system

Abstract

We provide the system. [Solution] An image acquisition means for obtaining input data for classifying waste, Artificial intelligence means for processing data obtained from the image acquisition means, A means of applying rules to obtain and apply waste sorting rules for each region, Instruction generation means for displaying or notifying the user of instructions via voice based on the aforementioned data, 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 persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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] In waste sorting, understanding complex rules that vary by region is required, and problems such as a decrease in recycling efficiency and an increase in environmental load due to incorrect sorting have emerged. Also, for visually impaired people and the elderly, sorting by conventional methods is difficult. To solve these problems, there is a need to develop a system that provides accurate sorting instructions in real time and improves user convenience.

Means for Solving the Problems

[0005] This invention acquires images of waste using an image acquisition means installed in a trash can, and analyzes the images using artificial intelligence to determine the type of waste. Subsequently, it acquires sorting rules for each region using a rule application means and provides appropriate sorting instructions to the user by including an instruction generation means that generates accurate sorting methods. Furthermore, by including a speech synthesis means, sorting assistance can be made usable by visually impaired people and the elderly.

[0006] "Image acquisition means" refers to a device or function for taking images of waste and acquiring them as electronic data.

[0007] "Artificial intelligence means" refers to a function that determines the type and characteristics of waste by analyzing acquired image data.

[0008] A "rule application mechanism" is a function for obtaining different waste sorting rules for each region and applying them based on the classification results of the waste in question.

[0009] The "instruction generation means" is a function that generates information to instruct the user on the appropriate sorting method based on the waste classification results and applicable rules.

[0010] A "speech synthesis means" is a function that converts the generated sorting instructions into a speech format, making it possible to provide information to people with visual impairments and other disabilities. [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, etc.

[0017] In the following embodiments, the numbered communication I / F (Interface) is an interface that includes 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), etc.

[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] The smart waste sorting system of the present invention operates by combining multiple technological elements to support accurate classification and proper sorting of waste. First, a terminal installed in the trash can captures an image of the object using an image acquisition means each time waste is placed inside. This allows data such as the appearance, shape, and color of the waste to be collected in real time. In addition, sensors equipped in the terminal measure the weight and volume of the waste to supplement its physical characteristics.

[0033] The captured and measured data is compressed and sent to a server. The server inputs the image and sensor data into artificial intelligence (AI) systems and determines the type of waste based on previously learned patterns. For example, it has the ability to distinguish between different types of waste, such as plastic bottles, glass bottles, and metal cans.

[0034] Subsequently, the server uses rule application means to retrieve regional sorting rules from the database based on the classification results. This is essential for providing instructions that conform to different sorting criteria for each region. The sorting instructions generated by the server are converted into text and audio information by the instruction generation means and returned to the terminal.

[0035] Users can receive visual and auditory sorting instructions from the device and properly sort their waste. For visually impaired users, speech synthesis provides instructions verbally, making the sorting process easy for anyone.

[0036] As a concrete example, consider a scenario where a user throws an empty plastic bottle into a trash can. The terminal acquires an image of the bottle and measures its weight. The server receives this data, recognizes it as a plastic bottle using artificial intelligence, and generates instructions such as "Remove the cap and rinse the inside" based on local regulations. The user follows these instructions for sorting, and the system accumulates the data to further improve accuracy. In this way, the present invention realizes appropriate waste disposal for each region, contributing to user convenience and environmental protection.

[0037] The following describes the processing flow.

[0038] Step 1:

[0039] The device uses a camera to photograph waste placed in the trash can and acquires image data. It also uses sensors to collect data on the weight and shape of the waste.

[0040] Step 2:

[0041] The device compresses the acquired images and sensor data and securely transmits them to the server. Data compression and encryption processing takes place at this stage.

[0042] Step 3:

[0043] The server analyzes the received data using artificial intelligence to determine the type of waste. Here, image analysis technology is used to extract the features of the objects, and classification is performed based on those features.

[0044] Step 4:

[0045] Based on the determined type of waste, the server uses rule application mechanisms to retrieve the sorting rules for the relevant area from the database.

[0046] Step 5:

[0047] The server uses an instruction generation mechanism to construct sorting instructions to be provided to the user, in accordance with the acquired regional rules. The instructions are generated in both text and audio formats.

[0048] Step 6:

[0049] The server sends the generated instructions to the terminal. Information is conveyed using speech synthesis, ensuring it is not dependent on visual information.

[0050] Step 7:

[0051] The terminal notifies the user of received sorting instructions, clearly communicating the instructions through display and voice. The user then properly disposes of the waste according to these instructions.

[0052] (Example 1)

[0053] 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."

[0054] Conventional waste sorting systems have problems accurately identifying types of waste and adapting to different sorting standards in different regions. They also have the challenge of providing insufficient instructions for visually impaired individuals. Furthermore, their accuracy is limited because they lack the ability to classify waste based on its physical characteristics.

[0055] 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.

[0056] In this invention, the server includes a visual acquisition means, a means for compressing and transmitting information obtained from a weight measuring device, a generation AI means for determining the type of waste based on previously learned patterns, a rule application means for acquiring and applying waste sorting standards for each region, and an instruction generation means for displaying or notifying the user of instructions via voice. This enables high-precision classification of waste and the provision of appropriate sorting instructions according to the region, making it possible for all users, including visually impaired individuals, to properly sort their waste.

[0057] A "visual acquisition means" is a device for collecting visual information about waste, and it uses cameras and sensors to acquire information such as the appearance, shape, and color of the waste.

[0058] A "weight measuring device" is a measuring device used to measure the weight of waste and to supplement the physical characteristics of the waste.

[0059] "Means for compressing and transmitting information" refers to means that have the function of compressing acquired data in order to transmit it effectively and then sending it to a receiving side such as a server.

[0060] "Generative AI means" refers to artificial intelligence technology used to identify and classify types of waste using previously learned data.

[0061] "Means of applying regulations" refers to a program or processing system for obtaining regional waste sorting standards and applying them to the waste classification results.

[0062] "Instruction generation means" refers to a device or function that generates differentiated instructions for the user based on information from the server and notifies the user of these instructions via display or sound.

[0063] The waste sorting system of the present invention operates in conjunction with a terminal and a server. The terminal is installed in a trash can and takes an image of the waste using visual acquisition means each time waste is put in. This visual acquisition means includes a camera and image sensors to acquire the appearance, color, and shape of the waste. In addition, a weight measuring device is incorporated into the terminal to measure the weight and volume of the waste and supplement its physical characteristics.

[0064] The captured and measured data is transmitted to the server by a means of compressing and transmitting terminal information. The server inputs the received data into a generating AI means and determines the type of waste using previously learned patterns. This generating AI means uses an artificial intelligence model (AI model) to perform image analysis and physical feature analysis of the waste. The server then uses a rule application means to retrieve and apply regional sorting standards from a database based on the determined type of waste.

[0065] The server converts the results into instructions using an instruction generation mechanism and provides them to the user. These include visual instructions via display and voice instructions via speech synthesis. This allows the user to make appropriate classifications according to the instructions provided from the terminal.

[0066] As a concrete example, consider a scenario where a user throws a glass bottle into a trash can. The terminal acquires an image of the glass bottle and measures its weight. The server receives this information and uses AI to identify the waste as a glass bottle. Then, based on local sorting rules, it generates an instruction such as, "Please place glass bottles in the designated recycling box." The user follows this instruction and sorts the waste appropriately. In this way, the system flexibly adapts to local sorting rules and contributes to environmental protection.

[0067] Example prompt for the generated AI model: "Generate a program that identifies glass bottles and plastic bottles in a smart waste sorting system and provides the user with appropriate sorting instructions based on that."

[0068] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0069] Step 1:

[0070] The terminal captures an image of the waste each time it is deposited using a visual acquisition device. The input is the actual waste, and the output is visual information (image data) of the waste. The terminal uses a camera to capture the appearance, color, and shape of the waste.

[0071] Step 2:

[0072] The terminal measures the weight of the waste using a weighing device. The input is the physical presence of the waste, and the output is the weight data of the waste. This supplements the weight as a physical characteristic.

[0073] Step 3:

[0074] The terminal compresses the acquired image data and weight data into a single data package and sends it to the server. The input is a pair of visual and weight information, and the output is a compressed data file sent to the server. Transmission takes place in real time over the network.

[0075] Step 4:

[0076] The server receives and decompresses compressed data. The input is a data file sent from the terminal, and the output is the decompressed image data and weight data. This data is then ready to be input into the generating AI system.

[0077] Step 5:

[0078] The server's AI generation method uses decompressed data to determine the type of waste. Inputs are image data and weight data, and output is the determined waste type information. The AI ​​model performs pattern recognition using past training data.

[0079] Step 6:

[0080] The server uses rule application methods to retrieve and apply local sorting standards based on the determined waste type. The input is waste type information, and the output is sorting instructions appropriate for the region. Rules are referenced from a database.

[0081] Step 7:

[0082] The server converts the sorting instructions into text or audio format using an instruction generation device and sends them to the terminal. The input is the sorting instructions, and the output is the instruction information provided to the user.

[0083] Step 8:

[0084] The user sorts waste appropriately according to instructions received from the terminal. Input consists of visual and auditory instructions, while output is the user's sorting actions. This facilitates the proper disposal of waste.

[0085] (Application Example 1)

[0086] 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."

[0087] In modern urban environments, proper waste sorting and recycling are critical social issues, but many people find it difficult to accurately understand and follow complex sorting rules. Furthermore, there is a lack of systems that allow diverse users, including the visually impaired, to easily and appropriately sort their waste. To address this challenge, there is a need to provide a system that allows users to receive real-time instructions, thereby improving user convenience and reducing environmental impact.

[0088] 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.

[0089] In this invention, the server includes an image acquisition means for acquiring input data for classifying waste, an artificial intelligence means for processing the data obtained from the image acquisition means, a rule application means for acquiring and applying waste sorting rules for each region, and a communication means that works in conjunction with a smart device that provides instructions in real time. This makes it possible for users to instantly receive instructions on the appropriate sorting method via a smart device when disposing of waste.

[0090] An "image acquisition means" is a device that uses cameras and sensors to acquire image data in order to collect the external characteristics of waste.

[0091] "Artificial intelligence means" refers to artificial intelligence algorithms and programs used to analyze acquired images and data to determine the type and classification of waste.

[0092] "Means of applying rules" refers to a database and its matching function that references local waste sorting standards and provides instructions tailored to the user.

[0093] "Instruction generation means" refers to a device or program that creates instructions in text or voice to communicate to the user the appropriate method of disposing of waste based on the analysis results.

[0094] "Communication means" refers to network connectivity technology that enables a system to send and receive data with smart devices and provide instructions in real time.

[0095] This invention provides a system for appropriately classifying waste and providing sorting instructions to the user. Specific embodiments for realizing this system are described below.

[0096] First, the system utilizes both a terminal installed in the trash can and the user's own smart device to respond to the user's waste disposal behavior. The terminal is equipped with a camera and a weight sensor to acquire images and physical characteristics of the waste. This image acquisition method collects detailed information about the waste by having the camera photograph the waste and the weight sensor supplement the data.

[0097] The collected data is transmitted to a server via artificial intelligence. This server uses AI models such as TENSORFLOW® to analyze the image data and identify the type of waste it belongs to. Furthermore, based on these results, the server uses rule application tools to retrieve regional sorting rules from a database and construct appropriate instructions for the user.

[0098] The instruction generation system converts these instructions into text and then into speech using speech synthesis technology, providing them to users in a format that is easy to understand in real time. Furthermore, the ability to provide instructions via voice enables an easy-to-understand interface for all users, including those with visual impairments.

[0099] The system uses Bluetooth and Wi-Fi for communication between smart devices and servers, enabling users to receive immediate feedback. This allows users to check the optimal sorting method on the spot when disposing of waste.

[0100] As a concrete example, when a user disposes of a beverage container, the device's camera captures an image and a sensor measures its weight. This data is sent to a server where AI recognizes it as a beverage container. A prompt message is then generated, such as "When a beverage container is identified, please generate instructions on how to separate the cap." The server then provides the user with voice and text instructions, such as "Remove the cap and put it in the recycling bin," according to local rules.

[0101] Through this process, users can easily understand sorting methods and contribute to recycling efforts.

[0102] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0103] Step 1:

[0104] The device uses its camera to photograph objects discarded by the user. The input here is visual data of the object, and the output is saved as image data. Along with the image, the device also acquires physical weight data of the object measured by a weight sensor.

[0105] Step 2:

[0106] The terminal compresses the acquired image data and weight data and sends it to the server. The input is image and weight data, which are processed into a transmittable format using a data compression algorithm. The output is the data packets received by the server.

