an object recognition algorithm. This identifies the material and composition of the waste. The output generates the analyzed material information.

[0564] Step 6:

[0565] The server generates responses to the user using a generative AI model based on natural language processing, image recognition, and sentiment analysis. Specifically, the response content is optimized and constructed in a tone that corresponds to the user's emotions. As output, a final response message is prepared for sending to the user.

[0566] Step 7:

[0567] The server sends the generated response message to the terminal. The terminal displays this message to the user, allowing the user to immediately learn the proper way to classify waste. The output provides organized information that is displayed in the user interface.

[0568] (Application Example 2)

[0569] Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0570] In logistics and factory settings, proper waste classification is crucial, but incorrect classification can occur if employees are not familiar with waste types or local regulations. Furthermore, waste classification can be stressful, increasing the burden on employees. In addition, in environments where multiple languages ​​are used, language barriers hinder communication, highlighting the need to overcome these challenges.

[0571] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0572] In this invention, the server includes means for analyzing user inquiries using natural language processing technology and referring to regional waste classification rules, means for analyzing images of waste taken by the user using image recognition technology, and means for detecting the user's emotional state using emotion recognition technology and providing information in an appropriate tone. This enables users to easily and accurately classify waste, overcoming language and emotional barriers.

[0573] "Natural language processing technology" is a technology that enables computers to understand and interpret human language.

[0574] "Waste classification regulations" are standards established for each region to properly classify waste.

[0575] "Image recognition technology" is a technology that uses computers to analyze image data and recognize objects and features.

[0576] "Emotion recognition technology" is a technology that detects human emotions from voice or text.

[0577] A "user" is an individual or organization that uses the system to classify waste.

[0578] A "device" is an electronic device that allows users to visually confirm information.

[0579] A "parsable format" is a data format optimized for computers to process data effectively.

[0580] This invention provides an AI assistant system that helps users accurately classify waste. The system includes a server, a user terminal (a visual device such as smart glasses), and a communication network.

[0581] The server processes input from each user using natural language processing, image recognition, and emotion recognition technologies. When a user scans waste using smart glasses or a smartphone, the image is sent to the server. The server analyzes the image using image recognition technology to identify the type of waste. Furthermore, the server uses natural language processing to analyze questions entered by the user via voice and generates answers based on regional waste classification rules.

[0582] Furthermore, emotion recognition technology determines the emotions a user expresses in questions and responses, and adjusts the information provided in an appropriate tone to reduce user stress. This allows users to understand and implement proper waste sorting methods without feeling stressed.

[0583] As a concrete example, in a logistics center, when a user scans a cardboard box using smart glasses, the system immediately notifies the user that the cardboard is recyclable. If the user asks, "How should I dispose of it?", the system provides persuasive guidance in a gentle, empathetic tone.

[0584] An example of a prompt when using a generative AI model to generate responses that respond to user emotions is as follows: "Generate a gentle-toned AI response to a frequently asked question from employees regarding waste classification for smart glasses at a logistics center."

[0585] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0586] Step 1:

[0587] The user wears smart glasses and places the waste object in their field of vision. The smart glasses use a built-in camera to capture an image of the waste object. The captured image data is transmitted to a server via wireless communication. In this case, the input is the image data of the waste object, and the output is the image data transmitted to the server.

[0588] Step 2:

[0589] The server receives the image data and uses image recognition technology to analyze the material and shape of the waste. This analysis process compares patterns and features in the image with a database to identify the type of waste. The input is the transmitted image data, and the output is the waste classification result. The server's specific actions involve image processing using an analysis library and the application of specific algorithms.

[0590] Step 3:

[0591] The user sends a question to the server using the voice input function. The question is sent to the server as audio data from the smart glasses. The server receives this audio data, converts it to text using natural language processing techniques, and analyzes the intent of the question. The input is audio data, and the output is an appropriate answer to the question. The specific operation involves the use of speech recognition software.

[0592] Step 4:

[0593] The server uses emotion recognition technology to detect the user's emotional state. This is a process that analyzes voice and text data to evaluate the user's emotions. Through this process, it determines whether the user is experiencing stress and adjusts the tone of its response accordingly. The input is the user's text data, and the output is the emotion evaluation result. The specific operation involves data analysis by the emotion recognition engine.

