System

Abstract

A system is provided.SOLUTION: The system includes a means for inputting an image, a means for analyzing the inputted image and extracting character information, a means for specifying commodity-specific information based on the extracted character information, a means for evaluating an environmental influence degree for each commodity based on the specified commodity information, and a means for presenting an evaluation result to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, many people are concerned about environmental issues, but the reality is that they do not know what specific actions they should take. Furthermore, when choosing eco-friendly products, there is insufficient information about the environmental impact of the products, making it difficult for consumers to make appropriate choices. To improve this situation, a system is needed that allows consumers to easily understand the environmental impact of products and make sustainable choices. [Means for solving the problem]

[0005] This invention is a system that includes a means for inputting an image, a means for analyzing the input image and extracting text information, a means for identifying product-specific information based on the extracted text information, a means for evaluating the environmental impact of each product based on the identified product information, and a means for presenting the evaluation results to the user. In particular, by extracting the text information using optical character recognition technology and evaluating the environmental impact of each product using an artificial intelligence model, the system enables consumers to easily and quickly select eco-friendly products. The system aims to enable consumers to make sustainable choices and contribute to solving environmental problems.

[0006] "Means for inputting images" refers to technology that allows users to take images of products, etc. using devices such as smartphones or tablets and save them as digital data.

[0007] "Means for analyzing input images and extracting text information" refers to a technology that uses optical character recognition (OCR) technology to analyze the characters contained in captured image data and extract them as text information.

[0008] "Means for identifying product-specific information" refers to technology for analyzing extracted text information and identifying product-specific information such as type, characteristics, and ingredients.

[0009] "Means for assessing environmental impact" refers to technology that uses an artificial intelligence model to assess the environmental impact of a product based on specific product information and calculate its eco-level.

[0010] "Means for presenting assessment results to users" refers to technology that displays the calculated environmental impact assessment results on the terminal screen and provides them in a form that is easily understandable to users.

[0011] "Optical character recognition technology" refers to the technology of reading characters in an image as digital text, and is also known as OCR.

[0012] "Artificial intelligence model" refers to a machine learning model or deep learning model that learns from data and assesses environmental impact. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0014] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0017] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0018] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0019] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0033] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0034] The present invention relates to a system for evaluating the environmental impact of a product by photographing the product using a device such as a smartphone or tablet. Specific embodiments will be described below.

[0035] When a user uses the system, they first launch the application, switch to camera mode, and take a picture of a product they are considering purchasing. The device temporarily saves the captured image data. The saved image data is then sent to the server. The device converts the image to JPEG format and uploads it to the server using an HTTP POST request.

[0036] The server analyzes the received image data and uses optical character recognition (OCR) technology to extract product label and ingredient information. The server first reads the image and uses an OCR library to extract text from the image. It then analyzes the extracted text data to identify keywords and ingredient information related to the product.

[0037] For example, if a user takes a photo of an organic food package, the server will extract keywords such as "certified organic" and "plastic-free."

[0038] The server then uses the extracted information to evaluate the product's environmental impact using a generative AI model, which operates on a pre-trained dataset, weights the extracted keywords, and scores the product's eco-level.

[0039] For example, the influence of each keyword is evaluated in the following way: "organic certified" will be given 10 eco points, and "plastic-free" will be given 10 eco points.

[0040] The server returns the calculated eco-level results to the terminal as an HTTP response. The terminal analyzes the received eco-level results and displays them to the user in an appropriate format. The user can check the evaluation results displayed on the screen and select environmentally friendly products.

[0041] For example, a message will appear on your smartphone screen saying, "This product is highly eco-friendly. It is certified organic and does not contain any plastic."

[0042] In this way, users can easily and quickly check the eco-level of a product via the application, enabling them to make more sustainable choices.

[0043] The processing flow will be explained below.

[0044] Step 1:

[0045] The user starts the application, switches to camera mode, and takes a picture of a product they are considering purchasing. The user then uses the device's camera to capture the product, and the image is temporarily saved in the application.

[0046] Step 2:

[0047] The device sends the stored image data to the server, where it is converted to JPEG format and uploaded to the server using an HTTP POST request. This transfers the image data to the server.

[0048] Step 3:

[0049] The server analyzes the received image data and uses optical character recognition (OCR) technology to extract product label and ingredient information. First, the server reads the stored image and uses an OCR library to extract text information from the image.

[0050] Step 4:

[0051] The server analyzes the extracted text data to identify keywords and ingredient information related to the product, identifying specific keywords and phrases such as "certified organic" or "plastic-free."

[0052] Step 5:

[0053] The server uses the extracted information to evaluate the product's environmental impact using a generative AI model, which weights each keyword based on a pre-trained dataset and scores the product's eco-level.

[0054] Step 6:

[0055] The server returns the calculated eco-level result to the device. The evaluation result is sent to the device as an HTTP response, and the device receives the data.

[0056] Step 7:

[0057] The device analyzes the received eco-level results and displays them in an appropriate format to the user, allowing the user to easily select environmentally friendly products.

[0058] Step 8:

[0059] Users can check the evaluation results displayed on the screen and select eco-friendly products. Based on this information, users can practice sustainable consumption behavior.

[0060] Example 1

[0061] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0062] In the past, assessing the environmental impact of a product required users to manually research product information and make judgments based on that data, which was time-consuming and labor-intensive. Furthermore, the criteria for assessing environmental impact were inconsistent, making reliable assessments difficult. The present invention aims to solve these problems by providing a system that allows users to easily and quickly check the environmental impact of a product and supports sustainable choices.

[0063] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0064] In this invention, the server includes means for inputting an image, means for analyzing the input image and extracting text information, means for identifying product-specific information based on the extracted text information, means for evaluating the environmental impact of each product based on the identified product information, means for presenting the evaluation results to a user, and means for using a generative AI model that weights the extracted keywords and scores the products. This enables a user to automatically evaluate the environmental impact based on photographed product images and obtain rapid and consistent evaluation results without having to manually research the information.

[0065] The "means for inputting an image" refers to a device or program that provides an interface for the user to photograph a product and can acquire the image data.

[0066] "Means for analyzing an input image and extracting text information" refers to techniques or devices that use image processing technology to identify and extract text information from an input image.

[0067] "Means for identifying product-specific information based on extracted character information" refers to technology or devices that use optical character recognition technology or data analysis algorithms to identify specific product information based on extracted character information.

[0068] The "means for assessing the environmental impact of each product based on identified product information" refers to an algorithm or program for assessing the environmental impact of a product based on information related to the product.

[0069] The "means for presenting the evaluation results to the user" refers to an interface or display device for displaying the environmental impact evaluation results in an easy-to-understand manner for the user.

[0070] "Means of using a generative AI model that weights extracted keywords and scores products" refers to technologies and programs that use an AI model to weight extracted keywords and score the environmental impact of products based on that weighting.

[0071] This invention is a system for evaluating the environmental impact of products by utilizing technologies such as an image input device, a server, and a generative AI model. Specific embodiments will be described below.

[0072] When a user uses the system, they first launch the application, switch to camera mode, and take a picture of a product they are considering purchasing. The device temporarily saves the captured image data, then converts it to JPEG format and uploads it to the server using an HTTP POST request. The hardware used for this includes mobile devices such as smartphones and tablets.

[0073] To analyze the image data received by the server, optical character recognition (OCR) technology is first used. The image is read and text information is extracted from the image using an OCR library. The extracted text data is then analyzed to identify keywords and ingredient information related to the product. The software used for this purpose includes various OCR engines and text analysis algorithms.

[0074] For example, when a user takes a photo of an organic food package, the server extracts keywords such as "certified organic" and "plastic-free." The server then uses a generative AI model to evaluate the product's environmental impact based on the extracted information. The AI ​​model operates based on a pre-trained dataset, weighting each keyword and scoring the product's eco-level. For example, the impact of each keyword is evaluated as follows: "certified organic" earns 10 eco points, and "plastic-free" earns 10 eco points.

[0075] The eco-level results calculated by the server are sent back to the terminal as an HTTP response. The terminal analyzes the received eco-level results and displays them to the user in an appropriate format. For example, a message might appear on a smartphone screen saying, "This product has a high eco-level. It is organically certified and does not contain plastic," allowing the user to select environmentally friendly products.

[0076] An example prompt for a generative AI model might look something like this:

[0077] "Information contained on the product label: 'Certified Organic', 'Plastic-free'. Please rate the eco-friendliness of the product."

[0078] In this way, users can easily and quickly check the eco-level of a product via the application and make more sustainable choices.

[0079] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0080] Step 1:

[0081] The user starts the application, switches to camera mode, and takes a photo of a product they are considering purchasing.

[0082] Specifically, the user taps the app to activate the camera function, points the camera at the product, and presses the shutter button.

[0083] Input: User-initiated camera activation and product photography

[0084] Output: Photographed product image data

[0085] Step 2:

[0086] The device temporarily saves the captured image data, converts it to JPEG format, and uploads the saved image data to the server using an HTTP POST request.

[0087] Specifically, the image is saved in a temporary folder on the device, converted to JPEG format using a conversion library, and sent to the server using an HTTP request library.

[0088] Input: Photographed product image data

[0089] Output: A request to upload JPEG image data to the server.

[0090] Step 3:

[0091] The server receives the HTTP POST request, retrieves the JPEG image data, and uses OCR technology to extract text information from the image.

[0092] Specifically, the server processes the request, performs OCR processing using an image analysis library, and reads the product label and ingredient information.

[0093] Input: JPEG format image data

[0094] Output: Extracted character information (text data)

[0095] Step 4:

[0096] The server analyzes the extracted text data and identifies keywords and ingredient information related to the product.

[0097] Specifically, it applies a text analysis algorithm to extract keywords such as "certified organic" and "plastic-free."

[0098] Input: Extracted character information (text data)

[0099] Output: Identified keywords and ingredient information

[0100] Step 5:

[0101] The server uses the generated AI model to weight the identified keywords and evaluate the environmental impact of the product.

[0102] Specifically, the system sends a prompt to the AI ​​model, calculates eco points for each keyword, and calculates an overall score.

[0103] Input: Identified keywords and ingredient information

[0104] Output: Product environmental impact score

[0105] Step 6:

[0106] The server returns the evaluation results to the terminal as an HTTP response.

[0107] Specifically, the evaluation results are packaged in JSON format and sent to the terminal as an HTTP response.

[0108] Input: Product environmental impact score

[0109] Output: HTTP response containing the environmental impact score

[0110] Step 7:

[0111] The terminal receives the HTTP response from the server, analyzes the evaluation results, and displays them to the user.

[0112] Specifically, it deserializes the response data and displays on the screen, "This product is highly eco-friendly. It is certified organic and does not contain plastic."

[0113] Input: HTTP response containing environmental impact score

[0114] Output: The evaluation result (text message) displayed to the user

[0115] Through the above steps, users can use the system to easily check the environmental impact of products.

[0116] (Application example 1)

[0117] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0118] Modern consumers often want to choose environmentally friendly products, but lack the means to quickly and easily evaluate their environmental impact. When shopping in a physical store, there is a demand for an immediate understanding of the environmental impact of products during the product selection process, but current technology makes it difficult to meet such needs.

[0119] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0120] In this invention, the server includes means for inputting an image, means for analyzing the input image and extracting text information, means for identifying product-specific information and environmental keywords based on the extracted text information, means for evaluating the environmental impact of each product using a generative AI model based on the identified information, and means for presenting the evaluation results to a user's terminal. This enables consumers to quickly and easily evaluate the environmental impact of products and make environmentally conscious choices when purchasing products in a physical store.

[0121] "Means for inputting images" refers to a mechanism that allows users to take photos of products using devices such as smartphones or tablets and import the image data into the system.

[0122] "Means for analyzing input images and extracting text information" refers to technology for identifying and extracting text from captured image data using optical character recognition (OCR) technology.

[0123] "Means for identifying product-specific information and environmental keywords based on extracted character information" refers to the process of analyzing text information extracted using OCR technology and identifying keywords related to specific product information and the environment.

[0124] "Means for assessing the environmental impact of each product using a generative AI model based on identified information" refers to a mechanism for inputting analyzed keyword information into a generative AI model and scoring the environmental impact of the product based on that model.

[0125] "Means for presenting the evaluation results on the user's device" refers to a function that responds to and visually displays the environmental impact score calculated by the generative AI model on the user's smartphone or tablet.

[0126] The present invention provides a system that allows consumers to easily understand the environmental impact of products in physical stores. Specific embodiments will be described below.

[0127] The system mainly consists of a device such as a smartphone or tablet and a server. The device is equipped with an image input means that allows the user to take a photo of a product they are considering purchasing. The user starts the application, switches to camera mode, and takes a photo of the product, which then acquires the image data.

[0128] The device converts the captured image data into JPEG format and then uploads it to the server using an HTTP POST request. The server first uses optical character recognition (OCR) technology to analyze the received image data. Specifically, it uses Tesseract OCR to extract text information from the image.

[0129] The server then analyzes the extracted text to identify keywords related to the product and environmental information. This process involves analyzing the input text and extracting environmental keywords such as "certified organic" and "plastic-free."

[0130] Based on the identified keywords, the server uses a generative AI model to evaluate the environmental impact of the product. The generative AI model operates based on a pre-trained dataset and weights the extracted keywords. The weighting of the keywords results in a score for the product's eco-level. This allows users to instantly understand the product's environmental impact.

[0131] The eco-level result calculated by the server is sent back to the user's device as an HTTP response, and the device visually displays the received eco-level result and provides it to the user.

[0132] Examples:

[0133] For example, consider the case where a user scans an organic food product at a supermarket. Using a smartphone app, the user scans the product packaging and sends the image data to a server. The server uses OCR to extract keywords such as "certified organic" and "plastic-free," and inputs these into a generative AI model to evaluate the environmental impact. The evaluation results are sent back to the device, which displays the message, "This product has a high eco-level. It is certified organic and plastic-free."

[0134] Example prompt sentence:

[0135] Input text: "Certified Organic Plastic Free"

[0136] Please carry out an Eco Level Assessment.

[0137] This embodiment allows users to make sustainable choices quickly and easily in physical stores.

[0138] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0139] Step 1:

[0140] (Input): The user activates the smartphone camera.

[0141] (Action): The user takes a photo of a product they are considering purchasing.

[0142] (Output): The captured product image is saved on the device.

[0143] Step 2:

[0144] (Input): Product image saved on the device.

[0145] (Operation): The device converts the product image to JPEG format and uploads it to the server using an HTTP POST request.

[0146] (Output): Product image data is sent to the server.

[0147] Step 3:

[0148] (Input): Product image data uploaded to the server.

[0149] (Operation): The server receives the image data and extracts the text information using optical character recognition (OCR) technology. Specifically, it uses Tesseract OCR to identify characters from the image.

[0150] (Output): Text information extracted from the image.

[0151] Step 4:

[0152] (Input): Text information extracted by OCR technology.

[0153] (Operation): The server analyzes the text information and identifies product-related and environment-related keywords.

[0154] (Output): Identified product information and environmental keyword list.

[0155] Step 5:

[0156] (Input): Identified product information and environmental keyword list.

[0157] (Operation): The server uses the generative AI model to evaluate and score the environmental impact of the product based on the input keyword information. For example, "certified organic" will receive a plus 10 points, and "plastic-free" will receive a plus 10 points.

[0158] (Output): Environmental impact score for each product.

[0159] Step 6:

[0160] (Input): Environmental impact score for each product.

[0161] (Operation): The server returns the calculated score to the user's device as an HTTP response.

[0162] (Output): The environmental impact score is sent to the user's device.

[0163] Step 7:

[0164] (Input): The environmental impact score sent to the user's device.

[0165] (Operation): The device analyzes the received score and displays it visually, for example, "This product has a high eco-level. It is certified organic and does not contain plastic."

[0166] (Output): Users can check the environmental impact of the product on the screen.

[0167] The specific processing flow is as follows:

[0168] The user takes a photo of a product (Step 1), and the device sends the image to the server (Step 2). The server uses OCR technology to extract text information from the image (Step 3) and analyzes the text information to identify environmental keywords (Step 4). The server then uses a generative AI model to evaluate the product's environmental impact (Step 5) and sends the results back to the user's device (Step 6). Finally, the user can visually confirm the environmental impact results on their device (Step 7).

[0169] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0170] This invention relates to a system that evaluates the environmental impact of products by taking photos of them using devices such as smartphones and tablets. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it supports the selection of eco-friendly products based on the user's emotional state.

[0171] When a user uses the system, they first launch the application, switch to camera mode, and take a picture of a product they are considering purchasing. The device temporarily saves the captured image data. The saved image data is then sent to the server. The device converts the image to JPEG format and uploads it to the server using an HTTP POST request.