[0107] Step 3:

[0108] The server inputs the received data into an artificial intelligence model to classify the type of object. The input is compressed data, which the AI ​​analyzes using image analysis techniques. The output is category information for the identified waste.

[0109] Step 4:

[0110] The server uses the identified category information to retrieve regional sorting rules from the database using rule application mechanisms. The input is waste category information, and the output is the corresponding sorting instruction.

[0111] Step 5:

[0112] The server utilizes a generative AI model to generate visual and audio instructions for the user. Input consists of sorting instructions and generated prompts, and both speech synthesis and text instructions are output.

[0113] Step 6:

[0114] The server sends generated voice and text instructions to the terminal. The input is the generated instruction data, and the terminal provides the user with appropriate instructions in real time as output. The terminal plays these instructions aloud, and the text is displayed on the screen.

[0115] 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.

[0116] The smart waste sorting system of the present invention incorporates an emotion engine to provide users with more personalized and effective waste sorting support. The system first uses a terminal to capture images of the waste with an image acquisition means when the waste is put in, and acquires its physical characteristics with sensors. This allows basic waste data to be collected in real time.

[0117] The device then sends the collected data to the server. The server uses artificial intelligence to determine the type of waste. Simultaneously, an emotion engine processes the emotional data acquired from the device, analyzing the user's voice tone and facial expressions. The server then combines the waste type determination with the emotional analysis results.

[0118] Next, the server retrieves regional sorting rules using rule application mechanisms and optimizes those rules according to the user's emotional state, as determined by the emotion engine. In other words, if it detects that the user is stressed, it is intended to generate more concise and helpful instructions.

[0119] The instruction generation means generates sorting methods in text and audio formats based on the obtained data and transmits them to the terminal. The speech synthesis means here is particularly useful for visually impaired users. Based on emotional personalization, instructions are given in a tone and pacing that matches the user's current emotional state.

[0120] For example, when a user throws away a plastic bottle, the device takes a picture of it and measures its weight. The server analyzes this data, identifies it as a plastic bottle, and if it detects that the user's voice is in a hurry, it provides a short, rapid instruction such as, "Please remove the cap from the plastic bottle before recycling."

[0121] This invention provides embodiments that improve the user experience while also contributing to environmental protection by adjusting instructions to take user emotions into consideration and streamlining the sorting process.

[0122] The following describes the processing flow.

[0123] Step 1:

[0124] The device automatically captures an image of the waste when it is placed in the container using its camera, and acquires physical characteristics such as weight and size using its sensors. This allows for the collection of basic data.

[0125] Step 2:

[0126] The device captures the user's voice and facial expressions using emotion sensors and collects data to evaluate the user's psychological state.

[0127] Step 3:

[0128] The device collects image data, physical feature data, and emotional data and sends them to the server. This data is compressed and encrypted in real time before being transmitted.

[0129] Step 4:

[0130] The server analyzes the received image data using artificial intelligence to determine the classification of the waste. In this process, machine learning algorithms compare the features of the objects.

[0131] Step 5:

[0132] The server uses an emotion engine to analyze the received emotional data and identify the user's current emotional state. For example, it can determine whether the user is anxious or relaxed.

[0133] Step 6:

[0134] The server synthesizes waste types and region-specific sorting rules to generate optimal sorting instructions tailored to the user's emotional state. During this process, the length and tone of the instructions are adjusted.

[0135] Step 7:

[0136] The server sends the generated instructions to the terminal in both voice and text formats, and the terminal effectively notifies the user, including when the speech synthesis system outputs the instructions to the visually impaired. The user follows these instructions and sorts the waste appropriately.

[0137] (Example 2)

[0138] 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".

[0139] Conventional waste sorting systems have the functionality to properly classify waste, but they lack sufficient interfaces that take into account the user's emotional state. As a result, users sometimes experience stress, and the sorting process becomes cumbersome, which is a problem.

[0140] 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.

[0141] In this invention, the server includes an acquisition device for obtaining input data for classifying waste, an inference device for processing the data obtained from the acquisition device, and a rule application device for obtaining and applying regional waste sorting rules. This makes it possible to analyze a person's emotional state and provide optimal instructions accordingly.

[0142] An "acquisition device" is a device used to acquire input data necessary for classifying waste.

[0143] An "inference device" is a device used to classify the type of waste based on data obtained from an acquisition device.

[0144] A "rule application device" is a device that obtains and applies waste sorting regulations specific to a particular region.

[0145] A "directive generation device" is a device that, based on data from an inference device and a rule application device, notifies humans of waste sorting instructions via display or voice.

[0146] An "emotion analysis device" is a device that analyzes a person's voice tone and facial expressions to determine their emotional state.

[0147] An "optimization device" is a device that optimizes the instructions generated by the instruction generation device based on the results of the emotion analysis device.

[0148] The smart waste sorting system according to this invention is designed to provide appropriate waste classification and flexible instructions that respond to the user's emotions. The system is configured as follows:

[0149] First, the user places the waste into the terminal. The terminal uses acquisition devices such as cameras and weight sensors to capture images and physical characteristics of the waste. Specific examples of such terminals include commercially available tablets with cameras and sensors.

[0150] The acquired data is sent from the terminal to the server. The server uses an inference device to classify the type of waste based on the acquired data. The inference device uses an AI framework that supports common image analysis techniques. For example, it uses a machine learning library to analyze the shape and weight information of the waste and identify items such as PET bottles and metal cans.

[0151] Furthermore, the server uses an emotion analysis device to analyze the user's emotional state based on the user's voice tone and facial expressions obtained from the terminal. This analysis determines whether the user is in a hurry, relaxed, or otherwise in a state of mind.

[0152] Subsequently, the server retrieves regionally specific classification rules from the database and applies them using a rule application device. The applied rules and the results of sentiment analysis are combined, and the instructions are optimized using an optimization device.

[0153] Finally, the instruction generation device generates the necessary sorting instructions in text or voice and sends them to the terminal. By utilizing speech synthesis technology, the instructions are also provided in voice to users with visual impairments.

[0154] For example, if a user throws away a plastic bottle, the device takes a picture of it and measures its weight using a sensor. The server analyzes this data, identifies it as a plastic bottle, and if it detects that the user's voice is in a hurry, it issues a short, rapid instruction such as, "Please remove the cap from the plastic bottle and put it out for recycling." An example of a prompt to the generative AI model in this case would be, "If the user indicates they are in a hurry, provide a short recycling instruction."

[0155] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0156] Step 1:

[0157] The user places waste into the terminal. The terminal uses a camera to acquire images of the waste and a weight sensor to measure its physical characteristics. The input is the actual waste, and the output is image data and weight data. This data contains the basic information necessary for identifying the waste.

[0158] Step 2:

[0159] The terminal transmits the acquired image data and weight data to the server. Internet protocols are used for communication. The input is the data collected by the terminal, and the output is the data that reaches the server. Subsequent processing is performed based on this data.

[0160] Step 3:

[0161] The server analyzes image data and weight data using an inference device. Here, a generative AI model is used to estimate the type of waste. The input is image and weight data sent from the terminal, and the output is a determination result indicating the type of waste. This determination result provides a classification criterion.

[0162] Step 4:

[0163] The device collects the user's voice tone and facial expressions. It uses a microphone and camera to acquire data about the user's emotional state. The input is the user's current facial expressions and voice, while the output is data indicating their emotional state. This data is used to personalize instructions.

[0164] Step 5:

[0165] The server uses an emotion analysis device to analyze the user's emotional state. It uses the obtained voice and facial expression data as input to determine the emotional state and outputs the result. This analysis result is used to generate appropriate instructions for the user.

[0166] Step 6:

[0167] The server uses a rule-applying device to retrieve local waste sorting rules from a database. The input is local information, and the output is the corresponding sorting rule. This information is referenced when generating sorting instructions.

[0168] Step 7:

[0169] The server optimizes instructions by combining the acquired emotional state with classification rules. Using an optimization device, it constructs classification instructions best suited to the user's emotional state. The input is the emotional analysis results and classification rules, and the output is the optimized instruction data.

[0170] Step 8:

[0171] The instruction generator produces optimized instructions in text and voice. The instructions are sent to a terminal and notified to the user. The input is optimized instruction data, and the output is specific instructions provided to the user. The instructions are delivered in a tone that matches the user's emotional state.

[0172] (Application Example 2)

[0173] 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".

[0174] Proper sorting and separation of waste is crucial for environmental protection, but it can cause stress and confusion for users. This can lead to incorrect sorting and reduced recycling efficiency. This invention aims to streamline the waste sorting process and reduce the burden on users by providing personalized instructions that respond to the user's emotional state.

[0175] 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.

[0176] In this invention, the server includes video acquisition means for obtaining input data for classifying waste, emotion analysis means for analyzing the user's voice and facial expressions to determine their emotional state, and instruction generation means for optimizing and notifying instructions. This makes it possible to quickly provide appropriate instructions based on the user's emotional state.

[0177] "Image acquisition means" refers to a device or method for capturing visual information necessary for classifying waste.

[0178] "Machine learning methods" refer to artificial intelligence technologies that process data obtained from video acquisition methods and emotion analysis to automatically determine the type of waste.

[0179] "Means of applying rules" refer to means of obtaining different waste sorting rules for each region and applying them to waste classification.

[0180] "Emotional analysis means" refers to a system or process that analyzes a user's voice and facial expression data to recognize and determine the user's emotional state.

[0181] "Instruction generation means" refers to means that have the function of generating instructions for waste sorting for the user based on acquired data and notifying the user via display or audio.

[0182] "Speech synthesis means" is a technology that outputs generated instructions as speech, providing voice guidance tailored to visually impaired individuals and different situations.

[0183] "Voice emotion adaptation means" refers to a method for optimizing the tone and pacing of speech synthesis based on emotion detection, and for providing information to users in an easily understandable format.

[0184] The system for realizing the present invention includes a terminal, a server, and a network connecting them. The user receives assistance with waste sorting by using the terminal to photograph waste and provide voice input. This terminal is equipped with image acquisition means and voice input means. Specifically, it collects video and audio data using the camera and microphone of a smartphone.

[0185] Data acquired by the device is sent to a server in the cloud via the internet. The data is encrypted using the SSL / TLS protocol during transmission. The server utilizes machine learning techniques to analyze the received data. TensorFlow and PyTorch are used as machine learning frameworks to determine the type of waste.

[0186] Furthermore, the server's emotion analysis system evaluates the user's stress level and emotions by analyzing their emotional state from their voice and facial expressions. Based on this, an instruction generation system optimizes disposal methods in accordance with local regulations to generate appropriate instructions. A natural language processing model is used for language processing, and an emotion adaptation system is used for speech synthesis. A speech synthesis engine such as Azure® Speech Services is useful.

[0187] The generated instructions are fed back to the user in both text and audio. The instructions are delivered gently or concisely, depending on the user's emotional state. For example, if a user tries to throw away a plastic bottle and the server identifies it as such, a short and clear instruction such as "Remove the cap from the plastic bottle and then put it in the recycling bin" will be provided.

[0188] Examples of prompt messages include "Real-time waste sorting and emotional response optimization using AI." This allows users to sort their waste smoothly without experiencing stress.

[0189] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0190] Step 1:

[0191] The device allows the user to take images of waste with its camera and record voice input with its microphone. The input data consists of video and audio data. The video data shows the visual characteristics of the waste, and the audio data is used to analyze the emotions from the user's statements. The acquired data is temporarily stored on the device.

[0192] Step 2:

[0193] The terminal transmits the acquired video and audio data to the server. The data is encrypted using the SSL / TLS protocol. The transmitted data is received by the server. The input information is kept secure.

[0194] Step 3:

[0195] The server analyzes the received video data using machine learning techniques to classify the type of waste. This process utilizes TensorFlow and PyTorch to analyze the features contained in the video and determine which category the waste belongs to. The output is the identified type of waste.

[0196] Step 4:

[0197] In parallel, the server processes the voice data using emotion analysis tools to determine the user's emotional state. By analyzing voice tone and speed, it assesses whether the user is relaxed or stressed. The output is the identified emotional state.

[0198] Step 5:

[0199] The server generates instructions by combining the type of waste and the user's emotional state. The generated instructions are optimized based on local waste sorting regulations, and their tone and content are adjusted according to the emotional state. The output is the specific disposal method to be presented to the user.

[0200] Step 6:

[0201] The server sends the generated instructions to the terminal. The terminal displays these instructions in text and audio, notifying the user. Audio notifications use speech synthesis and are played back in an appropriate tone by speech emotion adaptation. This allows the user to confirm the sorting method in both audio and text before taking action.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] [Second Embodiment]

[0206] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0207] 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.