[0594] Step 5:

[0595] The server uses a generative AI model to generate waste classification instruction messages for the user, taking into account the sentiment assessment results. These messages are tailored to a gentle tone and are generated using prompts. The input is the sentiment assessment results and data related to the question, and the output is a notification message for the user.

[0596] Step 6:

[0597] Ultimately, the server sends the generated instruction message to the smart glasses, displaying it directly in the user's field of view. The user can then use this information to properly classify waste. The input is the generated instruction message, and the output is the visual information displayed on the smart glasses. Specific operations include data transmission via a communication protocol and information display on the device.

[0598] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0599] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0600] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0601] [Fourth Embodiment]

[0602] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0603] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0604] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0605] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0606] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0607] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0608] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0609] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0610] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0611] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0612] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0613] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0614] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0615] This invention is implemented as an AI assistant system for users to accurately classify household waste. The system mainly consists of a 24 / 7 AI chatbot and a smartphone application, which work together to provide users with appropriate waste classification instructions.

[0616] Users submit questions about waste classification to the system via an AI chatbot using their smartphone or PC. These questions are analyzed by the server using natural language processing technology, and specific keywords and regional information are extracted. Based on this information, the server refers to regional waste classification regulations and instructs the user on the most appropriate classification method.

[0617] For example, if a user asks, "How should I dispose of this plastic?", the server detects the keyword "plastic," queries the local database, and returns instructions such as "Put it in the combustible waste bin."

[0618] Additionally, when a user takes a picture of composite material waste using a smartphone app, the device sends the image data to a server. The server analyzes the image using image recognition technology to identify the material and shape of the waste. Based on the analysis results, the server provides the user with instructions such as, "Please separate this packaging into paper and plastic before disposal."

[0619] In this way, the system provides immediate answers to user questions and can meet the needs of a wide range of residents through multilingual support. This reduces the effort required for traditional manual waste sorting and promotes proper recycling.

[0620] The following describes the processing flow.

[0621] Step 1:

[0622] Users use their smartphones or PCs to input and submit questions about waste classification to an AI chatbot.

[0623] Step 2:

[0624] The server receives questions submitted by users and analyzes the text data that makes up those questions using natural language processing techniques. Specifically, this involves language identification, keyword extraction, and contextual understanding.

[0625] Step 3:

[0626] Based on the analysis results, the server references the corresponding waste classification rules from the database along with regional information to identify the type of waste and the appropriate disposal method.

[0627] Step 4:

[0628] Based on the classification method identified by the server, it generates instructions for the user and creates responses such as, "This plastic is classified as combustible waste."

[0629] Step 5:

[0630] The server generates a response and sends it to the user in real time, displaying the answer on the chatbot interface.

[0631] Step 6:

[0632] Users use a smartphone app to take pictures of waste and send them to a server via the app.

[0633] Step 7:

[0634] The server receives the transmitted image data and performs preprocessing to make it ready for analysis. This includes adjusting the resolution and removing noise.

[0635] Step 8:

[0636] The server analyzes the processed images using image recognition technology to identify the material and components of the waste.

[0637] Step 9:

[0638] Based on the analysis results, the server determines the optimal waste classification method and generates suggestions such as, "Please separate this packaging into paper and plastic before disposal."

[0639] Step 10:

[0640] The server generates suggestions, which are then sent to the user's terminal and visualized on the application interface for the user to see.

[0641] (Example 1)

[0642] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0643] In modern society, improper classification of materials leads to environmental problems and waste of resources. This problem is difficult for users to address appropriately because different rules and information exist in different regions. Furthermore, manual classification of composite materials is particularly difficult, requiring an efficient and accurate solution.

[0644] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0645] In this invention, the server includes means for an information processing device to analyze queries using natural language processing technology and instruct the user on an appropriate method of classifying materials by referring to rules based on geographical information, and means for analyzing visual information of materials acquired by the device using image recognition technology and means for enabling the user to easily classify the materials. As a result, users can accurately classify materials based on the rules of their local area, reducing adverse environmental impacts and enabling efficient resource utilization.

[0646] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[0647] The term "information processing device" refers to any device that has the function of inputting, processing, and outputting data.

[0648] "Inquiry" refers to a question or request that a user makes to an information processing device.

[0649] "Geographical information" refers to data and knowledge about a specific region, and this information includes the rules and systems specific to that region.

