System

Abstract

A system is provided.SOLUTION: A system, comprising: a data collection unit, a preprocessing unit, a data analysis unit, a data reporting unit, and an information sharing unit.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] As the impacts of climate change and human activities on ecosystems become more serious, there is a growing demand for rapid and accurate collection and analysis of environmental data. However, conventional environmental monitoring systems are slow in data collection and analysis and have limited accuracy, making real-time environmental monitoring difficult. Furthermore, environmental protection organizations and government agencies often lack the resources to obtain appropriate data, which causes delays and inefficiencies in ecosystem protection activities. The present invention aims to solve these problems and enable rapid and accurate collection, analysis, and reporting of environmental data. [Means for solving the problem]

[0005] The present invention is a system including a data collection means, a preprocessing means, a data analysis means, a data reporting means, and an information sharing means, characterized by collecting data in real time from multiple sensors. Specifically, the collected data is preprocessed by removing noise and normalizing the data, and then analyzed using machine learning algorithms and deep learning models. The analysis results are reported to environmental protection organizations and government agencies via dashboards and alert systems. Furthermore, this information is shared with the general public and educational institutions to raise environmental awareness and support education. In this way, the present invention quickly and efficiently supports ecosystem protection activities.

[0006] A "data collection means" is a device or system capable of acquiring environmental data in real time from multiple sensors and data sources.

[0007] The "preprocessing means" is a device or system that performs processing to remove noise and normalize the collected data to improve the accuracy of the analysis.

[0008] A "data analysis means" is a device or system that has the ability to use machine learning algorithms or deep learning models based on preprocessed data to interpret the meaning of the data and detect specific environmental patterns or anomalies.

[0009] "Data reporting means" refers to a device or system that has the function of visually displaying the analysis results and notifying relevant parties in the form of alerts or reports as necessary.

[0010] An "information sharing tool" is a device or system that has the function of providing a platform for environmental protection organizations, government agencies, the general public, educational institutions, etc. to access analysis results and environmental data and share information. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0012] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

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

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

[0017] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0019] [First embodiment]

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

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

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

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

[0024] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0032] The present invention is a system including a data collection means, a preprocessing means, a data analysis means, a data reporting means, and an information sharing means, and by collecting data in real time from multiple sensors, preprocessing, analyzing, reporting, and sharing this data, it is possible to quickly and accurately collect, analyze, and report environmental data. Below, the processing of a specific program for implementing the present invention is explained in natural language.

[0033] 1. Data Collection

[0034] The server collects data from cameras, audio sensors, weather data sources, etc. For example, it acquires image data of birds and animals from outdoor cameras, receives audio recordings from audio sensors, and obtains weather information from weather data APIs.

[0035] 2. Data Preprocessing

[0036] The server preprocesses the collected data, applying contrast correction and noise reduction filters to image data and noise reduction algorithms to audio data, as well as normalizing meteorological data and imputing missing values.

[0037] 3. Data Analysis

[0038] The server performs analysis based on the preprocessed data. For image data, it uses a deep learning object detection model to identify the type and number of animals, converts audio data into a spectrogram to extract features, and uses a machine learning model to identify whale species. It also detects abnormal weather patterns from weather data.

[0039] 4. Data reporting

[0040] The server reports the results of the analysis to environmental organizations and government agencies by visualizing the data on a dashboard and displaying it in graphs and maps. It also sends email alerts when certain conditions are detected. Monthly reports are also automatically generated and sent to relevant parties.

[0041] 5. Information Sharing

[0042] The server provides data to the general public and educational institutions through an information-sharing platform. Specifically, devices (PCs and smartphones) can access a web portal, view analysis results and reports, and download necessary data. Users can also use publicly available educational resources to learn about ecosystem conservation. They can also provide feedback and suggest improvements and new features to the system.

[0043] This system will support ecosystem conservation activities and enable the rapid and accurate collection, analysis, and reporting of environmental data. Furthermore, by sharing information with the general public and educational institutions, it will also contribute to raising environmental awareness and supporting education.

[0044] The processing flow will be explained below.

[0045] Step 1: Collect data

[0046] The server collects data from multiple cameras, audio sensors, and a weather database. Specifically, it periodically acquires data sent from each sensor and stores it in the database.

[0047] The server periodically acquires image data from a camera installed outdoors.

[0048] The server periodically acquires audio data from audio sensors installed in the ocean.

[0049] The server uses a weather data API to obtain real-time weather information.

[0050] Step 2: Preprocessing the data

[0051] The server pre-processes the collected data, which includes noise removal, data normalization, and outlier detection.

[0052] The server applies contrast enhancement and noise reduction filters to the collected image data.

[0053] The server applies a noise reduction algorithm to the acquired audio data to obtain clean audio data.

[0054] The server normalizes the weather data and imputes missing values ​​appropriately.

[0055] Step 3: Analyze the data

[0056] The server performs analysis based on the preprocessed data, using machine learning algorithms and deep learning models to analyze the data.

[0057] The server applies deep learning models to the image data to identify specific animal or plant species.

[0058] The server converts the audio data into a spectrogram and extracts features to identify the type and number of whales.

[0059] The server detects abnormal weather patterns from the weather data and evaluates their impact.

[0060] Step 4: Report the data

[0061] The server reports the analysis results to stakeholders, including dashboard displays, alert notifications, and report generation.

[0062] The server visualizes the analysis results on a dashboard and displays them in the form of maps and graphs.

[0063] The server sends email alerts based on certain conditions (e.g., when the presence of an endangered species is confirmed).

[0064] The server automatically generates periodic reports and sends them to the relevant parties by email.

[0065] Step 5: Share information

[0066] The server provides a platform for sharing information for the general public and educational institutions.

[0067] Devices (PCs or smartphones owned by the general public or educational institutions) access the AI ​​Eco-Monitor Network's web portal to view analysis results and reports.

[0068] The terminal can download the necessary data and obtain detailed information.

[0069] Users can learn about environmental protection by using educational resources made publicly available on the platform.

[0070] Users can provide feedback and suggest improvements and new features to the system.

[0071] Example 1

[0072] 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."

[0073] In conventional environmental data collection and analysis systems, the process from data collection to reporting was extremely slow and sometimes lacked accuracy. Furthermore, data sharing with the general public and educational institutions was limited, resulting in insufficient contribution to raising environmental awareness and supporting education. Furthermore, the lack of a feedback function made it difficult to propose system improvements or new functions.

[0074] 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.

[0075] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, a data reporting means, and an information sharing means. This allows data to be collected in real time from multiple sensors and the collected data to be subjected to noise removal and normalization. Furthermore, by including a feedback function for visualizing and reporting the analyzed data and for suggesting system improvements and new functions, this enables rapid and accurate data collection, analysis, and reporting, and contributes to raising environmental awareness and supporting education through information sharing with the general public and educational institutions.

[0076] A "data collection means" is a device or mechanism for collecting data in real time from multiple sensors.

[0077] A "preprocessing means" is a device or mechanism for removing noise and normalizing data from collected data.

[0078] A "data analysis means" is a device or mechanism that performs analysis on pre-processed data.

[0079] "Data reporting means" refers to a device or mechanism for visualizing and reporting analytical results to relevant parties and organizations.

[0080] An "information sharing tool" is a device or mechanism for providing analysis results and related information to the public and educational institutions.

[0081] "Denoising" is the process of removing unnecessary information or noise from data.

[0082] "Data normalization" is the process of scaling and standardizing data to reduce variability and make it consistent.

[0083] "Visualization" is the process of transforming data into something visible, such as a graph, chart, or map.

[0084] The "feedback function" is a mechanism for collecting opinions and requests from users and reflecting them in improving the system and developing new functions.

[0085] The present invention is a system that includes a data collection means, a preprocessing means, a data analysis means, a data reporting means, and an information sharing means. The system aims to quickly and accurately collect, analyze, and report environmental data, and to share this information with the general public and educational institutions. Specific embodiments for implementing the present invention are described below.

[0086] 1. Data Collection Methods

[0087] The server collects data in real time from multiple sensors, including cameras, audio sensors, and weather data sources. For example, it acquires image data of birds and animals from outdoor cameras, receives audio recordings from audio sensors, and obtains weather information from a weather data API.

[0088] 2. Pretreatment Methods

[0089] The server preprocesses the collected data. For image data, contrast correction and noise reduction filters are applied using OpenCV, and for audio data, noise reduction algorithms are applied using Audacity or Apache Commons Math. For weather data, the Pandas library is used to normalize and impute missing values.

[0090] 3. Data Analysis Methods

[0091] The server performs analysis based on the preprocessed data. It uses TensorFlow to perform object detection on image data using a deep learning model to identify the type and number of animals. It converts audio data into spectrograms and uses a machine learning model to identify whale species. It uses SciPy to detect abnormal weather patterns from weather data.

[0092] 4. Data reporting methods

[0093] The server reports the analysis results to environmental organizations and government agencies. It uses Dash and Plotly to visualize the data on a dashboard, displaying it in graphs and maps. It also uses an SMTP server to send alert emails when certain conditions are detected. Monthly reports are automatically generated using LaTeX and sent to relevant parties in PDF format.

[0094] 5. Information sharing method

[0095] Devices (PCs and smartphones) can access a web portal to view analysis results and reports and download necessary data. Specifically, users can access data through a web portal developed with Django and Flask. Users can also learn about ecosystem conservation using publicly available educational resources, provide feedback, and suggest system improvements and new features.

[0096] This system will support ecosystem conservation activities and enable the rapid and accurate collection, analysis, and reporting of environmental data. Furthermore, by sharing information with the general public and educational institutions, it will contribute to raising environmental awareness and supporting education.

[0097] Examples of prompt statements

[0098] "Consider a Python program that uses image data from field cameras and audio recordings from audio sensors to analyze the current state of an ecosystem."

[0099] "Detail the data processing and analysis procedures used to collect weather data and detect unusual weather patterns."

[0100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0101] Step 1:

[0102] Data collection

[0103] The server collects data from multiple sensors in real time.

[0104] Inputs: Signals from cameras, audio sensors, weather data sources, etc.

[0105] Data processing: saving image data from cameras, collecting audio data from audio sensors, and obtaining data from weather data APIs

[0106] Output: Collected image data, audio data, and meteorological data

[0107] Specific operations: The camera periodically takes still images and sends them to the server. The audio sensor records audio at specified intervals and uploads the data to the server. Weather information is obtained from the weather data source using an API and stored on the server.

[0108] Step 2:

[0109] Data Preprocessing

[0110] The server pre-processes the collected data.

[0111] Input: Collected image data, audio data, and meteorological data

[0112] Data processing: Apply contrast correction and noise reduction filters to image data, apply noise reduction algorithms to audio data, normalize weather data and fill missing values

[0113] Output: Preprocessed image data, audio data, and weather data

[0114] What it does: It uses OpenCV to correct image contrast and a Gaussian filter to remove noise. For audio data, it uses signal processing tools to reduce background noise and make the audio clearer. For weather data, it normalizes the data frame and fills in missing values.

[0115] Step 3:

[0116] Data analysis

[0117] The server performs analysis based on the preprocessed data.

[0118] Input: Preprocessed image data, audio data, and meteorological data

[0119] Data processing: object detection from image data, feature extraction from audio data, and abnormal weather pattern detection from meteorological data

[0120] Output: Analysis results (species and numbers of animals, whale species, details of abnormal weather)

[0121] What it does: (TensorFlow) Uses deep learning models to detect and classify animals in images; converts audio data into spectrograms to extract features and uses machine learning models to estimate whale species; analyzes weather data for unusual weather patterns and detects anomalies.

[0122] Step 4:

[0123] Data reporting

[0124] The server reports the analysis results to the relevant organizations.

[0125] Input: Analysis results

[0126] Data manipulation: Visualize on dashboards, display in graphs and maps, send alerts, automatically generate reports

[0127] Output: Visualized data, alert emails, monthly reports (PDF format)

[0128] Specific tasks: Use Dash and Plotly to display analysis results in graphs and maps and create a dashboard that can be viewed by stakeholders. Use an SMTP server to send alert emails when certain conditions are met. Automatically generate monthly reports using LaTeX and send them to stakeholders in PDF format.

[0129] Step 5:

[0130] Information Sharing

[0131] The device allows the analysis results to be viewed through a web portal.

[0132] Input: Analysis results, reports, educational resources

[0133] Data processing: building a web portal, providing data, receiving feedback

[0134] Output: Displaying analysis results, downloading required data, and collecting feedback

[0135] What it does: Build a web portal using Django and Flask to allow users to easily view analysis results and reports. Users can use educational resources to learn more about ecosystem conservation and submit suggestions for improvements and requests for new features to the system through a feedback form.

[0136] This will improve the efficiency and accuracy of the entire system and enable a consistent flow of environmental data collection, analysis, reporting, and information sharing.