[0208] 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).

[0209] 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.

[0210] 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.

[0211] 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).

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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".

[0218] The smart waste sorting system of the present invention operates by combining multiple technological elements to support accurate classification and proper sorting of waste. First, a terminal installed in the trash can captures an image of the object using an image acquisition means each time waste is placed inside. This allows data such as the appearance, shape, and color of the waste to be collected in real time. In addition, sensors equipped in the terminal measure the weight and volume of the waste to supplement its physical characteristics.

[0219] The captured and measured data is compressed and sent to a server. The server inputs the image and sensor data into artificial intelligence (AI) systems and determines the type of waste based on previously learned patterns. For example, it has the ability to distinguish between different types of waste, such as plastic bottles, glass bottles, and metal cans.

[0220] Subsequently, the server uses rule application means to retrieve regional sorting rules from the database based on the classification results. This is essential for providing instructions that conform to different sorting criteria for each region. The sorting instructions generated by the server are converted into text and audio information by the instruction generation means and returned to the terminal.

[0221] Users can receive visual and auditory sorting instructions from the device and properly sort their waste. For visually impaired users, speech synthesis provides instructions verbally, making the sorting process easy for anyone.

[0222] As a concrete example, consider a scenario where a user throws an empty plastic bottle into a trash can. The terminal acquires an image of the bottle and measures its weight. The server receives this data, recognizes it as a plastic bottle using artificial intelligence, and generates instructions such as "Remove the cap and rinse the inside" based on local regulations. The user follows these instructions for sorting, and the system accumulates the data to further improve accuracy. In this way, the present invention realizes appropriate waste disposal for each region, contributing to user convenience and environmental protection.

[0223] The following describes the processing flow.

[0224] Step 1:

[0225] The device uses a camera to photograph waste placed in the trash can and acquires image data. It also uses sensors to collect data on the weight and shape of the waste.

[0226] Step 2:

[0227] The device compresses the acquired images and sensor data and securely transmits them to the server. Data compression and encryption processing takes place at this stage.

[0228] Step 3:

[0229] The server analyzes the received data using artificial intelligence to determine the type of waste. Here, image analysis technology is used to extract the features of the objects, and classification is performed based on those features.

[0230] Step 4:

[0231] Based on the determined type of waste, the server uses rule application mechanisms to retrieve the sorting rules for the relevant area from the database.

[0232] Step 5:

[0233] The server uses an instruction generation mechanism to construct sorting instructions to be provided to the user, in accordance with the acquired regional rules. The instructions are generated in both text and audio formats.

[0234] Step 6:

[0235] The server sends the generated instructions to the terminal. Information is conveyed using speech synthesis, ensuring it is not dependent on visual information.

[0236] Step 7:

[0237] The terminal notifies the user of received sorting instructions, clearly communicating the instructions through display and voice. The user then properly disposes of the waste according to these instructions.

[0238] (Example 1)

[0239] 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."

[0240] Conventional waste sorting systems have problems accurately identifying types of waste and adapting to different sorting standards in different regions. They also have the challenge of providing insufficient instructions for visually impaired individuals. Furthermore, their accuracy is limited because they lack the ability to classify waste based on its physical characteristics.

[0241] 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.

[0242] In this invention, the server includes a visual acquisition means, a means for compressing and transmitting information obtained from a weight measuring device, a generation AI means for determining the type of waste based on previously learned patterns, a rule application means for acquiring and applying waste sorting standards for each region, and an instruction generation means for displaying or notifying the user of instructions via voice. This enables high-precision classification of waste and the provision of appropriate sorting instructions according to the region, making it possible for all users, including visually impaired individuals, to properly sort their waste.

[0243] A "visual acquisition means" is a device for collecting visual information about waste, and it uses cameras and sensors to acquire information such as the appearance, shape, and color of the waste.

[0244] A "weight measuring device" is a measuring device used to measure the weight of waste and to supplement the physical characteristics of the waste.

[0245] "Means for compressing and transmitting information" refers to means that have the function of compressing acquired data in order to transmit it effectively and then sending it to a receiving side such as a server.

[0246] "Generative AI means" refers to artificial intelligence technology used to identify and classify types of waste using previously learned data.

[0247] "Means of applying regulations" refers to a program or processing system for obtaining regional waste sorting standards and applying them to the waste classification results.

[0248] "Instruction generation means" refers to a device or function that generates differentiated instructions for the user based on information from the server and notifies the user of these instructions via display or sound.

[0249] The waste sorting system of the present invention operates in conjunction with a terminal and a server. The terminal is installed in a trash can and takes an image of the waste using visual acquisition means each time waste is put in. This visual acquisition means includes a camera and image sensors to acquire the appearance, color, and shape of the waste. In addition, a weight measuring device is incorporated into the terminal to measure the weight and volume of the waste and supplement its physical characteristics.

[0250] The captured and measured data is transmitted to the server by a means of compressing and transmitting terminal information. The server inputs the received data into a generating AI means and determines the type of waste using previously learned patterns. This generating AI means uses an artificial intelligence model (AI model) to perform image analysis and physical feature analysis of the waste. The server then uses a rule application means to retrieve and apply regional sorting standards from a database based on the determined type of waste.

[0251] The server converts the results into instructions using an instruction generation mechanism and provides them to the user. These include visual instructions via display and voice instructions via speech synthesis. This allows the user to make appropriate classifications according to the instructions provided from the terminal.

[0252] As a concrete example, consider a scenario where a user throws a glass bottle into a trash can. The terminal acquires an image of the glass bottle and measures its weight. The server receives this information and uses AI to identify the waste as a glass bottle. Then, based on local sorting rules, it generates an instruction such as, "Please place glass bottles in the designated recycling box." The user follows this instruction and sorts the waste appropriately. In this way, the system flexibly adapts to local sorting rules and contributes to environmental protection.

[0253] Example prompt for the generated AI model: "Generate a program that identifies glass bottles and plastic bottles in a smart waste sorting system and provides the user with appropriate sorting instructions based on that."

[0254] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0255] Step 1:

[0256] The terminal captures an image of the waste each time it is deposited using a visual acquisition device. The input is the actual waste, and the output is visual information (image data) of the waste. The terminal uses a camera to capture the appearance, color, and shape of the waste.

[0257] Step 2:

[0258] The terminal measures the weight of the waste using a weighing device. The input is the physical presence of the waste, and the output is the weight data of the waste. This supplements the weight as a physical characteristic.

[0259] Step 3:

[0260] The terminal compresses the acquired image data and weight data into a single data package and sends it to the server. The input is a pair of visual and weight information, and the output is a compressed data file sent to the server. Transmission takes place in real time over the network.

[0261] Step 4:

[0262] The server receives and decompresses compressed data. The input is a data file sent from the terminal, and the output is the decompressed image data and weight data. This data is then ready to be input into the generating AI system.

[0263] Step 5:

[0264] The server's AI generation method uses decompressed data to determine the type of waste. Inputs are image data and weight data, and output is the determined waste type information. The AI ​​model performs pattern recognition using past training data.

[0265] Step 6:

[0266] The server uses rule application methods to retrieve and apply local sorting standards based on the determined waste type. The input is waste type information, and the output is sorting instructions appropriate for the region. Rules are referenced from a database.

[0267] Step 7:

[0268] The server converts the sorting instructions into text or audio format using an instruction generation device and sends them to the terminal. The input is the sorting instructions, and the output is the instruction information provided to the user.

[0269] Step 8:

[0270] The user sorts waste appropriately according to instructions received from the terminal. Input consists of visual and auditory instructions, while output is the user's sorting actions. This facilitates the proper disposal of waste.

[0271] (Application Example 1)

[0272] 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."

[0273] In modern urban environments, proper waste sorting and recycling are critical social issues, but many people find it difficult to accurately understand and follow complex sorting rules. Furthermore, there is a lack of systems that allow diverse users, including the visually impaired, to easily and appropriately sort their waste. To address this challenge, there is a need to provide a system that allows users to receive real-time instructions, thereby improving user convenience and reducing environmental impact.

[0274] 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.

[0275] In this invention, the server includes an image acquisition means for acquiring input data for classifying waste, an artificial intelligence means for processing the data obtained from the image acquisition means, a rule application means for acquiring and applying waste sorting rules for each region, and a communication means that works in conjunction with a smart device that provides instructions in real time. This makes it possible for users to instantly receive instructions on the appropriate sorting method via a smart device when disposing of waste.

[0276] An "image acquisition means" is a device that uses cameras and sensors to acquire image data in order to collect the external characteristics of waste.

[0277] "Artificial intelligence means" refers to artificial intelligence algorithms and programs used to analyze acquired images and data to determine the type and classification of waste.

[0278] "Means of applying rules" refers to a database and its matching function that references local waste sorting standards and provides instructions tailored to the user.

[0279] "Instruction generation means" refers to a device or program that creates instructions in text or voice to communicate to the user the appropriate method of disposing of waste based on the analysis results.

[0280] "Communication means" refers to a network connection technology that enables the system to transmit and receive data with smart devices and provide instructions in real time.

[0281] The present invention provides a system that appropriately classifies waste and provides users with sorting instructions. Specific embodiments for realizing this system are shown below.

[0282] First, in order to respond to the user's waste disposal behavior, the system utilizes both the terminal installed in the trash can and the smart device held by the user. The terminal is equipped with a camera and a weight sensor to acquire images and physical characteristics of the waste. This image acquisition means collects detailed information about the waste by the camera taking pictures of the waste and the sensor measuring the weight supplementing the data.

[0283] The collected data is transmitted to the server through artificial intelligence means. This server uses an AI model such as TensorFlow to analyze the image data and identify into which types the waste is classified. Furthermore, based on the result, the server uses rule application means to obtain the sorting rules for each region from the database and compose appropriate instructions for the user.

[0284] The instruction generation means texts these instructions and vocalizes them through voice synthesis technology to provide them to the user in a form that is easy to understand in real time. Also, by enabling voice instructions, an easy-to-understand interface is realized for all users including visually impaired users.

[0285] As communication means, data communication between the smart device and the server is performed using Bluetooth or Wi-Fi so that immediate feedback can be sent to the user. Thereby, when the user disposes of waste, the optimal sorting method can be confirmed on the spot.

[0286] As a specific example, when a user discards a beverage container, the camera of the terminal acquires an image and the sensor measures the weight. These data are sent to the server and recognized as a beverage container by the AI. The instruction is formulated in the form of a prompt sentence such as "When identifying a beverage container, please generate an instruction regarding the separation of the cap", and the server provides the user with instructions in voice and text according to the regional rules, such as "Remove the cap and put it into the recycling box".

[0287] Through this process, the user can easily understand the separation method and contribute to the recycling activities.

[0288] The flow of the specific process in Application Example 1 will be described with reference to FIG. 12.

[0289] Step 1:

[0290] The terminal takes a picture of the object discarded by the user with the camera. The input here is the visual data of the object, and the output is saved as image data. The terminal also acquires the physical weight data of the object measured by the weight sensor together with the image.

[0291] Step 2:

[0292] The terminal compresses the acquired image data and weight data and sends them to the server. The input is the image and weight data, which are processed into a transmissible form by the data compression algorithm. The output is the data packet received by the server.

[0293] Step 3:

[0294] The server inputs the received data into the artificial intelligence model to classify the type of the object. The input is the compressed data, and the AI analyzes it using image analysis technology. The output is the category information of the identified waste.

[0295] Step 4:

[0296] The server uses the identified category information to retrieve regional sorting rules from the database using rule application mechanisms. The input is waste category information, and the output is the corresponding sorting instruction.

[0297] Step 5:

[0298] The server utilizes a generative AI model to generate visual and audio instructions for the user. Input consists of sorting instructions and generated prompts, and both speech synthesis and text instructions are output.

[0299] Step 6:

[0300] The server sends generated voice and text instructions to the terminal. The input is the generated instruction data, and the terminal provides the user with appropriate instructions in real time as output. The terminal plays these instructions aloud, and the text is displayed on the screen.

[0301] 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.

[0302] The smart waste sorting system of the present invention incorporates an emotion engine to provide users with more personalized and effective waste sorting support. The system first uses a terminal to capture images of the waste with an image acquisition means when the waste is put in, and acquires its physical characteristics with sensors. This allows basic waste data to be collected in real time.

[0303] The device then sends the collected data to the server. The server uses artificial intelligence to determine the type of waste. Simultaneously, an emotion engine processes the emotional data acquired from the device, analyzing the user's voice tone and facial expressions. The server then combines the waste type determination with the emotional analysis results.

[0304] Subsequently, the server obtains the regional classification rules using the rule application means and optimizes the rules according to the user's emotional state by the emotion engine. That is, when it is sensed that the user is feeling stressed, it intends to generate more concise and friendly instructions.