[0650] A "rule" is a set of rules or guidelines established for a specific purpose.

[0651] "User" refers to an individual or organization that uses this system.

[0652] "Materials" refers to all objects that contain information or data, including waste.

[0653] "Image recognition technology" is a technology in which a computer analyzes image data, extracts information, and recognizes it.

[0654] "Visual information" refers to information that is structured as image data.

[0655] "Analysis results" refer to conclusions and knowledge derived from the input data.

[0656] A "composite material" refers to a material composed of multiple materials with different properties combined together.

[0657] This invention is an information processing system for users to accurately classify materials. This system mainly includes an AI conversation program that can operate continuously and application software for mobile devices, which work together to provide users with appropriate instructions for classifying materials.

[0658] Users can use their mobile phones or computers to make inquiries about document classification via an AI conversational program. These inquiries are analyzed by the server using natural language processing technology, extracting specific keywords and geographical information. Based on this extracted information, the server consults geographical rules and instructs the user on the most appropriate classification method.

[0659] For example, if a user asks, "How should I dispose of this plastic?", the server can identify the keyword "plastic," look up local information, and return instructions such as "classify it as combustible waste."

[0660] Furthermore, when a user uses a mobile device application to capture visual information of a composite material, that visual data is sent from the device to the server. The server uses image recognition technology to analyze this visual data and identify the material and shape of the material. Based on this, the server can provide instructions to the user, such as "Please separate this packaging into paper and plastic before disposal."

[0661] This system can meet the needs of many users by supporting multiple languages. By utilizing a generative AI model, the system can quickly analyze prompt sentences and efficiently perform information processing and classification instructions.

[0662] A possible example of a specific prompt message would be, "How should I dispose of metal products?" In response to this inquiry, the server would instruct the user on the appropriate disposal method based on geographical regulations. This would enable the user to accurately classify and dispose of materials in their local area.

[0663] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0664] Step 1:

[0665] The user enters a query into the AI ​​conversation program using a mobile device or computer. For example, they might enter a query like, "How should I dispose of this plastic?" This query is then sent to the system as input data.

[0666] Step 2:

[0667] The server receives queries sent by users and performs natural language processing using a generative AI model. Here, the query is analyzed to extract keywords such as "plastic." This data processing then outputs the extracted keywords and geographical information.

[0668] Step 3:

[0669] The server queries a geographical rules database based on the extracted keywords and geographical information. During information processing, it refers to relevant waste classification rules to identify the optimal classification method. As a result, output data is generated to provide instructions to the user.

[0670] Step 4:

[0671] The server uses the obtained output data to send waste classification instructions to the user. Specifically, it sends clear instructions, such as "classify as combustible resources," as text messages to the user's terminal.

[0672] Step 5:

[0673] When a user provides details of a document using images, they take a picture of the document using the camera function of their mobile device. This visual information is then sent to the server via the device as input data.

[0674] Step 6:

[0675] The server analyzes the received visual information using image recognition technology. It processes the image data to identify the material and shape of the object. This analysis generates output data regarding the type of material.

[0676] Step 7:

[0677] Based on the results of image analysis, the server provides the user with instructions for appropriate waste classification. For example, it sends the user specific instructions such as, "Please separate this packaging into paper and plastic before disposal." This information is output to the user's terminal, enabling accurate classification of the materials.

[0678] (Application Example 1)

[0679] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0680] In modern living environments, the diversification of waste necessitates its proper classification. However, the increasing complexity of waste types and differing regulations in various regions make it difficult for individual users to accurately classify their waste. Furthermore, in industrial environments, manual waste classification is inefficient, and addressing labor shortages is desirable. Therefore, systems and methods for accurately and efficiently classifying waste are needed in both personal and industrial settings.

[0681] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0682] In this invention, the server includes means for analyzing user inquiries using natural language processing technology, means for instructing the user on the correct method of waste classification by referring to regional waste sorting regulations, means for analyzing images of waste taken by the user using image recognition technology, and means for controlling automated machinery in an industrial environment to physically classify the waste. This enables efficient and accurate waste classification in both personal and industrial settings.

[0683] "Natural language processing technology" is a technology that allows computers to analyze human language and understand its meaning.

[0684] "Regional waste sorting regulations" are rules concerning the classification and disposal of waste that are enforced in a specific region.