[0137] (Application example 1)

[0138] 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."

[0139] In conventional logistics systems, the collection, pre-processing, analysis, and reporting of data from each sensor were not integrated, resulting in inefficient inventory management, temperature monitoring, and weight analysis. This resulted in delayed detection of inventory shortages and abnormal weather, hindering operational efficiency.

[0140] 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.

[0141] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, a data reporting means, an information sharing means, an inventory management means, a temperature monitoring means, a weight analysis means, and an image processing means. This enables real-time monitoring of inventory and anomaly detection at the logistics center, enabling efficient business operations. In addition, the collected data is noise-removed and normalized to obtain highly reliable analysis results, enabling prompt and accurate information provision to managers and related parties.

[0142] "Data collection means" refers to a means for collecting necessary data in real time from multiple sensors.

[0143] "Preprocessing means" refers to means for removing noise and normalizing data in order to prepare collected data in a form that is easier to analyze.

[0144] "Data analysis means" refers to means for performing analysis according to a specific purpose based on preprocessed data.

[0145] "Data reporting means" refers to the means for reporting analysis results to users and related organizations.

[0146] "Information sharing means" refers to the means for sharing analysis results and related data among stakeholders.

[0147] The "inventory management means" is a means for monitoring the inventory status at the logistics center in real time and detecting abnormalities.

[0148] "Temperature monitoring means" refers to a means for monitoring the temperature of the storage environment in real time and maintaining appropriate storage conditions.

[0149] The "weight analysis means" is a means for analyzing the weight data of each product and performing appropriate inventory management.

[0150] The "image processing means" is a means for preprocessing image data acquired from a camera and extracting necessary information.

[0151] This invention is a system for improving the efficiency of inventory management in a logistics center. The server collects data in real time from multiple sensors and includes various means for preprocessing, analyzing, reporting, and sharing information. Specifically, this system is configured as follows:

[0152] Data collection

[0153] The server collects data from weight sensors, temperature sensors, cameras, etc. The data collected includes weight data for incoming and outgoing products, temperature data for storage areas, and image data for products. This allows for a real-time understanding of all movements within the logistics center. Product location information can also be obtained using RFID tags and barcode scanners.

[0154] Data Preprocessing

[0155] The server performs noise reduction and normalization on the collected data. For example, weight data is normalized, and temperature data is also normalized. Contrast correction and noise reduction filters are applied to the image data. This allows for faster and more accurate data analysis later.

[0156] Data analysis

[0157] The server detects inventory anomalies based on the pre-processed data. A deep learning algorithm using a generative AI model is applied for analysis, identifying products from image data. Temperature data is used to detect abnormalities in the storage environment, and appropriate countermeasures are implemented. Weight data is analyzed for abnormal fluctuations, preventing shortages and overstocks.

[0158] Data reporting

[0159] The server reports the analysis results to administrators and business personnel by visualizing real-time data on a dashboard, sending alert emails, and automatically generating monthly reports, allowing relevant parties to take action based on prompt and accurate information.

[0160] Information Sharing

[0161] The server shares analysis results and related data with relevant parties through an information-sharing platform. For example, administrators and business personnel can check information in real time through a web portal. Users can also use the system's feedback function to suggest improvements and new functions.

[0162] Specific examples

[0163] For example, in an inventory management system, the server could instruct a generative AI model using the following prompt sentence:

[0164] "I'm thinking of designing an application that will collect data using weight sensors, temperature sensors, and cameras, and then preprocess, analyze, report, and share the information in order to improve the efficiency of inventory management at distribution centers. I'd like to make this available on smartphones, so please write a specific program for me."

[0165] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0166] Step 1:

[0167] The server collects data in real time from weight sensors, temperature sensors, and cameras. Product weight data is input from the weight sensor, storage area temperature data from the temperature sensor, and product image data from the camera. This allows environmental information within the logistics center to be collected in one place.

[0168] Step 2:

[0169] The server preprocesses the collected data. Specifically, it removes noise and normalizes the weight and temperature data, and applies contrast correction and a noise removal filter to the image data. This preprocessing improves the reliability of the data and increases the accuracy of the analysis. The input is the raw weight data, temperature data, and image data, and the output is the preprocessed data.

[0170] Step 3:

[0171] The server performs data analysis based on the preprocessed data. It applies a deep learning algorithm using a generative AI model to process the image data to identify products. It also detects abnormalities in the storage environment from temperature data and analyzes inventory abnormalities from weight data. This allows for real-time detection of inventory abnormalities. The input is the preprocessed data, and the output is the analysis results.

[0172] Step 4:

[0173] The server reports data based on the analysis results. It updates the dashboard and visualizes inventory status in real time. It also sends alert emails to relevant parties when certain conditions occur and automatically generates and sends monthly reports. This allows relevant parties to quickly obtain the information they need. The input is the data analysis results, and the output is visualized data and reports.

[0174] Step 5:

[0175] The server shares data with relevant parties through an information-sharing platform. Managers and business personnel can access a web portal and check information in real time. The system also has a function that allows users to provide feedback, collecting requests for system improvements and suggestions for new functions. This enables continuous improvement of the system. The inputs are analysis results and feedback, and the outputs are shared information and improvement suggestions.

[0176] 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.

[0177] The present invention includes a system including a data collection means, a preprocessing means, a data analysis means, a data reporting means, and an information sharing means, as well as an emotion engine that can recognize a user's emotion and adjust the information provided based on that emotion. Below, the processing of a specific program for implementing the present invention will be described in natural language.

[0178] 1. Data Collection

[0179] The server collects data from multiple cameras, audio sensors, and a weather database, for example, capturing bird and animal image data from outdoor cameras, receiving audio recordings from audio sensors, and retrieving weather information from a weather data API.

[0180] 2. Data Preprocessing

[0181] The server pre-processes the collected data, which includes noise removal, data normalization, and outlier detection.

[0182] The server applies contrast enhancement and noise reduction filters to the collected image data.

[0183] The server applies a noise reduction algorithm to the acquired audio data to obtain clean audio data.

[0184] The server normalizes the weather data and imputes missing values ​​appropriately.

[0185] 3. Data Analysis

[0186] The server performs analysis based on the preprocessed data, using machine learning algorithms and deep learning models to analyze the data.

[0187] The server applies deep learning models to the image data to identify specific animal or plant species.

[0188] The server converts the audio data into a spectrogram and extracts features to identify the type and number of whales.

[0189] The server detects abnormal weather patterns from the weather data and evaluates their impact.

[0190] 4. Analysis by Emotion Engine

[0191] The server recognizes the user's emotions using an emotion engine, which analyzes the user's usage patterns, input data, and real-time sensor information to identify emotions.

[0192] The server may, for example, utilize facial recognition software or voice tone analysis tools to identify the user's emotional state (happiness, anxiety, surprise, etc.).

[0193] 5. Data reporting and personalization of information

[0194] The server reports the analysis results to stakeholders, including dashboard displays, alert notifications, and report generation.

[0195] The server visualizes the analysis results on a dashboard, displaying them in the form of maps and graphs, and also sends email alerts based on specific conditions (e.g., if an endangered species is detected).

[0196] The server automatically generates periodic reports and sends them to the relevant parties by email.

[0197] Based on the analysis results of the emotion engine, the server adjusts the information provided to suit the user's emotional state and provides optimal content.

[0198] 6. Information sharing

[0199] The server provides a platform for sharing information for the general public and educational institutions.

[0200] Devices (PCs or smartphones owned by the general public or educational institutions) access the AI ​​Eco-Monitor Network's web portal to view analysis results and reports.

[0201] The terminal can download the necessary data and obtain detailed information.

[0202] Users can learn about environmental protection through educational resources published on the platform, and the content is personalized based on the user's emotional state.

[0203] Users can provide feedback and suggest improvements and new features to the system.

[0204] By combining this system with an emotion engine, it is possible to provide personalized information tailored to the user's emotional state, making a significant contribution to raising environmental awareness and supporting education.

[0205] The processing flow will be explained below.

[0206] Step 1: Collect data

[0207] The server collects data from multiple cameras, audio sensors, and a weather database. Specifically, it periodically acquires data sent from each sensor and stores it in the database.

[0208] The server periodically acquires image data from a camera installed outdoors.

[0209] The server periodically acquires audio data from audio sensors installed in the ocean.

[0210] The server uses a weather data API to obtain real-time weather information.

[0211] Step 2: Preprocessing the data

[0212] The server pre-processes the collected data, which includes noise removal, data normalization, and outlier detection.

[0213] The server applies contrast enhancement and noise reduction filters to the collected image data.

[0214] The server applies a noise reduction algorithm to the acquired audio data to obtain clean audio data.

[0215] The server normalizes the weather data and imputes missing values ​​appropriately.

[0216] Step 3: Analyze the data

[0217] The server performs analysis based on the preprocessed data, using machine learning algorithms and deep learning models to analyze the data.

[0218] The server applies deep learning models to the image data to identify specific animal or plant species.

[0219] The server converts the audio data into a spectrogram and extracts features to identify the type and number of whales.

[0220] The server detects abnormal weather patterns from the weather data and evaluates their impact.

[0221] Step 4: Analysis by Emotion Engine

[0222] The server recognizes the user's emotions using an emotion engine, which analyzes the user's usage patterns, input data, and real-time sensor information to identify emotions.

[0223] The server collects, for example, camera data to recognize the user's face and audio data to analyze the user's voice.

[0224] The server uses facial recognition software to analyze facial expressions and determine whether the user is happy or sad.

[0225] The server analyzes the tone of the voice using a voice tone analysis tool to determine whether the user is excited or relaxed.

[0226] Step 5: Reporting data and personalizing information

[0227] The server reports the results of the analysis to stakeholders, including dashboard displays, alert notifications, and report generation, and also tailors the information provided to the user's emotional state based on the analysis results of the emotion engine.

[0228] The server visualizes the analysis results on a dashboard and displays them in the form of maps and graphs.

[0229] The server sends email alerts based on certain conditions (e.g., when the presence of an endangered species is confirmed).

[0230] The server automatically generates periodic reports and sends them to the relevant parties by email.

[0231] The server personalizes educational content or environmental information based on the user's emotional state: for example, if the user is excited, it will show simple infographics rather than detailed technical information.

[0232] Step 6: Information sharing

[0233] The server provides a platform for sharing information for the general public and educational institutions.

[0234] Devices (PCs or smartphones owned by the general public or educational institutions) access the AI ​​Eco-Monitor Network's web portal to view analysis results and reports.

[0235] The terminal can download the necessary data and obtain detailed information.

[0236] Users can learn about environmental protection through educational resources published on the platform, and the content is personalized based on the user's emotional state.

[0237] Users can provide feedback and suggest improvements and new features to the system.

[0238] Example 2

[0239] 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."

[0240] Conventional data collection and analysis systems provide information without considering the user's emotional state. This creates a gap between the content users want and the information they receive, resulting in problems such as insufficient environmental awareness and educational support. Furthermore, the quality and reliability of the collected data are often insufficient.

[0241] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, a sentiment analysis means, a data reporting means, and an information provision means. This makes it possible to provide information tailored to the emotional state of the user, which greatly contributes to improving environmental awareness and supporting education. Furthermore, by improving the quality and reliability of the data, more accurate analysis results can be obtained.

[0242] A "data collection means" is a combination of hardware and software for collecting necessary information in real time from multiple sensors and databases.

[0243] "Preprocessing means" is a function that performs processes such as noise removal, data normalization, and outlier detection on collected data to improve the quality of analysis.

[0244] A "data analysis tool" is a system that analyzes data using machine learning algorithms or deep learning models based on pre-processed data to identify specific patterns or features.

[0245] The "emotion analysis means" is a system for identifying the user's emotional state through facial recognition, voice tone analysis, etc., and adjusting the information provided based on that.

[0246] "Data reporting means" is a function for providing information by means of dashboard display, alert notification, report generation, etc. in order to report the results of data analysis to relevant parties.

[0247] "Information provision means" refers to a platform for providing analysis results and related information to the general public and educational institutions, making them accessible.

[0248] The present invention provides a system including a data collection means, a pre-processing means, a data analysis means, a sentiment analysis means, a data reporting means, and an information providing means, the system being capable of recognizing a user's sentiment state and adjusting the information provided based on the sentiment state.

[0249] Data collection

[0250] The server collects data from multiple cameras, audio sensors, and a weather database. For example, it uses outdoor cameras to capture image data of birds and animals, audio sensors to receive recorded calls and environmental sounds, and weather data APIs to obtain the latest weather information.

[0251] Pretreatment

[0252] The server preprocesses the collected data, which includes applying contrast correction and noise reduction filters to image data using the OpenCV library, denoising audio data using the Librosa library, normalizing meteorological data, and imputing missing data.