[0305] The instruction generation means generates a classification method in the form of text and voice based on the obtained data and transmits it to the terminal. The voice synthesis means here is particularly utilized for visually impaired persons. Based on the personalization by emotion, instructions are given in a tone and pacing suitable for the user's current emotional state.

[0306] For example, when the user discards a PET bottle, the terminal takes a picture of it and measures its weight. The server analyzes it, and when it determines that it is a PET bottle and senses that the user's voice is in a hurry tone, it provides an instruction such as "Please remove the cap of the PET bottle and put it out for recycling" in a short and fast pace.

[0307] The present invention provides an embodiment that improves the user experience and contributes to environmental protection by adjusting instructions in consideration of the user's emotions and smoothing the sorting process.

[0308] The following describes the processing flow.

[0309] Step 1:

[0310] When waste is input, the terminal automatically takes a picture of it with a camera and obtains physical characteristics such as weight and size with a sensor. Thereby, basic data is collected.

[0311] Step 2:

[0312] The terminal captures the user's voice and expression with an emotion sensor and collects data for evaluating the user's psychological state.

[0313] Step 3:

[0314] The device collects image data, physical feature data, and emotional data and sends them to the server. This data is compressed and encrypted in real time before being transmitted.

[0315] Step 4:

[0316] The server analyzes the received image data using artificial intelligence to determine the classification of the waste. In this process, machine learning algorithms compare the features of the objects.

[0317] Step 5:

[0318] The server uses an emotion engine to analyze the received emotional data and identify the user's current emotional state. For example, it can determine whether the user is anxious or relaxed.

[0319] Step 6:

[0320] The server synthesizes waste types and region-specific sorting rules to generate optimal sorting instructions tailored to the user's emotional state. During this process, the length and tone of the instructions are adjusted.

[0321] Step 7:

[0322] The server sends the generated instructions to the terminal in both voice and text formats, and the terminal effectively notifies the user, including when the speech synthesis system outputs the instructions to the visually impaired. The user follows these instructions and sorts the waste appropriately.

[0323] (Example 2)

[0324] 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".

[0325] Conventional waste sorting systems have the functionality to properly classify waste, but they lack sufficient interfaces that take into account the user's emotional state. As a result, users sometimes experience stress, and the sorting process becomes cumbersome, which is a problem.

[0326] 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.

[0327] In this invention, the server includes an acquisition device for obtaining input data for classifying waste, an inference device for processing the data obtained from the acquisition device, and a rule application device for obtaining and applying regional waste sorting rules. This makes it possible to analyze a person's emotional state and provide optimal instructions accordingly.

[0328] An "acquisition device" is a device used to acquire input data necessary for classifying waste.

[0329] An "inference device" is a device used to classify the type of waste based on data obtained from an acquisition device.

[0330] A "rule application device" is a device that obtains and applies waste sorting regulations specific to a particular region.

[0331] A "directive generation device" is a device that, based on data from an inference device and a rule application device, notifies humans of waste sorting instructions via display or voice.

[0332] An "emotion analysis device" is a device that analyzes a person's voice tone and facial expressions to determine their emotional state.

[0333] An "optimization device" is a device that optimizes the instructions generated by the instruction generation device based on the results of the emotion analysis device.

[0334] The smart waste sorting system according to this invention is designed to provide appropriate waste classification and flexible instructions that respond to the user's emotions. The system is configured as follows:

[0335] First, the user places the waste into the terminal. The terminal uses acquisition devices such as cameras and weight sensors to capture images and physical characteristics of the waste. Specific examples of such terminals include commercially available tablets with cameras and sensors.

[0336] The acquired data is sent from the terminal to the server. The server uses an inference device to classify the type of waste based on the acquired data. The inference device uses an AI framework that supports common image analysis techniques. For example, it uses a machine learning library to analyze the shape and weight information of the waste and identify items such as PET bottles and metal cans.

[0337] Furthermore, the server uses an emotion analysis device to analyze the user's emotional state based on the user's voice tone and facial expressions obtained from the terminal. This analysis determines whether the user is in a hurry, relaxed, or otherwise in a state of mind.

[0338] Subsequently, the server retrieves regionally specific classification rules from the database and applies them using a rule application device. The applied rules and the results of sentiment analysis are combined, and the instructions are optimized using an optimization device.

[0339] Finally, the instruction generation device generates the necessary sorting instructions in text or voice and sends them to the terminal. By utilizing speech synthesis technology, the instructions are also provided in voice to users with visual impairments.

[0340] For example, if a user throws away a plastic bottle, the device takes a picture of it and measures its weight using a sensor. The server analyzes this data, identifies it as a plastic bottle, and if it detects that the user's voice is in a hurry, it issues a short, rapid instruction such as, "Please remove the cap from the plastic bottle and put it out for recycling." An example of a prompt to the generative AI model in this case would be, "If the user indicates they are in a hurry, provide a short recycling instruction."

[0341] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0342] Step 1:

[0343] The user places waste into the terminal. The terminal uses a camera to acquire images of the waste and a weight sensor to measure its physical characteristics. The input is the actual waste, and the output is image data and weight data. This data contains the basic information necessary for identifying the waste.

[0344] Step 2:

[0345] The terminal transmits the acquired image data and weight data to the server. Internet protocols are used for communication. The input is the data collected by the terminal, and the output is the data that reaches the server. Subsequent processing is performed based on this data.

[0346] Step 3:

[0347] The server analyzes image data and weight data using an inference device. Here, a generative AI model is used to estimate the type of waste. The input is image and weight data sent from the terminal, and the output is a determination result indicating the type of waste. This determination result provides a classification criterion.

[0348] Step 4:

[0349] The device collects the user's voice tone and facial expressions. It uses a microphone and camera to acquire data about the user's emotional state. The input is the user's current facial expressions and voice, while the output is data indicating their emotional state. This data is used to personalize instructions.

[0350] Step 5:

[0351] The server uses an emotion analysis device to analyze the user's emotional state. It uses the obtained voice and facial expression data as input to determine the emotional state and outputs the result. This analysis result is used to generate appropriate instructions for the user.

[0352] Step 6:

[0353] The server uses a rule-applying device to retrieve local waste sorting rules from a database. The input is local information, and the output is the corresponding sorting rule. This information is referenced when generating sorting instructions.

[0354] Step 7:

[0355] The server optimizes instructions by combining the acquired emotional state with classification rules. Using an optimization device, it constructs classification instructions best suited to the user's emotional state. The input is the emotional analysis results and classification rules, and the output is the optimized instruction data.

[0356] Step 8:

[0357] The instruction generator produces optimized instructions in text and voice. The instructions are sent to a terminal and notified to the user. The input is optimized instruction data, and the output is specific instructions provided to the user. The instructions are delivered in a tone that matches the user's emotional state.

[0358] (Application Example 2)

[0359] 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."

[0360] Proper sorting and separation of waste is crucial for environmental protection, but it can cause stress and confusion for users. This can lead to incorrect sorting and reduced recycling efficiency. This invention aims to streamline the waste sorting process and reduce the burden on users by providing personalized instructions that respond to the user's emotional state.

[0361] 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.

[0362] In this invention, the server includes video acquisition means for obtaining input data for classifying waste, emotion analysis means for analyzing the user's voice and facial expressions to determine their emotional state, and instruction generation means for optimizing and notifying instructions. This makes it possible to quickly provide appropriate instructions based on the user's emotional state.

[0363] "Image acquisition means" refers to a device or method for capturing visual information necessary for classifying waste.

[0364] "Machine learning methods" refer to artificial intelligence technologies that process data obtained from video acquisition methods and emotion analysis to automatically determine the type of waste.

[0365] "Means of applying rules" refer to means of obtaining different waste sorting rules for each region and applying them to waste classification.

[0366] "Emotional analysis means" refers to a system or process that analyzes a user's voice and facial expression data to recognize and determine the user's emotional state.

[0367] "Instruction generation means" refers to means that have the function of generating instructions for waste sorting for the user based on acquired data and notifying the user via display or audio.

[0368] "Speech synthesis means" is a technology that outputs generated instructions as speech, providing voice guidance tailored to visually impaired individuals and different situations.

[0369] "Voice emotion adaptation means" refers to a method for optimizing the tone and pacing of speech synthesis based on emotion detection, and for providing information to users in an easily understandable format.

[0370] The system for realizing the present invention includes a terminal, a server, and a network connecting them. The user receives assistance with waste sorting by using the terminal to photograph waste and provide voice input. This terminal is equipped with image acquisition means and voice input means. Specifically, it collects video and audio data using the camera and microphone of a smartphone.

[0371] Data acquired by the device is sent to a server in the cloud via the internet. The data is encrypted using the SSL / TLS protocol during transmission. The server utilizes machine learning techniques to analyze the received data. TensorFlow and PyTorch are used as machine learning frameworks to determine the type of waste.

[0372] Furthermore, the server's emotion analysis system evaluates the user's stress level and emotions by analyzing their emotional state from their voice and facial expressions. Based on this, an instruction generation system optimizes disposal methods in accordance with local regulations to generate appropriate instructions. A natural language processing model is used for language processing, and an emotion-adaptive speech synthesis system is used for speech synthesis. A speech synthesis engine such as Azure Speech Services is useful.

[0373] The generated instructions are fed back to the user in both text and audio. The instructions are delivered gently or concisely, depending on the user's emotional state. For example, if a user tries to throw away a plastic bottle and the server identifies it as such, a short and clear instruction such as "Remove the cap from the plastic bottle and then put it in the recycling bin" will be provided.

[0374] Examples of prompt messages include "Real-time waste sorting and emotional response optimization using AI." This allows users to sort their waste smoothly without experiencing stress.

[0375] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0376] Step 1:

[0377] The device allows the user to take images of waste with its camera and record voice input with its microphone. The input data consists of video and audio data. The video data shows the visual characteristics of the waste, and the audio data is used to analyze the emotions from the user's statements. The acquired data is temporarily stored on the device.

[0378] Step 2:

[0379] The terminal transmits the acquired video and audio data to the server. The data is encrypted using the SSL / TLS protocol. The transmitted data is received by the server. The input information is kept secure.

[0380] Step 3:

[0381] The server analyzes the received video data using machine learning techniques to classify the type of waste. This process utilizes TensorFlow and PyTorch to analyze the features contained in the video and determine which category the waste belongs to. The output is the identified type of waste.

[0382] Step 4:

[0383] In parallel, the server processes the voice data using emotion analysis tools to determine the user's emotional state. By analyzing voice tone and speed, it assesses whether the user is relaxed or stressed. The output is the identified emotional state.

[0384] Step 5:

[0385] The server generates instructions by combining the type of waste and the user's emotional state. The generated instructions are optimized based on local waste sorting regulations, and their tone and content are adjusted according to the emotional state. The output is the specific disposal method to be presented to the user.

[0386] Step 6:

[0387] The server sends the generated instructions to the terminal. The terminal displays these instructions in text and audio, notifying the user. Audio notifications use speech synthesis and are played back in an appropriate tone by speech emotion adaptation. This allows the user to confirm the sorting method in both audio and text before taking action.

[0388] 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.

[0389] 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.

[0390] 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.

[0391] [Third Embodiment]

[0392] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0393] 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.

[0394] 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).

[0395] 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.

[0396] 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.

[0397] 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).

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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.

[0403] 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".

[0404] The smart waste sorting system of the present invention operates by combining multiple technological elements to support accurate classification and proper sorting of waste. First, a terminal installed in the trash can captures an image of the object using an image acquisition means each time waste is placed inside. This allows data such as the appearance, shape, and color of the waste to be collected in real time. In addition, sensors equipped in the terminal measure the weight and volume of the waste to supplement its physical characteristics.

[0405] The captured and measured data is compressed and sent to a server. The server inputs the image and sensor data into artificial intelligence (AI) systems and determines the type of waste based on previously learned patterns. For example, it has the ability to distinguish between different types of waste, such as plastic bottles, glass bottles, and metal cans.

[0406] Subsequently, the server uses rule application means to retrieve regional sorting rules from the database based on the classification results. This is essential for providing instructions that conform to different sorting criteria for each region. The sorting instructions generated by the server are converted into text and audio information by the instruction generation means and returned to the terminal.

[0407] Users can receive visual and auditory sorting instructions from the device and properly sort their waste. For visually impaired users, speech synthesis provides instructions verbally, making the sorting process easy for anyone.