[0685] "Image recognition technology" is a technique in which a computer analyzes image data and identifies the objects and features contained within it.

[0686] "User" refers to an individual or legal entity that operates or utilizes this system.

[0687] "Industrial environment" refers to environments related to manufacturing, such as factories and production lines.

[0688] "Controlling automated machinery" refers to operating a machine based on a program to perform a specific task.

[0689] A description of the embodiment for carrying out the invention will be provided.

[0690] This invention is a system that assists users in accurately classifying household waste. The system efficiently responds to user inquiries by combining natural language processing and image recognition technologies. It also enables the physical classification of waste in industrial environments by controlling automated machinery.

[0691] The server first analyzes the text data sent from the user's terminal using natural language processing technology (specifically, advanced natural language processing models) to extract key information. This information includes regional waste sorting rules, which serve as a basis for the user to determine how to classify their waste. The server also analyzes the waste images received from the user's terminal using image recognition technology (specifically, state-of-the-art image processing libraries) to identify the material and shape. This allows the server to provide the user with specific instructions for waste classification.

[0692] In industrial settings, servers transmit control signals to automated machinery to classify recognized waste into appropriate categories. This includes identifying the type of waste material and operating the machinery accordingly to perform the classification process.

[0693] For example, when a user sends an image of a plastic bottle using their smartphone, the server recognizes the material and provides instructions to classify it as "plastic waste" based on local regulations. These instructions are then transmitted to the user or industrial robots, enabling accurate waste classification. Generative AI models can also be utilized with prompts such as, "Explain a system where a factory robot recognizes waste and automatically classifies it based on local regulations."

[0694] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0695] Step 1:

[0696] The user uses a terminal to input and submit a question about waste. The input is natural language text. The server receives this text data and analyzes it using natural language processing techniques. Specifically, it extracts keywords from the user's question and compares them with regional waste sorting regulations. The output is basic information necessary for waste classification.

[0697] Step 2:

[0698] The user takes a picture of the waste using a device and sends it to the server. The server analyzes the image data using image recognition technology to identify the material and characteristics of the waste. This analysis processes the data to recognize the material and shape of the objects in the image. The output is the identified material information.

[0699] Step 3:

[0700] The server combines the keywords obtained in Step 1 with the material information identified in Step 2, consults regional waste sorting regulations, and determines the most appropriate disposal method. In this step, the server queries the regulations database internally and generates specific instructions from the matched results. The output is specific disposal instructions for the user or industrial machinery.

[0701] Step 4:

[0702] The server sends and displays the generated instructions in text format to the user's terminal. When used in an industrial environment, the instructions are also sent as control signals to automated machinery, initiating the physical sorting of waste. This ensures the automated machinery operates in a way that properly sorts the waste. The output consists of the instructions displayed to the user and the start of the automated machinery's operation.

[0703] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0704] This invention is an AI assistant system that combines natural language processing technology, image recognition technology, and an emotion engine to help users accurately and efficiently sort household waste. The system functions at the core of a 24 / 7 AI chatbot and smartphone application, supporting various user interactions.

[0705] Users can ask the AI ​​chatbot questions about waste classification via their smartphone or PC. The server analyzes these questions using natural language processing technology to understand relevant keywords and context. The analyzed information is then cross-referenced with a database of regional waste classification rules. The server then utilizes an emotion engine to detect the emotions expressed in the text accompanying the user's question. For example, if the user appears confused, the AI ​​chatbot adjusts its tone to provide additional information in a gentler manner.

[0706] As a concrete example, suppose a user expresses anxiety, saying, "I don't know what to do with this bottle cap." The server extracts "bottle cap" as a keyword using natural language processing, and the emotion engine recognizes the user's anxiety. In this case, the server generates a response that includes encouraging information such as, "Please calm down. Bottle caps are usually classified as recyclable waste."

[0707] Furthermore, users can take pictures of waste materials via a smartphone app and send them to a server. The server preprocesses the image data and analyzes it using image recognition technology. This analysis identifies the material and composition of the waste. Based on the analysis results, the server suggests an appropriate classification method for the waste and sends it to the user. User reactions are also monitored by an emotion engine, and the interaction is adjusted as needed.