[0253] Data analysis

[0254] The server then applies machine learning algorithms and deep learning models to the preprocessed data and analyzes it. For example, a deep learning model trained with TensorFlow or PyTorch can be applied to image data to identify specific plant or animal species. Audio data can be converted into spectrograms to extract the features needed to identify whale species and numbers. Weather data can be used to detect abnormal weather patterns and assess their impact.

[0255] Emotion analysis

[0256] The server recognizes the user's emotions using an emotion engine that uses facial recognition software and voice analysis tools to perform real-time facial recognition and voice tone analysis of the user and identify the user's emotional state (e.g., joy, anxiety, surprise).

[0257] Data reporting and information provision

[0258] The server reports the analysis results to relevant parties. The analysis results are visualized on a dashboard and displayed in the form of maps and graphs. If certain conditions are met, an alert email is sent. In addition, based on the results of the emotion analysis, the information provided is adjusted to match the user's emotional state, providing optimal content.

[0259] Information sharing

[0260] The server provides a platform for sharing information with the general public and educational institutions. Devices (PCs and smartphones of the general public and educational institutions) can access the web portal to view analysis results and reports. They can also download necessary data and obtain detailed information. Users can use publicly available educational resources to learn about environmental protection. Personalized content is also provided based on the user's emotional state. A feedback function allows users to suggest improvements to the system and new functions.

[0261] Examples and prompts:

[0262] When a user inputs a prompt such as "Tell me the types of birds you have observed in the mountains," the server first processes the data obtained from the camera and audio sensors. Then, based on the preprocessed image data, it applies a deep learning model to identify the bird species. The analysis results are then visualized on a dashboard for the user to access. Finally, it uses sentiment analysis to recognize that the user is excited, and provides detailed information and additional observation points according to that excitement. Specifically, the following prompt is used:

[0263] Prompt: "What types of birds have you seen in the mountains?"

[0264] By working in conjunction with an emotion engine, this system provides personalized information tailored to the user's emotional state, making a significant contribution to improving environmental awareness and supporting education.

[0265] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0266] Step 1: Data collection

[0267] The server collects data from multiple cameras, audio sensors, and a weather database. Input data includes image data, audio data, and weather information. Specifically, it uses cameras installed outdoors to obtain image data of birds and animals, and audio sensors to receive recorded calls and environmental sounds. It also uses a weather data API to obtain the latest weather information. As output, this data is aggregated on the server.

[0268] Step 2: Preprocessing the data

[0269] The server preprocesses the collected data. The input data are the image data, audio data, and weather information collected in step 1. Specific operations include contrast correction and noise reduction filter application to the image data using the OpenCV library, noise reduction to the audio data using the Librosa library, normalization of the weather data, and completion of missing data. The output is preprocessed image data, audio data, and normalized weather data.

[0270] Step 3: Data analysis

[0271] The server analyzes the preprocessed data by applying machine learning algorithms and deep learning models. The input data is the image data, audio data, and weather information preprocessed in step 2. Specifically, a deep learning model trained using TensorFlow or PyTorch is applied to the image data to identify specific types of plants and animals. The audio data is converted into a spectrogram, and the features needed to identify the type and number of whales are extracted. The weather data is used to detect abnormal weather patterns and evaluate their impact. The analysis results are obtained as output.

[0272] Step 4: Sentiment Analysis

[0273] The server uses an emotion engine to recognize the user's emotions. The input data is the user's real-time facial recognition data and voice data. Specifically, it uses facial recognition software and voice tone analysis tools to identify the user's emotional state (e.g., joy, anxiety, surprise) from their facial expressions and voice tone. The output is the user's emotional state.

[0274] Step 5: Data reporting and information provision

[0275] The server reports the analysis results to the relevant parties. The input data are the analysis results from step 3 and the sentiment analysis results from step 4. Specific operations include visualizing the analysis results on a dashboard and displaying them in the form of maps and graphs. Additionally, an alert email is sent when certain conditions are met. The visualized analysis results and the sent alert are obtained as outputs.

[0276] Step 6: Information sharing

[0277] Terminals (PCs or smartphones of the general public or educational institutions) access the platform provided by the server to view analysis results and reports. The input data are the analysis results visualized in step 5. Users can download the necessary data from the web portal and obtain more detailed information. They can also use publicly available educational resources to learn about environmental protection. They can also suggest improvements to the system or new functions through the feedback function. The output includes the data used, educational resources, and submitted feedback.

[0278] An example of a specific prompt: "Tell me what kinds of birds you saw in the mountains."

[0279] In this way, this system has a consistent process from data collection to analysis and provision of information based on the user's emotional state, thereby providing advanced information tailored to the user's needs.

[0280] (Application example 2)

[0281] 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."

[0282] Conventional systems have had difficulty providing information according to a user's emotions, making it difficult to realize personalized services. This has prevented users from improving their satisfaction and engagement. The present invention aims to solve these problems by providing a system that recognizes a user's emotions and adjusts the information provided based on those emotions.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, a means for analyzing a user's emotions using an emotion engine, a means for adjusting information to be provided based on the emotion analysis, a data reporting means, and an information sharing means. This makes it possible to provide personalized information according to the user's emotional state.

[0284] "Data collection means" refers to a device or method for collecting data in real time from multiple sensors.

[0285] "Preprocessing means" refers to devices or methods that normalize collected data, remove noise, and otherwise prepare the data in a form that is easier to analyze.

[0286] "Data analysis means" refers to devices or methods that use machine learning algorithms or deep learning models to analyze data and extract useful information.

[0287] "Means for analyzing a user's emotions using an emotion engine" refers to a device or method that utilizes an emotion engine to identify and assess a user's emotional state in real time.

[0288] "Means for adjusting provided information based on emotion analysis" refers to a device or method for personalizing and adjusting provided information or content based on the user's emotion data.

[0289] "Data reporting means" refers to devices or methods for visualizing analysis results as dashboards or reports and sharing them with stakeholders.

[0290] "Information sharing means" refers to devices and methods for sharing analysis results and useful information with the general public, educational institutions, and other stakeholders.

[0291] The present invention provides a system for analyzing user emotions and providing personalized information based on the analyzed emotions. The system includes a data collection unit, a preprocessing unit, a data analysis unit, an emotion engine, a unit for adjusting information provided based on the emotion analysis, a data reporting unit, and an information sharing unit.

[0292] First, the server collects data in real time from multiple sensors such as cameras and microphones through data collection means, including the user's facial expressions, voice tone, and other vital data.

[0293] The preprocessing means performs noise reduction and normalization on the collected data to prepare it for analysis. For example, this includes normalizing facial expression data and denoising voice data.

[0294] The data analysis means then uses machine learning algorithms and deep learning models to analyze the pre-processed data and identify the user's emotions. An emotion engine is used to analyze the user's emotional state (e.g., joy, anxiety, surprise, etc.).

[0295] The information provision adjustment means based on emotion analysis personalizes the information provided according to the user's emotional state. For example, if the user is smiling, it suggests products that may be needed for relaxation, and if the user is feeling stressed, it recommends stress relief products.

[0296] The data reporting tool allows analysis results to be visualized in the form of dashboards and reports, which can be shared with stakeholders. It is also possible to send alerts based on specific conditions.

[0297] Analysis results and reports are provided to general users and educational institutions through information sharing channels, allowing users to easily access interesting products and content and provide feedback.

[0298] With the above functions, the present invention can provide personalized information according to the user's emotional state, thereby improving customer satisfaction and engagement.

[0299] For example, a smartphone or smart glasses can be used to scan the user's facial expression and suggest relaxation items to smiling users. Also, if a user's voice tone indicates that they are feeling stressed, relaxation music or stress relief goods can be recommended.

[0300] Example prompt sentence:

[0301] "What products do you recommend when a user smiles?"

[0302] "What content should I recommend if the user has a calm voice tone?"

[0303] "Recommend optimal products based on user emotional data and purchase history."

[0304] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0305] Step 1: Data collection

[0306] The server collects real-time data from cameras, microphones, and other sensors, such as the user's facial expression data, voice tone, and heart rate. The input data is the user's real-time sensor information, and the output is the collected raw data, which is used in the next pre-processing step.

[0307] Step 2: Data Preprocessing

[0308] The server performs noise removal and normalization on the collected data. The input is the raw data collected in step 1, and the output is clean, normalized data with noise removed. Specifically, it normalizes facial expression data and removes noise from voice data to prepare it for analysis.

[0309] Step 3: Data analysis

[0310] The server uses the preprocessed data to run machine learning algorithms or deep learning models to identify the user's emotions. The input data is denoised and normalized data, and the output is the user's emotional state (e.g., joy, anxiety, surprise). As a specific example, a deep learning model is used to classify emotions from the user's facial expressions.

[0311] Step 4: Analysis by Emotion Engine

[0312] The server uses an emotion engine to analyze the user's emotions. The input data is the user's emotional state obtained in step 3, and the output is a more precise emotion analysis result. Specifically, the server evaluates the user's emotional state in detail and quantifies the degree of joy or anxiety the user feels.

[0313] Step 5: Reporting data and personalizing information

[0314] The server personalizes the information it provides based on the analysis results of the emotion engine. The input data is the emotion analysis results obtained in step 4, and the output is a personalized list of recommended products and content. For example, if the user is smiling, it will recommend relaxation items, and if they are feeling stressed, it will recommend stress relief products.

[0315] Step 6: Information sharing

[0316] The server and device share the analysis results and recommendation list with the user and other relevant parties. The input data is the personalized information obtained in step 5, and the output is notifications and dashboard displays for the user. Specifically, the personalized product list is sent to the user via a web portal or email.

[0317] 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.

[0318] 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.

[0319] 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.

[0320] [Second embodiment]

[0321] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0322] 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.

[0323] 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).

[0324] 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.

[0325] 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.

[0326] 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).

[0327] 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.

[0328] 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.

[0329] 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.

[0330] 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.

[0331] In the smart glasses 214, 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.

[0332] 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."

[0333] The present invention is a system including a data collection means, a preprocessing means, a data analysis means, a data reporting means, and an information sharing means, and by collecting data in real time from multiple sensors, preprocessing, analyzing, reporting, and sharing this data, it is possible to quickly and accurately collect, analyze, and report environmental data. Below, the processing of a specific program for implementing the present invention is explained in natural language.

[0334] 1. Data Collection

[0335] The server collects data from cameras, audio sensors, weather data sources, etc. For example, it acquires image data of birds and animals from outdoor cameras, receives audio recordings from audio sensors, and obtains weather information from weather data APIs.

[0336] 2. Data Preprocessing

[0337] The server preprocesses the collected data, applying contrast correction and noise reduction filters to image data and noise reduction algorithms to audio data, as well as normalizing meteorological data and imputing missing values.

[0338] 3. Data Analysis

[0339] The server performs analysis based on the preprocessed data. For image data, it uses a deep learning object detection model to identify the type and number of animals, converts audio data into a spectrogram to extract features, and uses a machine learning model to identify whale species. It also detects abnormal weather patterns from weather data.

[0340] 4. Data reporting

[0341] The server reports the results of the analysis to environmental organizations and government agencies by visualizing the data on a dashboard and displaying it in graphs and maps. It also sends email alerts when certain conditions are detected. Monthly reports are also automatically generated and sent to relevant parties.

[0342] 5. Information Sharing

[0343] The server provides data to the general public and educational institutions through an information-sharing platform. Specifically, devices (PCs and smartphones) can access a web portal, view analysis results and reports, and download necessary data. Users can also use publicly available educational resources to learn about ecosystem conservation. They can also provide feedback and suggest improvements and new features to the system.

[0344] This system will support ecosystem conservation activities and enable the rapid and accurate collection, analysis, and reporting of environmental data. Furthermore, by sharing information with the general public and educational institutions, it will also contribute to raising environmental awareness and supporting education.

[0345] The processing flow will be explained below.

[0346] Step 1: Collect data

[0347] The server collects data from multiple cameras, audio sensors, and a weather database. Specifically, it periodically acquires data sent from each sensor and stores it in the database.

[0348] The server periodically acquires image data from a camera installed outdoors.

[0349] The server periodically acquires audio data from audio sensors installed in the ocean.

[0350] The server uses a weather data API to obtain real-time weather information.

[0351] Step 2: Preprocessing the data

[0352] The server pre-processes the collected data, which includes noise removal, data normalization, and outlier detection.

[0353] The server applies contrast enhancement and noise reduction filters to the collected image data.

[0354] The server applies a noise reduction algorithm to the acquired audio data to obtain clean audio data.

[0355] The server normalizes the weather data and imputes missing values ​​appropriately.

[0356] Step 3: Analyze the data

[0357] The server performs analysis based on the preprocessed data, using machine learning algorithms and deep learning models to analyze the data.

[0358] The server applies deep learning models to the image data to identify specific animal or plant species.