[0408] As a concrete example, consider a scenario where a user throws an empty plastic bottle into a trash can. The terminal acquires an image of the bottle and measures its weight. The server receives this data, recognizes it as a plastic bottle using artificial intelligence, and generates instructions such as "Remove the cap and rinse the inside" based on local regulations. The user follows these instructions for sorting, and the system accumulates the data to further improve accuracy. In this way, the present invention realizes appropriate waste disposal for each region, contributing to user convenience and environmental protection.

[0409] The following describes the processing flow.

[0410] Step 1:

[0411] The device uses a camera to photograph waste placed in the trash can and acquires image data. It also uses sensors to collect data on the weight and shape of the waste.

[0412] Step 2:

[0413] The device compresses the acquired images and sensor data and securely transmits them to the server. Data compression and encryption processing takes place at this stage.

[0414] Step 3:

[0415] The server analyzes the received data using artificial intelligence to determine the type of waste. Here, image analysis technology is used to extract the features of the objects, and classification is performed based on those features.

[0416] Step 4:

[0417] Based on the determined type of waste, the server uses rule application mechanisms to retrieve the sorting rules for the relevant area from the database.

[0418] Step 5:

[0419] The server uses an instruction generation mechanism to construct sorting instructions to be provided to the user, in accordance with the acquired regional rules. The instructions are generated in both text and audio formats.

[0420] Step 6:

[0421] The server sends the generated instructions to the terminal. Information is conveyed using speech synthesis, ensuring it is not dependent on visual information.

[0422] Step 7:

[0423] The terminal notifies the user of received sorting instructions, clearly communicating the instructions through display and voice. The user then properly disposes of the waste according to these instructions.

[0424] (Example 1)

[0425] 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."

[0426] Conventional waste sorting systems have problems accurately identifying types of waste and adapting to different sorting standards in different regions. They also have the challenge of providing insufficient instructions for visually impaired individuals. Furthermore, their accuracy is limited because they lack the ability to classify waste based on its physical characteristics.

[0427] 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.

[0428] In this invention, the server includes a visual acquisition means, a means for compressing and transmitting information obtained from a weight measuring device, a generation AI means for determining the type of waste based on previously learned patterns, a rule application means for acquiring and applying waste sorting standards for each region, and an instruction generation means for displaying or notifying the user of instructions via voice. This enables high-precision classification of waste and the provision of appropriate sorting instructions according to the region, making it possible for all users, including visually impaired individuals, to properly sort their waste.

[0429] A "visual acquisition means" is a device for collecting visual information about waste, and it uses cameras and sensors to acquire information such as the appearance, shape, and color of the waste.

[0430] A "weight measuring device" is a measuring device used to measure the weight of waste and to supplement the physical characteristics of the waste.

[0431] "Means for compressing and transmitting information" refers to means that have the function of compressing acquired data in order to transmit it effectively and then sending it to a receiving side such as a server.

[0432] "Generative AI means" refers to artificial intelligence technology used to identify and classify types of waste using previously learned data.

[0433] "Means of applying regulations" refers to a program or processing system for obtaining regional waste sorting standards and applying them to the waste classification results.

[0434] "Instruction generation means" refers to a device or function that generates differentiated instructions for the user based on information from the server and notifies the user of these instructions via display or sound.

[0435] The waste sorting system of the present invention operates in conjunction with a terminal and a server. The terminal is installed in a trash can and takes an image of the waste using visual acquisition means each time waste is put in. This visual acquisition means includes a camera and image sensors to acquire the appearance, color, and shape of the waste. In addition, a weight measuring device is incorporated into the terminal to measure the weight and volume of the waste and supplement its physical characteristics.

[0436] The captured and measured data is transmitted to the server by a means of compressing and transmitting terminal information. The server inputs the received data into a generating AI means and determines the type of waste using previously learned patterns. This generating AI means uses an artificial intelligence model (AI model) to perform image analysis and physical feature analysis of the waste. The server then uses a rule application means to retrieve and apply regional sorting standards from a database based on the determined type of waste.

[0437] The server converts the results into instructions using an instruction generation mechanism and provides them to the user. These include visual instructions via display and voice instructions via speech synthesis. This allows the user to make appropriate classifications according to the instructions provided from the terminal.

[0438] As a concrete example, consider a scenario where a user throws a glass bottle into a trash can. The terminal acquires an image of the glass bottle and measures its weight. The server receives this information and uses AI to identify the waste as a glass bottle. Then, based on local sorting rules, it generates an instruction such as, "Please place glass bottles in the designated recycling box." The user follows this instruction and sorts the waste appropriately. In this way, the system flexibly adapts to local sorting rules and contributes to environmental protection.

[0439] Example prompt for the generated AI model: "Generate a program that identifies glass bottles and plastic bottles in a smart waste sorting system and provides the user with appropriate sorting instructions based on that."

[0440] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0441] Step 1:

[0442] The terminal captures an image of the waste each time it is deposited using a visual acquisition device. The input is the actual waste, and the output is visual information (image data) of the waste. The terminal uses a camera to capture the appearance, color, and shape of the waste.

[0443] Step 2:

[0444] The terminal measures the weight of the waste using a weighing device. The input is the physical presence of the waste, and the output is the weight data of the waste. This supplements the weight as a physical characteristic.

[0445] Step 3:

[0446] The terminal compresses the acquired image data and weight data into a single data package and sends it to the server. The input is a pair of visual and weight information, and the output is a compressed data file sent to the server. Transmission takes place in real time over the network.

[0447] Step 4:

[0448] The server receives and decompresses compressed data. The input is a data file sent from the terminal, and the output is the decompressed image data and weight data. This data is then ready to be input into the generating AI system.

[0449] Step 5:

[0450] The server's AI generation method uses decompressed data to determine the type of waste. Inputs are image data and weight data, and output is the determined waste type information. The AI ​​model performs pattern recognition using past training data.

[0451] Step 6:

[0452] The server uses rule application methods to retrieve and apply local sorting standards based on the determined waste type. The input is waste type information, and the output is sorting instructions appropriate for the region. Rules are referenced from a database.

[0453] Step 7:

[0454] The server converts the sorting instructions into text or audio format using an instruction generation device and sends them to the terminal. The input is the sorting instructions, and the output is the instruction information provided to the user.

[0455] Step 8:

[0456] The user sorts waste appropriately according to instructions received from the terminal. Input consists of visual and auditory instructions, while output is the user's sorting actions. This facilitates the proper disposal of waste.

[0457] (Application Example 1)

[0458] 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."

[0459] In modern urban environments, proper waste sorting and recycling are critical social issues, but many people find it difficult to accurately understand and follow complex sorting rules. Furthermore, there is a lack of systems that allow diverse users, including the visually impaired, to easily and appropriately sort their waste. To address this challenge, there is a need to provide a system that allows users to receive real-time instructions, thereby improving user convenience and reducing environmental impact.

[0460] 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.

[0461] In this invention, the server includes an image acquisition means for acquiring input data for classifying waste, an artificial intelligence means for processing the data obtained from the image acquisition means, a rule application means for acquiring and applying waste sorting rules for each region, and a communication means that works in conjunction with a smart device that provides instructions in real time. This makes it possible for users to instantly receive instructions on the appropriate sorting method via a smart device when disposing of waste.

[0462] An "image acquisition means" is a device that uses cameras and sensors to acquire image data in order to collect the external characteristics of waste.

[0463] "Artificial intelligence means" refers to artificial intelligence algorithms and programs used to analyze acquired images and data to determine the type and classification of waste.

[0464] "Means of applying rules" refers to a database and its matching function that references local waste sorting standards and provides instructions tailored to the user.

[0465] "Instruction generation means" refers to a device or program that creates instructions in text or voice to communicate to the user the appropriate method of disposing of waste based on the analysis results.

[0466] "Communication means" refers to network connectivity technology that enables a system to send and receive data with smart devices and provide instructions in real time.

[0467] This invention provides a system for appropriately classifying waste and providing sorting instructions to the user. Specific embodiments for realizing this system are described below.

[0468] First, the system utilizes both a terminal installed in the trash can and the user's own smart device to respond to the user's waste disposal behavior. The terminal is equipped with a camera and a weight sensor to acquire images and physical characteristics of the waste. This image acquisition method collects detailed information about the waste by having the camera photograph the waste and the weight sensor supplement the data.

[0469] The collected data is transmitted to a server via artificial intelligence. This server uses AI models such as TensorFlow to analyze the image data and identify the type of waste it belongs to. Furthermore, based on the results, the server uses rule-applying mechanisms to retrieve regional sorting rules from a database and construct appropriate instructions for the user.

[0470] The instruction generation system converts these instructions into text and then into speech using speech synthesis technology, providing them to users in a format that is easy to understand in real time. Furthermore, the ability to provide instructions via voice enables an easy-to-understand interface for all users, including those with visual impairments.

[0471] The system uses Bluetooth and Wi-Fi for communication between smart devices and servers, enabling users to receive immediate feedback. This allows users to check the optimal sorting method on the spot when disposing of waste.

[0472] As a concrete example, when a user disposes of a beverage container, the device's camera captures an image and a sensor measures its weight. This data is sent to a server where AI recognizes it as a beverage container. A prompt message is then generated, such as "When a beverage container is identified, please generate instructions on how to separate the cap." The server then provides the user with voice and text instructions, such as "Remove the cap and put it in the recycling bin," according to local rules.

[0473] Through this process, users can easily understand sorting methods and contribute to recycling efforts.

[0474] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0475] Step 1:

[0476] The device uses its camera to photograph objects discarded by the user. The input here is visual data of the object, and the output is saved as image data. Along with the image, the device also acquires physical weight data of the object measured by a weight sensor.

[0477] Step 2:

[0478] The terminal compresses the acquired image data and weight data and sends it to the server. The input is image and weight data, which are processed into a transmittable format using a data compression algorithm. The output is the data packets received by the server.

[0479] Step 3:

[0480] The server inputs the received data into an artificial intelligence model to classify the type of object. The input is compressed data, which the AI ​​analyzes using image analysis techniques. The output is category information for the identified waste.

[0481] Step 4:

[0482] The server uses the identified category information to retrieve regional sorting rules from the database using rule application mechanisms. The input is waste category information, and the output is the corresponding sorting instruction.

[0483] Step 5:

[0484] The server utilizes a generative AI model to generate visual and audio instructions for the user. Input consists of sorting instructions and generated prompts, and both speech synthesis and text instructions are output.

[0485] Step 6:

[0486] The server sends generated voice and text instructions to the terminal. The input is the generated instruction data, and the terminal provides the user with appropriate instructions in real time as output. The terminal plays these instructions aloud, and the text is displayed on the screen.

[0487] 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.

[0488] The smart waste sorting system of the present invention incorporates an emotion engine to provide users with more personalized and effective waste sorting support. The system first uses a terminal to capture images of the waste with an image acquisition means when the waste is put in, and acquires its physical characteristics with sensors. This allows basic waste data to be collected in real time.

[0489] The device then sends the collected data to the server. The server uses artificial intelligence to determine the type of waste. Simultaneously, an emotion engine processes the emotional data acquired from the device, analyzing the user's voice tone and facial expressions. The server then combines the waste type determination with the emotional analysis results.

[0490] Next, the server retrieves regional sorting rules using rule application mechanisms and optimizes those rules according to the user's emotional state, as determined by the emotion engine. In other words, if it detects that the user is stressed, it is intended to generate more concise and helpful instructions.

[0491] The instruction generation means generates sorting methods in text and audio formats based on the obtained data and transmits them to the terminal. The speech synthesis means here is particularly useful for visually impaired users. Based on emotional personalization, instructions are given in a tone and pacing that matches the user's current emotional state.

[0492] For example, when a user throws away a plastic bottle, the device takes a picture of it and measures its weight. The server analyzes this data, identifies it as a plastic bottle, and if it detects that the user's voice is in a hurry, it provides a short, rapid instruction such as, "Please remove the cap from the plastic bottle before recycling."

[0493] This invention provides embodiments that improve the user experience while also contributing to environmental protection by adjusting instructions to take user emotions into consideration and streamlining the sorting process.

[0494] The following describes the processing flow.

[0495] Step 1:

[0496] The device automatically captures an image of the waste when it is placed in the container using its camera, and acquires physical characteristics such as weight and size using its sensors. This allows for the collection of basic data.

[0497] Step 2:

[0498] The device captures the user's voice and facial expressions using emotion sensors and collects data to evaluate the user's psychological state.

[0499] Step 3:

[0500] The device collects image data, physical feature data, and emotional data and sends them to the server. This data is compressed and encrypted in real time before being transmitted.

[0501] Step 4:

[0502] The server analyzes the received image data using artificial intelligence to determine the classification of the waste. In this process, machine learning algorithms compare the features of the objects.

[0503] Step 5:

[0504] The server uses an emotion engine to analyze the received emotional data and identify the user's current emotional state. For example, it can determine whether the user is anxious or relaxed.