[0172] The server analyzes the received image data and uses optical character recognition (OCR) technology to extract product label and ingredient information. The server first reads the image and uses an OCR library to extract text from the image. It then analyzes the extracted text data to identify keywords and ingredient information related to the product.

[0173] For example, if a user takes a photo of an organic food package, the server will extract keywords such as "certified organic" and "plastic-free."

[0174] The server then uses the extracted information to evaluate the product's environmental impact using a generative AI model, which weights each keyword based on a pre-trained dataset and scores the product's eco-level.

[0175] For example, the influence of each keyword is evaluated in the following way: "organic certified" will be given 10 eco points, and "plastic-free" will be given 10 eco points.

[0176] The server returns the calculated eco-level results to the terminal as an HTTP response. The terminal analyzes the received eco-level results and displays them to the user in an appropriate format. The user can check the evaluation results displayed on the screen and select environmentally friendly products.

[0177] The system also incorporates an emotion engine that recognizes the user's emotional state to optimize the user's experience in selecting eco-friendly products. The emotion engine analyzes the user's facial expressions and voice to determine whether they are relaxed, interested, or otherwise. Based on this information, the system displays eco-level results at the appropriate time or provides additional information to the user.

[0178] For example, if the emotion engine recognizes the user's interest while checking the eco-level, the system will provide detailed information such as, "This product is very environmentally friendly. It is certified organic and does not contain plastic."

[0179] In this way, users can easily and quickly check the eco-friendliness of products through the application, and with the support of the emotion engine, they can make better choices. This system aims not only to contribute to environmental issues, but also to improve users' shopping experience.

[0180] The processing flow will be explained below.

[0181] Step 1:

[0182] The user starts the application, switches to camera mode, and takes a picture of a product they are considering purchasing. The user then uses the device's camera to capture the product, and the image is temporarily saved in the application.

[0183] Step 2:

[0184] The device sends the stored image data to the server. The image data is converted to JPEG format and uploaded to the server using an HTTP POST request. This operation transfers the image data to the server.

[0185] Step 3:

[0186] The server analyzes the received image data and uses optical character recognition (OCR) technology to extract product label and ingredient information. The server first reads the image and uses an OCR library to extract text information from the image.

[0187] Step 4:

[0188] The server analyzes the extracted text data to identify keywords and ingredient information related to the product. This analysis identifies specific keywords such as "certified organic" or "plastic-free."

[0189] Step 5:

[0190] The server uses the extracted information to evaluate the product's environmental impact using a generative AI model, which weights each keyword based on a pre-trained dataset and scores the product's eco-level.

[0191] Step 6:

[0192] The server returns the calculated eco-level result to the device. The evaluation result is sent to the device as an HTTP response, and the device receives the data.

[0193] Step 7:

[0194] The device analyzes the received eco-level results and displays them in an appropriate format to the user, allowing the user to easily select environmentally friendly products.

[0195] Step 8:

[0196] Users can check the evaluation results displayed on the screen and select eco-friendly products. Based on this information, users can practice sustainable consumption behavior.

[0197] Step 9:

[0198] The emotion engine recognizes the user's emotions. Here, the device's camera and microphone are used to capture the user's facial expressions and voice, and the emotion engine analyzes this data to evaluate the user's emotional state.

[0199] Step 10:

[0200] The device uses the analysis results of the emotion engine to provide feedback according to the user's emotional state. For example, if the user is interested, detailed information is displayed, and if the user is relaxed, an encouraging message is displayed.

[0201] In this way, by combining the emotion engine, users can have a more personalized eco-product selection experience. This system allows users to easily select environmentally friendly products and enjoy a pleasant purchasing experience.

[0202] Example 2

[0203] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0204] Conventional systems only evaluate the environmental impact of products and are unable to consider the user's emotional state, making it difficult to provide information at the optimal time for the user. Furthermore, the analysis of captured images and presentation of evaluation results are insufficient, making it difficult to fully improve the user's shopping experience.

[0205] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0206] In this invention, the server includes means for inputting an image, means for analyzing the input image and extracting text information, means for identifying product-specific information based on the extracted text information, means for evaluating the environmental impact of each product based on the identified product information, means for presenting the evaluation results to the user, means for analyzing the emotional state of the user, and means for optimizing the presentation of the evaluation results based on the emotional state of the user. This makes it possible to provide the user with an accurate evaluation of the environmental impact and to provide information at an optimal timing tailored to the user's emotional state.

[0207] 1. "Means for inputting images" refers to a function that allows users to take product images using the camera on their smartphone or tablet and import that image data into the system.

[0208] 2. "Means for analyzing input images and extracting text information" refers to the process of identifying text information from captured images and extracting it as text data.

[0209] 3. "Means for identifying product-specific information based on extracted character information" refers to a function that identifies and identifies product characteristics and ingredient information from character information extracted using OCR technology, etc.

[0210] 4. "Means for assessing the environmental impact of each product based on identified product information" refers to a function that scores or assesses the environmental impact of a product using an AI model or other method in accordance with identified product information.

[0211] 5. "Means for presenting evaluation results to users" refers to a function for displaying the environmental impact of evaluated products and other related information in a user-friendly format.

[0212] 6. "Means for analyzing the user's emotional state" refers to a function that uses a camera or microphone to analyze the user's facial expressions and voice and evaluate their emotional state.

[0213] 7. "Means for optimizing the presentation of evaluation results based on the user's emotional state" refers to a function for providing evaluation results and additional information to the user at the optimal timing and in the optimal format based on the analyzed user's emotional state.

[0214] This invention relates to a system that evaluates the environmental impact of products by taking photos of them using devices such as smartphones and tablets. It also supports the selection of eco-friendly products based on the user's emotional state by combining it with an emotion engine that recognizes the user's emotions.

[0215] When a user uses this system, they first launch the application, switch to camera mode, and take a picture of a product they are considering purchasing. The device controls the smartphone's camera hardware and temporarily stores the captured image data. The image data is converted to JPEG format and sent to the server using an HTTP POST request. The server analyzes the image using the OpenCV library and extracts text information using the Tesseract OCR library.

[0216] Specifically, the server performs OCR processing to recognize keywords such as "certified organic" and "plastic-free" from the image. Next, product-specific information is identified based on the extracted text information, and this information is used to evaluate the environmental impact of each product using a generative AI model. The AI ​​model weights each keyword based on a dataset pre-trained using "TENSORFLOW (registered trademark)" and generates a score for the eco-level. For example, "certified organic" is evaluated as +10 eco points, and "plastic-free" is evaluated as +10 eco points.

[0217] The server returns the evaluation results to the terminal as an HTTP response, and the terminal analyzes the received JSON format data and displays it to the user. The evaluation results are displayed in the user interface in easy-to-understand graphs and text format. For example, the user might see on the screen, "This product has an eco-point rating of 20. It is certified organic and uses no plastic, making it a very environmentally friendly product."

[0218] Furthermore, the system incorporates an emotion engine that uses the device's camera and microphone to capture the user's facial expressions and voice in real time and analyzes the user's emotional state. The server evaluates the user's emotional state based on this data and provides the evaluation results and additional information at the optimal time based on the user's emotional state. For example, when a user is checking the eco-level results, the emotion engine recognizes the user's interest and displays additional detailed information, such as, "This product is very environmentally friendly. It is certified organic and does not use plastic."

[0219] This system not only allows users to easily check the environmental impact of products, but also helps them make better choices with the support of an emotion engine, improving the user's shopping experience while also promoting contributions to environmental issues.

[0220] Prompt Sentence Examples

[0221] A user took a photo of an organic food package. We used OCR technology to extract the keywords "organic certified" and "plastic-free." Based on these keywords, you can evaluate the product's environmental impact.

[0222] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0223] Step 1:

[0224] Launching the application and switching to camera mode

[0225] The user starts an application on their smartphone or tablet and switches to camera mode.

[0226] Input: An application is started by a user action.

[0227] Output: The device switches to camera mode and displays the camera image.

[0228] Step 2:

[0229] Capture and save image data

[0230] The user takes a photo of a product they are considering purchasing, and the device temporarily saves the image data in JPEG format.

[0231] Input: User presses the capture button.

[0232] Output: Image data is saved in JPEG format on the device.

[0233] Step 3:

[0234] Sending image data

[0235] The device sends the stored image data to the server using an HTTP POST request.

[0236] Input: Image data in JPEG format.

[0237] Output: Image data is sent to the server via an HTTP POST request.

[0238] Step 4:

[0239] Receiving and analyzing image data

[0240] The server receives the image data sent via the HTTP POST request and begins analysis.

[0241] Input: Image data in JPEG format.

[0242] Output: Log information informing the start of image analysis.

[0243] Step 5:

[0244] Extracting text information

[0245] The server reads the image using the "OpenCV" library and extracts characters from the image using the "Tesseract" OCR library.

[0246] Input: Image data.

[0247] Output: Extracted character information (text format).

[0248] Step 6:

[0249] Identifying product information

[0250] The server analyzes the extracted text information and identifies keywords related to the product.

[0251] Input: Extracted text information.

[0252] Output: Identified keywords (e.g. "certified organic" or "plastic-free").

[0253] Step 7:

[0254] Environmental impact assessment

[0255] The server evaluates the environmental impact of a product using a generative AI model based on the identified keywords. The AI ​​model uses TensorFlow to weight each keyword based on a pre-trained dataset and score the product's eco-level.

[0256] Input: Identified keywords.

[0257] Output: Eco-level score (e.g. "Certified Organic: 10" or "Plastic-free: 10").

[0258] Step 8:

[0259] Sending evaluation results

[0260] The server returns the calculated environmental impact score to the terminal as an HTTP response.

[0261] Input: Eco-level score.

[0262] Output: JSON data sent to the device in the HTTP response.

[0263] Step 9:

[0264] Displaying the evaluation results

[0265] The device analyzes the received JSON data and displays the evaluation results to the user. Specifically, the evaluation results are displayed in an easy-to-understand graph or text format on the user interface.

[0266] Input: JSON data.

[0267] Output: The rating result shown to the user (e.g. "This product has 20 eco points. It is certified organic and plastic-free, making it a very environmentally friendly product.").

[0268] Step 10:

[0269] Emotional state analysis

[0270] The device's emotion engine uses the camera and microphone to analyze the user's facial expressions and voice and assess their emotional state.

[0271] Input: User's facial expression data, voice data.

[0272] Output: Evaluated emotional state (e.g., interested, relaxed, etc.).

[0273] Step 11:

[0274] Emotion-Based Optimization

[0275] The server optimizes the timing and content of information provided to the user based on the evaluated emotional state.

[0276] Input: Emotional state data.

[0277] Output: Display additional information optimized for the user (e.g. "This product is very environmentally friendly. It is certified organic and plastic-free.").

[0278] (Application example 2)

[0279] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0280] In recent years, growing environmental awareness among consumers has led to an increased demand for selecting environmentally friendly products. However, current systems have difficulty quickly and accurately providing consumers with the specific environmental impact of each product, and do not provide information that reflects the user's emotions or interests. This makes it difficult for consumers to obtain appropriate information when selecting products, and they are unable to efficiently select eco-friendly products. Furthermore, current systems are unable to recognize the user's emotional state and provide information based on their emotions, so improvements to the user experience are needed.

[0281] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0282] In this invention, the server includes means for inputting an image, means for analyzing the input image and extracting text information, means for identifying product-specific information based on the extracted text information, means for evaluating the environmental impact of each product based on the identified product information, means for recognizing the user's emotional state, means for providing additional information to the user at an optimal timing based on the evaluation results and the emotion analysis results, and means for presenting the evaluation results to the user. This enables consumers to quickly and accurately grasp the environmental impact of a product when selecting it, and also makes it possible to provide optimal information according to the user's emotional state.

[0283] An "image" is a digital representation of visual information.

[0284] "Input means" refers to a device or interface that allows a user to input image data into the system.

[0285] "Means for analyzing and extracting character information" refers to technology and devices for automatically identifying and recognizing characters and their meanings from image data.

[0286] "Means for identifying product-specific information" refers to a method or system for determining detailed information about the product based on the extracted text information.

[0287] "Means for assessing environmental impact" refers to a system for assessing and quantifying the impact of a product on the environment based on information specific to the identified product.

[0288] "Means for recognizing emotional states" refers to technologies and mechanisms that analyze and recognize a user's emotions and psychological state from their facial expressions, voice, and actions.

[0289] "Means for providing additional information at the most appropriate time" refers to a system or method that provides the information a user needs at the most appropriate time based on the user's emotional state and evaluation results.

[0290] "Optical character recognition technology" refers to technology that optically reads characters contained in image data and converts them into machine-readable character data.

[0291] "Artificial intelligence model" refers to an algorithm or system that is trained to analyze data and make predictions or decisions using techniques such as machine learning and deep learning.

[0292] An "emotion engine" is a system that analyzes a user's emotions and provides the most appropriate information and takes appropriate action based on the results.

[0293] A "generative AI model" refers to an artificial intelligence algorithm that is pre-trained on a large dataset to generate the required information.

[0294] This invention relates to a system in which a user photographs a product using a terminal, evaluates the product's environmental impact, and provides information based on the user's emotional state. The main components for implementing this invention are an image capturing unit, a text information analyzing unit, a product information identifying unit, an environmental impact evaluation unit, an emotional state recognition unit, an additional information providing unit, and an evaluation result presentation unit. These components are described in detail below.

[0295] The server uses the device's camera as a means of image input. When the user takes a photo of a product, the device converts the image data into JPEG format, temporarily stores it, and then uploads it to the server using an HTTP POST request.

[0296] The server uses an optical character recognition (OCR) library to analyze the received image data. Specifically, it extracts text information from the received image and uses that information to identify product-specific information. For this, it uses OCR tools such as OpenCV and Pytesseract.

[0297] The server then evaluates the product's environmental impact based on the identified product-specific information. This evaluation is performed using a pre-trained generative AI model. The AI ​​model weights the identified keywords and scores the product's eco-level. For example, it calculates eco-points based on keywords such as "certified organic" and "plastic-free."

[0298] The server uses an emotion engine to recognize the user's emotional state. The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and voice to determine whether the user is relaxed, interested, etc. For example, an emotion analysis tool such as Emotion Engine is used.

[0299] Based on the evaluation results and sentiment analysis results, the server has the means to provide additional information to the user at the optimal time. When the user is checking the eco-level, if the sentiment engine recognizes the user's interest, the system will provide detailed information (e.g., "This product is very environmentally friendly. It is certified organic and does not use plastic.").

[0300] The terminal displays the eco-level and detailed information received from the server to the user as a means of presenting the evaluation results to the user, allowing the user to quickly and accurately understand the environmental impact of a product when selecting it.

[0301] As a concrete example, suppose a user takes a photo of a cosmetic product package in a virtual store and uploads it to the system. The system extracts keywords such as "paraben-free" and "no animal testing" from the image and evaluates the product's eco-friendliness based on those keywords. If the emotion engine recognizes the user's interest while the user is selecting a product on the screen, the system will provide information such as, "This cosmetic product is environmentally friendly. It is paraben-free and has not been tested on animals."

[0302] Also, the following is an example of a prompt sentence for the generative AI model:

[0303] "Based on the product images uploaded by users, extract keywords related to eco-friendly and environmentally conscious products, such as 'certified organic' or 'plastic-free'. Also, assess the user's emotional state and provide information at the right time."

[0304] This is expected to make it easier for users to choose more eco-friendly products and improve their shopping experience.

[0305] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0306] Step 1:

[0307] The device takes a photo of the product for the user. The user takes a photo of the desired product using the device's camera and temporarily stores the image data on the device. The input is the captured image, and the output is the stored image data.

[0308] Step 2:

[0309] The device converts the captured image data into JPEG format and uploads it to the server using an HTTP POST request. The input is the saved image data, and the output is the image data sent to the server.

[0310] Step 3:

[0311] The server analyzes the received image data using optical character recognition (OCR). Specifically, it uses software such as OpenCV or Pytesseract to extract text information from the image. The input is the received image data, and the output is the extracted text information.

[0312] Step 4:

[0313] The server analyzes the extracted text information and identifies product-specific information. For example, it extracts product label information and ingredient information and uses that information to identify detailed product data. The input is the extracted text information, and the output is product-specific information.

[0314] Step 5:

[0315] The server uses a generative AI model to evaluate the environmental impact of a product based on the product-specific information it has identified. For example, it scores the eco-level based on keywords such as "certified organic" or "plastic-free." The input is the product-specific information, and the output is the eco-level score.

[0316] Step 6:

[0317] The device recognizes the user's emotional state. It uses the device's camera and microphone to analyze the user's facial expressions and voice to determine whether the user is relaxed, interested, etc. The system relies on analytical processing using an emotion engine. The input is the user's facial expressions and voice data, and the output is data on the user's emotional state.