[0359] The server converts the audio data into a spectrogram and extracts features to identify the type and number of whales.

[0360] The server detects abnormal weather patterns from the weather data and evaluates their impact.

[0361] Step 4: Report the data

[0362] The server reports the analysis results to stakeholders, including dashboard displays, alert notifications, and report generation.

[0363] The server visualizes the analysis results on a dashboard and displays them in the form of maps and graphs.

[0364] The server sends email alerts based on certain conditions (e.g., when the presence of an endangered species is confirmed).

[0365] The server automatically generates periodic reports and sends them to the relevant parties by email.

[0366] Step 5: Share information

[0367] The server provides a platform for sharing information for the general public and educational institutions.

[0368] Devices (PCs or smartphones owned by the general public or educational institutions) access the AI ​​Eco-Monitor Network's web portal to view analysis results and reports.

[0369] The terminal can download the necessary data and obtain detailed information.

[0370] Users can learn about environmental protection by using educational resources made publicly available on the platform.

[0371] Users can provide feedback and suggest improvements and new features to the system.

[0372] Example 1

[0373] 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."

[0374] In conventional environmental data collection and analysis systems, the process from data collection to reporting was extremely slow and sometimes lacked accuracy. Furthermore, data sharing with the general public and educational institutions was limited, resulting in insufficient contribution to raising environmental awareness and supporting education. Furthermore, the lack of a feedback function made it difficult to propose system improvements or new functions.

[0375] 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.

[0376] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, a data reporting means, and an information sharing means. This allows data to be collected in real time from multiple sensors and the collected data to be subjected to noise removal and normalization. Furthermore, by including a feedback function for visualizing and reporting the analyzed data and for suggesting system improvements and new functions, this enables rapid and accurate data collection, analysis, and reporting, and contributes to raising environmental awareness and supporting education through information sharing with the general public and educational institutions.

[0377] A "data collection means" is a device or mechanism for collecting data in real time from multiple sensors.

[0378] A "preprocessing means" is a device or mechanism for removing noise and normalizing data from collected data.

[0379] A "data analysis means" is a device or mechanism that performs analysis on pre-processed data.

[0380] "Data reporting means" refers to a device or mechanism for visualizing and reporting analytical results to relevant parties and organizations.

[0381] An "information sharing tool" is a device or mechanism for providing analysis results and related information to the public and educational institutions.

[0382] "Denoising" is the process of removing unnecessary information or noise from data.

[0383] "Data normalization" is the process of scaling and standardizing data to reduce variability and make it consistent.

[0384] "Visualization" is the process of transforming data into something visible, such as a graph, chart, or map.

[0385] The "feedback function" is a mechanism for collecting opinions and requests from users and reflecting them in improving the system and developing new functions.

[0386] The present invention is a system that includes a data collection means, a preprocessing means, a data analysis means, a data reporting means, and an information sharing means. The system aims to quickly and accurately collect, analyze, and report environmental data, and to share this information with the general public and educational institutions. Specific embodiments for implementing the present invention are described below.

[0387] 1. Data Collection Methods

[0388] The server collects data in real time from multiple sensors, including cameras, audio sensors, and weather data sources. For example, it acquires image data of birds and animals from outdoor cameras, receives audio recordings from audio sensors, and obtains weather information from a weather data API.

[0389] 2. Pretreatment Methods

[0390] The server preprocesses the collected data. For image data, contrast correction and noise reduction filters are applied using OpenCV, and for audio data, noise reduction algorithms are applied using Audacity or Apache Commons Math. For weather data, the Pandas library is used to normalize and impute missing values.

[0391] 3. Data Analysis Methods

[0392] The server performs analysis based on the preprocessed data. It uses TensorFlow to perform object detection on image data using a deep learning model to identify the type and number of animals. It converts audio data into spectrograms and uses a machine learning model to identify whale species. It uses SciPy to detect abnormal weather patterns from weather data.

[0393] 4. Data reporting methods

[0394] The server reports the analysis results to environmental organizations and government agencies. It uses Dash and Plotly to visualize the data on a dashboard, displaying it in graphs and maps. It also uses an SMTP server to send alert emails when certain conditions are detected. Monthly reports are automatically generated using LaTeX and sent to relevant parties in PDF format.

[0395] 5. Information sharing method

[0396] Devices (PCs and smartphones) can access a web portal to view analysis results and reports and download necessary data. Specifically, users can access data through a web portal developed with Django and Flask. Users can also learn about ecosystem conservation using publicly available educational resources, provide feedback, and suggest system improvements and new features.

[0397] This system will support ecosystem conservation activities and enable the rapid and accurate collection, analysis, and reporting of environmental data. Furthermore, by sharing information with the general public and educational institutions, it will contribute to raising environmental awareness and supporting education.

[0398] Examples of prompt statements

[0399] "Consider a Python program that uses image data from field cameras and audio recordings from audio sensors to analyze the current state of an ecosystem."

[0400] "Detail the data processing and analysis procedures used to collect weather data and detect unusual weather patterns."

[0401] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0402] Step 1:

[0403] Data collection

[0404] The server collects data from multiple sensors in real time.

[0405] Inputs: Signals from cameras, audio sensors, weather data sources, etc.

[0406] Data processing: saving image data from cameras, collecting audio data from audio sensors, and obtaining data from weather data APIs

[0407] Output: Collected image data, audio data, and meteorological data

[0408] Specific operations: The camera periodically takes still images and sends them to the server. The audio sensor records audio at specified intervals and uploads the data to the server. Weather information is obtained from the weather data source using an API and stored on the server.

[0409] Step 2:

[0410] Data Preprocessing

[0411] The server pre-processes the collected data.

[0412] Input: Collected image data, audio data, and meteorological data

[0413] Data processing: Apply contrast correction and noise reduction filters to image data, apply noise reduction algorithms to audio data, normalize weather data and fill missing values

[0414] Output: Preprocessed image data, audio data, and weather data

[0415] What it does: It uses OpenCV to correct image contrast and a Gaussian filter to remove noise. For audio data, it uses signal processing tools to reduce background noise and make the audio clearer. For weather data, it normalizes the data frame and fills in missing values.

[0416] Step 3:

[0417] Data analysis

[0418] The server performs analysis based on the preprocessed data.

[0419] Input: Preprocessed image data, audio data, and meteorological data

[0420] Data processing: object detection from image data, feature extraction from audio data, and abnormal weather pattern detection from meteorological data

[0421] Output: Analysis results (species and numbers of animals, whale species, details of abnormal weather)

[0422] What it does: (TensorFlow) Uses deep learning models to detect and classify animals in images; converts audio data into spectrograms to extract features and uses machine learning models to estimate whale species; analyzes weather data for unusual weather patterns and detects anomalies.

[0423] Step 4:

[0424] Data reporting

[0425] The server reports the analysis results to the relevant organizations.

[0426] Input: Analysis results

[0427] Data manipulation: Visualize on dashboards, display in graphs and maps, send alerts, automatically generate reports

[0428] Output: Visualized data, alert emails, monthly reports (PDF format)

[0429] Specific tasks: Use Dash and Plotly to display analysis results in graphs and maps and create a dashboard that can be viewed by stakeholders. Use an SMTP server to send alert emails when certain conditions are met. Automatically generate monthly reports using LaTeX and send them to stakeholders in PDF format.

[0430] Step 5:

[0431] Information Sharing

[0432] The device allows the analysis results to be viewed through a web portal.

[0433] Input: Analysis results, reports, educational resources

[0434] Data processing: building a web portal, providing data, receiving feedback

[0435] Output: Displaying analysis results, downloading required data, and collecting feedback

[0436] What it does: Build a web portal using Django and Flask to allow users to easily view analysis results and reports. Users can use educational resources to learn more about ecosystem conservation and submit suggestions for improvements and requests for new features to the system through a feedback form.

[0437] This will improve the efficiency and accuracy of the entire system and enable a consistent flow of environmental data collection, analysis, reporting, and information sharing.

[0438] (Application example 1)

[0439] 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."

[0440] In conventional logistics systems, the collection, pre-processing, analysis, and reporting of data from each sensor were not integrated, resulting in inefficient inventory management, temperature monitoring, and weight analysis. This resulted in delayed detection of inventory shortages and abnormal weather, hindering operational efficiency.

[0441] 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.

[0442] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, a data reporting means, an information sharing means, an inventory management means, a temperature monitoring means, a weight analysis means, and an image processing means. This enables real-time monitoring of inventory and anomaly detection at the logistics center, enabling efficient business operations. In addition, the collected data is noise-removed and normalized to obtain highly reliable analysis results, enabling prompt and accurate information provision to managers and related parties.

[0443] "Data collection means" refers to a means for collecting necessary data in real time from multiple sensors.

[0444] "Preprocessing means" refers to means for removing noise and normalizing data in order to prepare collected data in a form that is easier to analyze.

[0445] "Data analysis means" refers to means for performing analysis according to a specific purpose based on preprocessed data.

[0446] "Data reporting means" refers to the means for reporting analysis results to users and related organizations.

[0447] "Information sharing means" refers to the means for sharing analysis results and related data among stakeholders.

[0448] The "inventory management means" is a means for monitoring the inventory status at the logistics center in real time and detecting abnormalities.

[0449] "Temperature monitoring means" refers to a means for monitoring the temperature of the storage environment in real time and maintaining appropriate storage conditions.

[0450] The "weight analysis means" is a means for analyzing the weight data of each product and performing appropriate inventory management.

[0451] The "image processing means" is a means for preprocessing image data acquired from a camera and extracting necessary information.

[0452] This invention is a system for improving the efficiency of inventory management in a logistics center. The server collects data in real time from multiple sensors and includes various means for preprocessing, analyzing, reporting, and sharing information. Specifically, this system is configured as follows:

[0453] Data collection

[0454] The server collects data from weight sensors, temperature sensors, cameras, etc. The data collected includes weight data for incoming and outgoing products, temperature data for storage areas, and image data for products. This allows for a real-time understanding of all movements within the logistics center. Product location information can also be obtained using RFID tags and barcode scanners.

[0455] Data Preprocessing

[0456] The server performs noise reduction and normalization on the collected data. For example, weight data is normalized, and temperature data is also normalized. Contrast correction and noise reduction filters are applied to the image data. This allows for faster and more accurate data analysis later.

[0457] Data analysis

[0458] The server detects inventory anomalies based on the pre-processed data. A deep learning algorithm using a generative AI model is applied for analysis, identifying products from image data. Temperature data is used to detect abnormalities in the storage environment, and appropriate countermeasures are implemented. Weight data is analyzed for abnormal fluctuations, preventing shortages and overstocks.

[0459] Data reporting

[0460] The server reports the analysis results to administrators and business personnel by visualizing real-time data on a dashboard, sending alert emails, and automatically generating monthly reports, allowing relevant parties to take action based on prompt and accurate information.

[0461] Information Sharing

[0462] The server shares analysis results and related data with relevant parties through an information-sharing platform. For example, administrators and business personnel can check information in real time through a web portal. Users can also use the system's feedback function to suggest improvements and new functions.

[0463] Specific examples

[0464] For example, in an inventory management system, the server could instruct a generative AI model using the following prompt sentence:

[0465] "I'm thinking of designing an application that will collect data using weight sensors, temperature sensors, and cameras, and then preprocess, analyze, report, and share the information in order to improve the efficiency of inventory management at distribution centers. I'd like to make this available on smartphones, so please write a specific program for me."

[0466] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0467] Step 1:

[0468] The server collects data in real time from weight sensors, temperature sensors, and cameras. Product weight data is input from the weight sensor, storage area temperature data from the temperature sensor, and product image data from the camera. This allows environmental information within the logistics center to be collected in one place.

[0469] Step 2:

[0470] The server preprocesses the collected data. Specifically, it removes noise and normalizes the weight and temperature data, and applies contrast correction and a noise removal filter to the image data. This preprocessing improves the reliability of the data and increases the accuracy of the analysis. The input is the raw weight data, temperature data, and image data, and the output is the preprocessed data.

[0471] Step 3:

[0472] The server performs data analysis based on the preprocessed data. It applies a deep learning algorithm using a generative AI model to process the image data to identify products. It also detects abnormalities in the storage environment from temperature data and analyzes inventory abnormalities from weight data. This allows for real-time detection of inventory abnormalities. The input is the preprocessed data, and the output is the analysis results.

[0473] Step 4:

[0474] The server reports data based on the analysis results. It updates the dashboard and visualizes inventory status in real time. It also sends alert emails to relevant parties when certain conditions occur and automatically generates and sends monthly reports. This allows relevant parties to quickly obtain the information they need. The input is the data analysis results, and the output is visualized data and reports.