[0708] By using such a system, users can easily learn the correct way to classify waste and reduce emotional frustration during the process. This invention has the effect of improving the user experience, increasing recycling efficiency, and reducing environmental impact.

[0709] The following describes the processing flow.

[0710] Step 1:

[0711] Users use their smartphones or PCs to input and submit questions about waste management to an AI chatbot.

[0712] Step 2:

[0713] The server receives text sent by the user and analyzes it using natural language processing techniques. This analysis extracts keywords from the text and understands the intent of the question.

[0714] Step 3:

[0715] Based on the extracted keywords and intent, the server accesses a regional waste classification rules database to search for information regarding appropriate classification.

[0716] Step 4:

[0717] The server uses an emotion engine to recognize the user's emotional state from their questions and statements. For example, if the user is showing signs of confusion or anxiety, the server will capture those emotions.

[0718] Step 5:

[0719] The server generates responses based on regional classification information and the results of the emotion engine's analysis. If necessary, it considers the user's emotional state and adds words of encouragement or additional explanations.

[0720] Step 6:

[0721] The server sends the generated response to the user in real time, and it is displayed on the chatbot interface.

[0722] Step 7:

[0723] Users use a smartphone app to take pictures of the waste they want to classify and send them to the server through the application.

[0724] Step 8:

[0725] The server verifies the received image data, performs necessary preprocessing, and prepares the image for analysis. This preprocessing includes adjusting the image resolution and denoising.

[0726] Step 9:

[0727] The server analyzes the pre-processed images using image recognition technology to identify the material and components of the waste.

[0728] Step 10:

[0729] Based on the image analysis results, the server determines the appropriate waste classification method and generates specific suggestions. The emotion engine is then used again to confirm the user's emotions and adjust the suggestions based on that feedback.

[0730] Step 11:

[0731] The server sends the generated classification method to the terminal, and the application visually displays the method to the user. It uses diagrams and user-friendly language to guide the user in an easy-to-understand manner.

[0732] (Example 2)

[0733] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0734] The classification of household waste is subject to different rules depending on the region, which can be complex and difficult for users to understand. Furthermore, standard waste classification support systems often fail to consider the user's feelings, leading to frustration. In addition, the lack of multilingual support and the inability to classify composite material waste are also challenges.

[0735] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0736] In this invention, the server includes means for analyzing user questions using natural language processing technology, means for analyzing images of waste using image recognition technology, and emotion engine means for detecting the user's emotional state and adjusting the response content. This makes it possible for the user to classify waste accurately and easily while taking their emotions into consideration.

[0737] "Natural language processing technology" refers to the technology that enables computers to analyze, understand, and generate human language.

[0738] "Regional waste classification regulations" are rules that specify the waste classification methods and related regulations applicable to a particular region.

[0739] "Image recognition technology" is a technology that uses computers to analyze image data and identify or classify its content.

[0740] An "emotion engine" is a technology that analyzes and detects emotions from input text and other data, and reflects them in the output.

[0741] A "generative AI model" is an algorithm that uses machine learning to automatically generate natural-sounding text and responses for specific tasks, similar to those produced by humans.

[0742] This invention is implemented as an AI system combining natural language processing technology, image recognition technology, and an emotion engine. This system is designed to allow users to understand the correct way to classify waste by sending questions and images related to waste via a smartphone or PC.

[0743] Users can use their smartphones or PCs (devices) to ask questions about waste classification through an AI chatbot. The device provides an interface for sending questions and images of waste to the server.

[0744] The server analyzes received questions using natural language processing techniques. This analysis utilizes generative AI models (e.g., BERT and GPT) to extract keywords and context from user questions and compare them with a regional waste classification rules database. This process allows the server to understand the user's intent and derive appropriate classification information. Furthermore, an emotion engine can be used to detect the user's emotional state and adjust the response accordingly.

[0745] Furthermore, the server analyzes the images of waste submitted by the user using image recognition technology. The image data is preprocessed to identify the material and composition of the waste. Based on the analysis results, an appropriate classification method for the waste is then generated and sent to the user in an appropriate tone through an emotion engine.

[0746] As a concrete example of using this system, consider a scenario where a user sends a text message asking, "Can this plastic be recycled?" The server analyzes the question using natural language processing technology, compares it to local classification rules, and provides the user with appropriate classification information. Furthermore, if the user takes a picture and sends it, the server can suggest the correct classification method through image recognition technology.