[0318] Step 7:

[0319] The server provides additional information to the user at the optimal time based on the evaluation results and emotional state data. For example, if the user is interested, it can present detailed eco-friendly information about a product. The input is the eco-level score and emotional state data, and the output is the additional information presented to the user.

[0320] Step 8:

[0321] The terminal receives the evaluation results and additional information from the server and presents them to the user. The user can check the eco-level score and specific product information on the screen. The input is the response data from the server, and the output is the information displayed to the user.

[0322] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0323] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0324] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0325] [Second embodiment]

[0326] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0327] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0328] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0329] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0330] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0331] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0332] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0333] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0334] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0335] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0336] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0337] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0338] The present invention relates to a system for evaluating the environmental impact of a product by photographing the product using a device such as a smartphone or tablet. Specific embodiments will be described below.

[0339] When a user uses the system, they first launch the application, switch to camera mode, and take a picture of a product they are considering purchasing. The device temporarily saves the captured image data. The saved image data is then sent to the server. The device converts the image to JPEG format and uploads it to the server using an HTTP POST request.

[0340] The server analyzes the received image data and uses optical character recognition (OCR) technology to extract product label and ingredient information. The server first reads the image and uses an OCR library to extract text from the image. It then analyzes the extracted text data to identify keywords and ingredient information related to the product.

[0341] For example, if a user takes a photo of an organic food package, the server will extract keywords such as "certified organic" and "plastic-free."

[0342] The server then uses the extracted information to evaluate the product's environmental impact using a generative AI model, which operates on a pre-trained dataset, weights the extracted keywords, and scores the product's eco-level.

[0343] For example, the influence of each keyword is evaluated in the following way: "organic certified" will be given 10 eco points, and "plastic-free" will be given 10 eco points.

[0344] The server returns the calculated eco-level results to the terminal as an HTTP response. The terminal analyzes the received eco-level results and displays them to the user in an appropriate format. The user can check the evaluation results displayed on the screen and select environmentally friendly products.

[0345] For example, a message will appear on your smartphone screen saying, "This product is highly eco-friendly. It is certified organic and does not contain any plastic."

[0346] In this way, users can easily and quickly check the eco-level of a product via the application, enabling them to make more sustainable choices.

[0347] The processing flow will be explained below.

[0348] Step 1:

[0349] The user starts the application, switches to camera mode, and takes a picture of a product they are considering purchasing. The user then uses the device's camera to capture the product, and the image is temporarily saved in the application.

[0350] Step 2:

[0351] The device sends the stored image data to the server, where it is converted to JPEG format and uploaded to the server using an HTTP POST request. This transfers the image data to the server.

[0352] Step 3:

[0353] The server analyzes the received image data and uses optical character recognition (OCR) technology to extract product label and ingredient information. First, the server reads the stored image and uses an OCR library to extract text information from the image.

[0354] Step 4:

[0355] The server analyzes the extracted text data to identify keywords and ingredient information related to the product, identifying specific keywords and phrases such as "certified organic" or "plastic-free."

[0356] Step 5:

[0357] The server uses the extracted information to evaluate the product's environmental impact using a generative AI model, which weights each keyword based on a pre-trained dataset and scores the product's eco-level.

[0358] Step 6:

[0359] The server returns the calculated eco-level result to the device. The evaluation result is sent to the device as an HTTP response, and the device receives the data.

[0360] Step 7:

[0361] The device analyzes the received eco-level results and displays them in an appropriate format to the user, allowing the user to easily select environmentally friendly products.

[0362] Step 8:

[0363] Users can check the evaluation results displayed on the screen and select eco-friendly products. Based on this information, users can practice sustainable consumption behavior.

[0364] Example 1

[0365] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0366] In the past, assessing the environmental impact of a product required users to manually research product information and make judgments based on that data, which was time-consuming and labor-intensive. Furthermore, the criteria for assessing environmental impact were inconsistent, making reliable assessments difficult. The present invention aims to solve these problems by providing a system that allows users to easily and quickly check the environmental impact of a product and supports sustainable choices.

[0367] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0368] In this invention, the server includes means for inputting an image, means for analyzing the input image and extracting text information, means for identifying product-specific information based on the extracted text information, means for evaluating the environmental impact of each product based on the identified product information, means for presenting the evaluation results to a user, and means for using a generative AI model that weights the extracted keywords and scores the products. This enables a user to automatically evaluate the environmental impact based on photographed product images and obtain rapid and consistent evaluation results without having to manually research the information.

[0369] The "means for inputting an image" refers to a device or program that provides an interface for the user to photograph a product and can acquire the image data.

[0370] "Means for analyzing an input image and extracting text information" refers to techniques or devices that use image processing technology to identify and extract text information from an input image.

[0371] "Means for identifying product-specific information based on extracted character information" refers to technology or devices that use optical character recognition technology or data analysis algorithms to identify specific product information based on extracted character information.

[0372] The "means for assessing the environmental impact of each product based on identified product information" refers to an algorithm or program for assessing the environmental impact of a product based on information related to the product.

[0373] The "means for presenting the evaluation results to the user" refers to an interface or display device for displaying the environmental impact evaluation results in an easy-to-understand manner for the user.

[0374] "Means of using a generative AI model that weights extracted keywords and scores products" refers to technologies and programs that use an AI model to weight extracted keywords and score the environmental impact of products based on that weighting.

[0375] This invention is a system for evaluating the environmental impact of products by utilizing technologies such as an image input device, a server, and a generative AI model. Specific embodiments will be described below.

[0376] When a user uses the system, they first launch the application, switch to camera mode, and take a picture of a product they are considering purchasing. The device temporarily saves the captured image data, then converts it to JPEG format and uploads it to the server using an HTTP POST request. The hardware used for this includes mobile devices such as smartphones and tablets.

[0377] To analyze the image data received by the server, optical character recognition (OCR) technology is first used. The image is read and text information is extracted from the image using an OCR library. The extracted text data is then analyzed to identify keywords and ingredient information related to the product. The software used for this purpose includes various OCR engines and text analysis algorithms.

[0378] For example, when a user takes a photo of an organic food package, the server extracts keywords such as "certified organic" and "plastic-free." The server then uses a generative AI model to evaluate the product's environmental impact based on the extracted information. The AI ​​model operates based on a pre-trained dataset, weighting each keyword and scoring the product's eco-level. For example, the impact of each keyword is evaluated as follows: "certified organic" earns 10 eco points, and "plastic-free" earns 10 eco points.

[0379] The eco-level results calculated by the server are sent back to the terminal as an HTTP response. The terminal analyzes the received eco-level results and displays them to the user in an appropriate format. For example, a message might appear on a smartphone screen saying, "This product has a high eco-level. It is organically certified and does not contain plastic," allowing the user to select environmentally friendly products.

[0380] An example prompt for a generative AI model might look something like this:

[0381] "Information contained on the product label: 'Certified Organic', 'Plastic-free'. Please rate the eco-friendliness of the product."

[0382] In this way, users can easily and quickly check the eco-level of a product via the application and make more sustainable choices.

[0383] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0384] Step 1:

[0385] The user starts the application, switches to camera mode, and takes a photo of a product they are considering purchasing.

[0386] Specifically, the user taps the app to activate the camera function, points the camera at the product, and presses the shutter button.

[0387] Input: User-initiated camera activation and product photography

[0388] Output: Photographed product image data

[0389] Step 2:

[0390] The device temporarily saves the captured image data, converts it to JPEG format, and uploads the saved image data to the server using an HTTP POST request.

[0391] Specifically, the image is saved in a temporary folder on the device, converted to JPEG format using a conversion library, and sent to the server using an HTTP request library.

[0392] Input: Photographed product image data

[0393] Output: A request to upload JPEG image data to the server.

[0394] Step 3:

[0395] The server receives the HTTP POST request, retrieves the JPEG image data, and uses OCR technology to extract text information from the image.

[0396] Specifically, the server processes the request, performs OCR processing using an image analysis library, and reads the product label and ingredient information.

[0397] Input: JPEG format image data

[0398] Output: Extracted character information (text data)

[0399] Step 4:

[0400] The server analyzes the extracted text data and identifies keywords and ingredient information related to the product.

[0401] Specifically, it applies a text analysis algorithm to extract keywords such as "certified organic" and "plastic-free."

[0402] Input: Extracted character information (text data)

[0403] Output: Identified keywords and ingredient information

[0404] Step 5:

[0405] The server uses the generated AI model to weight the identified keywords and evaluate the environmental impact of the product.

[0406] Specifically, the system sends a prompt to the AI ​​model, calculates eco points for each keyword, and calculates an overall score.

[0407] Input: Identified keywords and ingredient information

[0408] Output: Product environmental impact score

[0409] Step 6:

[0410] The server returns the evaluation results to the terminal as an HTTP response.

[0411] Specifically, the evaluation results are packaged in JSON format and sent to the terminal as an HTTP response.

[0412] Input: Product environmental impact score

[0413] Output: HTTP response containing the environmental impact score

[0414] Step 7:

[0415] The terminal receives the HTTP response from the server, analyzes the evaluation results, and displays them to the user.

[0416] Specifically, it deserializes the response data and displays on the screen, "This product is highly eco-friendly. It is certified organic and does not contain plastic."

[0417] Input: HTTP response containing environmental impact score

[0418] Output: The evaluation result (text message) displayed to the user

[0419] Through the above steps, users can use the system to easily check the environmental impact of products.

[0420] (Application example 1)

[0421] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0422] Modern consumers often want to choose environmentally friendly products, but lack the means to quickly and easily evaluate their environmental impact. When shopping in a physical store, there is a demand for an immediate understanding of the environmental impact of products during the product selection process, but current technology makes it difficult to meet such needs.

[0423] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0424] In this invention, the server includes means for inputting an image, means for analyzing the input image and extracting text information, means for identifying product-specific information and environmental keywords based on the extracted text information, means for evaluating the environmental impact of each product using a generative AI model based on the identified information, and means for presenting the evaluation results to a user's terminal. This enables consumers to quickly and easily evaluate the environmental impact of products and make environmentally conscious choices when purchasing products in a physical store.

[0425] "Means for inputting images" refers to a mechanism that allows users to take photos of products using devices such as smartphones or tablets and import the image data into the system.

[0426] "Means for analyzing input images and extracting text information" refers to technology for identifying and extracting text from captured image data using optical character recognition (OCR) technology.

[0427] "Means for identifying product-specific information and environmental keywords based on extracted character information" refers to the process of analyzing text information extracted using OCR technology and identifying keywords related to specific product information and the environment.

[0428] "Means for assessing the environmental impact of each product using a generative AI model based on identified information" refers to a mechanism for inputting analyzed keyword information into a generative AI model and scoring the environmental impact of the product based on that model.

[0429] "Means for presenting the evaluation results on the user's device" refers to a function that responds to and visually displays the environmental impact score calculated by the generative AI model on the user's smartphone or tablet.

[0430] The present invention provides a system that allows consumers to easily understand the environmental impact of products in physical stores. Specific embodiments will be described below.

[0431] The system mainly consists of a device such as a smartphone or tablet and a server. The device is equipped with an image input means that allows the user to take a photo of a product they are considering purchasing. The user starts the application, switches to camera mode, and takes a photo of the product, which then acquires the image data.

[0432] The device converts the captured image data into JPEG format and then uploads it to the server using an HTTP POST request. The server first uses optical character recognition (OCR) technology to analyze the received image data. Specifically, it uses Tesseract OCR to extract text information from the image.

[0433] The server then analyzes the extracted text to identify keywords related to the product and environmental information. This process involves analyzing the input text and extracting environmental keywords such as "certified organic" and "plastic-free."

[0434] Based on the identified keywords, the server uses a generative AI model to evaluate the environmental impact of the product. The generative AI model operates based on a pre-trained dataset and weights the extracted keywords. The weighting of the keywords results in a score for the product's eco-level. This allows users to instantly understand the product's environmental impact.

[0435] The eco-level result calculated by the server is sent back to the user's device as an HTTP response, and the device visually displays the received eco-level result and provides it to the user.

[0436] Examples:

[0437] For example, consider the case where a user scans an organic food product at a supermarket. Using a smartphone app, the user scans the product packaging and sends the image data to a server. The server uses OCR to extract keywords such as "certified organic" and "plastic-free," and inputs these into a generative AI model to evaluate the environmental impact. The evaluation results are sent back to the device, which displays the message, "This product has a high eco-level. It is certified organic and plastic-free."

[0438] Example prompt sentence:

[0439] Input text: "Certified Organic Plastic Free"

[0440] Please carry out an Eco Level Assessment.

[0441] This embodiment allows users to make sustainable choices quickly and easily in physical stores.

[0442] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0443] Step 1:

[0444] (Input): The user activates the smartphone camera.

[0445] (Action): The user takes a photo of a product they are considering purchasing.

[0446] (Output): The captured product image is saved on the device.

[0447] Step 2:

[0448] (Input): Product image saved on the device.

[0449] (Operation): The device converts the product image to JPEG format and uploads it to the server using an HTTP POST request.

[0450] (Output): Product image data is sent to the server.

[0451] Step 3:

[0452] (Input): Product image data uploaded to the server.

[0453] (Operation): The server receives the image data and extracts the text information using optical character recognition (OCR) technology. Specifically, it uses Tesseract OCR to identify characters from the image.

[0454] (Output): Text information extracted from the image.

[0455] Step 4:

[0456] (Input): Text information extracted by OCR technology.

[0457] (Operation): The server analyzes the text information and identifies product-related and environment-related keywords.

[0458] (Output): Identified product information and environmental keyword list.

[0459] Step 5:

[0460] (Input): Identified product information and environmental keyword list.

[0461] (Operation): The server uses the generative AI model to evaluate and score the environmental impact of the product based on the input keyword information. For example, "certified organic" will receive a plus 10 points, and "plastic-free" will receive a plus 10 points.

[0462] (Output): Environmental impact score for each product.

[0463] Step 6:

[0464] (Input): Environmental impact score for each product.

[0465] (Operation): The server returns the calculated score to the user's device as an HTTP response.

[0466] (Output): The environmental impact score is sent to the user's device.

[0467] Step 7:

[0468] (Input): The environmental impact score sent to the user's device.

[0469] (Operation): The device analyzes the received score and displays it visually, for example, "This product has a high eco-level. It is certified organic and does not contain plastic."

[0470] (Output): Users can check the environmental impact of the product on the screen.

[0471] The specific processing flow is as follows:

[0472] The user takes a photo of a product (Step 1), and the device sends the image to the server (Step 2). The server uses OCR technology to extract text information from the image (Step 3) and analyzes the text information to identify environmental keywords (Step 4). The server then uses a generative AI model to evaluate the product's environmental impact (Step 5) and sends the results back to the user's device (Step 6). Finally, the user can visually confirm the environmental impact results on their device (Step 7).

[0473] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0474] This invention relates to a system that evaluates the environmental impact of products by taking photos of them using devices such as smartphones and tablets. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it supports the selection of eco-friendly products based on the user's emotional state.

[0475] When a user uses the system, they first launch the application, switch to camera mode, and take a picture of a product they are considering purchasing. The device temporarily saves the captured image data. The saved image data is then sent to the server. The device converts the image to JPEG format and uploads it to the server using an HTTP POST request.

[0476] The server analyzes the received image data and uses optical character recognition (OCR) technology to extract product label and ingredient information. The server first reads the image and uses an OCR library to extract text from the image. It then analyzes the extracted text data to identify keywords and ingredient information related to the product.

[0477] For example, if a user takes a photo of an organic food package, the server will extract keywords such as "certified organic" and "plastic-free."

[0478] The server then uses the extracted information to evaluate the product's environmental impact using a generative AI model, which weights each keyword based on a pre-trained dataset and scores the product's eco-level.

[0479] For example, the influence of each keyword is evaluated in the following way: "organic certified" will be given 10 eco points, and "plastic-free" will be given 10 eco points.

[0480] The server returns the calculated eco-level results to the terminal as an HTTP response. The terminal analyzes the received eco-level results and displays them to the user in an appropriate format. The user can check the evaluation results displayed on the screen and select environmentally friendly products.

[0481] The system also incorporates an emotion engine that recognizes the user's emotional state to optimize the user's experience in selecting eco-friendly products. The emotion engine analyzes the user's facial expressions and voice to determine whether they are relaxed, interested, or otherwise. Based on this information, the system displays eco-level results at the appropriate time or provides additional information to the user.

[0482] For example, if the emotion engine recognizes the user's interest while checking the eco-level, the system will provide detailed information such as, "This product is very environmentally friendly. It is certified organic and does not contain plastic."

[0483] In this way, users can easily and quickly check the eco-friendliness of products through the application, and with the support of the emotion engine, they can make better choices. This system aims not only to contribute to environmental issues, but also to improve users' shopping experience.

[0484] The processing flow will be explained below.

[0485] Step 1:

[0486] The user starts the application, switches to camera mode, and takes a picture of a product they are considering purchasing. The user then uses the device's camera to capture the product, and the image is temporarily saved in the application.