[0475] Step 5:

[0476] The server shares data with relevant parties through an information-sharing platform. Managers and business personnel can access a web portal and check information in real time. The system also has a function that allows users to provide feedback, collecting requests for system improvements and suggestions for new functions. This enables continuous improvement of the system. The inputs are analysis results and feedback, and the outputs are shared information and improvement suggestions.

[0477] 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.

[0478] The present invention includes a system including a data collection means, a preprocessing means, a data analysis means, a data reporting means, and an information sharing means, as well as an emotion engine that can recognize a user's emotion and adjust the information provided based on that emotion. Below, the processing of a specific program for implementing the present invention will be described in natural language.

[0479] 1. Data Collection

[0480] The server collects data from multiple cameras, audio sensors, and a weather database, for example, capturing bird and animal image data from outdoor cameras, receiving audio recordings from audio sensors, and retrieving weather information from a weather data API.

[0481] 2. Data Preprocessing

[0482] The server pre-processes the collected data, which includes noise removal, data normalization, and outlier detection.

[0483] The server applies contrast enhancement and noise reduction filters to the collected image data.

[0484] The server applies a noise reduction algorithm to the acquired audio data to obtain clean audio data.

[0485] The server normalizes the weather data and imputes missing values ​​appropriately.

[0486] 3. Data Analysis

[0487] The server performs analysis based on the preprocessed data, using machine learning algorithms and deep learning models to analyze the data.

[0488] The server applies deep learning models to the image data to identify specific animal or plant species.

[0489] The server converts the audio data into a spectrogram and extracts features to identify the type and number of whales.

[0490] The server detects abnormal weather patterns from the weather data and evaluates their impact.

[0491] 4. Analysis by Emotion Engine

[0492] The server recognizes the user's emotions using an emotion engine, which analyzes the user's usage patterns, input data, and real-time sensor information to identify emotions.

[0493] The server may, for example, utilize facial recognition software or voice tone analysis tools to identify the user's emotional state (happiness, anxiety, surprise, etc.).

[0494] 5. Data reporting and personalization of information

[0495] The server reports the analysis results to stakeholders, including dashboard displays, alert notifications, and report generation.

[0496] The server visualizes the analysis results on a dashboard, displaying them in the form of maps and graphs, and also sends email alerts based on specific conditions (e.g., if an endangered species is detected).

[0497] The server automatically generates periodic reports and sends them to the relevant parties by email.

[0498] Based on the analysis results of the emotion engine, the server adjusts the information provided to suit the user's emotional state and provides optimal content.

[0499] 6. Information sharing

[0500] The server provides a platform for sharing information for the general public and educational institutions.

[0501] Devices (PCs or smartphones owned by the general public or educational institutions) access the AI ​​Eco-Monitor Network's web portal to view analysis results and reports.

[0502] The terminal can download the necessary data and obtain detailed information.

[0503] Users can learn about environmental protection through educational resources published on the platform, and the content is personalized based on the user's emotional state.

[0504] Users can provide feedback and suggest improvements and new features to the system.

[0505] By combining this system with an emotion engine, it is possible to provide personalized information tailored to the user's emotional state, making a significant contribution to raising environmental awareness and supporting education.

[0506] The processing flow will be explained below.

[0507] Step 1: Collect data

[0508] The server collects data from multiple cameras, audio sensors, and a weather database. Specifically, it periodically acquires data sent from each sensor and stores it in the database.

[0509] The server periodically acquires image data from a camera installed outdoors.

[0510] The server periodically acquires audio data from audio sensors installed in the ocean.

[0511] The server uses a weather data API to obtain real-time weather information.

[0512] Step 2: Preprocessing the data

[0513] The server pre-processes the collected data, which includes noise removal, data normalization, and outlier detection.

[0514] The server applies contrast enhancement and noise reduction filters to the collected image data.

[0515] The server applies a noise reduction algorithm to the acquired audio data to obtain clean audio data.

[0516] The server normalizes the weather data and imputes missing values ​​appropriately.

[0517] Step 3: Analyze the data

[0518] The server performs analysis based on the preprocessed data, using machine learning algorithms and deep learning models to analyze the data.

[0519] The server applies deep learning models to the image data to identify specific animal or plant species.

[0520] The server converts the audio data into a spectrogram and extracts features to identify the type and number of whales.

[0521] The server detects abnormal weather patterns from the weather data and evaluates their impact.

[0522] Step 4: Analysis by Emotion Engine

[0523] The server recognizes the user's emotions using an emotion engine, which analyzes the user's usage patterns, input data, and real-time sensor information to identify emotions.

[0524] The server collects, for example, camera data to recognize the user's face and audio data to analyze the user's voice.

[0525] The server uses facial recognition software to analyze facial expressions and determine whether the user is happy or sad.

[0526] The server analyzes the tone of the voice using a voice tone analysis tool to determine whether the user is excited or relaxed.

[0527] Step 5: Reporting data and personalizing information

[0528] The server reports the results of the analysis to stakeholders, including dashboard displays, alert notifications, and report generation, and also tailors the information provided to the user's emotional state based on the analysis results of the emotion engine.

[0529] The server visualizes the analysis results on a dashboard and displays them in the form of maps and graphs.

[0530] The server sends email alerts based on certain conditions (e.g., when the presence of an endangered species is confirmed).

[0531] The server automatically generates periodic reports and sends them to the relevant parties by email.

[0532] The server personalizes educational content or environmental information based on the user's emotional state: for example, if the user is excited, it will show simple infographics rather than detailed technical information.

[0533] Step 6: Information sharing

[0534] The server provides a platform for sharing information for the general public and educational institutions.

[0535] Devices (PCs or smartphones owned by the general public or educational institutions) access the AI ​​Eco-Monitor Network's web portal to view analysis results and reports.

[0536] The terminal can download the necessary data and obtain detailed information.

[0537] Users can learn about environmental protection through educational resources published on the platform, and the content is personalized based on the user's emotional state.

[0538] Users can provide feedback and suggest improvements and new features to the system.

[0539] Example 2

[0540] 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."

[0541] Conventional data collection and analysis systems provide information without considering the user's emotional state. This creates a gap between the content users want and the information they receive, resulting in problems such as insufficient environmental awareness and educational support. Furthermore, the quality and reliability of the collected data are often insufficient.

[0542] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, a sentiment analysis means, a data reporting means, and an information provision means. This makes it possible to provide information tailored to the emotional state of the user, which greatly contributes to improving environmental awareness and supporting education. Furthermore, by improving the quality and reliability of the data, more accurate analysis results can be obtained.

[0543] A "data collection means" is a combination of hardware and software for collecting necessary information in real time from multiple sensors and databases.

[0544] "Preprocessing means" is a function that performs processes such as noise removal, data normalization, and outlier detection on collected data to improve the quality of analysis.

[0545] A "data analysis tool" is a system that analyzes data using machine learning algorithms or deep learning models based on pre-processed data to identify specific patterns or features.

[0546] The "emotion analysis means" is a system for identifying the user's emotional state through facial recognition, voice tone analysis, etc., and adjusting the information provided based on that.

[0547] "Data reporting means" is a function for providing information by means of dashboard display, alert notification, report generation, etc. in order to report the results of data analysis to relevant parties.

[0548] "Information provision means" refers to a platform for providing analysis results and related information to the general public and educational institutions, making them accessible.

[0549] The present invention provides a system including a data collection means, a pre-processing means, a data analysis means, a sentiment analysis means, a data reporting means, and an information providing means, the system being capable of recognizing a user's sentiment state and adjusting the information provided based on the sentiment state.

[0550] Data collection

[0551] The server collects data from multiple cameras, audio sensors, and a weather database. For example, it uses outdoor cameras to capture image data of birds and animals, audio sensors to receive recorded calls and environmental sounds, and weather data APIs to obtain the latest weather information.

[0552] Pretreatment

[0553] The server preprocesses the collected data, which includes applying contrast correction and noise reduction filters to image data using the OpenCV library, denoising audio data using the Librosa library, normalizing meteorological data, and imputing missing data.

[0554] Data analysis

[0555] The server then applies machine learning algorithms and deep learning models to the preprocessed data and analyzes it. For example, a deep learning model trained with TensorFlow or PyTorch can be applied to image data to identify specific plant or animal species. Audio data can be converted into spectrograms to extract the features needed to identify whale species and numbers. Weather data can be used to detect abnormal weather patterns and assess their impact.

[0556] Emotion analysis

[0557] The server recognizes the user's emotions using an emotion engine that uses facial recognition software and voice analysis tools to perform real-time facial recognition and voice tone analysis of the user and identify the user's emotional state (e.g., joy, anxiety, surprise).

[0558] Data reporting and information provision

[0559] The server reports the analysis results to relevant parties. The analysis results are visualized on a dashboard and displayed in the form of maps and graphs. If certain conditions are met, an alert email is sent. In addition, based on the results of the emotion analysis, the information provided is adjusted to match the user's emotional state, providing optimal content.

[0560] Information sharing

[0561] The server provides a platform for sharing information with the general public and educational institutions. Devices (PCs and smartphones of the general public and educational institutions) can access the web portal to view analysis results and reports. They can also download necessary data and obtain detailed information. Users can use publicly available educational resources to learn about environmental protection. Personalized content is also provided based on the user's emotional state. A feedback function allows users to suggest improvements to the system and new functions.

[0562] Examples and prompts:

[0563] When a user inputs a prompt such as "Tell me the types of birds you have observed in the mountains," the server first processes the data obtained from the camera and audio sensors. Then, based on the preprocessed image data, it applies a deep learning model to identify the bird species. The analysis results are then visualized on a dashboard for the user to access. Finally, it uses sentiment analysis to recognize that the user is excited, and provides detailed information and additional observation points according to that excitement. Specifically, the following prompt is used:

[0564] Prompt: "What types of birds have you seen in the mountains?"

[0565] By working in conjunction with an emotion engine, this system provides personalized information tailored to the user's emotional state, making a significant contribution to improving environmental awareness and supporting education.

[0566] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0567] Step 1: Data collection

[0568] The server collects data from multiple cameras, audio sensors, and a weather database. Input data includes image data, audio data, and weather information. Specifically, it uses cameras installed outdoors to obtain image data of birds and animals, and audio sensors to receive recorded calls and environmental sounds. It also uses a weather data API to obtain the latest weather information. As output, this data is aggregated on the server.

[0569] Step 2: Preprocessing the data

[0570] The server preprocesses the collected data. The input data are the image data, audio data, and weather information collected in step 1. Specific operations include contrast correction and noise reduction filter application to the image data using the OpenCV library, noise reduction to the audio data using the Librosa library, normalization of the weather data, and completion of missing data. The output is preprocessed image data, audio data, and normalized weather data.

[0571] Step 3: Data analysis

[0572] The server analyzes the preprocessed data by applying machine learning algorithms and deep learning models. The input data is the image data, audio data, and weather information preprocessed in step 2. Specifically, a deep learning model trained using TensorFlow or PyTorch is applied to the image data to identify specific types of plants and animals. The audio data is converted into a spectrogram, and the features needed to identify the type and number of whales are extracted. The weather data is used to detect abnormal weather patterns and evaluate their impact. The analysis results are obtained as output.

[0573] Step 4: Sentiment Analysis

[0574] The server uses an emotion engine to recognize the user's emotions. The input data is the user's real-time facial recognition data and voice data. Specifically, it uses facial recognition software and voice tone analysis tools to identify the user's emotional state (e.g., joy, anxiety, surprise) from their facial expressions and voice tone. The output is the user's emotional state.

[0575] Step 5: Data reporting and information provision

[0576] The server reports the analysis results to the relevant parties. The input data are the analysis results from step 3 and the sentiment analysis results from step 4. Specific operations include visualizing the analysis results on a dashboard and displaying them in the form of maps and graphs. Additionally, an alert email is sent when certain conditions are met. The visualized analysis results and the sent alert are obtained as outputs.

[0577] Step 6: Information sharing

[0578] Terminals (PCs or smartphones of the general public or educational institutions) access the platform provided by the server to view analysis results and reports. The input data are the analysis results visualized in step 5. Users can download the necessary data from the web portal and obtain more detailed information. They can also use publicly available educational resources to learn about environmental protection. They can also suggest improvements to the system or new functions through the feedback function. The output includes the data used, educational resources, and submitted feedback.

[0579] An example of a specific prompt: "Tell me what kinds of birds you saw in the mountains."

[0580] In this way, this system has a consistent process from data collection to analysis and provision of information based on the user's emotional state, thereby providing advanced information tailored to the user's needs.

[0581] (Application example 2)

[0582] 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."

[0583] Conventional systems have had difficulty providing information according to a user's emotions, making it difficult to realize personalized services. This has prevented users from improving their satisfaction and engagement. The present invention aims to solve these problems by providing a system that recognizes a user's emotions and adjusts the information provided based on those emotions.