[0747] These factors enable users to sort waste accurately and quickly in an emotionally sensitive manner, thereby improving the efficiency of recycling.

[0748] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0749] Step 1:

[0750] Users use their smartphones or PCs (devices) to send questions about waste classification and images of waste to an AI chatbot. Questions are sent as text input, and images are sent in standard image file formats. The device then forwards this data to the server. The server processes the received data as wireless output.

[0751] Step 2:

[0752] The server analyzes the received text data using natural language processing techniques. Specifically, it uses a generative AI model to extract keywords and key context from the input text. Through this data processing, the server understands the gist of the question and identifies keywords related to waste (e.g., "bottle caps"). The output generates a list of analyzed keywords and contextual information.

[0753] Step 3:

[0754] The server compares the results of natural language processing with a regional waste classification rules database. This step searches for appropriate classification rules based on the analyzed keywords. As a data calculation, it derives optimal waste classification information based on the matching results. As output, it prepares a waste classification guide for the user.

[0755] Step 4:

[0756] The server uses an emotion engine to analyze the user's emotional state. Specifically, it performs emotion analysis on the text sent by the user to detect emotional elements such as anxiety and reassurance. This data processing prepares the server to generate a response in an appropriate tone based on the user's emotions. The output is a determined response tone based on emotion.

[0757] Step 5:

[0758] The server preprocesses the image data submitted by the user and analyzes its content using image recognition technology. The image data is first converted to the required format and then applied to an object recognition algorithm. This identifies the material and composition of the waste. The output generates the analyzed material information.

[0759] Step 6:

[0760] The server generates responses to the user using a generative AI model based on natural language processing, image recognition, and sentiment analysis. Specifically, the response content is optimized and constructed in a tone that corresponds to the user's emotions. As output, a final response message is prepared for sending to the user.

[0761] Step 7:

[0762] The server sends the generated response message to the terminal. The terminal displays this message to the user, allowing the user to immediately learn the proper way to classify waste. The output provides organized information that is displayed in the user interface.

[0763] (Application Example 2)

[0764] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0765] In logistics and factory settings, proper waste classification is crucial, but incorrect classification can occur if employees are not familiar with waste types or local regulations. Furthermore, waste classification can be stressful, increasing the burden on employees. In addition, in environments where multiple languages ​​are used, language barriers hinder communication, highlighting the need to overcome these challenges.

[0766] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0767] In this invention, the server includes means for analyzing user inquiries using natural language processing technology and referring to regional waste classification rules, means for analyzing images of waste taken by the user using image recognition technology, and means for detecting the user's emotional state using emotion recognition technology and providing information in an appropriate tone. This enables users to easily and accurately classify waste, overcoming language and emotional barriers.

[0768] "Natural language processing technology" is a technology that enables computers to understand and interpret human language.

[0769] "Waste classification regulations" are standards established for each region to properly classify waste.

[0770] "Image recognition technology" is a technology that uses computers to analyze image data and recognize objects and features.

[0771] "Emotion recognition technology" is a technology that detects human emotions from voice or text.

[0772] A "user" is an individual or organization that uses the system to classify waste.

[0773] A "device" is an electronic device that allows users to visually confirm information.

[0774] A "parsable format" is a data format optimized for computers to process data effectively.

[0775] This invention provides an AI assistant system that helps users accurately classify waste. The system includes a server, a user terminal (a visual device such as smart glasses), and a communication network.

[0776] The server processes input from each user using natural language processing, image recognition, and emotion recognition technologies. When a user scans waste using smart glasses or a smartphone, the image is sent to the server. The server analyzes the image using image recognition technology to identify the type of waste. Furthermore, the server uses natural language processing to analyze questions entered by the user via voice and generates answers based on regional waste classification rules.

[0777] Furthermore, emotion recognition technology determines the emotions a user expresses in questions and responses, and adjusts the information provided in an appropriate tone to reduce user stress. This allows users to understand and implement proper waste sorting methods without feeling stressed.

[0778] As a concrete example, in a logistics center, when a user scans a cardboard box using smart glasses, the system immediately notifies the user that the cardboard is recyclable. If the user asks, "How should I dispose of it?", the system provides persuasive guidance in a gentle, empathetic tone.