[0487] Step 2:

[0488] The device sends the stored image data to the server. The image data is converted to JPEG format and uploaded to the server using an HTTP POST request. This operation transfers the image data to the server.

[0489] Step 3:

[0490] The server analyzes the received image data and uses optical character recognition (OCR) technology to extract product label and ingredient information. The server first reads the image and uses an OCR library to extract text information from the image.

[0491] Step 4:

[0492] The server analyzes the extracted text data to identify keywords and ingredient information related to the product. This analysis identifies specific keywords such as "certified organic" or "plastic-free."

[0493] Step 5:

[0494] The server uses the extracted information to evaluate the product's environmental impact using a generative AI model, which weights each keyword based on a pre-trained dataset and scores the product's eco-level.

[0495] Step 6:

[0496] The server returns the calculated eco-level result to the device. The evaluation result is sent to the device as an HTTP response, and the device receives the data.

[0497] Step 7:

[0498] The device analyzes the received eco-level results and displays them in an appropriate format to the user, allowing the user to easily select environmentally friendly products.

[0499] Step 8:

[0500] Users can check the evaluation results displayed on the screen and select eco-friendly products. Based on this information, users can practice sustainable consumption behavior.

[0501] Step 9:

[0502] The emotion engine recognizes the user's emotions. Here, the device's camera and microphone are used to capture the user's facial expressions and voice, and the emotion engine analyzes this data to evaluate the user's emotional state.

[0503] Step 10:

[0504] The device uses the analysis results of the emotion engine to provide feedback according to the user's emotional state. For example, if the user is interested, detailed information is displayed, and if the user is relaxed, an encouraging message is displayed.

[0505] In this way, by combining the emotion engine, users can have a more personalized eco-product selection experience. This system allows users to easily select environmentally friendly products and enjoy a pleasant purchasing experience.

[0506] Example 2

[0507] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0508] Conventional systems only evaluate the environmental impact of products and are unable to consider the user's emotional state, making it difficult to provide information at the optimal time for the user. Furthermore, the analysis of captured images and presentation of evaluation results are insufficient, making it difficult to fully improve the user's shopping experience.

[0509] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0510] In this invention, the server includes means for inputting an image, means for analyzing the input image and extracting text information, means for identifying product-specific information based on the extracted text information, means for evaluating the environmental impact of each product based on the identified product information, means for presenting the evaluation results to the user, means for analyzing the emotional state of the user, and means for optimizing the presentation of the evaluation results based on the emotional state of the user. This makes it possible to provide the user with an accurate evaluation of the environmental impact and to provide information at an optimal timing tailored to the user's emotional state.

[0511] 1. "Means for inputting images" refers to a function that allows users to take product images using the camera on their smartphone or tablet and import that image data into the system.

[0512] 2. "Means for analyzing input images and extracting text information" refers to the process of identifying text information from captured images and extracting it as text data.

[0513] 3. "Means for identifying product-specific information based on extracted character information" refers to a function that identifies and identifies product characteristics and ingredient information from character information extracted using OCR technology, etc.

[0514] 4. "Means for assessing the environmental impact of each product based on identified product information" refers to a function that scores or assesses the environmental impact of a product using an AI model or other method in accordance with identified product information.

[0515] 5. "Means for presenting evaluation results to users" refers to a function for displaying the environmental impact of evaluated products and other related information in a user-friendly format.

[0516] 6. "Means for analyzing the user's emotional state" refers to a function that uses a camera or microphone to analyze the user's facial expressions and voice and evaluate their emotional state.

[0517] 7. "Means for optimizing the presentation of evaluation results based on the user's emotional state" refers to a function for providing evaluation results and additional information to the user at the optimal timing and in the optimal format based on the analyzed user's emotional state.

[0518] This invention relates to a system that evaluates the environmental impact of products by taking photos of them using devices such as smartphones and tablets. It also supports the selection of eco-friendly products based on the user's emotional state by combining it with an emotion engine that recognizes the user's emotions.

[0519] When a user uses this system, they first launch the application, switch to camera mode, and take a picture of a product they are considering purchasing. The device controls the smartphone's camera hardware and temporarily stores the captured image data. The image data is converted to JPEG format and sent to the server using an HTTP POST request. The server analyzes the image using the OpenCV library and extracts text information using the Tesseract OCR library.

[0520] Specifically, the server performs OCR processing to recognize keywords such as "certified organic" and "plastic-free" from the image. Next, product-specific information is identified based on the extracted text information, and this information is used to evaluate the environmental impact of each product using a generative AI model. The AI ​​model uses TensorFlow to weight each keyword based on a pre-trained dataset and generate a score for the eco-level. For example, "certified organic" is evaluated as +10 eco points, and "plastic-free" is evaluated as +10 eco points.

[0521] The server returns the evaluation results to the terminal as an HTTP response, and the terminal analyzes the received JSON format data and displays it to the user. The evaluation results are displayed in the user interface in easy-to-understand graphs and text format. For example, the user might see on the screen, "This product has an eco-point rating of 20. It is certified organic and uses no plastic, making it a very environmentally friendly product."

[0522] Furthermore, the system incorporates an emotion engine that uses the device's camera and microphone to capture the user's facial expressions and voice in real time and analyzes the user's emotional state. The server evaluates the user's emotional state based on this data and provides the evaluation results and additional information at the optimal time based on the user's emotional state. For example, when a user is checking the eco-level results, the emotion engine recognizes the user's interest and displays additional detailed information, such as, "This product is very environmentally friendly. It is certified organic and does not use plastic."

[0523] This system not only allows users to easily check the environmental impact of products, but also helps them make better choices with the support of an emotion engine, improving the user's shopping experience while also promoting contributions to environmental issues.

[0524] Prompt Sentence Examples

[0525] A user took a photo of an organic food package. We used OCR technology to extract the keywords "organic certified" and "plastic-free." Based on these keywords, you can evaluate the product's environmental impact.

[0526] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0527] Step 1:

[0528] Launching the application and switching to camera mode

[0529] The user starts an application on their smartphone or tablet and switches to camera mode.

[0530] Input: An application is started by a user action.

[0531] Output: The device switches to camera mode and displays the camera image.

[0532] Step 2:

[0533] Capture and save image data

[0534] The user takes a photo of a product they are considering purchasing, and the device temporarily saves the image data in JPEG format.

[0535] Input: User presses the capture button.

[0536] Output: Image data is saved in JPEG format on the device.

[0537] Step 3:

[0538] Sending image data

[0539] The device sends the stored image data to the server using an HTTP POST request.

[0540] Input: Image data in JPEG format.

[0541] Output: Image data is sent to the server via an HTTP POST request.

[0542] Step 4:

[0543] Receiving and analyzing image data

[0544] The server receives the image data sent via the HTTP POST request and begins analysis.

[0545] Input: Image data in JPEG format.

[0546] Output: Log information informing the start of image analysis.

[0547] Step 5:

[0548] Extracting text information

[0549] The server reads the image using the "OpenCV" library and extracts characters from the image using the "Tesseract" OCR library.

[0550] Input: Image data.

[0551] Output: Extracted character information (text format).

[0552] Step 6:

[0553] Identifying product information

[0554] The server analyzes the extracted text information and identifies keywords related to the product.

[0555] Input: Extracted text information.

[0556] Output: Identified keywords (e.g. "certified organic" or "plastic-free").

[0557] Step 7:

[0558] Environmental impact assessment

[0559] The server evaluates the environmental impact of a product using a generative AI model based on the identified keywords. The AI ​​model uses TensorFlow to weight each keyword based on a pre-trained dataset and score the product's eco-level.

[0560] Input: Identified keywords.

[0561] Output: Eco-level score (e.g. "Certified Organic: 10" or "Plastic-free: 10").

[0562] Step 8:

[0563] Sending evaluation results

[0564] The server returns the calculated environmental impact score to the terminal as an HTTP response.

[0565] Input: Eco-level score.

[0566] Output: JSON data sent to the device in the HTTP response.

[0567] Step 9:

[0568] Displaying the evaluation results

[0569] The device analyzes the received JSON data and displays the evaluation results to the user. Specifically, the evaluation results are displayed in an easy-to-understand graph or text format on the user interface.

[0570] Input: JSON data.

[0571] Output: The rating result shown to the user (e.g. "This product has 20 eco points. It is certified organic and plastic-free, making it a very environmentally friendly product.").

[0572] Step 10:

[0573] Emotional state analysis

[0574] The device's emotion engine uses the camera and microphone to analyze the user's facial expressions and voice and assess their emotional state.

[0575] Input: User's facial expression data, voice data.

[0576] Output: Evaluated emotional state (e.g., interested, relaxed, etc.).

[0577] Step 11:

[0578] Emotion-Based Optimization

[0579] The server optimizes the timing and content of information provided to the user based on the evaluated emotional state.

[0580] Input: Emotional state data.

[0581] Output: Display additional information optimized for the user (e.g. "This product is very environmentally friendly. It is certified organic and plastic-free.").

[0582] (Application example 2)

[0583] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0584] In recent years, growing environmental awareness among consumers has led to an increased demand for selecting environmentally friendly products. However, current systems have difficulty quickly and accurately providing consumers with the specific environmental impact of each product, and do not provide information that reflects the user's emotions or interests. This makes it difficult for consumers to obtain appropriate information when selecting products, and they are unable to efficiently select eco-friendly products. Furthermore, current systems are unable to recognize the user's emotional state and provide information based on their emotions, so improvements to the user experience are needed.

[0585] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0586] In this invention, the server includes means for inputting an image, means for analyzing the input image and extracting text information, means for identifying product-specific information based on the extracted text information, means for evaluating the environmental impact of each product based on the identified product information, means for recognizing the user's emotional state, means for providing additional information to the user at an optimal timing based on the evaluation results and the emotion analysis results, and means for presenting the evaluation results to the user. This enables consumers to quickly and accurately grasp the environmental impact of a product when selecting it, and also makes it possible to provide optimal information according to the user's emotional state.

[0587] An "image" is a digital representation of visual information.

[0588] "Input means" refers to a device or interface that allows a user to input image data into the system.

[0589] "Means for analyzing and extracting character information" refers to technology and devices for automatically identifying and recognizing characters and their meanings from image data.

[0590] "Means for identifying product-specific information" refers to a method or system for determining detailed information about the product based on the extracted text information.

[0591] "Means for assessing environmental impact" refers to a system for assessing and quantifying the impact of a product on the environment based on information specific to the identified product.

[0592] "Means for recognizing emotional states" refers to technologies and mechanisms that analyze and recognize a user's emotions and psychological state from their facial expressions, voice, and actions.

[0593] "Means for providing additional information at the most appropriate time" refers to a system or method that provides the information a user needs at the most appropriate time based on the user's emotional state and evaluation results.

[0594] "Optical character recognition technology" refers to technology that optically reads characters contained in image data and converts them into machine-readable character data.

[0595] "Artificial intelligence model" refers to an algorithm or system that is trained to analyze data and make predictions or decisions using techniques such as machine learning and deep learning.

[0596] An "emotion engine" is a system that analyzes a user's emotions and provides the most appropriate information and takes appropriate action based on the results.

[0597] A "generative AI model" refers to an artificial intelligence algorithm that is pre-trained on a large dataset to generate the required information.

[0598] This invention relates to a system in which a user photographs a product using a terminal, evaluates the product's environmental impact, and provides information based on the user's emotional state. The main components for implementing this invention are an image capturing unit, a text information analyzing unit, a product information identifying unit, an environmental impact evaluation unit, an emotional state recognition unit, an additional information providing unit, and an evaluation result presentation unit. These components are described in detail below.

[0599] The server uses the device's camera as a means of image input. When the user takes a photo of a product, the device converts the image data into JPEG format, temporarily stores it, and then uploads it to the server using an HTTP POST request.

[0600] The server uses an optical character recognition (OCR) library to analyze the received image data. Specifically, it extracts text information from the received image and uses that information to identify product-specific information. For this, it uses OCR tools such as OpenCV and Pytesseract.

[0601] The server then evaluates the product's environmental impact based on the identified product-specific information. This evaluation is performed using a pre-trained generative AI model. The AI ​​model weights the identified keywords and scores the product's eco-level. For example, it calculates eco-points based on keywords such as "certified organic" and "plastic-free."

[0602] The server uses an emotion engine to recognize the user's emotional state. The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and voice to determine whether the user is relaxed, interested, etc. For example, an emotion analysis tool such as Emotion Engine is used.

[0603] Based on the evaluation results and sentiment analysis results, the server has the means to provide additional information to the user at the optimal time. When the user is checking the eco-level, if the sentiment engine recognizes the user's interest, the system will provide detailed information (e.g., "This product is very environmentally friendly. It is certified organic and does not use plastic.").

[0604] The terminal displays the eco-level and detailed information received from the server to the user as a means of presenting the evaluation results to the user, allowing the user to quickly and accurately understand the environmental impact of a product when selecting it.

[0605] As a concrete example, suppose a user takes a photo of a cosmetic product package in a virtual store and uploads it to the system. The system extracts keywords such as "paraben-free" and "no animal testing" from the image and evaluates the product's eco-friendliness based on those keywords. If the emotion engine recognizes the user's interest while the user is selecting a product on the screen, the system will provide information such as, "This cosmetic product is environmentally friendly. It is paraben-free and has not been tested on animals."

[0606] Also, the following is an example of a prompt sentence for the generative AI model:

[0607] "Based on the product images uploaded by users, extract keywords related to eco-friendly and environmentally conscious products, such as 'certified organic' or 'plastic-free'. Also, assess the user's emotional state and provide information at the right time."

[0608] This is expected to make it easier for users to choose more eco-friendly products and improve their shopping experience.

[0609] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0610] Step 1:

[0611] The device takes a photo of the product for the user. The user takes a photo of the desired product using the device's camera and temporarily stores the image data on the device. The input is the captured image, and the output is the stored image data.

[0612] Step 2:

[0613] The device converts the captured image data into JPEG format and uploads it to the server using an HTTP POST request. The input is the saved image data, and the output is the image data sent to the server.

[0614] Step 3:

[0615] The server analyzes the received image data using optical character recognition (OCR). Specifically, it uses software such as OpenCV or Pytesseract to extract text information from the image. The input is the received image data, and the output is the extracted text information.

[0616] Step 4:

[0617] The server analyzes the extracted text information and identifies product-specific information. For example, it extracts product label information and ingredient information and uses that information to identify detailed product data. The input is the extracted text information, and the output is product-specific information.

[0618] Step 5:

[0619] The server uses a generative AI model to evaluate the environmental impact of a product based on the product-specific information it has identified. For example, it scores the eco-level based on keywords such as "certified organic" or "plastic-free." The input is the product-specific information, and the output is the eco-level score.

[0620] Step 6:

[0621] The device recognizes the user's emotional state. It uses the device's camera and microphone to analyze the user's facial expressions and voice to determine whether the user is relaxed, interested, etc. The system relies on analytical processing using an emotion engine. The input is the user's facial expressions and voice data, and the output is data on the user's emotional state.

[0622] Step 7:

[0623] The server provides additional information to the user at the optimal time based on the evaluation results and emotional state data. For example, if the user is interested, it can present detailed eco-friendly information about a product. The input is the eco-level score and emotional state data, and the output is the additional information presented to the user.

[0624] Step 8:

[0625] The terminal receives the evaluation results and additional information from the server and presents them to the user. The user can check the eco-level score and specific product information on the screen. The input is the response data from the server, and the output is the information displayed to the user.

[0626] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0627] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0628] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0629] [Third embodiment]

[0630] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0631] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0632] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0633] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0634] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0635] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0636] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0637] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0638] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0639] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0640] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0641] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0642] The present invention relates to a system for evaluating the environmental impact of a product by photographing the product using a device such as a smartphone or tablet. Specific embodiments will be described below.

[0643] When a user uses the system, they first launch the application, switch to camera mode, and take a picture of a product they are considering purchasing. The device temporarily saves the captured image data. The saved image data is then sent to the server. The device converts the image to JPEG format and uploads it to the server using an HTTP POST request.

[0644] The server analyzes the received image data and uses optical character recognition (OCR) technology to extract product label and ingredient information. The server first reads the image and uses an OCR library to extract text from the image. It then analyzes the extracted text data to identify keywords and ingredient information related to the product.

[0645] For example, if a user takes a photo of an organic food package, the server will extract keywords such as "certified organic" and "plastic-free."

[0646] The server then uses the extracted information to evaluate the product's environmental impact using a generative AI model, which operates on a pre-trained dataset, weights the extracted keywords, and scores the product's eco-level.

[0647] For example, the influence of each keyword is evaluated in the following way: "organic certified" will be given 10 eco points, and "plastic-free" will be given 10 eco points.