[0584] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, a means for analyzing a user's emotions using an emotion engine, a means for adjusting information to be provided based on the emotion analysis, a data reporting means, and an information sharing means. This makes it possible to provide personalized information according to the user's emotional state.

[0585] "Data collection means" refers to a device or method for collecting data in real time from multiple sensors.

[0586] "Preprocessing means" refers to devices or methods that normalize collected data, remove noise, and otherwise prepare the data in a form that is easier to analyze.

[0587] "Data analysis means" refers to devices or methods that use machine learning algorithms or deep learning models to analyze data and extract useful information.

[0588] "Means for analyzing a user's emotions using an emotion engine" refers to a device or method that utilizes an emotion engine to identify and assess a user's emotional state in real time.

[0589] "Means for adjusting provided information based on emotion analysis" refers to a device or method for personalizing and adjusting provided information or content based on the user's emotion data.

[0590] "Data reporting means" refers to devices or methods for visualizing analysis results as dashboards or reports and sharing them with stakeholders.

[0591] "Information sharing means" refers to devices and methods for sharing analysis results and useful information with the general public, educational institutions, and other stakeholders.

[0592] The present invention provides a system for analyzing user emotions and providing personalized information based on the analyzed emotions. The system includes a data collection unit, a preprocessing unit, a data analysis unit, an emotion engine, a unit for adjusting information provided based on the emotion analysis, a data reporting unit, and an information sharing unit.

[0593] First, the server collects data in real time from multiple sensors such as cameras and microphones through data collection means, including the user's facial expressions, voice tone, and other vital data.

[0594] The preprocessing means performs noise reduction and normalization on the collected data to prepare it for analysis. For example, this includes normalizing facial expression data and denoising voice data.

[0595] The data analysis means then uses machine learning algorithms and deep learning models to analyze the pre-processed data and identify the user's emotions. An emotion engine is used to analyze the user's emotional state (e.g., joy, anxiety, surprise, etc.).

[0596] The information provision adjustment means based on emotion analysis personalizes the information provided according to the user's emotional state. For example, if the user is smiling, it suggests products that may be needed for relaxation, and if the user is feeling stressed, it recommends stress relief products.

[0597] The data reporting tool allows analysis results to be visualized in the form of dashboards and reports, which can be shared with stakeholders. It is also possible to send alerts based on specific conditions.

[0598] Analysis results and reports are provided to general users and educational institutions through information sharing channels, allowing users to easily access interesting products and content and provide feedback.

[0599] With the above functions, the present invention can provide personalized information according to the user's emotional state, thereby improving customer satisfaction and engagement.

[0600] For example, a smartphone or smart glasses can be used to scan the user's facial expression and suggest relaxation items to smiling users. Also, if a user's voice tone indicates that they are feeling stressed, relaxation music or stress relief goods can be recommended.

[0601] Example prompt sentence:

[0602] "What products do you recommend when a user smiles?"

[0603] "What content should I recommend if the user has a calm voice tone?"

[0604] "Recommend optimal products based on user emotional data and purchase history."

[0605] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0606] Step 1: Data collection

[0607] The server collects real-time data from cameras, microphones, and other sensors, such as the user's facial expression data, voice tone, and heart rate. The input data is the user's real-time sensor information, and the output is the collected raw data, which is used in the next pre-processing step.

[0608] Step 2: Data Preprocessing

[0609] The server performs noise removal and normalization on the collected data. The input is the raw data collected in step 1, and the output is clean, normalized data with noise removed. Specifically, it normalizes facial expression data and removes noise from voice data to prepare it for analysis.

[0610] Step 3: Data analysis

[0611] The server uses the preprocessed data to run machine learning algorithms or deep learning models to identify the user's emotions. The input data is denoised and normalized data, and the output is the user's emotional state (e.g., joy, anxiety, surprise). As a specific example, a deep learning model is used to classify emotions from the user's facial expressions.

[0612] Step 4: Analysis by Emotion Engine

[0613] The server uses an emotion engine to analyze the user's emotions. The input data is the user's emotional state obtained in step 3, and the output is a more precise emotion analysis result. Specifically, the server evaluates the user's emotional state in detail and quantifies the degree of joy or anxiety the user feels.

[0614] Step 5: Reporting data and personalizing information

[0615] The server personalizes the information it provides based on the analysis results of the emotion engine. The input data is the emotion analysis results obtained in step 4, and the output is a personalized list of recommended products and content. For example, if the user is smiling, it will recommend relaxation items, and if they are feeling stressed, it will recommend stress relief products.

[0616] Step 6: Information sharing

[0617] The server and device share the analysis results and recommendation list with the user and other relevant parties. The input data is the personalized information obtained in step 5, and the output is notifications and dashboard displays for the user. Specifically, the personalized product list is sent to the user via a web portal or email.

[0618] 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.

[0619] 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.

[0620] 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.

[0621] [Third embodiment]

[0622] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0623] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0624] 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).

[0625] 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.

[0626] 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.

[0627] 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).

[0628] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0629] 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.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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."

[0634] The present invention is a system including a data collection means, a preprocessing means, a data analysis means, a data reporting means, and an information sharing means, and by collecting data in real time from multiple sensors, preprocessing, analyzing, reporting, and sharing this data, it is possible to quickly and accurately collect, analyze, and report environmental data. Below, the processing of a specific program for implementing the present invention is explained in natural language.

[0635] 1. Data Collection

[0636] The server collects data from cameras, audio sensors, weather data sources, etc. For example, it acquires image data of birds and animals from outdoor cameras, receives audio recordings from audio sensors, and obtains weather information from weather data APIs.

[0637] 2. Data Preprocessing

[0638] The server preprocesses the collected data, applying contrast correction and noise reduction filters to image data and noise reduction algorithms to audio data, as well as normalizing meteorological data and imputing missing values.

[0639] 3. Data Analysis

[0640] The server performs analysis based on the preprocessed data. For image data, it uses a deep learning object detection model to identify the type and number of animals, converts audio data into a spectrogram to extract features, and uses a machine learning model to identify whale species. It also detects abnormal weather patterns from weather data.

[0641] 4. Data reporting

[0642] The server reports the results of the analysis to environmental organizations and government agencies by visualizing the data on a dashboard and displaying it in graphs and maps. It also sends email alerts when certain conditions are detected. Monthly reports are also automatically generated and sent to relevant parties.

[0643] 5. Information Sharing

[0644] The server provides data to the general public and educational institutions through an information-sharing platform. Specifically, devices (PCs and smartphones) can access a web portal, view analysis results and reports, and download necessary data. Users can also use publicly available educational resources to learn about ecosystem conservation. They can also provide feedback and suggest improvements and new features to the system.

[0645] This system will support ecosystem conservation activities and enable the rapid and accurate collection, analysis, and reporting of environmental data. Furthermore, by sharing information with the general public and educational institutions, it will contribute to raising environmental awareness and supporting education.

[0646] The processing flow will be explained below.

[0647] Step 1: Collect data

[0648] The server collects data from multiple cameras, audio sensors, and a weather database. Specifically, it periodically acquires data sent from each sensor and stores it in the database.

[0649] The server periodically acquires image data from a camera installed outdoors.

[0650] The server periodically acquires audio data from audio sensors installed in the ocean.

[0651] The server uses a weather data API to obtain real-time weather information.

[0652] Step 2: Preprocessing the data

[0653] The server pre-processes the collected data, which includes noise removal, data normalization, and outlier detection.

[0654] The server applies contrast enhancement and noise reduction filters to the collected image data.

[0655] The server applies a noise reduction algorithm to the acquired audio data to obtain clean audio data.

[0656] The server normalizes the weather data and imputes missing values ​​appropriately.

[0657] Step 3: Analyze the data

[0658] The server performs analysis based on the preprocessed data, using machine learning algorithms and deep learning models to analyze the data.

[0659] The server applies deep learning models to the image data to identify specific animal or plant species.

[0660] The server converts the audio data into a spectrogram and extracts features to identify the type and number of whales.

[0661] The server detects abnormal weather patterns from the weather data and evaluates their impact.

[0662] Step 4: Report the data

[0663] The server reports the analysis results to stakeholders, including dashboard displays, alert notifications, and report generation.

[0664] The server visualizes the analysis results on a dashboard and displays them in the form of maps and graphs.

[0665] The server sends email alerts based on certain conditions (e.g., when the presence of an endangered species is confirmed).

[0666] The server automatically generates periodic reports and sends them to the relevant parties by email.

[0667] Step 5: Share information

[0668] The server provides a platform for sharing information for the general public and educational institutions.

[0669] Devices (PCs or smartphones owned by the general public or educational institutions) access the AI ​​Eco-Monitor Network's web portal to view analysis results and reports.

[0670] The terminal can download the necessary data and obtain detailed information.

[0671] Users can learn about environmental protection by using educational resources made publicly available on the platform.

[0672] Users can provide feedback and suggest improvements and new features to the system.

[0673] Example 1

[0674] 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."

[0675] In conventional environmental data collection and analysis systems, the process from data collection to reporting was extremely slow and sometimes lacked accuracy. Furthermore, data sharing with the general public and educational institutions was limited, resulting in insufficient contribution to raising environmental awareness and supporting education. Furthermore, the lack of a feedback function made it difficult to propose system improvements or new functions.

[0676] 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.

[0677] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, a data reporting means, and an information sharing means. This allows data to be collected in real time from multiple sensors and the collected data to be subjected to noise removal and normalization. Furthermore, by including a feedback function for visualizing and reporting the analyzed data and for suggesting system improvements and new functions, this enables rapid and accurate data collection, analysis, and reporting, and contributes to raising environmental awareness and supporting education through information sharing with the general public and educational institutions.

[0678] A "data collection means" is a device or mechanism for collecting data in real time from multiple sensors.

[0679] A "preprocessing means" is a device or mechanism for removing noise and normalizing data from collected data.

[0680] A "data analysis means" is a device or mechanism that performs analysis on pre-processed data.

[0681] "Data reporting means" refers to a device or mechanism for visualizing and reporting analytical results to relevant parties and organizations.

[0682] An "information sharing tool" is a device or mechanism for providing analysis results and related information to the public and educational institutions.

[0683] "Denoising" is the process of removing unnecessary information or noise from data.

[0684] "Data normalization" is the process of scaling and standardizing data to reduce variability and make it consistent.

[0685] "Visualization" is the process of transforming data into something visible, such as a graph, chart, or map.

[0686] The "feedback function" is a mechanism for collecting opinions and requests from users and reflecting them in improving the system and developing new functions.

[0687] The present invention is a system that includes a data collection means, a preprocessing means, a data analysis means, a data reporting means, and an information sharing means. The system aims to quickly and accurately collect, analyze, and report environmental data, and to share this information with the general public and educational institutions. Specific embodiments for implementing the present invention are described below.

[0688] 1. Data Collection Methods

[0689] The server collects data in real time from multiple sensors, including cameras, audio sensors, and weather data sources. For example, it acquires image data of birds and animals from outdoor cameras, receives audio recordings from audio sensors, and obtains weather information from a weather data API.

[0690] 2. Pretreatment Methods

[0691] The server preprocesses the collected data. For image data, contrast correction and noise reduction filters are applied using OpenCV, and for audio data, noise reduction algorithms are applied using Audacity or Apache Commons Math. For weather data, the Pandas library is used to normalize and impute missing values.

[0692] 3. Data Analysis Methods

[0693] The server performs analysis based on the preprocessed data. It uses TensorFlow to perform object detection on image data using a deep learning model to identify the type and number of animals. It converts audio data into spectrograms and uses a machine learning model to identify whale species. It uses SciPy to detect abnormal weather patterns from weather data.

[0694] 4. Data reporting methods

[0695] The server reports the analysis results to environmental organizations and government agencies. It uses Dash and Plotly to visualize the data on a dashboard, displaying it in graphs and maps. It also uses an SMTP server to send alert emails when certain conditions are detected. Monthly reports are automatically generated using LaTeX and sent to relevant parties in PDF format.

[0696] 5. Information sharing method

[0697] Devices (PCs and smartphones) can access a web portal to view analysis results and reports and download necessary data. Specifically, users can access data through a web portal developed with Django and Flask. Users can also learn about ecosystem conservation using publicly available educational resources, provide feedback, and suggest system improvements and new features.

[0698] This system will support ecosystem conservation activities and enable the rapid and accurate collection, analysis, and reporting of environmental data. Furthermore, by sharing information with the general public and educational institutions, it will contribute to raising environmental awareness and supporting education.

[0699] Examples of prompt statements

[0700] "Consider a Python program that uses image data from field cameras and audio recordings from audio sensors to analyze the current state of an ecosystem."

[0701] "Detail the data processing and analysis procedures used to collect weather data and detect unusual weather patterns."

[0702] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0703] Step 1:

[0704] Data collection

[0705] The server collects data from multiple sensors in real time.