[0505] Step 6:

[0506] The server synthesizes waste types and region-specific sorting rules to generate optimal sorting instructions tailored to the user's emotional state. During this process, the length and tone of the instructions are adjusted.

[0507] Step 7:

[0508] The server sends the generated instructions to the terminal in both voice and text formats, and the terminal effectively notifies the user, including when the speech synthesis system outputs the instructions to the visually impaired. The user follows these instructions and sorts the waste appropriately.

[0509] (Example 2)

[0510] 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."

[0511] Conventional waste sorting systems have the functionality to properly classify waste, but they lack sufficient interfaces that take into account the user's emotional state. As a result, users sometimes experience stress, and the sorting process becomes cumbersome, which is a problem.

[0512] 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.

[0513] In this invention, the server includes an acquisition device for obtaining input data for classifying waste, an inference device for processing the data obtained from the acquisition device, and a rule application device for obtaining and applying regional waste sorting rules. This makes it possible to analyze a person's emotional state and provide optimal instructions accordingly.

[0514] An "acquisition device" is a device used to acquire input data necessary for classifying waste.

[0515] An "inference device" is a device used to classify the type of waste based on data obtained from an acquisition device.

[0516] A "rule application device" is a device that obtains and applies waste sorting regulations specific to a particular region.

[0517] A "directive generation device" is a device that, based on data from an inference device and a rule application device, notifies humans of waste sorting instructions via display or voice.

[0518] An "emotion analysis device" is a device that analyzes a person's voice tone and facial expressions to determine their emotional state.

[0519] An "optimization device" is a device that optimizes the instructions generated by the instruction generation device based on the results of the emotion analysis device.

[0520] The smart waste sorting system according to this invention is designed to provide appropriate waste classification and flexible instructions that respond to the user's emotions. The system is configured as follows:

[0521] First, the user places the waste into the terminal. The terminal uses acquisition devices such as cameras and weight sensors to capture images and physical characteristics of the waste. Specific examples of such terminals include commercially available tablets with cameras and sensors.

[0522] The acquired data is sent from the terminal to the server. The server uses an inference device to classify the type of waste based on the acquired data. The inference device uses an AI framework that supports common image analysis techniques. For example, it uses a machine learning library to analyze the shape and weight information of the waste and identify items such as PET bottles and metal cans.

[0523] Furthermore, the server uses an emotion analysis device to analyze the user's emotional state based on the user's voice tone and facial expressions obtained from the terminal. This analysis determines whether the user is in a hurry, relaxed, or otherwise in a state of mind.

[0524] Subsequently, the server retrieves regionally specific classification rules from the database and applies them using a rule application device. The applied rules and the results of sentiment analysis are combined, and the instructions are optimized using an optimization device.

[0525] Finally, the instruction generation device generates the necessary sorting instructions in text or voice and sends them to the terminal. By utilizing speech synthesis technology, the instructions are also provided in voice to users with visual impairments.

[0526] For example, if a user throws away a plastic bottle, the device takes a picture of it and measures its weight using a sensor. The server analyzes this data, identifies it as a plastic bottle, and if it detects that the user's voice is in a hurry, it issues a short, rapid instruction such as, "Please remove the cap from the plastic bottle and put it out for recycling." An example of a prompt to the generative AI model in this case would be, "If the user indicates they are in a hurry, provide a short recycling instruction."

[0527] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0528] Step 1:

[0529] The user places waste into the terminal. The terminal uses a camera to acquire images of the waste and a weight sensor to measure its physical characteristics. The input is the actual waste, and the output is image data and weight data. This data contains the basic information necessary for identifying the waste.

[0530] Step 2:

[0531] The terminal transmits the acquired image data and weight data to the server. Internet protocols are used for communication. The input is the data collected by the terminal, and the output is the data that reaches the server. Subsequent processing is performed based on this data.

[0532] Step 3:

[0533] The server analyzes image data and weight data using an inference device. Here, a generative AI model is used to estimate the type of waste. The input is image and weight data sent from the terminal, and the output is a determination result indicating the type of waste. This determination result provides a classification criterion.

[0534] Step 4:

[0535] The device collects the user's voice tone and facial expressions. It uses a microphone and camera to acquire data about the user's emotional state. The input is the user's current facial expressions and voice, while the output is data indicating their emotional state. This data is used to personalize instructions.

[0536] Step 5:

[0537] The server uses an emotion analysis device to analyze the user's emotional state. It uses the obtained voice and facial expression data as input to determine the emotional state and outputs the result. This analysis result is used to generate appropriate instructions for the user.

[0538] Step 6:

[0539] The server uses a rule-applying device to retrieve local waste sorting rules from a database. The input is local information, and the output is the corresponding sorting rule. This information is referenced when generating sorting instructions.

[0540] Step 7:

[0541] The server optimizes instructions by combining the acquired emotional state with classification rules. Using an optimization device, it constructs classification instructions best suited to the user's emotional state. The input is the emotional analysis results and classification rules, and the output is the optimized instruction data.

[0542] Step 8:

[0543] The instruction generator produces optimized instructions in text and voice. The instructions are sent to a terminal and notified to the user. The input is optimized instruction data, and the output is specific instructions provided to the user. The instructions are delivered in a tone that matches the user's emotional state.

[0544] (Application Example 2)

[0545] 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."

[0546] Proper sorting and separation of waste is crucial for environmental protection, but it can cause stress and confusion for users. This can lead to incorrect sorting and reduced recycling efficiency. This invention aims to streamline the waste sorting process and reduce the burden on users by providing personalized instructions that respond to the user's emotional state.

[0547] 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.

[0548] In this invention, the server includes video acquisition means for obtaining input data for classifying waste, emotion analysis means for analyzing the user's voice and facial expressions to determine their emotional state, and instruction generation means for optimizing and notifying instructions. This makes it possible to quickly provide appropriate instructions based on the user's emotional state.

[0549] "Image acquisition means" refers to a device or method for capturing visual information necessary for classifying waste.

[0550] "Machine learning methods" refer to artificial intelligence technologies that process data obtained from video acquisition methods and emotion analysis to automatically determine the type of waste.

[0551] "Means of applying rules" refer to means of obtaining different waste sorting rules for each region and applying them to waste classification.

[0552] "Emotional analysis means" refers to a system or process that analyzes a user's voice and facial expression data to recognize and determine the user's emotional state.

[0553] "Instruction generation means" refers to means that have the function of generating instructions for waste sorting for the user based on acquired data and notifying the user via display or audio.

[0554] "Speech synthesis means" is a technology that outputs generated instructions as speech, providing voice guidance tailored to visually impaired individuals and different situations.

[0555] "Voice emotion adaptation means" refers to a method for optimizing the tone and pacing of speech synthesis based on emotion detection, and for providing information to users in an easily understandable format.

[0556] The system for realizing the present invention includes a terminal, a server, and a network connecting them. The user receives assistance with waste sorting by using the terminal to photograph waste and provide voice input. This terminal is equipped with image acquisition means and voice input means. Specifically, it collects video and audio data using the camera and microphone of a smartphone.

[0557] Data acquired by the device is sent to a server in the cloud via the internet. The data is encrypted using the SSL / TLS protocol during transmission. The server utilizes machine learning techniques to analyze the received data. TensorFlow and PyTorch are used as machine learning frameworks to determine the type of waste.

[0558] Furthermore, the server's emotion analysis system evaluates the user's stress level and emotions by analyzing their emotional state from their voice and facial expressions. Based on this, an instruction generation system optimizes disposal methods in accordance with local regulations to generate appropriate instructions. A natural language processing model is used for language processing, and an emotion-adaptive speech synthesis system is used for speech synthesis. A speech synthesis engine such as Azure Speech Services is useful.

[0559] The generated instructions are fed back to the user in both text and audio. The instructions are delivered gently or concisely, depending on the user's emotional state. For example, if a user tries to throw away a plastic bottle and the server identifies it as such, a short and clear instruction such as "Remove the cap from the plastic bottle and then put it in the recycling bin" will be provided.

[0560] Examples of prompt messages include "Real-time waste sorting and emotional response optimization using AI." This allows users to sort their waste smoothly without experiencing stress.

[0561] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0562] Step 1:

[0563] The device allows the user to take images of waste with its camera and record voice input with its microphone. The input data consists of video and audio data. The video data shows the visual characteristics of the waste, and the audio data is used to analyze the emotions from the user's statements. The acquired data is temporarily stored on the device.

[0564] Step 2:

[0565] The terminal transmits the acquired video and audio data to the server. The data is encrypted using the SSL / TLS protocol. The transmitted data is received by the server. The input information is kept secure.

[0566] Step 3:

[0567] The server analyzes the received video data using machine learning techniques to classify the type of waste. This process utilizes TensorFlow and PyTorch to analyze the features contained in the video and determine which category the waste belongs to. The output is the identified type of waste.

[0568] Step 4:

[0569] In parallel, the server processes the voice data using emotion analysis tools to determine the user's emotional state. By analyzing voice tone and speed, it assesses whether the user is relaxed or stressed. The output is the identified emotional state.

[0570] Step 5:

[0571] The server generates instructions by combining the type of waste and the user's emotional state. The generated instructions are optimized based on local waste sorting regulations, and their tone and content are adjusted according to the emotional state. The output is the specific disposal method to be presented to the user.

[0572] Step 6:

[0573] The server sends the generated instructions to the terminal. The terminal displays these instructions in text and audio, notifying the user. Audio notifications use speech synthesis and are played back in an appropriate tone by speech emotion adaptation. This allows the user to confirm the sorting method in both audio and text before taking action.

[0574] 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.

[0575] 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.

[0576] 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.

[0577] [Fourth Embodiment]

[0578] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0579] 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.

[0580] 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).

[0581] 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.

[0582] 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.

[0583] 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).

[0584] 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.

[0585] 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.

[0586] 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.

[0587] 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.

[0588] 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.

[0589] 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.

[0590] 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".

[0591] The smart waste sorting system of the present invention operates by combining multiple technological elements to support accurate classification and proper sorting of waste. First, a terminal installed in the trash can captures an image of the object using an image acquisition means each time waste is placed inside. This allows data such as the appearance, shape, and color of the waste to be collected in real time. In addition, sensors equipped in the terminal measure the weight and volume of the waste to supplement its physical characteristics.

[0592] The captured and measured data is compressed and sent to a server. The server inputs the image and sensor data into artificial intelligence (AI) systems and determines the type of waste based on previously learned patterns. For example, it has the ability to distinguish between different types of waste, such as plastic bottles, glass bottles, and metal cans.

[0593] Subsequently, the server uses rule application means to retrieve regional sorting rules from the database based on the classification results. This is essential for providing instructions that conform to different sorting criteria for each region. The sorting instructions generated by the server are converted into text and audio information by the instruction generation means and returned to the terminal.

[0594] Users can receive visual and auditory sorting instructions from the device and properly sort their waste. For visually impaired users, speech synthesis provides instructions verbally, making the sorting process easy for anyone.

[0595] As a concrete example, consider a scenario where a user throws an empty plastic bottle into a trash can. The terminal acquires an image of the bottle and measures its weight. The server receives this data, recognizes it as a plastic bottle using artificial intelligence, and generates instructions such as "Remove the cap and rinse the inside" based on local regulations. The user follows these instructions for sorting, and the system accumulates the data to further improve accuracy. In this way, the present invention realizes appropriate waste disposal for each region, contributing to user convenience and environmental protection.

[0596] The following describes the processing flow.

[0597] Step 1:

[0598] The device uses a camera to photograph waste placed in the trash can and acquires image data. It also uses sensors to collect data on the weight and shape of the waste.

[0599] Step 2:

[0600] The device compresses the acquired images and sensor data and securely transmits them to the server. Data compression and encryption processing takes place at this stage.

[0601] Step 3:

[0602] The server analyzes the received data using artificial intelligence to determine the type of waste. Here, image analysis technology is used to extract the features of the objects, and classification is performed based on those features.

[0603] Step 4:

[0604] Based on the determined type of waste, the server uses rule application mechanisms to retrieve the sorting rules for the relevant area from the database.

[0605] Step 5:

[0606] The server uses an instruction generation mechanism to construct sorting instructions to be provided to the user, in accordance with the acquired regional rules. The instructions are generated in both text and audio formats.

[0607] Step 6:

[0608] The server sends the generated instructions to the terminal. Information is conveyed using speech synthesis, ensuring it is not dependent on visual information.

[0609] Step 7:

[0610] The terminal notifies the user of received sorting instructions, clearly communicating the instructions through display and voice. The user then properly disposes of the waste according to these instructions.

[0611] (Example 1)

[0612] 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".