[0648] The server returns the calculated eco-level results to the terminal as an HTTP response. The terminal analyzes the received eco-level results and displays them to the user in an appropriate format. The user can check the evaluation results displayed on the screen and select environmentally friendly products.

[0649] For example, a message will appear on your smartphone screen saying, "This product is highly eco-friendly. It is certified organic and does not contain any plastic."

[0650] In this way, users can easily and quickly check the eco-level of a product via the application, enabling them to make more sustainable choices.

[0651] The processing flow will be explained below.

[0652] Step 1:

[0653] The user starts the application, switches to camera mode, and takes a picture of a product they are considering purchasing. The user then uses the device's camera to capture the product, and the image is temporarily saved in the application.

[0654] Step 2:

[0655] The device sends the stored image data to the server, where it is converted to JPEG format and uploaded to the server using an HTTP POST request. This transfers the image data to the server.

[0656] Step 3:

[0657] The server analyzes the received image data and uses optical character recognition (OCR) technology to extract product label and ingredient information. First, the server reads the stored image and uses an OCR library to extract text information from the image.

[0658] Step 4:

[0659] The server analyzes the extracted text data to identify keywords and ingredient information related to the product, identifying specific keywords and phrases such as "certified organic" or "plastic-free."

[0660] Step 5:

[0661] The server uses the extracted information to evaluate the product's environmental impact using a generative AI model, which weights each keyword based on a pre-trained dataset and scores the product's eco-level.

[0662] Step 6:

[0663] The server returns the calculated eco-level result to the device. The evaluation result is sent to the device as an HTTP response, and the device receives the data.

[0664] Step 7:

[0665] The device analyzes the received eco-level results and displays them in an appropriate format to the user, allowing the user to easily select environmentally friendly products.

[0666] Step 8:

[0667] Users can check the evaluation results displayed on the screen and select eco-friendly products. Based on this information, users can practice sustainable consumption behavior.

[0668] Example 1

[0669] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0670] In the past, assessing the environmental impact of a product required users to manually research product information and make judgments based on that data, which was time-consuming and labor-intensive. Furthermore, the criteria for assessing environmental impact were inconsistent, making reliable assessments difficult. The present invention aims to solve these problems by providing a system that allows users to easily and quickly check the environmental impact of a product and supports sustainable choices.

[0671] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0672] In this invention, the server includes means for inputting an image, means for analyzing the input image and extracting text information, means for identifying product-specific information based on the extracted text information, means for evaluating the environmental impact of each product based on the identified product information, means for presenting the evaluation results to a user, and means for using a generative AI model that weights the extracted keywords and scores the products. This enables a user to automatically evaluate the environmental impact based on photographed product images and obtain rapid and consistent evaluation results without having to manually research the information.

[0673] The "means for inputting an image" refers to a device or program that provides an interface for the user to photograph a product and can acquire the image data.

[0674] "Means for analyzing an input image and extracting text information" refers to techniques or devices that use image processing technology to identify and extract text information from an input image.

[0675] "Means for identifying product-specific information based on extracted character information" refers to technology or devices that use optical character recognition technology or data analysis algorithms to identify specific product information based on extracted character information.

[0676] The "means for assessing the environmental impact of each product based on identified product information" refers to an algorithm or program for assessing the environmental impact of a product based on information related to the product.

[0677] The "means for presenting the evaluation results to the user" refers to an interface or display device for displaying the environmental impact evaluation results in an easy-to-understand manner for the user.

[0678] "Means of using a generative AI model that weights extracted keywords and scores products" refers to technologies and programs that use an AI model to weight extracted keywords and score the environmental impact of products based on that weighting.

[0679] This invention is a system for evaluating the environmental impact of products by utilizing technologies such as an image input device, a server, and a generative AI model. Specific embodiments will be described below.

[0680] When a user uses the system, they first launch the application, switch to camera mode, and take a picture of a product they are considering purchasing. The device temporarily saves the captured image data, then converts it to JPEG format and uploads it to the server using an HTTP POST request. The hardware used for this includes mobile devices such as smartphones and tablets.

[0681] To analyze the image data received by the server, optical character recognition (OCR) technology is first used. The image is read and text information is extracted from the image using an OCR library. The extracted text data is then analyzed to identify keywords and ingredient information related to the product. The software used for this purpose includes various OCR engines and text analysis algorithms.

[0682] For example, when a user takes a photo of an organic food package, the server extracts keywords such as "certified organic" and "plastic-free." The server then uses a generative AI model to evaluate the product's environmental impact based on the extracted information. The AI ​​model operates based on a pre-trained dataset, weighting each keyword and scoring the product's eco-level. For example, the impact of each keyword is evaluated as follows: "certified organic" earns 10 eco points, and "plastic-free" earns 10 eco points.

[0683] The eco-level results calculated by the server are sent back to the terminal as an HTTP response. The terminal analyzes the received eco-level results and displays them to the user in an appropriate format. For example, a message might appear on a smartphone screen saying, "This product has a high eco-level. It is organically certified and does not contain plastic," allowing the user to select environmentally friendly products.

[0684] An example prompt for a generative AI model might look something like this:

[0685] "Information contained on the product label: 'Certified Organic', 'Plastic-free'. Please rate the eco-friendliness of the product."

[0686] In this way, users can easily and quickly check the eco-level of a product via the application and make more sustainable choices.

[0687] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0688] Step 1:

[0689] The user starts the application, switches to camera mode, and takes a photo of a product they are considering purchasing.

[0690] Specifically, the user taps the app to activate the camera function, points the camera at the product, and presses the shutter button.

[0691] Input: User-initiated camera activation and product photography

[0692] Output: Photographed product image data

[0693] Step 2:

[0694] The device temporarily saves the captured image data, converts it to JPEG format, and uploads the saved image data to the server using an HTTP POST request.

[0695] Specifically, the image is saved in a temporary folder on the device, converted to JPEG format using a conversion library, and sent to the server using an HTTP request library.

[0696] Input: Photographed product image data

[0697] Output: A request to upload JPEG image data to the server.

[0698] Step 3:

[0699] The server receives the HTTP POST request, retrieves the JPEG image data, and uses OCR technology to extract text information from the image.

[0700] Specifically, the server processes the request, performs OCR processing using an image analysis library, and reads the product label and ingredient information.

[0701] Input: JPEG format image data

[0702] Output: Extracted character information (text data)

[0703] Step 4:

[0704] The server analyzes the extracted text data and identifies keywords and ingredient information related to the product.

[0705] Specifically, it applies a text analysis algorithm to extract keywords such as "certified organic" and "plastic-free."

[0706] Input: Extracted character information (text data)

[0707] Output: Identified keywords and ingredient information

[0708] Step 5:

[0709] The server uses the generated AI model to weight the identified keywords and evaluate the environmental impact of the product.

[0710] Specifically, the system sends a prompt to the AI ​​model, calculates eco points for each keyword, and calculates an overall score.

[0711] Input: Identified keywords and ingredient information

[0712] Output: Product environmental impact score

[0713] Step 6:

[0714] The server returns the evaluation results to the terminal as an HTTP response.

[0715] Specifically, the evaluation results are packaged in JSON format and sent to the terminal as an HTTP response.

[0716] Input: Product environmental impact score

[0717] Output: HTTP response containing the environmental impact score

[0718] Step 7:

[0719] The terminal receives the HTTP response from the server, analyzes the evaluation results, and displays them to the user.

[0720] Specifically, it deserializes the response data and displays on the screen, "This product is highly eco-friendly. It is certified organic and does not contain plastic."

[0721] Input: HTTP response containing environmental impact score

[0722] Output: The evaluation result (text message) displayed to the user

[0723] Through the above steps, users can use the system to easily check the environmental impact of products.

[0724] (Application example 1)

[0725] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0726] Modern consumers often want to choose environmentally friendly products, but lack the means to quickly and easily evaluate their environmental impact. When shopping in a physical store, there is a demand for an immediate understanding of the environmental impact of products during the product selection process, but current technology makes it difficult to meet such needs.

[0727] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0728] In this invention, the server includes means for inputting an image, means for analyzing the input image and extracting text information, means for identifying product-specific information and environmental keywords based on the extracted text information, means for evaluating the environmental impact of each product using a generative AI model based on the identified information, and means for presenting the evaluation results to a user's terminal. This enables consumers to quickly and easily evaluate the environmental impact of products and make environmentally conscious choices when purchasing products in a physical store.

[0729] "Means for inputting images" refers to a mechanism that allows users to take photos of products using devices such as smartphones or tablets and import the image data into the system.

[0730] "Means for analyzing input images and extracting text information" refers to technology for identifying and extracting text from captured image data using optical character recognition (OCR) technology.

[0731] "Means for identifying product-specific information and environmental keywords based on extracted character information" refers to the process of analyzing text information extracted using OCR technology and identifying keywords related to specific product information and the environment.

[0732] "Means for assessing the environmental impact of each product using a generative AI model based on identified information" refers to a mechanism for inputting analyzed keyword information into a generative AI model and scoring the environmental impact of the product based on that model.

[0733] "Means for presenting the evaluation results on the user's device" refers to a function that responds to and visually displays the environmental impact score calculated by the generative AI model on the user's smartphone or tablet.

[0734] The present invention provides a system that allows consumers to easily understand the environmental impact of products in physical stores. Specific embodiments will be described below.

[0735] The system mainly consists of a device such as a smartphone or tablet and a server. The device is equipped with an image input means that allows the user to take a photo of a product they are considering purchasing. The user starts the application, switches to camera mode, and takes a photo of the product, which then acquires the image data.

[0736] The device converts the captured image data into JPEG format and then uploads it to the server using an HTTP POST request. The server first uses optical character recognition (OCR) technology to analyze the received image data. Specifically, it uses Tesseract OCR to extract text information from the image.

[0737] The server then analyzes the extracted text to identify keywords related to the product and environmental information. This process involves analyzing the input text and extracting environmental keywords such as "certified organic" and "plastic-free."

[0738] Based on the identified keywords, the server uses a generative AI model to evaluate the environmental impact of the product. The generative AI model operates based on a pre-trained dataset and weights the extracted keywords. The weighting of the keywords results in a score for the product's eco-level. This allows users to instantly understand the product's environmental impact.

[0739] The eco-level result calculated by the server is sent back to the user's device as an HTTP response, and the device visually displays the received eco-level result and provides it to the user.

[0740] Examples:

[0741] For example, consider the case where a user scans an organic food product at a supermarket. Using a smartphone app, the user scans the product packaging and sends the image data to a server. The server uses OCR to extract keywords such as "certified organic" and "plastic-free," and inputs these into a generative AI model to evaluate the environmental impact. The evaluation results are sent back to the device, which displays the message, "This product has a high eco-level. It is certified organic and plastic-free."

[0742] Example prompt sentence:

[0743] Input text: "Certified Organic Plastic Free"

[0744] Please carry out an Eco Level Assessment.

[0745] This embodiment allows users to make sustainable choices quickly and easily in physical stores.

[0746] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0747] Step 1:

[0748] (Input): The user activates the smartphone camera.

[0749] (Action): The user takes a photo of a product they are considering purchasing.

[0750] (Output): The captured product image is saved on the device.

[0751] Step 2:

[0752] (Input): Product image saved on the device.

[0753] (Operation): The device converts the product image to JPEG format and uploads it to the server using an HTTP POST request.

[0754] (Output): Product image data is sent to the server.

[0755] Step 3:

[0756] (Input): Product image data uploaded to the server.

[0757] (Operation): The server receives the image data and extracts the text information using optical character recognition (OCR) technology. Specifically, it uses Tesseract OCR to identify characters from the image.

[0758] (Output): Text information extracted from the image.

[0759] Step 4:

[0760] (Input): Text information extracted by OCR technology.

[0761] (Operation): The server analyzes the text information and identifies product-related and environment-related keywords.

[0762] (Output): Identified product information and environmental keyword list.

[0763] Step 5:

[0764] (Input): Identified product information and environmental keyword list.

[0765] (Operation): The server uses the generative AI model to evaluate and score the environmental impact of the product based on the input keyword information. For example, "certified organic" will receive a plus 10 points, and "plastic-free" will receive a plus 10 points.

[0766] (Output): Environmental impact score for each product.

[0767] Step 6:

[0768] (Input): Environmental impact score for each product.

[0769] (Operation): The server returns the calculated score to the user's device as an HTTP response.

[0770] (Output): The environmental impact score is sent to the user's device.

[0771] Step 7:

[0772] (Input): The environmental impact score sent to the user's device.

[0773] (Operation): The device analyzes the received score and displays it visually, for example, "This product has a high eco-level. It is certified organic and does not contain plastic."

[0774] (Output): Users can check the environmental impact of the product on the screen.

[0775] The specific processing flow is as follows:

[0776] The user takes a photo of a product (Step 1), and the device sends the image to the server (Step 2). The server uses OCR technology to extract text information from the image (Step 3) and analyzes the text information to identify environmental keywords (Step 4). The server then uses a generative AI model to evaluate the product's environmental impact (Step 5) and sends the results back to the user's device (Step 6). Finally, the user can visually confirm the environmental impact results on their device (Step 7).

[0777] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0778] This invention relates to a system that evaluates the environmental impact of products by taking photos of them using devices such as smartphones and tablets. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it supports the selection of eco-friendly products based on the user's emotional state.

[0779] When a user uses the system, they first launch the application, switch to camera mode, and take a picture of a product they are considering purchasing. The device temporarily saves the captured image data. The saved image data is then sent to the server. The device converts the image to JPEG format and uploads it to the server using an HTTP POST request.

[0780] The server analyzes the received image data and uses optical character recognition (OCR) technology to extract product label and ingredient information. The server first reads the image and uses an OCR library to extract text from the image. It then analyzes the extracted text data to identify keywords and ingredient information related to the product.

[0781] For example, if a user takes a photo of an organic food package, the server will extract keywords such as "certified organic" and "plastic-free."

[0782] The server then uses the extracted information to evaluate the product's environmental impact using a generative AI model, which weights each keyword based on a pre-trained dataset and scores the product's eco-level.

[0783] For example, the influence of each keyword is evaluated in the following way: "organic certified" will be given 10 eco points, and "plastic-free" will be given 10 eco points.

[0784] The server returns the calculated eco-level results to the terminal as an HTTP response. The terminal analyzes the received eco-level results and displays them to the user in an appropriate format. The user can check the evaluation results displayed on the screen and select environmentally friendly products.

[0785] The system also incorporates an emotion engine that recognizes the user's emotional state to optimize the user's experience in selecting eco-friendly products. The emotion engine analyzes the user's facial expressions and voice to determine whether they are relaxed, interested, or otherwise. Based on this information, the system displays eco-level results at the appropriate time or provides additional information to the user.

[0786] For example, if the emotion engine recognizes the user's interest while checking the eco-level, the system will provide detailed information such as, "This product is very environmentally friendly. It is certified organic and does not contain plastic."

[0787] In this way, users can easily and quickly check the eco-friendliness of products through the application, and with the support of the emotion engine, they can make better choices. This system aims not only to contribute to environmental issues, but also to improve users' shopping experience.

[0788] The processing flow will be explained below.

[0789] Step 1:

[0790] The user starts the application, switches to camera mode, and takes a picture of a product they are considering purchasing. The user then uses the device's camera to capture the product, and the image is temporarily saved in the application.

[0791] Step 2:

[0792] The device sends the stored image data to the server. The image data is converted to JPEG format and uploaded to the server using an HTTP POST request. This operation transfers the image data to the server.

[0793] Step 3:

[0794] The server analyzes the received image data and uses optical character recognition (OCR) technology to extract product label and ingredient information. The server first reads the image and uses an OCR library to extract text information from the image.

[0795] Step 4:

[0796] The server analyzes the extracted text data to identify keywords and ingredient information related to the product. This analysis identifies specific keywords such as "certified organic" or "plastic-free."

[0797] Step 5:

[0798] The server uses the extracted information to evaluate the product's environmental impact using a generative AI model, which weights each keyword based on a pre-trained dataset and scores the product's eco-level.

[0799] Step 6:

[0800] The server returns the calculated eco-level result to the device. The evaluation result is sent to the device as an HTTP response, and the device receives the data.

[0801] Step 7:

[0802] The device analyzes the received eco-level results and displays them in an appropriate format to the user, allowing the user to easily select environmentally friendly products.

[0803] Step 8:

[0804] Users can check the evaluation results displayed on the screen and select eco-friendly products. Based on this information, users can practice sustainable consumption behavior.

[0805] Step 9:

[0806] The emotion engine recognizes the user's emotions. Here, the device's camera and microphone are used to capture the user's facial expressions and voice, and the emotion engine analyzes this data to evaluate the user's emotional state.

[0807] Step 10:

[0808] The device uses the analysis results of the emotion engine to provide feedback according to the user's emotional state. For example, if the user is interested, detailed information is displayed, and if the user is relaxed, an encouraging message is displayed.