[0706] Inputs: Signals from cameras, audio sensors, weather data sources, etc.

[0707] Data processing: saving image data from cameras, collecting audio data from audio sensors, and obtaining data from weather data APIs

[0708] Output: Collected image data, audio data, and meteorological data

[0709] Specific operations: The camera periodically takes still images and sends them to the server. The audio sensor records audio at specified intervals and uploads the data to the server. Weather information is obtained from the weather data source using an API and stored on the server.

[0710] Step 2:

[0711] Data Preprocessing

[0712] The server pre-processes the collected data.

[0713] Input: Collected image data, audio data, and meteorological data

[0714] Data processing: Apply contrast correction and noise reduction filters to image data, apply noise reduction algorithms to audio data, normalize weather data and fill missing values

[0715] Output: Preprocessed image data, audio data, and weather data

[0716] What it does: It uses OpenCV to correct image contrast and a Gaussian filter to remove noise. For audio data, it uses signal processing tools to reduce background noise and make the audio clearer. For weather data, it normalizes the data frame and fills in missing values.

[0717] Step 3:

[0718] Data analysis

[0719] The server performs analysis based on the preprocessed data.

[0720] Input: Preprocessed image data, audio data, and meteorological data

[0721] Data processing: object detection from image data, feature extraction from audio data, and abnormal weather pattern detection from meteorological data

[0722] Output: Analysis results (species and numbers of animals, whale species, details of abnormal weather)

[0723] What it does: (TensorFlow) Uses deep learning models to detect and classify animals in images; converts audio data into spectrograms to extract features and uses machine learning models to estimate whale species; analyzes weather data for unusual weather patterns and detects anomalies.

[0724] Step 4:

[0725] Data reporting

[0726] The server reports the analysis results to the relevant organizations.

[0727] Input: Analysis results

[0728] Data manipulation: Visualize on dashboards, display in graphs and maps, send alerts, automatically generate reports

[0729] Output: Visualized data, alert emails, monthly reports (PDF format)

[0730] Specific tasks: Use Dash and Plotly to display analysis results in graphs and maps and create a dashboard that can be viewed by stakeholders. Use an SMTP server to send alert emails when certain conditions are met. Automatically generate monthly reports using LaTeX and send them to stakeholders in PDF format.

[0731] Step 5:

[0732] Information Sharing

[0733] The device allows the analysis results to be viewed through a web portal.

[0734] Input: Analysis results, reports, educational resources

[0735] Data processing: building a web portal, providing data, receiving feedback

[0736] Output: Displaying analysis results, downloading required data, and collecting feedback

[0737] What it does: Build a web portal using Django and Flask to allow users to easily view analysis results and reports. Users can use educational resources to learn more about ecosystem conservation and submit suggestions for improvements and requests for new features to the system through a feedback form.

[0738] This will improve the efficiency and accuracy of the entire system and enable a consistent flow of environmental data collection, analysis, reporting, and information sharing.

[0739] (Application example 1)

[0740] 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."

[0741] In conventional logistics systems, the collection, pre-processing, analysis, and reporting of data from each sensor were not integrated, resulting in inefficient inventory management, temperature monitoring, and weight analysis. This resulted in delayed detection of inventory shortages and abnormal weather, hindering operational efficiency.

[0742] 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.

[0743] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, a data reporting means, an information sharing means, an inventory management means, a temperature monitoring means, a weight analysis means, and an image processing means. This enables real-time monitoring of inventory and anomaly detection at the logistics center, enabling efficient business operations. In addition, the collected data is noise-removed and normalized to obtain highly reliable analysis results, enabling prompt and accurate information provision to managers and related parties.

[0744] "Data collection means" refers to a means for collecting necessary data in real time from multiple sensors.

[0745] "Preprocessing means" refers to means for removing noise and normalizing data in order to prepare collected data in a form that is easier to analyze.

[0746] "Data analysis means" refers to means for performing analysis according to a specific purpose based on preprocessed data.

[0747] "Data reporting means" refers to the means for reporting analysis results to users and related organizations.

[0748] "Information sharing means" refers to the means for sharing analysis results and related data among stakeholders.

[0749] "Inventory management means" refers to means for monitoring the inventory status at the logistics center in real time and detecting abnormalities.

[0750] "Temperature monitoring means" refers to a means for monitoring the temperature of the storage environment in real time and maintaining appropriate storage conditions.

[0751] The "weight analysis means" is a means for analyzing the weight data of each product and performing appropriate inventory management.

[0752] The "image processing means" is a means for preprocessing image data acquired from a camera and extracting necessary information.

[0753] This invention is a system for improving the efficiency of inventory management in a logistics center. The server collects data in real time from multiple sensors and includes various means for preprocessing, analyzing, reporting, and sharing information. Specifically, this system is configured as follows:

[0754] Data collection

[0755] The server collects data from weight sensors, temperature sensors, cameras, etc. The data collected includes weight data for incoming and outgoing products, temperature data for storage areas, and image data for products. This allows for a real-time understanding of all movements within the logistics center. Product location information can also be obtained using RFID tags and barcode scanners.

[0756] Data Preprocessing

[0757] The server performs noise reduction and normalization on the collected data. For example, weight data is normalized, and temperature data is also normalized. Contrast correction and noise reduction filters are applied to the image data. This allows for faster and more accurate data analysis later.

[0758] Data analysis

[0759] The server detects inventory anomalies based on the pre-processed data. A deep learning algorithm using a generative AI model is applied for analysis, identifying products from image data. Temperature data is used to detect abnormalities in the storage environment, and appropriate countermeasures are implemented. Weight data is analyzed for abnormal fluctuations, preventing shortages and overstocks.

[0760] Data reporting

[0761] The server reports the analysis results to administrators and business personnel by visualizing real-time data on a dashboard, sending alert emails, and automatically generating monthly reports, allowing relevant parties to take action based on prompt and accurate information.

[0762] Information Sharing

[0763] The server shares analysis results and related data with relevant parties through an information-sharing platform. For example, administrators and business personnel can check information in real time through a web portal. Users can also use the system's feedback function to suggest improvements and new functions.

[0764] Specific examples

[0765] For example, in an inventory management system, the server could instruct a generative AI model using the following prompt sentence:

[0766] "I'm thinking of designing an application that will collect data using weight sensors, temperature sensors, and cameras, and then preprocess, analyze, report, and share the information in order to improve the efficiency of inventory management at distribution centers. I'd like to make this available on smartphones, so please write a specific program for me."

[0767] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0768] Step 1:

[0769] The server collects data in real time from weight sensors, temperature sensors, and cameras. Product weight data is input from the weight sensor, storage area temperature data from the temperature sensor, and product image data from the camera. This allows environmental information within the logistics center to be collected in one place.

[0770] Step 2:

[0771] The server preprocesses the collected data. Specifically, it removes noise and normalizes the weight and temperature data, and applies contrast correction and a noise removal filter to the image data. This preprocessing improves the reliability of the data and increases the accuracy of the analysis. The input is the raw weight data, temperature data, and image data, and the output is the preprocessed data.

[0772] Step 3:

[0773] The server performs data analysis based on the preprocessed data. It applies a deep learning algorithm using a generative AI model to process the image data to identify products. It also detects abnormalities in the storage environment from temperature data and analyzes inventory abnormalities from weight data. This allows for real-time detection of inventory abnormalities. The input is the preprocessed data, and the output is the analysis results.

[0774] Step 4:

[0775] The server reports data based on the analysis results. It updates the dashboard and visualizes inventory status in real time. It also sends alert emails to relevant parties when certain conditions occur and automatically generates and sends monthly reports. This allows relevant parties to quickly obtain the information they need. The input is the data analysis results, and the output is visualized data and reports.

[0776] Step 5:

[0777] The server shares data with relevant parties through an information-sharing platform. Managers and business personnel can access a web portal and check information in real time. The system also has a function that allows users to provide feedback, collecting requests for system improvements and suggestions for new functions. This enables continuous improvement of the system. The inputs are analysis results and feedback, and the outputs are shared information and improvement suggestions.

[0778] 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.

[0779] The present invention includes a system including a data collection means, a preprocessing means, a data analysis means, a data reporting means, and an information sharing means, as well as an emotion engine that can recognize a user's emotion and adjust the information provided based on that emotion. Below, the processing of a specific program for implementing the present invention will be described in natural language.

[0780] 1. Data Collection

[0781] The server collects data from multiple cameras, audio sensors, and a weather database, for example, capturing bird and animal image data from outdoor cameras, receiving audio recordings from audio sensors, and retrieving weather information from a weather data API.

[0782] 2. Data Preprocessing

[0783] The server pre-processes the collected data, which includes noise removal, data normalization, and outlier detection.

[0784] The server applies contrast enhancement and noise reduction filters to the collected image data.

[0785] The server applies a noise reduction algorithm to the acquired audio data to obtain clean audio data.

[0786] The server normalizes the weather data and imputes missing values ​​appropriately.

[0787] 3. Data Analysis

[0788] The server performs analysis based on the preprocessed data, using machine learning algorithms and deep learning models to analyze the data.

[0789] The server applies deep learning models to the image data to identify specific animal or plant species.

[0790] The server converts the audio data into a spectrogram and extracts features to identify the type and number of whales.

[0791] The server detects abnormal weather patterns from the weather data and evaluates their impact.

[0792] 4. Analysis by Emotion Engine

[0793] The server recognizes the user's emotions using an emotion engine, which analyzes the user's usage patterns, input data, and real-time sensor information to identify emotions.

[0794] The server may, for example, utilize facial recognition software or voice tone analysis tools to identify the user's emotional state (happiness, anxiety, surprise, etc.).

[0795] 5. Data reporting and personalization of information

[0796] The server reports the analysis results to stakeholders, including dashboard displays, alert notifications, and report generation.

[0797] The server visualizes the analysis results on a dashboard, displaying them in the form of maps and graphs, and also sends email alerts based on specific conditions (e.g., if an endangered species is detected).

[0798] The server automatically generates periodic reports and sends them to the relevant parties by email.

[0799] Based on the analysis results of the emotion engine, the server adjusts the information provided to suit the user's emotional state and provides optimal content.

[0800] 6. Information sharing

[0801] The server provides a platform for sharing information for the general public and educational institutions.

[0802] Devices (PCs or smartphones owned by the general public or educational institutions) access the AI ​​Eco-Monitor Network's web portal to view analysis results and reports.

[0803] The terminal can download the necessary data and obtain detailed information.

[0804] Users can learn about environmental protection through educational resources published on the platform, and the content is personalized based on the user's emotional state.

[0805] Users can provide feedback and suggest improvements and new features to the system.

[0806] By combining this system with an emotion engine, it is possible to provide personalized information tailored to the user's emotional state, making a significant contribution to raising environmental awareness and supporting education.

[0807] The processing flow will be explained below.

[0808] Step 1: Collect data

[0809] The server collects data from multiple cameras, audio sensors, and a weather database. Specifically, it periodically acquires data sent from each sensor and stores it in the database.

[0810] The server periodically acquires image data from a camera installed outdoors.

[0811] The server periodically acquires audio data from audio sensors installed in the ocean.

[0812] The server uses a weather data API to obtain real-time weather information.

[0813] Step 2: Preprocessing the data

[0814] The server pre-processes the collected data, which includes noise removal, data normalization, and outlier detection.

[0815] The server applies contrast enhancement and noise reduction filters to the collected image data.

[0816] The server applies a noise reduction algorithm to the acquired audio data to obtain clean audio data.

[0817] The server normalizes the weather data and imputes missing values ​​appropriately.

[0818] Step 3: Analyze the data

[0819] The server performs analysis based on the preprocessed data, using machine learning algorithms and deep learning models to analyze the data.

[0820] The server applies deep learning models to the image data to identify specific animal or plant species.

[0821] The server converts the audio data into a spectrogram and extracts features to identify the type and number of whales.

[0822] The server detects abnormal weather patterns from the weather data and evaluates their impact.

[0823] Step 4: Analysis by Emotion Engine

[0824] The server recognizes the user's emotions using an emotion engine, which analyzes the user's usage patterns, input data, and real-time sensor information to identify emotions.

[0825] The server collects, for example, camera data to recognize the user's face and audio data to analyze the user's voice.

[0826] The server uses facial recognition software to analyze facial expressions and determine whether the user is happy or sad.

[0827] The server analyzes the tone of the voice using a voice tone analysis tool to determine whether the user is excited or relaxed.

[0828] Step 5: Reporting data and personalizing information

[0829] The server reports the results of the analysis to stakeholders, including dashboard displays, alert notifications, and report generation, and also tailors the information provided to the user's emotional state based on the analysis results of the emotion engine.

[0830] The server visualizes the analysis results on a dashboard and displays them in the form of maps and graphs.