[0779] An example of a prompt when using a generative AI model to generate responses that respond to user emotions is as follows: "Generate a gentle-toned AI response to a frequently asked question from employees regarding waste classification for smart glasses at a logistics center."

[0780] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0781] Step 1:

[0782] The user wears smart glasses and places the waste object in their field of vision. The smart glasses use a built-in camera to capture an image of the waste object. The captured image data is transmitted to a server via wireless communication. In this case, the input is the image data of the waste object, and the output is the image data transmitted to the server.

[0783] Step 2:

[0784] The server receives the image data and uses image recognition technology to analyze the material and shape of the waste. This analysis process compares patterns and features in the image with a database to identify the type of waste. The input is the transmitted image data, and the output is the waste classification result. The server's specific actions involve image processing using an analysis library and the application of specific algorithms.

[0785] Step 3:

[0786] The user sends a question to the server using the voice input function. The question is sent to the server as audio data from the smart glasses. The server receives this audio data, converts it to text using natural language processing techniques, and analyzes the intent of the question. The input is audio data, and the output is an appropriate answer to the question. The specific operation involves the use of speech recognition software.

[0787] Step 4:

[0788] The server uses emotion recognition technology to detect the user's emotional state. This is a process that analyzes voice and text data to evaluate the user's emotions. Through this process, it determines whether the user is experiencing stress and adjusts the tone of its response accordingly. The input is the user's text data, and the output is the emotion evaluation result. The specific operation involves data analysis by the emotion recognition engine.

[0789] Step 5:

[0790] The server uses a generative AI model to generate waste classification instruction messages for the user, taking into account the sentiment assessment results. These messages are tailored to a gentle tone and are generated using prompts. The input is the sentiment assessment results and data related to the question, and the output is a notification message for the user.

[0791] Step 6:

[0792] Ultimately, the server sends the generated instruction message to the smart glasses, displaying it directly in the user's field of view. The user can then use this information to properly classify waste. The input is the generated instruction message, and the output is the visual information displayed on the smart glasses. Specific operations include data transmission via a communication protocol and information display on the device.

[0793] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0794] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0795] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0796] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0797] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0798] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0799] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0800] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0801] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0802] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0803] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0804] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0805] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0806] 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.

[0807] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0808] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0809] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0810] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0811] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0812] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0813] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0814] The following is further disclosed regarding the embodiments described above.

[0815] (Claim 1)

[0816] Using natural language processing techniques, we analyze user questions.

[0817] By referring to regional waste classification rules,

[0818] A means of instructing users on the proper method of sorting waste,

[0819] Using image recognition technology, we analyze images of waste taken by the user.

[0820] A means of proposing a waste classification method to the user based on the analysis results,

[0821] These means are integrated to enable users to easily classify waste,

[0822] A system that includes this.

[0823] (Claim 2)

[0824] Supports multiple languages ​​used by the user,

[0825] By using translation technology to perform natural language processing,

[0826] It is possible to provide instructions for waste classification even when answering questions in multiple languages.

[0827] The system according to claim 1.

[0828] (Claim 3)

[0829] A preprocessing means for converting the user's image data into a format that can be analyzed in advance,

[0830] It is equipped with analytical means to perform detailed material decomposition based on the pre-processed data,

[0831] We also provide appropriate classification methods for composite material waste.

[0832] The system according to claim 1.

[0833] "Example 1"

[0834] (Claim 1)

[0835] The information processing device analyzes the query using natural language processing technology.

[0836] By referring to rules based on geographical information,

[0837] A means of instructing users on the appropriate method of classifying materials,

[0838] Using image recognition technology, the device analyzes the visual information of the materials it acquires.

[0839] A means of proposing a data classification method to the user based on the analysis results,

[0840] These means are integrated to enable users to easily classify materials,

[0841] A system that includes this.

[0842] (Claim 2)

[0843] Supports multiple languages ​​used by the user,

[0844] By using translation technology to perform natural language processing,

[0845] It is possible to instruct the classification of materials even for inquiries in multiple languages.

[0846] The system according to claim 1.

[0847] (Claim 3)

[0848] A preprocessing means for converting the user's visual information into a format that can be analyzed in advance,

[0849] It is equipped with analytical means to perform detailed material decomposition based on the pre-processed information,

[0850] We also provide appropriate classification methods for composite material materials.