[0809] In this way, by combining the emotion engine, users can have a more personalized eco-product selection experience. This system allows users to easily select environmentally friendly products and enjoy a pleasant purchasing experience.

[0810] Example 2

[0811] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0812] Conventional systems only evaluate the environmental impact of products and are unable to consider the user's emotional state, making it difficult to provide information at the optimal time for the user. Furthermore, the analysis of captured images and presentation of evaluation results are insufficient, making it difficult to fully improve the user's shopping experience.

[0813] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0814] In this invention, the server includes means for inputting an image, means for analyzing the input image and extracting text information, means for identifying product-specific information based on the extracted text information, means for evaluating the environmental impact of each product based on the identified product information, means for presenting the evaluation results to the user, means for analyzing the emotional state of the user, and means for optimizing the presentation of the evaluation results based on the emotional state of the user. This makes it possible to provide the user with an accurate evaluation of the environmental impact and to provide information at an optimal timing tailored to the user's emotional state.

[0815] 1. "Means for inputting images" refers to a function that allows users to take product images using the camera on their smartphone or tablet and import that image data into the system.

[0816] 2. "Means for analyzing input images and extracting text information" refers to the process of identifying text information from captured images and extracting it as text data.

[0817] 3. "Means for identifying product-specific information based on extracted character information" refers to a function that identifies and identifies product characteristics and ingredient information from character information extracted using OCR technology, etc.

[0818] 4. "Means for assessing the environmental impact of each product based on identified product information" refers to a function that scores or assesses the environmental impact of a product using an AI model or other method in accordance with identified product information.

[0819] 5. "Means for presenting evaluation results to users" refers to a function for displaying the environmental impact of evaluated products and other related information in a user-friendly format.

[0820] 6. "Means for analyzing the user's emotional state" refers to a function that uses a camera or microphone to analyze the user's facial expressions and voice and evaluate their emotional state.

[0821] 7. "Means for optimizing the presentation of evaluation results based on the user's emotional state" refers to a function for providing evaluation results and additional information to the user at the optimal timing and in the optimal format based on the analyzed user's emotional state.

[0822] This invention relates to a system that evaluates the environmental impact of products by taking photos of them using devices such as smartphones and tablets. It also supports the selection of eco-friendly products based on the user's emotional state by combining it with an emotion engine that recognizes the user's emotions.

[0823] When a user uses this system, they first launch the application, switch to camera mode, and take a picture of a product they are considering purchasing. The device controls the smartphone's camera hardware and temporarily stores the captured image data. The image data is converted to JPEG format and sent to the server using an HTTP POST request. The server analyzes the image using the OpenCV library and extracts text information using the Tesseract OCR library.

[0824] Specifically, the server performs OCR processing to recognize keywords such as "certified organic" and "plastic-free" from the image. Next, product-specific information is identified based on the extracted text information, and this information is used to evaluate the environmental impact of each product using a generative AI model. The AI ​​model uses TensorFlow to weight each keyword based on a pre-trained dataset and generate a score for the eco-level. For example, "certified organic" is evaluated as +10 eco points, and "plastic-free" is evaluated as +10 eco points.

[0825] The server returns the evaluation results to the terminal as an HTTP response, and the terminal analyzes the received JSON format data and displays it to the user. The evaluation results are displayed in the user interface in easy-to-understand graphs and text format. For example, the user might see on the screen, "This product has an eco-point rating of 20. It is certified organic and uses no plastic, making it a very environmentally friendly product."

[0826] Furthermore, the system incorporates an emotion engine that uses the device's camera and microphone to capture the user's facial expressions and voice in real time and analyzes the user's emotional state. The server evaluates the user's emotional state based on this data and provides the evaluation results and additional information at the optimal time based on the user's emotional state. For example, when a user is checking the eco-level results, the emotion engine recognizes the user's interest and displays additional detailed information, such as, "This product is very environmentally friendly. It is certified organic and does not use plastic."

[0827] This system not only allows users to easily check the environmental impact of products, but also helps them make better choices with the support of an emotion engine, improving the user's shopping experience while also promoting contributions to environmental issues.

[0828] Prompt Sentence Examples

[0829] A user took a photo of an organic food package. We used OCR technology to extract the keywords "organic certified" and "plastic-free." Based on these keywords, you can evaluate the product's environmental impact.

[0830] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0831] Step 1:

[0832] Launching the application and switching to camera mode

[0833] The user starts an application on their smartphone or tablet and switches to camera mode.

[0834] Input: An application is started by a user action.

[0835] Output: The device switches to camera mode and displays the camera image.

[0836] Step 2:

[0837] Capture and save image data

[0838] The user takes a photo of a product they are considering purchasing, and the device temporarily saves the image data in JPEG format.

[0839] Input: User presses the capture button.

[0840] Output: Image data is saved in JPEG format on the device.

[0841] Step 3:

[0842] Sending image data

[0843] The device sends the stored image data to the server using an HTTP POST request.

[0844] Input: Image data in JPEG format.

[0845] Output: Image data is sent to the server via an HTTP POST request.

[0846] Step 4:

[0847] Receiving and analyzing image data

[0848] The server receives the image data sent via the HTTP POST request and begins analysis.

[0849] Input: Image data in JPEG format.

[0850] Output: Log information informing the start of image analysis.

[0851] Step 5:

[0852] Extracting text information

[0853] The server reads the image using the "OpenCV" library and extracts characters from the image using the "Tesseract" OCR library.

[0854] Input: Image data.

[0855] Output: Extracted character information (text format).

[0856] Step 6:

[0857] Identifying product information

[0858] The server analyzes the extracted text information and identifies keywords related to the product.

[0859] Input: Extracted text information.

[0860] Output: Identified keywords (e.g. "certified organic" or "plastic-free").

[0861] Step 7:

[0862] Environmental impact assessment

[0863] The server evaluates the environmental impact of a product using a generative AI model based on the identified keywords. The AI ​​model uses TensorFlow to weight each keyword based on a pre-trained dataset and score the product's eco-level.

[0864] Input: Identified keywords.

[0865] Output: Eco-level score (e.g. "Certified Organic: 10" or "Plastic-free: 10").

[0866] Step 8:

[0867] Sending evaluation results

[0868] The server returns the calculated environmental impact score to the terminal as an HTTP response.

[0869] Input: Eco-level score.

[0870] Output: JSON data sent to the device in the HTTP response.

[0871] Step 9:

[0872] Displaying the evaluation results

[0873] The device analyzes the received JSON data and displays the evaluation results to the user. Specifically, the evaluation results are displayed in an easy-to-understand graph or text format on the user interface.

[0874] Input: JSON data.

[0875] Output: The rating result shown to the user (e.g. "This product has 20 eco points. It is certified organic and plastic-free, making it a very environmentally friendly product.").

[0876] Step 10:

[0877] Emotional state analysis

[0878] The device's emotion engine uses the camera and microphone to analyze the user's facial expressions and voice and assess their emotional state.

[0879] Input: User's facial expression data, voice data.

[0880] Output: Evaluated emotional state (e.g., interested, relaxed, etc.).

[0881] Step 11:

[0882] Emotion-Based Optimization

[0883] The server optimizes the timing and content of information provided to the user based on the evaluated emotional state.

[0884] Input: Emotional state data.

[0885] Output: Display additional information optimized for the user (e.g. "This product is very environmentally friendly. It is certified organic and plastic-free.").

[0886] (Application example 2)

[0887] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0888] In recent years, growing environmental awareness among consumers has led to an increased demand for selecting environmentally friendly products. However, current systems have difficulty quickly and accurately providing consumers with the specific environmental impact of each product, and do not provide information that reflects the user's emotions or interests. This makes it difficult for consumers to obtain appropriate information when selecting products, and they are unable to efficiently select eco-friendly products. Furthermore, current systems are unable to recognize the user's emotional state and provide information based on their emotions, so improvements to the user experience are needed.

[0889] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0890] In this invention, the server includes means for inputting an image, means for analyzing the input image and extracting text information, means for identifying product-specific information based on the extracted text information, means for evaluating the environmental impact of each product based on the identified product information, means for recognizing the user's emotional state, means for providing additional information to the user at an optimal timing based on the evaluation results and the emotion analysis results, and means for presenting the evaluation results to the user. This enables consumers to quickly and accurately grasp the environmental impact of a product when selecting it, and also makes it possible to provide optimal information according to the user's emotional state.

[0891] An "image" is a digital representation of visual information.

[0892] "Input means" refers to a device or interface that allows a user to input image data into the system.

[0893] "Means for analyzing and extracting character information" refers to technology and devices for automatically identifying and recognizing characters and their meanings from image data.

[0894] "Means for identifying product-specific information" refers to a method or system for determining detailed information about the product based on the extracted text information.

[0895] "Means for assessing environmental impact" refers to a system for assessing and quantifying the impact of a product on the environment based on information specific to the identified product.

[0896] "Means for recognizing emotional states" refers to technologies and mechanisms that analyze and recognize a user's emotions and psychological state from their facial expressions, voice, and actions.

[0897] "Means for providing additional information at the most appropriate time" refers to a system or method that provides the information a user needs at the most appropriate time based on the user's emotional state and evaluation results.

[0898] "Optical character recognition technology" refers to technology that optically reads characters contained in image data and converts them into machine-readable character data.

[0899] "Artificial intelligence model" refers to an algorithm or system that is trained to analyze data and make predictions or decisions using techniques such as machine learning and deep learning.

[0900] An "emotion engine" is a system that analyzes a user's emotions and provides the most appropriate information and takes appropriate action based on the results.

[0901] A "generative AI model" refers to an artificial intelligence algorithm that is pre-trained on a large dataset to generate the required information.

[0902] This invention relates to a system in which a user photographs a product using a terminal, evaluates the product's environmental impact, and provides information based on the user's emotional state. The main components for implementing this invention are an image capturing unit, a text information analyzing unit, a product information identifying unit, an environmental impact evaluation unit, an emotional state recognition unit, an additional information providing unit, and an evaluation result presentation unit. These components are described in detail below.

[0903] The server uses the device's camera as a means of image input. When the user takes a photo of a product, the device converts the image data into JPEG format, temporarily stores it, and then uploads it to the server using an HTTP POST request.

[0904] The server uses an optical character recognition (OCR) library to analyze the received image data. Specifically, it extracts text information from the received image and uses that information to identify product-specific information. For this, it uses OCR tools such as OpenCV and Pytesseract.

[0905] The server then evaluates the product's environmental impact based on the identified product-specific information. This evaluation is performed using a pre-trained generative AI model. The AI ​​model weights the identified keywords and scores the product's eco-level. For example, it calculates eco-points based on keywords such as "certified organic" and "plastic-free."

[0906] The server uses an emotion engine to recognize the user's emotional state. The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and voice to determine whether the user is relaxed, interested, etc. For example, an emotion analysis tool such as Emotion Engine is used.

[0907] Based on the evaluation results and sentiment analysis results, the server has the means to provide additional information to the user at the optimal time. When the user is checking the eco-level, if the sentiment engine recognizes the user's interest, the system will provide detailed information (e.g., "This product is very environmentally friendly. It is certified organic and does not use plastic.").

[0908] The terminal displays the eco-level and detailed information received from the server to the user as a means of presenting the evaluation results to the user, allowing the user to quickly and accurately understand the environmental impact of a product when selecting it.

[0909] As a concrete example, suppose a user takes a photo of a cosmetic product package in a virtual store and uploads it to the system. The system extracts keywords such as "paraben-free" and "no animal testing" from the image and evaluates the product's eco-friendliness based on those keywords. If the emotion engine recognizes the user's interest while the user is selecting a product on the screen, the system will provide information such as, "This cosmetic product is environmentally friendly. It is paraben-free and has not been tested on animals."

[0910] Also, the following is an example of a prompt sentence for the generative AI model:

[0911] "Based on the product images uploaded by users, extract keywords related to eco-friendly and environmentally conscious products, such as 'certified organic' or 'plastic-free'. Also, assess the user's emotional state and provide information at the right time."

[0912] This is expected to make it easier for users to choose more eco-friendly products and improve their shopping experience.

[0913] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0914] Step 1:

[0915] The device takes a photo of the product for the user. The user takes a photo of the desired product using the device's camera and temporarily stores the image data on the device. The input is the captured image, and the output is the stored image data.

[0916] Step 2:

[0917] The device converts the captured image data into JPEG format and uploads it to the server using an HTTP POST request. The input is the saved image data, and the output is the image data sent to the server.

[0918] Step 3:

[0919] The server analyzes the received image data using optical character recognition (OCR). Specifically, it uses software such as OpenCV or Pytesseract to extract text information from the image. The input is the received image data, and the output is the extracted text information.

[0920] Step 4:

[0921] The server analyzes the extracted text information and identifies product-specific information. For example, it extracts product label information and ingredient information and uses that information to identify detailed product data. The input is the extracted text information, and the output is product-specific information.

[0922] Step 5:

[0923] The server uses a generative AI model to evaluate the environmental impact of a product based on the product-specific information it has identified. For example, it scores the eco-level based on keywords such as "certified organic" or "plastic-free." The input is the product-specific information, and the output is the eco-level score.

[0924] Step 6:

[0925] The device recognizes the user's emotional state. It uses the device's camera and microphone to analyze the user's facial expressions and voice to determine whether the user is relaxed, interested, etc. The system relies on analytical processing using an emotion engine. The input is the user's facial expressions and voice data, and the output is data on the user's emotional state.

[0926] Step 7:

[0927] The server provides additional information to the user at the optimal time based on the evaluation results and emotional state data. For example, if the user is interested, it can present detailed eco-friendly information about a product. The input is the eco-level score and emotional state data, and the output is the additional information presented to the user.

[0928] Step 8:

[0929] The terminal receives the evaluation results and additional information from the server and presents them to the user. The user can check the eco-level score and specific product information on the screen. The input is the response data from the server, and the output is the information displayed to the user.

[0930] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0931] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0932] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0933] [Fourth embodiment]

[0934] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0935] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0936] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0937] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0938] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0939] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0940] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0941] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0942] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0943] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0944] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0945] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0946] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0947] The present invention relates to a system for evaluating the environmental impact of a product by photographing the product using a device such as a smartphone or tablet. Specific embodiments will be described below.

[0948] When a user uses the system, they first launch the application, switch to camera mode, and take a picture of a product they are considering purchasing. The device temporarily saves the captured image data. The saved image data is then sent to the server. The device converts the image to JPEG format and uploads it to the server using an HTTP POST request.

[0949] The server analyzes the received image data and uses optical character recognition (OCR) technology to extract product label and ingredient information. The server first reads the image and uses an OCR library to extract text from the image. It then analyzes the extracted text data to identify keywords and ingredient information related to the product.

[0950] For example, if a user takes a photo of an organic food package, the server will extract keywords such as "certified organic" and "plastic-free."

[0951] The server then uses the extracted information to evaluate the product's environmental impact using a generative AI model, which operates on a pre-trained dataset, weights the extracted keywords, and scores the product's eco-level.

[0952] For example, the influence of each keyword is evaluated in the following way: "organic certified" will be given 10 eco points, and "plastic-free" will be given 10 eco points.

[0953] The server returns the calculated eco-level results to the terminal as an HTTP response. The terminal analyzes the received eco-level results and displays them to the user in an appropriate format. The user can check the evaluation results displayed on the screen and select environmentally friendly products.

[0954] For example, a message will appear on your smartphone screen saying, "This product is highly eco-friendly. It is certified organic and does not contain any plastic."

[0955] In this way, users can easily and quickly check the eco-level of a product via the application, enabling them to make more sustainable choices.

[0956] The processing flow will be explained below.

[0957] Step 1:

[0958] The user starts the application, switches to camera mode, and takes a picture of a product they are considering purchasing. The user then uses the device's camera to capture the product, and the image is temporarily saved in the application.

[0959] Step 2:

[0960] The device sends the stored image data to the server, where it is converted to JPEG format and uploaded to the server using an HTTP POST request. This transfers the image data to the server.

[0961] Step 3:

[0962] The server analyzes the received image data and uses optical character recognition (OCR) technology to extract product label and ingredient information. First, the server reads the stored image and uses an OCR library to extract text information from the image.

[0963] Step 4:

[0964] The server analyzes the extracted text data to identify keywords and ingredient information related to the product, identifying specific keywords and phrases such as "certified organic" or "plastic-free."

[0965] Step 5:

[0966] The server uses the extracted information to evaluate the product's environmental impact using a generative AI model, which weights each keyword based on a pre-trained dataset and scores the product's eco-level.

[0967] Step 6:

[0968] The server returns the calculated eco-level result to the device. The evaluation result is sent to the device as an HTTP response, and the device receives the data.

[0969] Step 7:

[0970] The device analyzes the received eco-level results and displays them in an appropriate format to the user, allowing the user to easily select environmentally friendly products.