[0613] Conventional waste sorting systems have problems accurately identifying types of waste and adapting to different sorting standards in different regions. They also have the challenge of providing insufficient instructions for visually impaired individuals. Furthermore, their accuracy is limited because they lack the ability to classify waste based on its physical characteristics.

[0614] 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.

[0615] In this invention, the server includes a visual acquisition means, a means for compressing and transmitting information obtained from a weight measuring device, a generation AI means for determining the type of waste based on previously learned patterns, a rule application means for acquiring and applying waste sorting standards for each region, and an instruction generation means for displaying or notifying the user of instructions via voice. This enables high-precision classification of waste and the provision of appropriate sorting instructions according to the region, making it possible for all users, including visually impaired individuals, to properly sort their waste.

[0616] A "visual acquisition means" is a device for collecting visual information about waste, and it uses cameras and sensors to acquire information such as the appearance, shape, and color of the waste.

[0617] A "weight measuring device" is a measuring device used to measure the weight of waste and to supplement the physical characteristics of the waste.

[0618] "Means for compressing and transmitting information" refers to means that have the function of compressing acquired data in order to transmit it effectively and then sending it to a receiving side such as a server.

[0619] "Generative AI means" refers to artificial intelligence technology used to identify and classify types of waste using previously learned data.

[0620] "Means of applying regulations" refers to a program or processing system for obtaining regional waste sorting standards and applying them to the waste classification results.

[0621] "Instruction generation means" refers to a device or function that generates differentiated instructions for the user based on information from the server and notifies the user of these instructions via display or sound.

[0622] The waste sorting system of the present invention operates in conjunction with a terminal and a server. The terminal is installed in a trash can and takes an image of the waste using visual acquisition means each time waste is put in. This visual acquisition means includes a camera and image sensors to acquire the appearance, color, and shape of the waste. In addition, a weight measuring device is incorporated into the terminal to measure the weight and volume of the waste and supplement its physical characteristics.

[0623] The captured and measured data is transmitted to the server by a means of compressing and transmitting terminal information. The server inputs the received data into a generating AI means and determines the type of waste using previously learned patterns. This generating AI means uses an artificial intelligence model (AI model) to perform image analysis and physical feature analysis of the waste. The server then uses a rule application means to retrieve and apply regional sorting standards from a database based on the determined type of waste.

[0624] The server converts the results into instructions using an instruction generation mechanism and provides them to the user. These include visual instructions via display and voice instructions via speech synthesis. This allows the user to make appropriate classifications according to the instructions provided from the terminal.

[0625] As a concrete example, consider a scenario where a user throws a glass bottle into a trash can. The terminal acquires an image of the glass bottle and measures its weight. The server receives this information and uses AI to identify the waste as a glass bottle. Then, based on local sorting rules, it generates an instruction such as, "Please place glass bottles in the designated recycling box." The user follows this instruction and sorts the waste appropriately. In this way, the system flexibly adapts to local sorting rules and contributes to environmental protection.

[0626] Example prompt for the generated AI model: "Generate a program that identifies glass bottles and plastic bottles in a smart waste sorting system and provides the user with appropriate sorting instructions based on that."

[0627] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0628] Step 1:

[0629] The terminal captures an image of the waste each time it is deposited using a visual acquisition device. The input is the actual waste, and the output is visual information (image data) of the waste. The terminal uses a camera to capture the appearance, color, and shape of the waste.

[0630] Step 2:

[0631] The terminal measures the weight of the waste using a weighing device. The input is the physical presence of the waste, and the output is the weight data of the waste. This supplements the weight as a physical characteristic.

[0632] Step 3:

[0633] The terminal compresses the acquired image data and weight data into a single data package and sends it to the server. The input is a pair of visual and weight information, and the output is a compressed data file sent to the server. Transmission takes place in real time over the network.

[0634] Step 4:

[0635] The server receives and decompresses compressed data. The input is a data file sent from the terminal, and the output is the decompressed image data and weight data. This data is then ready to be input into the generating AI system.

[0636] Step 5:

[0637] The server's AI generation method uses decompressed data to determine the type of waste. Inputs are image data and weight data, and output is the determined waste type information. The AI ​​model performs pattern recognition using past training data.

[0638] Step 6:

[0639] The server uses rule application methods to retrieve and apply local sorting standards based on the determined waste type. The input is waste type information, and the output is sorting instructions appropriate for the region. Rules are referenced from a database.

[0640] Step 7:

[0641] The server converts the sorting instructions into text or audio format using an instruction generation device and sends them to the terminal. The input is the sorting instructions, and the output is the instruction information provided to the user.

[0642] Step 8:

[0643] The user sorts waste appropriately according to instructions received from the terminal. Input consists of visual and auditory instructions, while output is the user's sorting actions. This facilitates the proper disposal of waste.

[0644] (Application Example 1)

[0645] 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".

[0646] In modern urban environments, proper waste sorting and recycling are critical social issues, but many people find it difficult to accurately understand and follow complex sorting rules. Furthermore, there is a lack of systems that allow diverse users, including the visually impaired, to easily and appropriately sort their waste. To address this challenge, there is a need to provide a system that allows users to receive real-time instructions, thereby improving user convenience and reducing environmental impact.

[0647] 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.

[0648] In this invention, the server includes an image acquisition means for acquiring input data for classifying waste, an artificial intelligence means for processing the data obtained from the image acquisition means, a rule application means for acquiring and applying waste sorting rules for each region, and a communication means that works in conjunction with a smart device that provides instructions in real time. This makes it possible for users to instantly receive instructions on the appropriate sorting method via a smart device when disposing of waste.

[0649] An "image acquisition means" is a device that uses cameras and sensors to acquire image data in order to collect the external characteristics of waste.

[0650] "Artificial intelligence means" refers to artificial intelligence algorithms and programs used to analyze acquired images and data to determine the type and classification of waste.

[0651] "Means of applying rules" refers to a database and its matching function that references local waste sorting standards and provides instructions tailored to the user.

[0652] "Instruction generation means" refers to a device or program that creates instructions in text or voice to communicate to the user the appropriate method of disposing of waste based on the analysis results.

[0653] "Communication means" refers to network connectivity technology that enables a system to send and receive data with smart devices and provide instructions in real time.

[0654] This invention provides a system for appropriately classifying waste and providing sorting instructions to the user. Specific embodiments for realizing this system are described below.

[0655] First, the system utilizes both a terminal installed in the trash can and the user's own smart device to respond to the user's waste disposal behavior. The terminal is equipped with a camera and a weight sensor to acquire images and physical characteristics of the waste. This image acquisition method collects detailed information about the waste by having the camera photograph the waste and the weight sensor supplement the data.

[0656] The collected data is transmitted to a server via artificial intelligence. This server uses AI models such as TensorFlow to analyze the image data and identify the type of waste it belongs to. Furthermore, based on the results, the server uses rule-applying mechanisms to retrieve regional sorting rules from a database and construct appropriate instructions for the user.

[0657] The instruction generation system converts these instructions into text and then into speech using speech synthesis technology, providing them to users in a format that is easy to understand in real time. Furthermore, the ability to provide instructions via voice enables an easy-to-understand interface for all users, including those with visual impairments.

[0658] The system uses Bluetooth and Wi-Fi for communication between smart devices and servers, enabling users to receive immediate feedback. This allows users to check the optimal sorting method on the spot when disposing of waste.

[0659] As a concrete example, when a user disposes of a beverage container, the device's camera captures an image and a sensor measures its weight. This data is sent to a server where AI recognizes it as a beverage container. A prompt message is then generated, such as "When a beverage container is identified, please generate instructions on how to separate the cap." The server then provides the user with voice and text instructions, such as "Remove the cap and put it in the recycling bin," according to local rules.

[0660] Through this process, users can easily understand sorting methods and contribute to recycling efforts.

[0661] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0662] Step 1:

[0663] The device uses its camera to photograph objects discarded by the user. The input here is visual data of the object, and the output is saved as image data. Along with the image, the device also acquires physical weight data of the object measured by a weight sensor.

[0664] Step 2:

[0665] The terminal compresses the acquired image data and weight data and sends it to the server. The input is image and weight data, which are processed into a transmittable format using a data compression algorithm. The output is the data packets received by the server.

[0666] Step 3:

[0667] The server inputs the received data into an artificial intelligence model to classify the type of object. The input is compressed data, which the AI ​​analyzes using image analysis techniques. The output is category information for the identified waste.

[0668] Step 4:

[0669] The server uses the identified category information to retrieve regional sorting rules from the database using rule application mechanisms. The input is waste category information, and the output is the corresponding sorting instruction.

[0670] Step 5:

[0671] The server utilizes a generative AI model to generate visual and audio instructions for the user. Input consists of sorting instructions and generated prompts, and both speech synthesis and text instructions are output.

[0672] Step 6:

[0673] The server sends generated voice and text instructions to the terminal. The input is the generated instruction data, and the terminal provides the user with appropriate instructions in real time as output. The terminal plays these instructions aloud, and the text is displayed on the screen.

[0674] 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.

[0675] The smart waste sorting system of the present invention incorporates an emotion engine to provide users with more personalized and effective waste sorting support. The system first uses a terminal to capture images of the waste with an image acquisition means when the waste is put in, and acquires its physical characteristics with sensors. This allows basic waste data to be collected in real time.

[0676] The device then sends the collected data to the server. The server uses artificial intelligence to determine the type of waste. Simultaneously, an emotion engine processes the emotional data acquired from the device, analyzing the user's voice tone and facial expressions. The server then combines the waste type determination with the emotional analysis results.

[0677] Next, the server retrieves regional sorting rules using rule application mechanisms and optimizes those rules according to the user's emotional state, as determined by the emotion engine. In other words, if it detects that the user is stressed, it is intended to generate more concise and helpful instructions.

[0678] The instruction generation means generates sorting methods in text and audio formats based on the obtained data and transmits them to the terminal. The speech synthesis means here is particularly useful for visually impaired users. Based on emotional personalization, instructions are given in a tone and pacing that matches the user's current emotional state.

[0679] For example, when a user throws away a plastic bottle, the device takes a picture of it and measures its weight. The server analyzes this data, identifies it as a plastic bottle, and if it detects that the user's voice is in a hurry, it provides a short, rapid instruction such as, "Please remove the cap from the plastic bottle before recycling."

[0680] This invention provides embodiments that improve the user experience while also contributing to environmental protection by adjusting instructions to take user emotions into consideration and streamlining the sorting process.

[0681] The following describes the processing flow.

[0682] Step 1:

[0683] The device automatically captures an image of the waste when it is placed in the container using its camera, and acquires physical characteristics such as weight and size using its sensors. This allows for the collection of basic data.

[0684] Step 2:

[0685] The device captures the user's voice and facial expressions using emotion sensors and collects data to evaluate the user's psychological state.

[0686] Step 3:

[0687] The device collects image data, physical feature data, and emotional data and sends them to the server. This data is compressed and encrypted in real time before being transmitted.

[0688] Step 4:

[0689] The server analyzes the received image data using artificial intelligence to determine the classification of the waste. In this process, machine learning algorithms compare the features of the objects.

[0690] Step 5:

[0691] The server uses an emotion engine to analyze the received emotional data and identify the user's current emotional state. For example, it can determine whether the user is anxious or relaxed.

[0692] Step 6:

[0693] The server synthesizes waste types and region-specific sorting rules to generate optimal sorting instructions tailored to the user's emotional state. During this process, the length and tone of the instructions are adjusted.

[0694] Step 7:

[0695] The server sends the generated instructions to the terminal in both voice and text formats, and the terminal effectively notifies the user, including when the speech synthesis system outputs the instructions to the visually impaired. The user follows these instructions and sorts the waste appropriately.

[0696] (Example 2)

[0697] 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".

[0698] Conventional waste sorting systems have the functionality to properly classify waste, but they lack sufficient interfaces that take into account the user's emotional state. As a result, users sometimes experience stress, and the sorting process becomes cumbersome, which is a problem.

[0699] 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.

[0700] In this invention, the server includes an acquisition device for obtaining input data for classifying waste, an inference device for processing the data obtained from the acquisition device, and a rule application device for obtaining and applying regional waste sorting rules. This makes it possible to analyze a person's emotional state and provide optimal instructions accordingly.

[0701] An "acquisition device" is a device used to acquire input data necessary for classifying waste.

[0702] An "inference device" is a device used to classify the type of waste based on data obtained from an acquisition device.

[0703] A "rule application device" is a device that obtains and applies waste sorting regulations specific to a particular region.

[0704] A "directive generation device" is a device that, based on data from an inference device and a rule application device, notifies humans of waste sorting instructions via display or voice.