[0851] The system according to claim 1.

[0852] "Application Example 1"

[0853] (Claim 1)

[0854] A means of analyzing user inquiries using natural language processing technology,

[0855] A means of instructing users on the correct method of waste classification by referring to local waste sorting regulations,

[0856] A means of analyzing images of waste taken by the user using image recognition technology,

[0857] A means of proposing a waste classification method to the user based on the analysis results,

[0858] In industrial environments, means of controlling automated machinery to physically classify waste,

[0859] By combining these methods, a means is created to enable users to easily classify waste,

[0860] ...

[0861] A device that includes this.

[0862] (Claim 2)

[0863] The apparatus according to claim 1, which supports multiple languages ​​used by the user and can provide instructions for waste classification even in response to inquiries in multiple languages ​​by performing natural language processing using translation technology.

[0864] (Claim 3)

[0865] The apparatus according to claim 1, comprising a pre-processing means for converting the user's image data into an analyzable format in advance, and an analysis means for performing detailed material decomposition based on the pre-processed data, thereby providing an appropriate classification method for composite material waste.

[0866] "Example 2 of combining an emotion engine"

[0867] (Claim 1)

[0868] Using natural language processing technology, we analyze questions from users.

[0869] By referring to regional waste classification rules,

[0870] A means of instructing users on the proper method of waste classification,

[0871] Using image recognition technology, the system analyzes images of waste taken by the user.

[0872] A means of proposing a waste classification method to the user based on the analysis results,

[0873] An emotion engine means that detects the user's emotional state and adjusts the response content,

[0874] A means of creating responses to users using a generative AI model,

[0875] These means are integrated to enable users to easily classify waste,

[0876] A system that includes this.

[0877] (Claim 2)

[0878] Supports multiple languages ​​used by the user,

[0879] By using translation technology to perform natural language processing,

[0880] It is possible to provide instructions for waste classification even when answering questions in multiple languages.

[0881] The system according to claim 1.

[0882] (Claim 3)

[0883] A preprocessing means for converting the user's image data into a format that can be analyzed in advance,

[0884] It is equipped with analytical means to perform detailed material decomposition based on the pre-processed data,

[0885] We also provide appropriate classification methods for composite material waste.

[0886] The system according to claim 1.

[0887] "Application example 2 when combining with an emotional engine"

[0888] (Claim 1)

[0889] Using natural language processing technology, we analyze user inquiries.

[0890] By referring to the waste classification rules for each region,

[0891] A means of guiding users on the proper way to classify waste,

[0892] Using image recognition technology, images of waste taken by users are analyzed.

[0893] A means of proposing a waste classification method to users based on the analysis results,

[0894] Using emotion recognition technology, the emotional state of the user is detected.

[0895] Means of providing information in an appropriate tone,

[0896] A means of displaying classification information via a device that allows users to visually recognize waste,

[0897] These means are integrated to enable users to perform waste sorting tasks smoothly,

[0898] A system that includes this.

[0899] (Claim 2)

[0900] Supports multiple languages ​​used by the user,

[0901] By using translation technology to perform natural language processing,

[0902] It is possible to provide guidance on waste classification even in inquiries in multiple languages.

[0903] The system according to claim 1.

[0904] (Claim 3)

[0905] A preprocessing means for converting the user's image data into a format that can be analyzed in advance,

[0906] It is equipped with analytical means to perform detailed material decomposition based on the pre-processed data,

[0907] We also provide appropriate classification methods for composite material waste.

[0908] The system according to claim 1. [Explanation of Symbols]

[0909] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Using natural language processing techniques, we analyze user questions. By referring to regional waste classification rules, A means of instructing users on the proper method of sorting waste, Using image recognition technology, we analyze images of waste taken by the user. A means of proposing a waste classification method to the user based on the analysis results, These means are integrated to enable users to easily classify waste, A system that includes this.

2. Supports multiple languages ​​used by the user, By using translation technology to perform natural language processing, It is possible to provide instructions for waste classification even when answering questions in multiple languages. The system according to claim 1.

3. A preprocessing means for converting the user's image data into a format that can be analyzed in advance, It is equipped with analytical means to perform detailed material decomposition based on the pre-processed data, We also provide appropriate classification methods for composite material waste. The system according to claim 1.

Images