[0971] Step 8:

[0972] Users can check the evaluation results displayed on the screen and select eco-friendly products. Based on this information, users can practice sustainable consumption behavior.

[0973] Example 1

[0974] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0975] In the past, assessing the environmental impact of a product required users to manually research product information and make judgments based on that data, which was time-consuming and labor-intensive. Furthermore, the criteria for assessing environmental impact were inconsistent, making reliable assessments difficult. The present invention aims to solve these problems by providing a system that allows users to easily and quickly check the environmental impact of a product and supports sustainable choices.

[0976] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0977] In this invention, the server includes means for inputting an image, means for analyzing the input image and extracting text information, means for identifying product-specific information based on the extracted text information, means for evaluating the environmental impact of each product based on the identified product information, means for presenting the evaluation results to a user, and means for using a generative AI model that weights the extracted keywords and scores the products. This enables a user to automatically evaluate the environmental impact based on photographed product images and obtain rapid and consistent evaluation results without having to manually research the information.

[0978] The "means for inputting an image" refers to a device or program that provides an interface for the user to photograph a product and can acquire the image data.

[0979] "Means for analyzing an input image and extracting text information" refers to techniques or devices that use image processing technology to identify and extract text information from an input image.

[0980] "Means for identifying product-specific information based on extracted character information" refers to technology or devices that use optical character recognition technology or data analysis algorithms to identify specific product information based on extracted character information.

[0981] The "means for assessing the environmental impact of each product based on identified product information" refers to an algorithm or program for assessing the environmental impact of a product based on information related to the product.

[0982] The "means for presenting the evaluation results to the user" refers to an interface or display device for displaying the environmental impact evaluation results in an easy-to-understand manner for the user.

[0983] "Means of using a generative AI model that weights extracted keywords and scores products" refers to technologies and programs that use an AI model to weight extracted keywords and score the environmental impact of products based on that weighting.

[0984] This invention is a system for evaluating the environmental impact of products by utilizing technologies such as an image input device, a server, and a generative AI model. Specific embodiments will be described below.

[0985] When a user uses the system, they first launch the application, switch to camera mode, and take a picture of a product they are considering purchasing. The device temporarily saves the captured image data, then converts it to JPEG format and uploads it to the server using an HTTP POST request. The hardware used for this includes mobile devices such as smartphones and tablets.

[0986] To analyze the image data received by the server, optical character recognition (OCR) technology is first used. The image is read and text information is extracted from the image using an OCR library. The extracted text data is then analyzed to identify keywords and ingredient information related to the product. The software used for this purpose includes various OCR engines and text analysis algorithms.

[0987] For example, when a user takes a photo of an organic food package, the server extracts keywords such as "certified organic" and "plastic-free." The server then uses a generative AI model to evaluate the product's environmental impact based on the extracted information. The AI ​​model operates based on a pre-trained dataset, weighting each keyword and scoring the product's eco-level. For example, the impact of each keyword is evaluated as follows: "certified organic" earns 10 eco points, and "plastic-free" earns 10 eco points.

[0988] The eco-level results calculated by the server are sent back to the terminal as an HTTP response. The terminal analyzes the received eco-level results and displays them to the user in an appropriate format. For example, a message might appear on a smartphone screen saying, "This product has a high eco-level. It is organically certified and does not contain plastic," allowing the user to select environmentally friendly products.

[0989] An example prompt for a generative AI model might look something like this:

[0990] "Information contained on the product label: 'Certified Organic', 'Plastic-free'. Please rate the eco-friendliness of the product."

[0991] In this way, users can easily and quickly check the eco-level of a product via the application and make more sustainable choices.

[0992] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0993] Step 1:

[0994] The user starts the application, switches to camera mode, and takes a photo of a product they are considering purchasing.

[0995] Specifically, the user taps the app to activate the camera function, points the camera at the product, and presses the shutter button.

[0996] Input: User-initiated camera activation and product photography

[0997] Output: Photographed product image data

[0998] Step 2:

[0999] The device temporarily saves the captured image data, converts it to JPEG format, and uploads the saved image data to the server using an HTTP POST request.

[1000] Specifically, the image is saved in a temporary folder on the device, converted to JPEG format using a conversion library, and sent to the server using an HTTP request library.

[1001] Input: Photographed product image data

[1002] Output: A request to upload JPEG image data to the server.

[1003] Step 3:

[1004] The server receives the HTTP POST request, retrieves the JPEG image data, and uses OCR technology to extract text information from the image.

[1005] Specifically, the server processes the request, performs OCR processing using an image analysis library, and reads the product label and ingredient information.

[1006] Input: JPEG format image data

[1007] Output: Extracted character information (text data)

[1008] Step 4:

[1009] The server analyzes the extracted text data and identifies keywords and ingredient information related to the product.

[1010] Specifically, it applies a text analysis algorithm to extract keywords such as "certified organic" and "plastic-free."

[1011] Input: Extracted character information (text data)

[1012] Output: Identified keywords and ingredient information

[1013] Step 5:

[1014] The server uses the generated AI model to weight the identified keywords and evaluate the environmental impact of the product.

[1015] Specifically, the system sends a prompt to the AI ​​model, calculates eco points for each keyword, and calculates an overall score.

[1016] Input: Identified keywords and ingredient information

[1017] Output: Product environmental impact score

[1018] Step 6:

[1019] The server returns the evaluation results to the terminal as an HTTP response.

[1020] Specifically, the evaluation results are packaged in JSON format and sent to the terminal as an HTTP response.

[1021] Input: Product environmental impact score

[1022] Output: HTTP response containing the environmental impact score

[1023] Step 7:

[1024] The terminal receives the HTTP response from the server, analyzes the evaluation results, and displays them to the user.

[1025] Specifically, it deserializes the response data and displays on the screen, "This product is highly eco-friendly. It is certified organic and does not contain plastic."

[1026] Input: HTTP response containing environmental impact score

[1027] Output: The evaluation result (text message) displayed to the user

[1028] Through the above steps, users can use the system to easily check the environmental impact of products.

[1029] (Application example 1)

[1030] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1031] Modern consumers often want to choose environmentally friendly products, but lack the means to quickly and easily evaluate their environmental impact. When shopping in a physical store, there is a demand for an immediate understanding of the environmental impact of products during the product selection process, but current technology makes it difficult to meet such needs.

[1032] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1033] In this invention, the server includes means for inputting an image, means for analyzing the input image and extracting text information, means for identifying product-specific information and environmental keywords based on the extracted text information, means for evaluating the environmental impact of each product using a generative AI model based on the identified information, and means for presenting the evaluation results to a user's terminal. This enables consumers to quickly and easily evaluate the environmental impact of products and make environmentally conscious choices when purchasing products in a physical store.

[1034] "Means for inputting images" refers to a mechanism that allows users to take photos of products using devices such as smartphones or tablets and import the image data into the system.

[1035] "Means for analyzing input images and extracting text information" refers to technology for identifying and extracting text from captured image data using optical character recognition (OCR) technology.

[1036] "Means for identifying product-specific information and environmental keywords based on extracted character information" refers to the process of analyzing text information extracted using OCR technology and identifying keywords related to specific product information and the environment.

[1037] "Means for assessing the environmental impact of each product using a generative AI model based on identified information" refers to a mechanism for inputting analyzed keyword information into a generative AI model and scoring the environmental impact of the product based on that model.

[1038] "Means for presenting the evaluation results on the user's device" refers to a function that responds to and visually displays the environmental impact score calculated by the generative AI model on the user's smartphone or tablet.

[1039] The present invention provides a system that allows consumers to easily understand the environmental impact of products in physical stores. Specific embodiments will be described below.

[1040] The system mainly consists of a device such as a smartphone or tablet and a server. The device is equipped with an image input means that allows the user to take a photo of a product they are considering purchasing. The user starts the application, switches to camera mode, and takes a photo of the product, which then acquires the image data.

[1041] The device converts the captured image data into JPEG format and then uploads it to the server using an HTTP POST request. The server first uses optical character recognition (OCR) technology to analyze the received image data. Specifically, it uses Tesseract OCR to extract text information from the image.

[1042] The server then analyzes the extracted text to identify keywords related to the product and environmental information. This process involves analyzing the input text and extracting environmental keywords such as "certified organic" and "plastic-free."

[1043] Based on the identified keywords, the server uses a generative AI model to evaluate the environmental impact of the product. The generative AI model operates based on a pre-trained dataset and weights the extracted keywords. The weighting of the keywords results in a score for the product's eco-level. This allows users to instantly understand the product's environmental impact.

[1044] The eco-level result calculated by the server is sent back to the user's device as an HTTP response, and the device visually displays the received eco-level result and provides it to the user.

[1045] Examples:

[1046] For example, consider the case where a user scans an organic food product at a supermarket. Using a smartphone app, the user scans the product packaging and sends the image data to a server. The server uses OCR to extract keywords such as "certified organic" and "plastic-free," and inputs these into a generative AI model to evaluate the environmental impact. The evaluation results are sent back to the device, which displays the message, "This product has a high eco-level. It is certified organic and plastic-free."

[1047] Example prompt sentence:

[1048] Input text: "Certified Organic Plastic Free"

[1049] Please carry out an Eco Level Assessment.

[1050] This embodiment allows users to make sustainable choices quickly and easily in physical stores.

[1051] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1052] Step 1:

[1053] (Input): The user activates the smartphone camera.

[1054] (Action): The user takes a photo of a product they are considering purchasing.

[1055] (Output): The captured product image is saved on the device.

[1056] Step 2:

[1057] (Input): Product image saved on the device.

[1058] (Operation): The device converts the product image to JPEG format and uploads it to the server using an HTTP POST request.

[1059] (Output): Product image data is sent to the server.

[1060] Step 3:

[1061] (Input): Product image data uploaded to the server.

[1062] (Operation): The server receives the image data and extracts the text information using optical character recognition (OCR) technology. Specifically, it uses Tesseract OCR to identify characters from the image.

[1063] (Output): Text information extracted from the image.

[1064] Step 4:

[1065] (Input): Text information extracted by OCR technology.

[1066] (Operation): The server analyzes the text information and identifies product-related and environment-related keywords.

[1067] (Output): Identified product information and environmental keyword list.

[1068] Step 5:

[1069] (Input): Identified product information and environmental keyword list.

[1070] (Operation): The server uses the generative AI model to evaluate and score the environmental impact of the product based on the input keyword information. For example, "certified organic" will receive a plus 10 points, and "plastic-free" will receive a plus 10 points.

[1071] (Output): Environmental impact score for each product.

[1072] Step 6:

[1073] (Input): Environmental impact score for each product.

[1074] (Operation): The server returns the calculated score to the user's device as an HTTP response.

[1075] (Output): The environmental impact score is sent to the user's device.

[1076] Step 7:

[1077] (Input): The environmental impact score sent to the user's device.

[1078] (Operation): The device analyzes the received score and displays it visually, for example, "This product has a high eco-level. It is certified organic and does not contain plastic."

[1079] (Output): Users can check the environmental impact of the product on the screen.

[1080] The specific processing flow is as follows:

[1081] The user takes a photo of a product (Step 1), and the device sends the image to the server (Step 2). The server uses OCR technology to extract text information from the image (Step 3) and analyzes the text information to identify environmental keywords (Step 4). The server then uses a generative AI model to evaluate the product's environmental impact (Step 5) and sends the results back to the user's device (Step 6). Finally, the user can visually confirm the environmental impact results on their device (Step 7).

[1082] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1083] This invention relates to a system that evaluates the environmental impact of products by taking photos of them using devices such as smartphones and tablets. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it supports the selection of eco-friendly products based on the user's emotional state.

[1084] When a user uses the system, they first launch the application, switch to camera mode, and take a picture of a product they are considering purchasing. The device temporarily saves the captured image data. The saved image data is then sent to the server. The device converts the image to JPEG format and uploads it to the server using an HTTP POST request.

[1085] The server analyzes the received image data and uses optical character recognition (OCR) technology to extract product label and ingredient information. The server first reads the image and uses an OCR library to extract text from the image. It then analyzes the extracted text data to identify keywords and ingredient information related to the product.

[1086] For example, if a user takes a photo of an organic food package, the server will extract keywords such as "certified organic" and "plastic-free."

[1087] The server then uses the extracted information to evaluate the product's environmental impact using a generative AI model, which weights each keyword based on a pre-trained dataset and scores the product's eco-level.

[1088] For example, the influence of each keyword is evaluated in the following way: "organic certified" will be given 10 eco points, and "plastic-free" will be given 10 eco points.

[1089] The server returns the calculated eco-level results to the terminal as an HTTP response. The terminal analyzes the received eco-level results and displays them to the user in an appropriate format. The user can check the evaluation results displayed on the screen and select environmentally friendly products.

[1090] The system also incorporates an emotion engine that recognizes the user's emotional state to optimize the user's experience in selecting eco-friendly products. The emotion engine analyzes the user's facial expressions and voice to determine whether they are relaxed, interested, or otherwise. Based on this information, the system displays eco-level results at the appropriate time or provides additional information to the user.

[1091] For example, if the emotion engine recognizes the user's interest while checking the eco-level, the system will provide detailed information such as, "This product is very environmentally friendly. It is certified organic and does not contain plastic."

[1092] In this way, users can easily and quickly check the eco-friendliness of products through the application, and with the support of the emotion engine, they can make better choices. This system aims not only to contribute to environmental issues, but also to improve users' shopping experience.

[1093] The processing flow will be explained below.

[1094] Step 1:

[1095] The user starts the application, switches to camera mode, and takes a picture of a product they are considering purchasing. The user then uses the device's camera to capture the product, and the image is temporarily saved in the application.

[1096] Step 2:

[1097] The device sends the stored image data to the server. The image data is converted to JPEG format and uploaded to the server using an HTTP POST request. This operation transfers the image data to the server.

[1098] Step 3:

[1099] The server analyzes the received image data and uses optical character recognition (OCR) technology to extract product label and ingredient information. The server first reads the image and uses an OCR library to extract text information from the image.

[1100] Step 4:

[1101] The server analyzes the extracted text data to identify keywords and ingredient information related to the product. This analysis identifies specific keywords such as "certified organic" or "plastic-free."

[1102] Step 5:

[1103] The server uses the extracted information to evaluate the product's environmental impact using a generative AI model, which weights each keyword based on a pre-trained dataset and scores the product's eco-level.

[1104] Step 6:

[1105] The server returns the calculated eco-level result to the device. The evaluation result is sent to the device as an HTTP response, and the device receives the data.

[1106] Step 7:

[1107] The device analyzes the received eco-level results and displays them in an appropriate format to the user, allowing the user to easily select environmentally friendly products.

[1108] Step 8:

[1109] Users can check the evaluation results displayed on the screen and select eco-friendly products. Based on this information, users can practice sustainable consumption behavior.

[1110] Step 9:

[1111] The emotion engine recognizes the user's emotions. Here, the device's camera and microphone are used to capture the user's facial expressions and voice, and the emotion engine analyzes this data to evaluate the user's emotional state.

[1112] Step 10:

[1113] The device uses the analysis results of the emotion engine to provide feedback according to the user's emotional state. For example, if the user is interested, detailed information is displayed, and if the user is relaxed, an encouraging message is displayed.

[1114] In this way, by combining the emotion engine, users can have a more personalized eco-product selection experience. This system allows users to easily select environmentally friendly products and enjoy a pleasant purchasing experience.

[1115] Example 2

[1116] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1117] Conventional systems only evaluate the environmental impact of products and are unable to consider the user's emotional state, making it difficult to provide information at the optimal time for the user. Furthermore, the analysis of captured images and presentation of evaluation results are insufficient, making it difficult to fully improve the user's shopping experience.

[1118] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1119] In this invention, the server includes means for inputting an image, means for analyzing the input image and extracting text information, means for identifying product-specific information based on the extracted text information, means for evaluating the environmental impact of each product based on the identified product information, means for presenting the evaluation results to the user, means for analyzing the emotional state of the user, and means for optimizing the presentation of the evaluation results based on the emotional state of the user. This makes it possible to provide the user with an accurate evaluation of the environmental impact and to provide information at an optimal timing tailored to the user's emotional state.

[1120] 1. "Means for inputting images" refers to a function that allows users to take product images using the camera on their smartphone or tablet and import that image data into the system.

[1121] 2. "Means for analyzing input images and extracting text information" refers to the process of identifying text information from captured images and extracting it as text data.

[1122] 3. "Means for identifying product-specific information based on extracted character information" refers to a function that identifies and identifies product characteristics and ingredient information from character information extracted using OCR technology, etc.

[1123] 4. "Means for assessing the environmental impact of each product based on identified product information" refers to a function that scores or assesses the environmental impact of a product using an AI model or other method in accordance with identified product information.