[0705] An "emotion analysis device" is a device that analyzes a person's voice tone and facial expressions to determine their emotional state.

[0706] An "optimization device" is a device that optimizes the instructions generated by the instruction generation device based on the results of the emotion analysis device.

[0707] The smart waste sorting system according to this invention is designed to provide appropriate waste classification and flexible instructions that respond to the user's emotions. The system is configured as follows:

[0708] First, the user places the waste into the terminal. The terminal uses acquisition devices such as cameras and weight sensors to capture images and physical characteristics of the waste. Specific examples of such terminals include commercially available tablets with cameras and sensors.

[0709] The acquired data is sent from the terminal to the server. The server uses an inference device to classify the type of waste based on the acquired data. The inference device uses an AI framework that supports common image analysis techniques. For example, it uses a machine learning library to analyze the shape and weight information of the waste and identify items such as PET bottles and metal cans.

[0710] Furthermore, the server uses an emotion analysis device to analyze the user's emotional state based on the user's voice tone and facial expressions obtained from the terminal. This analysis determines whether the user is in a hurry, relaxed, or otherwise in a state of mind.

[0711] Subsequently, the server retrieves regionally specific classification rules from the database and applies them using a rule application device. The applied rules and the results of sentiment analysis are combined, and the instructions are optimized using an optimization device.

[0712] Finally, the instruction generation device generates the necessary sorting instructions in text or voice and sends them to the terminal. By utilizing speech synthesis technology, the instructions are also provided in voice to users with visual impairments.

[0713] For example, if a user throws away a plastic bottle, the device takes a picture of it and measures its weight using a sensor. The server analyzes this data, identifies it as a plastic bottle, and if it detects that the user's voice is in a hurry, it issues a short, rapid instruction such as, "Please remove the cap from the plastic bottle and put it out for recycling." An example of a prompt to the generative AI model in this case would be, "If the user indicates they are in a hurry, provide a short recycling instruction."

[0714] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0715] Step 1:

[0716] The user places waste into the terminal. The terminal uses a camera to acquire images of the waste and a weight sensor to measure its physical characteristics. The input is the actual waste, and the output is image data and weight data. This data contains the basic information necessary for identifying the waste.

[0717] Step 2:

[0718] The terminal transmits the acquired image data and weight data to the server. Internet protocols are used for communication. The input is the data collected by the terminal, and the output is the data that reaches the server. Subsequent processing is performed based on this data.

[0719] Step 3:

[0720] The server analyzes image data and weight data using an inference device. Here, a generative AI model is used to estimate the type of waste. The input is image and weight data sent from the terminal, and the output is a determination result indicating the type of waste. This determination result provides a classification criterion.

[0721] Step 4:

[0722] The device collects the user's voice tone and facial expressions. It uses a microphone and camera to acquire data about the user's emotional state. The input is the user's current facial expressions and voice, while the output is data indicating their emotional state. This data is used to personalize instructions.

[0723] Step 5:

[0724] The server uses an emotion analysis device to analyze the user's emotional state. It uses the obtained voice and facial expression data as input to determine the emotional state and outputs the result. This analysis result is used to generate appropriate instructions for the user.

[0725] Step 6:

[0726] The server uses a rule-applying device to retrieve local waste sorting rules from a database. The input is local information, and the output is the corresponding sorting rule. This information is referenced when generating sorting instructions.

[0727] Step 7:

[0728] The server optimizes instructions by combining the acquired emotional state with classification rules. Using an optimization device, it constructs classification instructions best suited to the user's emotional state. The input is the emotional analysis results and classification rules, and the output is the optimized instruction data.

[0729] Step 8:

[0730] The instruction generator produces optimized instructions in text and voice. The instructions are sent to a terminal and notified to the user. The input is optimized instruction data, and the output is specific instructions provided to the user. The instructions are delivered in a tone that matches the user's emotional state.

[0731] (Application Example 2)

[0732] 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".

[0733] Proper sorting and separation of waste is crucial for environmental protection, but it can cause stress and confusion for users. This can lead to incorrect sorting and reduced recycling efficiency. This invention aims to streamline the waste sorting process and reduce the burden on users by providing personalized instructions that respond to the user's emotional state.

[0734] 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.

[0735] In this invention, the server includes video acquisition means for obtaining input data for classifying waste, emotion analysis means for analyzing the user's voice and facial expressions to determine their emotional state, and instruction generation means for optimizing and notifying instructions. This makes it possible to quickly provide appropriate instructions based on the user's emotional state.

[0736] "Image acquisition means" refers to a device or method for capturing visual information necessary for classifying waste.

[0737] "Machine learning methods" refer to artificial intelligence technologies that process data obtained from video acquisition methods and emotion analysis to automatically determine the type of waste.

[0738] "Means of applying rules" refer to means of obtaining different waste sorting rules for each region and applying them to waste classification.

[0739] "Emotional analysis means" refers to a system or process that analyzes a user's voice and facial expression data to recognize and determine the user's emotional state.

[0740] "Instruction generation means" refers to means that have the function of generating instructions for waste sorting for the user based on acquired data and notifying the user via display or audio.

[0741] "Speech synthesis means" is a technology that outputs generated instructions as speech, providing voice guidance tailored to visually impaired individuals and different situations.

[0742] "Voice emotion adaptation means" refers to a method for optimizing the tone and pacing of speech synthesis based on emotion detection, and for providing information to users in an easily understandable format.

[0743] The system for realizing the present invention includes a terminal, a server, and a network connecting them. The user receives assistance with waste sorting by using the terminal to photograph waste and provide voice input. This terminal is equipped with image acquisition means and voice input means. Specifically, it collects video and audio data using the camera and microphone of a smartphone.

[0744] Data acquired by the device is sent to a server in the cloud via the internet. The data is encrypted using the SSL / TLS protocol during transmission. The server utilizes machine learning techniques to analyze the received data. TensorFlow and PyTorch are used as machine learning frameworks to determine the type of waste.

[0745] Furthermore, the server's emotion analysis system evaluates the user's stress level and emotions by analyzing their emotional state from their voice and facial expressions. Based on this, an instruction generation system optimizes disposal methods in accordance with local regulations to generate appropriate instructions. A natural language processing model is used for language processing, and an emotion-adaptive speech synthesis system is used for speech synthesis. A speech synthesis engine such as Azure Speech Services is useful.

[0746] The generated instructions are fed back to the user in both text and audio. The instructions are delivered gently or concisely, depending on the user's emotional state. For example, if a user tries to throw away a plastic bottle and the server identifies it as such, a short and clear instruction such as "Remove the cap from the plastic bottle and then put it in the recycling bin" will be provided.

[0747] Examples of prompt messages include "Real-time waste sorting and emotional response optimization using AI." This allows users to sort their waste smoothly without experiencing stress.

[0748] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0749] Step 1:

[0750] The device allows the user to take images of waste with its camera and record voice input with its microphone. The input data consists of video and audio data. The video data shows the visual characteristics of the waste, and the audio data is used to analyze the emotions from the user's statements. The acquired data is temporarily stored on the device.

[0751] Step 2:

[0752] The terminal transmits the acquired video and audio data to the server. The data is encrypted using the SSL / TLS protocol. The transmitted data is received by the server. The input information is kept secure.

[0753] Step 3:

[0754] The server analyzes the received video data using machine learning techniques to classify the type of waste. This process utilizes TensorFlow and PyTorch to analyze the features contained in the video and determine which category the waste belongs to. The output is the identified type of waste.

[0755] Step 4:

[0756] In parallel, the server processes the voice data using emotion analysis tools to determine the user's emotional state. By analyzing voice tone and speed, it assesses whether the user is relaxed or stressed. The output is the identified emotional state.

[0757] Step 5:

[0758] The server generates instructions by combining the type of waste and the user's emotional state. The generated instructions are optimized based on local waste sorting regulations, and their tone and content are adjusted according to the emotional state. The output is the specific disposal method to be presented to the user.

[0759] Step 6:

[0760] The server sends the generated instructions to the terminal. The terminal displays these instructions in text and audio, notifying the user. Audio notifications use speech synthesis and are played back in an appropriate tone by speech emotion adaptation. This allows the user to confirm the sorting method in both audio and text before taking action.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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."

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] The following is further disclosed regarding the embodiments described above.

[0783] (Claim 1)

[0784] An image acquisition means for obtaining input data for classifying waste,

[0785] Artificial intelligence means for processing data obtained from the image acquisition means,

[0786] A means of applying rules to obtain and apply waste sorting rules for each region,

[0787] Instruction generation means for displaying or notifying the user of instructions via voice based on the aforementioned data,

[0788] A system that includes this.

[0789] (Claim 2)

[0790] The system according to claim 1, wherein the instruction generation means further comprises a speech synthesis means for providing audio output for visually impaired persons.

[0791] (Claim 3)

[0792] The system according to claim 1, wherein the artificial intelligence means uses image analysis technology to classify waste based on the physical characteristics of the waste.

[0793] "Example 1"

[0794] (Claim 1)

[0795] A visual acquisition means for obtaining input information for classifying waste,

[0796] A means for compressing and transmitting information obtained from the visual acquisition means and the weight measuring device,

[0797] A generation AI means for determining the type of waste based on patterns learned in the past,

[0798] A means of applying regulations to obtain and apply waste sorting standards for each region,

[0799] Instruction generation means for displaying or notifying the user of instructions via voice based on the aforementioned information,

[0800] A system that includes this.

[0801] (Claim 2)

[0802] The system according to claim 1, wherein the instruction generation means comprises a speech synthesis means that provides audio output for visually impaired persons.

[0803] (Claim 3)

[0804] The system according to claim 1, wherein the generating AI means uses image analysis technology to classify waste based on the physical characteristics of the waste.

[0805] "Application Example 1"

[0806] (Claim 1)

[0807] An image acquisition means for obtaining input data for classifying waste,

[0808] Artificial intelligence means for processing data obtained from the image acquisition means,

[0809] A means of applying rules to obtain and apply waste sorting rules for each region,

[0810] Instruction generation means for displaying or notifying the user of instructions via voice based on the aforementioned data,

[0811] A communication method that works in conjunction with a smart device that provides instructions in real time,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] The system according to claim 1, wherein the instruction generation means further comprises a speech synthesis means for providing audio output for visually impaired persons.

[0815] (Claim 3)

[0816] The artificial intelligence means uses image analysis technology to classify waste based on its physical characteristics,

[0817] The system according to claim 1, which uses a generative AI model to prompt for an appropriate sorting method.

[0818] "Example 2 of combining an emotion engine"

[0819] (Claim 1)

[0820] An acquisition device for obtaining input data for classifying waste,

[0821] An inference device for processing data obtained from the acquisition device,

[0822] A rule application device for obtaining and applying waste sorting regulations for each region,

[0823] An instruction generating device for displaying or audibly notifying a human of instructions based on the aforementioned data,

[0824] An emotion analysis device for analyzing human emotional states,

[0825] An optimization device for optimizing instructions based on emotion analysis results,

[0826] A system that includes this.

[0827] (Claim 2)

[0828] The system according to claim 1, further comprising a speech synthesis device that provides voice output for visually impaired persons as an instruction generating device.

[0829] (Claim 3)

[0830] The system according to claim 1, wherein the inference device uses image analysis techniques to classify waste based on the physical characteristics of the waste.

[0831] "Application example 2 when combining with an emotional engine"

[0832] (Claim 1)

[0833] A means for acquiring video data to obtain input data for classifying waste,

[0834] A machine learning means for processing data obtained from the video acquisition means,

[0835] A means of applying regulations to obtain and apply waste sorting rules specific to each region,

[0836] An emotion analysis method that analyzes the user's voice and facial expressions to determine their emotional state,

[0837] Instruction generation means for optimizing instructions to the user based on the determined emotional state and notifying the user via display or sound,

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1, further comprising a speech synthesis means for providing audio output for visually impaired persons and a speech emotion adaptation means for generating audio in an appropriate tone based on emotion determination.

[0841] (Claim 3)

[0842] The system according to claim 1, wherein the machine learning means uses image analysis technology to classify waste based on data obtained from the physical characteristics of the waste and the emotional analysis of the user. [Explanation of symbols]

[0843] 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. An image acquisition means for obtaining input data for classifying waste, Artificial intelligence means for processing data obtained from the image acquisition means, A means of applying rules to obtain and apply waste sorting rules for each region, Instruction generation means for displaying or notifying the user of instructions via voice based on the aforementioned data, A system that includes this.

2. The system according to claim 1, wherein the instruction generation means further comprises a speech synthesis means for providing audio output for visually impaired persons.

3. The system according to claim 1, wherein the artificial intelligence means uses image analysis technology to classify waste based on the physical characteristics of the waste.

Images