[1124] 5. "Means for presenting evaluation results to users" refers to a function for displaying the environmental impact of evaluated products and other related information in a user-friendly format.

[1125] 6. "Means for analyzing the user's emotional state" refers to a function that uses a camera or microphone to analyze the user's facial expressions and voice and evaluate their emotional state.

[1126] 7. "Means for optimizing the presentation of evaluation results based on the user's emotional state" refers to a function for providing evaluation results and additional information to the user at the optimal timing and in the optimal format based on the analyzed user's emotional state.

[1127] This invention relates to a system that evaluates the environmental impact of products by taking photos of them using devices such as smartphones and tablets. It also supports the selection of eco-friendly products based on the user's emotional state by combining it with an emotion engine that recognizes the user's emotions.

[1128] When a user uses this system, they first launch the application, switch to camera mode, and take a picture of a product they are considering purchasing. The device controls the smartphone's camera hardware and temporarily stores the captured image data. The image data is converted to JPEG format and sent to the server using an HTTP POST request. The server analyzes the image using the OpenCV library and extracts text information using the Tesseract OCR library.

[1129] Specifically, the server performs OCR processing to recognize keywords such as "certified organic" and "plastic-free" from the image. Next, product-specific information is identified based on the extracted text information, and this information is used to evaluate the environmental impact of each product using a generative AI model. The AI ​​model uses TensorFlow to weight each keyword based on a pre-trained dataset and generate a score for the eco-level. For example, "certified organic" is evaluated as +10 eco points, and "plastic-free" is evaluated as +10 eco points.

[1130] The server returns the evaluation results to the terminal as an HTTP response, and the terminal analyzes the received JSON format data and displays it to the user. The evaluation results are displayed in the user interface in easy-to-understand graphs and text format. For example, the user might see on the screen, "This product has an eco-point rating of 20. It is certified organic and uses no plastic, making it a very environmentally friendly product."

[1131] Furthermore, the system incorporates an emotion engine that uses the device's camera and microphone to capture the user's facial expressions and voice in real time and analyzes the user's emotional state. The server evaluates the user's emotional state based on this data and provides the evaluation results and additional information at the optimal time based on the user's emotional state. For example, when a user is checking the eco-level results, the emotion engine recognizes the user's interest and displays additional detailed information, such as, "This product is very environmentally friendly. It is certified organic and does not use plastic."

[1132] This system not only allows users to easily check the environmental impact of products, but also helps them make better choices with the support of an emotion engine, improving the user's shopping experience while also promoting contributions to environmental issues.

[1133] Prompt Sentence Examples

[1134] A user took a photo of an organic food package. We used OCR technology to extract the keywords "organic certified" and "plastic-free." Based on these keywords, you can evaluate the product's environmental impact.

[1135] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1136] Step 1:

[1137] Launching the application and switching to camera mode

[1138] The user starts an application on their smartphone or tablet and switches to camera mode.

[1139] Input: An application is started by a user action.

[1140] Output: The device switches to camera mode and displays the camera image.

[1141] Step 2:

[1142] Capture and save image data

[1143] The user takes a photo of a product they are considering purchasing, and the device temporarily saves the image data in JPEG format.

[1144] Input: User presses the capture button.

[1145] Output: Image data is saved in JPEG format on the device.

[1146] Step 3:

[1147] Sending image data

[1148] The device sends the stored image data to the server using an HTTP POST request.

[1149] Input: Image data in JPEG format.

[1150] Output: Image data is sent to the server via an HTTP POST request.

[1151] Step 4:

[1152] Receiving and analyzing image data

[1153] The server receives the image data sent via the HTTP POST request and begins analysis.

[1154] Input: Image data in JPEG format.

[1155] Output: Log information informing the start of image analysis.

[1156] Step 5:

[1157] Extracting text information

[1158] The server reads the image using the "OpenCV" library and extracts characters from the image using the "Tesseract" OCR library.

[1159] Input: Image data.

[1160] Output: Extracted character information (text format).

[1161] Step 6:

[1162] Identifying product information

[1163] The server analyzes the extracted text information and identifies keywords related to the product.

[1164] Input: Extracted text information.

[1165] Output: Identified keywords (e.g. "certified organic" or "plastic-free").

[1166] Step 7:

[1167] Environmental impact assessment

[1168] The server evaluates the environmental impact of a product using a generative AI model based on the identified keywords. The AI ​​model uses TensorFlow to weight each keyword based on a pre-trained dataset and score the product's eco-level.

[1169] Input: Identified keywords.

[1170] Output: Eco-level score (e.g. "Certified Organic: 10" or "Plastic-free: 10").

[1171] Step 8:

[1172] Sending evaluation results

[1173] The server returns the calculated environmental impact score to the terminal as an HTTP response.

[1174] Input: Eco-level score.

[1175] Output: JSON data sent to the device in the HTTP response.

[1176] Step 9:

[1177] Displaying the evaluation results

[1178] The device analyzes the received JSON data and displays the evaluation results to the user. Specifically, the evaluation results are displayed in an easy-to-understand graph or text format on the user interface.

[1179] Input: JSON data.

[1180] Output: The rating result shown to the user (e.g. "This product has 20 eco points. It is certified organic and plastic-free, making it a very environmentally friendly product.").

[1181] Step 10:

[1182] Emotional state analysis

[1183] The device's emotion engine uses the camera and microphone to analyze the user's facial expressions and voice and assess their emotional state.

[1184] Input: User's facial expression data, voice data.

[1185] Output: Evaluated emotional state (e.g., interested, relaxed, etc.).

[1186] Step 11:

[1187] Emotion-Based Optimization

[1188] The server optimizes the timing and content of information provided to the user based on the evaluated emotional state.

[1189] Input: Emotional state data.

[1190] Output: Display additional information optimized for the user (e.g. "This product is very environmentally friendly. It is certified organic and plastic-free.").

[1191] (Application example 2)

[1192] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1193] In recent years, growing environmental awareness among consumers has led to an increased demand for selecting environmentally friendly products. However, current systems have difficulty quickly and accurately providing consumers with the specific environmental impact of each product, and do not provide information that reflects the user's emotions or interests. This makes it difficult for consumers to obtain appropriate information when selecting products, and they are unable to efficiently select eco-friendly products. Furthermore, current systems are unable to recognize the user's emotional state and provide information based on their emotions, so improvements to the user experience are needed.

[1194] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1195] In this invention, the server includes means for inputting an image, means for analyzing the input image and extracting text information, means for identifying product-specific information based on the extracted text information, means for evaluating the environmental impact of each product based on the identified product information, means for recognizing the user's emotional state, means for providing additional information to the user at an optimal timing based on the evaluation results and the emotion analysis results, and means for presenting the evaluation results to the user. This enables consumers to quickly and accurately grasp the environmental impact of a product when selecting it, and also makes it possible to provide optimal information according to the user's emotional state.

[1196] An "image" is a digital representation of visual information.

[1197] "Input means" refers to a device or interface that allows a user to input image data into the system.

[1198] "Means for analyzing and extracting character information" refers to technology and devices for automatically identifying and recognizing characters and their meanings from image data.

[1199] "Means for identifying product-specific information" refers to a method or system for determining detailed information about the product based on the extracted text information.

[1200] "Means for assessing environmental impact" refers to a system for assessing and quantifying the impact of a product on the environment based on information specific to the identified product.

[1201] "Means for recognizing emotional states" refers to technologies and mechanisms that analyze and recognize a user's emotions and psychological state from their facial expressions, voice, and actions.

[1202] "Means for providing additional information at the most appropriate time" refers to a system or method that provides the information a user needs at the most appropriate time based on the user's emotional state and evaluation results.

[1203] "Optical character recognition technology" refers to technology that optically reads characters contained in image data and converts them into machine-readable character data.

[1204] "Artificial intelligence model" refers to an algorithm or system that is trained to analyze data and make predictions or decisions using techniques such as machine learning and deep learning.

[1205] An "emotion engine" is a system that analyzes a user's emotions and provides the most appropriate information and takes appropriate action based on the results.

[1206] A "generative AI model" refers to an artificial intelligence algorithm that is pre-trained on a large dataset to generate the required information.

[1207] This invention relates to a system in which a user photographs a product using a terminal, evaluates the product's environmental impact, and provides information based on the user's emotional state. The main components for implementing this invention are an image capturing unit, a text information analyzing unit, a product information identifying unit, an environmental impact evaluation unit, an emotional state recognition unit, an additional information providing unit, and an evaluation result presentation unit. These components are described in detail below.

[1208] The server uses the device's camera as a means of image input. When the user takes a photo of a product, the device converts the image data into JPEG format, temporarily stores it, and then uploads it to the server using an HTTP POST request.

[1209] The server uses an optical character recognition (OCR) library to analyze the received image data. Specifically, it extracts text information from the received image and uses that information to identify product-specific information. For this, it uses OCR tools such as OpenCV and Pytesseract.

[1210] The server then evaluates the product's environmental impact based on the identified product-specific information. This evaluation is performed using a pre-trained generative AI model. The AI ​​model weights the identified keywords and scores the product's eco-level. For example, it calculates eco-points based on keywords such as "certified organic" and "plastic-free."

[1211] The server uses an emotion engine to recognize the user's emotional state. The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and voice to determine whether the user is relaxed, interested, etc. For example, an emotion analysis tool such as Emotion Engine is used.

[1212] Based on the evaluation results and sentiment analysis results, the server has the means to provide additional information to the user at the optimal time. When the user is checking the eco-level, if the sentiment engine recognizes the user's interest, the system will provide detailed information (e.g., "This product is very environmentally friendly. It is certified organic and does not use plastic.").

[1213] The terminal displays the eco-level and detailed information received from the server to the user as a means of presenting the evaluation results to the user, allowing the user to quickly and accurately understand the environmental impact of a product when selecting it.

[1214] As a concrete example, suppose a user takes a photo of a cosmetic product package in a virtual store and uploads it to the system. The system extracts keywords such as "paraben-free" and "no animal testing" from the image and evaluates the product's eco-friendliness based on those keywords. If the emotion engine recognizes the user's interest while the user is selecting a product on the screen, the system will provide information such as, "This cosmetic product is environmentally friendly. It is paraben-free and has not been tested on animals."

[1215] Also, the following is an example of a prompt sentence for the generative AI model:

[1216] "Based on the product images uploaded by users, extract keywords related to eco-friendly and environmentally conscious products, such as 'certified organic' or 'plastic-free'. Also, assess the user's emotional state and provide information at the right time."

[1217] This is expected to make it easier for users to choose more eco-friendly products and improve their shopping experience.

[1218] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1219] Step 1:

[1220] The device takes a photo of the product for the user. The user takes a photo of the desired product using the device's camera and temporarily stores the image data on the device. The input is the captured image, and the output is the stored image data.

[1221] Step 2:

[1222] The device converts the captured image data into JPEG format and uploads it to the server using an HTTP POST request. The input is the saved image data, and the output is the image data sent to the server.

[1223] Step 3:

[1224] The server analyzes the received image data using optical character recognition (OCR). Specifically, it uses software such as OpenCV or Pytesseract to extract text information from the image. The input is the received image data, and the output is the extracted text information.

[1225] Step 4:

[1226] The server analyzes the extracted text information and identifies product-specific information. For example, it extracts product label information and ingredient information and uses that information to identify detailed product data. The input is the extracted text information, and the output is product-specific information.

[1227] Step 5:

[1228] The server uses a generative AI model to evaluate the environmental impact of a product based on the product-specific information it has identified. For example, it scores the eco-level based on keywords such as "certified organic" or "plastic-free." The input is the product-specific information, and the output is the eco-level score.

[1229] Step 6:

[1230] The device recognizes the user's emotional state. It uses the device's camera and microphone to analyze the user's facial expressions and voice to determine whether the user is relaxed, interested, etc. The system relies on analytical processing using an emotion engine. The input is the user's facial expressions and voice data, and the output is data on the user's emotional state.

[1231] Step 7:

[1232] The server provides additional information to the user at the optimal time based on the evaluation results and emotional state data. For example, if the user is interested, it can present detailed eco-friendly information about a product. The input is the eco-level score and emotional state data, and the output is the additional information presented to the user.

[1233] Step 8:

[1234] The terminal receives the evaluation results and additional information from the server and presents them to the user. The user can check the eco-level score and specific product information on the screen. The input is the response data from the server, and the output is the information displayed to the user.

[1235] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1236] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1237] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1238] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1239] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1240] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1241] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1242] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1243] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1244] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1245] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1246] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1247] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1248] 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.

[1249] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1250] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1251] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1252] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1253] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1254] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1255] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1256] The following is further disclosed regarding the above embodiment.

[1257] (Claim 1)

[1258] A means for inputting an image;

[1259] A means for analyzing an input image and extracting text information;

[1260] A means for identifying product-specific information based on the extracted character information;

[1261] A means for evaluating the environmental impact of each product based on the identified product information;

[1262] a means for presenting the evaluation results to the user;

[1263] A system including:

[1264] (Claim 2)

[1265] 10. The system of claim 1, further comprising means for analyzing the extracted textual information using optical character recognition techniques.

[1266] (Claim 3)

[1267] 2. The system according to claim 1, further comprising means for evaluating the environmental impact of each product using an artificial intelligence model.

[1268] "Example 1"

[1269] (Claim 1)

[1270] A means for inputting an image;

[1271] A means for analyzing an input image and extracting text information;

[1272] A means for identifying product-specific information based on the extracted character information;

[1273] A means for evaluating the environmental impact of each product based on the identified product information;

[1274] means for presenting the evaluation results to a user;

[1275] A method that uses a generative AI model to weight the extracted keywords and score the products.

[1276] A system including:

[1277] (Claim 2)

[1278] 10. The system of claim 1, further comprising means for analyzing the extracted textual information using optical character recognition techniques.

[1279] (Claim 3)

[1280] The system of claim 1, further comprising means for assessing the environmental impact of each product using a generative AI model.

[1281] "Application Example 1"

[1282] (Claim 1)

[1283] A means for inputting an image;

[1284] A means for analyzing an input image and extracting text information;

[1285] A means for identifying product-specific information and environmental keywords based on the extracted character information;

[1286] a means for assessing the environmental impact of each product using a generative AI model based on the identified information; and

[1287] A means for presenting the evaluation results to a user's terminal;

[1288] A system including:

[1289] (Claim 2)

[1290] 10. The system of claim 1, wherein the extracted text information and keywords are analyzed using optical character recognition technology.

[1291] (Claim 3)

[1292] The system according to claim 1, further comprising means for inputting a prompt statement into the generative AI model to evaluate the environmental impact of each product.

[1293] "Example 2: Combining Emotion Engines"

[1294] (Claim 1)

[1295] A means for inputting an image;

[1296] A means for analyzing an input image and extracting text information;

[1297] A means for identifying product-specific information based on the extracted character information;

[1298] A means for evaluating the environmental impact of each product based on the identified product information;

[1299] a means for presenting the evaluation results to the user;

[1300] a means for analyzing the emotional state of a user;

[1301] means for optimizing the presentation of the assessment results based on the emotional state of the user;

[1302] A system including:

[1303] (Claim 2)

[1304] 10. The system of claim 1, further comprising means for analyzing the extracted textual information using optical character recognition techniques.

[1305] (Claim 3)

[1306] The system of claim 1, further comprising means for assessing the environmental impact of each product using a generative AI model.

[1307] "Application example 2 when combining emotion engines"

[1308] (Claim 1)

[1309] A means for inputting an image;

[1310] A means for analyzing an input image and extracting text information;

[1311] A means for identifying product-specific information based on the extracted character information;

[1312] A means for evaluating the environmental impact of each product based on the identified product information;

[1313] a means for recognizing the emotional state of a user;

[1314] A means for providing additional information to users at optimal timing based on the evaluation results and sentiment analysis results;

[1315] a means for presenting the evaluation results to the user;

[1316] A system including:

[1317] (Claim 2)

[1318] 10. The system of claim 1, further comprising means for analyzing the extracted textual information using optical character recognition techniques.

[1319] (Claim 3)

[1320] 2. The system according to claim 1, further comprising means for evaluating the environmental impact of each product using an artificial intelligence model.

[1321] (Claim 4)

[1322] 10. The system of claim 1, further comprising an emotion engine that analyzes an emotional state of the user.

[1323] (Claim 5)

[1324] The system of claim 3, further comprising means for using the generative AI model when assessing environmental impact using the artificial intelligence model. [Explanation of symbols]

[1325] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for inputting an image; A means for analyzing an input image and extracting text information; A means for identifying product-specific information based on the extracted character information; A means for evaluating the environmental impact of each product based on the identified product information; a means for presenting the evaluation results to the user; A system including:

2. 10. The system of claim 1, further comprising means for analyzing the extracted textual information using optical character recognition techniques.

3. The system according to claim 1, further comprising means for evaluating the environmental impact of each product using an artificial intelligence model.

Images