[0831] The server sends email alerts based on certain conditions (e.g., when the presence of an endangered species is confirmed).

[0832] The server automatically generates periodic reports and sends them to the relevant parties by email.

[0833] The server personalizes educational content or environmental information based on the user's emotional state: for example, if the user is excited, it will show simple infographics rather than detailed technical information.

[0834] Step 6: Information sharing

[0835] The server provides a platform for sharing information for the general public and educational institutions.

[0836] Devices (PCs or smartphones owned by the general public or educational institutions) access the AI ​​Eco-Monitor Network's web portal to view analysis results and reports.

[0837] The terminal can download the necessary data and obtain detailed information.

[0838] Users can learn about environmental protection through educational resources published on the platform, and the content is personalized based on the user's emotional state.

[0839] Users can provide feedback and suggest improvements and new features to the system.

[0840] Example 2

[0841] 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."

[0842] Conventional data collection and analysis systems provide information without considering the user's emotional state. This creates a gap between the content users want and the information they receive, resulting in problems such as insufficient environmental awareness and educational support. Furthermore, the quality and reliability of the collected data are often insufficient.

[0843] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, a sentiment analysis means, a data reporting means, and an information provision means. This makes it possible to provide information tailored to the emotional state of the user, which greatly contributes to improving environmental awareness and supporting education. Furthermore, by improving the quality and reliability of the data, more accurate analysis results can be obtained.

[0844] A "data collection means" is a combination of hardware and software for collecting necessary information in real time from multiple sensors and databases.

[0845] "Preprocessing means" is a function that performs processes such as noise removal, data normalization, and outlier detection on collected data to improve the quality of analysis.

[0846] A "data analysis tool" is a system that analyzes data using machine learning algorithms or deep learning models based on pre-processed data to identify specific patterns or features.

[0847] The "emotion analysis means" is a system for identifying the user's emotional state through facial recognition, voice tone analysis, etc., and adjusting the information provided based on that.

[0848] "Data reporting means" is a function for providing information by means of dashboard display, alert notification, report generation, etc. in order to report the results of data analysis to relevant parties.

[0849] "Information provision means" refers to a platform for providing analysis results and related information to the general public and educational institutions, making them accessible.

[0850] The present invention provides a system including a data collection means, a pre-processing means, a data analysis means, a sentiment analysis means, a data reporting means, and an information providing means, the system being capable of recognizing a user's sentiment state and adjusting the information provided based on the sentiment state.

[0851] Data collection

[0852] The server collects data from multiple cameras, audio sensors, and a weather database. For example, it uses outdoor cameras to capture image data of birds and animals, audio sensors to receive recorded calls and environmental sounds, and weather data APIs to obtain the latest weather information.

[0853] Pretreatment

[0854] The server preprocesses the collected data, which includes applying contrast correction and noise reduction filters to image data using the OpenCV library, denoising audio data using the Librosa library, normalizing meteorological data, and imputing missing data.

[0855] Data analysis

[0856] The server then applies machine learning algorithms and deep learning models to the preprocessed data and analyzes it. For example, a deep learning model trained with TensorFlow or PyTorch can be applied to image data to identify specific plant or animal species. Audio data can be converted into spectrograms to extract the features needed to identify whale species and numbers. Weather data can be used to detect abnormal weather patterns and assess their impact.

[0857] Emotion analysis

[0858] The server recognizes the user's emotions using an emotion engine that uses facial recognition software and voice analysis tools to perform real-time facial recognition and voice tone analysis of the user and identify the user's emotional state (e.g., joy, anxiety, surprise).

[0859] Data reporting and information provision

[0860] The server reports the analysis results to relevant parties. The analysis results are visualized on a dashboard and displayed in the form of maps and graphs. If certain conditions are met, an alert email is sent. In addition, based on the results of the emotion analysis, the information provided is adjusted to match the user's emotional state, providing optimal content.

[0861] Information sharing

[0862] The server provides a platform for sharing information with the general public and educational institutions. Devices (PCs and smartphones of the general public and educational institutions) can access the web portal to view analysis results and reports. They can also download necessary data and obtain detailed information. Users can use publicly available educational resources to learn about environmental protection. Personalized content is also provided based on the user's emotional state. A feedback function allows users to suggest improvements to the system and new functions.

[0863] Examples and prompts:

[0864] When a user inputs a prompt such as "Tell me the types of birds you have observed in the mountains," the server first processes the data obtained from the camera and audio sensors. Then, based on the preprocessed image data, it applies a deep learning model to identify the bird species. The analysis results are then visualized on a dashboard for the user to access. Finally, it uses sentiment analysis to recognize that the user is excited, and provides detailed information and additional observation points according to that excitement. Specifically, the following prompt is used:

[0865] Prompt: "What types of birds have you seen in the mountains?"

[0866] By working in conjunction with an emotion engine, this system provides personalized information tailored to the user's emotional state, making a significant contribution to improving environmental awareness and supporting education.

[0867] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0868] Step 1: Data collection

[0869] The server collects data from multiple cameras, audio sensors, and a weather database. Input data includes image data, audio data, and weather information. Specifically, it uses cameras installed outdoors to obtain image data of birds and animals, and audio sensors to receive recorded calls and environmental sounds. It also uses a weather data API to obtain the latest weather information. As output, this data is aggregated on the server.

[0870] Step 2: Preprocessing the data

[0871] The server preprocesses the collected data. The input data are the image data, audio data, and weather information collected in step 1. Specific operations include contrast correction and noise reduction filter application to the image data using the OpenCV library, noise reduction to the audio data using the Librosa library, normalization of the weather data, and completion of missing data. The output is preprocessed image data, audio data, and normalized weather data.

[0872] Step 3: Data analysis

[0873] The server analyzes the preprocessed data by applying machine learning algorithms and deep learning models. The input data is the image data, audio data, and weather information preprocessed in step 2. Specifically, a deep learning model trained using TensorFlow or PyTorch is applied to the image data to identify specific types of plants and animals. The audio data is converted into a spectrogram, and the features needed to identify the type and number of whales are extracted. The weather data is used to detect abnormal weather patterns and evaluate their impact. The analysis results are obtained as output.

[0874] Step 4: Sentiment Analysis

[0875] The server uses an emotion engine to recognize the user's emotions. The input data is the user's real-time facial recognition data and voice data. Specifically, it uses facial recognition software and voice tone analysis tools to identify the user's emotional state (e.g., joy, anxiety, surprise) from their facial expressions and voice tone. The output is the user's emotional state.

[0876] Step 5: Data reporting and information provision

[0877] The server reports the analysis results to the relevant parties. The input data are the analysis results from step 3 and the sentiment analysis results from step 4. Specific operations include visualizing the analysis results on a dashboard and displaying them in the form of maps and graphs. Additionally, an alert email is sent when certain conditions are met. The visualized analysis results and the sent alert are obtained as outputs.

[0878] Step 6: Information sharing

[0879] Terminals (PCs or smartphones of the general public or educational institutions) access the platform provided by the server to view analysis results and reports. The input data are the analysis results visualized in step 5. Users can download the necessary data from the web portal and obtain more detailed information. They can also use publicly available educational resources to learn about environmental protection. They can also suggest improvements to the system or new functions through the feedback function. The output includes the data used, educational resources, and submitted feedback.

[0880] An example of a specific prompt: "Tell me what kinds of birds you saw in the mountains."

[0881] In this way, this system has a consistent process from data collection to analysis and provision of information based on the user's emotional state, thereby providing advanced information tailored to the user's needs.

[0882] (Application example 2)

[0883] 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."

[0884] Conventional systems have had difficulty providing information according to a user's emotions, making it difficult to realize personalized services. This has prevented users from improving their satisfaction and engagement. The present invention aims to solve these problems by providing a system that recognizes a user's emotions and adjusts the information provided based on those emotions.

[0885] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, a means for analyzing a user's emotions using an emotion engine, a means for adjusting information to be provided based on the emotion analysis, a data reporting means, and an information sharing means. This makes it possible to provide personalized information according to the user's emotional state.

[0886] "Data collection means" refers to a device or method for collecting data in real time from multiple sensors.

[0887] "Preprocessing means" refers to devices or methods that normalize collected data, remove noise, and otherwise prepare the data in a form that is easier to analyze.

[0888] "Data analysis means" refers to devices or methods that use machine learning algorithms or deep learning models to analyze data and extract useful information.

[0889] "Means for analyzing a user's emotions using an emotion engine" refers to a device or method that utilizes an emotion engine to identify and assess a user's emotional state in real time.

[0890] "Means for adjusting provided information based on emotion analysis" refers to a device or method for personalizing and adjusting provided information or content based on the user's emotion data.

[0891] "Data reporting means" refers to devices or methods for visualizing analysis results as dashboards or reports and sharing them with stakeholders.

[0892] "Information sharing means" refers to devices and methods for sharing analysis results and useful information with the general public, educational institutions, and other stakeholders.

[0893] The present invention provides a system for analyzing user emotions and providing personalized information based on the analyzed emotions. The system includes a data collection unit, a preprocessing unit, a data analysis unit, an emotion engine, a unit for adjusting information provided based on the emotion analysis, a data reporting unit, and an information sharing unit.

[0894] First, the server collects data in real time from multiple sensors such as cameras and microphones through data collection means, including the user's facial expressions, voice tone, and other vital data.

[0895] The preprocessing means performs noise reduction and normalization on the collected data to prepare it for analysis. For example, this includes normalizing facial expression data and denoising voice data.

[0896] The data analysis means then uses machine learning algorithms and deep learning models to analyze the pre-processed data and identify the user's emotions. An emotion engine is used to analyze the user's emotional state (e.g., joy, anxiety, surprise, etc.).

[0897] The information provision adjustment means based on emotion analysis personalizes the information provided according to the user's emotional state. For example, if the user is smiling, it suggests products that may be needed for relaxation, and if the user is feeling stressed, it recommends stress relief products.

[0898] The data reporting tool allows analysis results to be visualized in the form of dashboards and reports, which can be shared with stakeholders. It is also possible to send alerts based on specific conditions.

[0899] Analysis results and reports are provided to general users and educational institutions through information sharing channels, allowing users to easily access interesting products and content and provide feedback.

[0900] With the above functions, the present invention can provide personalized information according to the user's emotional state, thereby improving customer satisfaction and engagement.

[0901] For example, a smartphone or smart glasses can be used to scan the user's facial expression and suggest relaxation items to smiling users. Also, if a user's voice tone indicates that they are feeling stressed, relaxation music or stress relief goods can be recommended.

[0902] Example prompt sentence:

[0903] "What products do you recommend when a user smiles?"

[0904] "What content should I recommend if the user has a calm voice tone?"

[0905] "Recommend optimal products based on user emotional data and purchase history."

[0906] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0907] Step 1: Data collection

[0908] The server collects real-time data from cameras, microphones, and other sensors, such as the user's facial expression data, voice tone, and heart rate. The input data is the user's real-time sensor information, and the output is the collected raw data, which is used in the next pre-processing step.

[0909] Step 2: Data Preprocessing

[0910] The server performs noise removal and normalization on the collected data. The input is the raw data collected in step 1, and the output is clean, normalized data with noise removed. Specifically, it normalizes facial expression data and removes noise from voice data to prepare it for analysis.

[0911] Step 3: Data analysis

[0912] The server uses the preprocessed data to run machine learning algorithms or deep learning models to identify the user's emotions. The input data is denoised and normalized data, and the output is the user's emotional state (e.g., joy, anxiety, surprise). As a specific example, a deep learning model is used to classify emotions from the user's facial expressions.

[0913] Step 4: Analysis by Emotion Engine

[0914] The server uses an emotion engine to analyze the user's emotions. The input data is the user's emotional state obtained in step 3, and the output is a more precise emotion analysis result. Specifically, the server evaluates the user's emotional state in detail and quantifies the degree of joy or anxiety the user feels.

[0915] Step 5: Reporting data and personalizing information

[0916] The server personalizes the information it provides based on the analysis results of the emotion engine. The input data is the emotion analysis results obtained in step 4, and the output is a personalized list of recommended products and content. For example, if the user is smiling, it will recommend relaxation items, and if they are feeling stressed, it will recommend stress relief products.

[0917] Step 6: Information sharing

[0918] The server and device share the analysis results and recommendation list with the user and other relevant parties. The input data is the personalized information obtained in step 5, and the output is notifications and dashboard displays for the user. Specifically, the personalized product list is sent to the user via a web portal or email.

[0919] 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.

[0920] 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.

[0921] 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.

[0922] [Fourth embodiment]

[0923] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0924] 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.

[0925] 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).

[0926] 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.

[0927] 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.

[0928] 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).

[0929] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0930] 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.

[0931] 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.

[0932] 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.

[0933] 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.

[0934] 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.

[0935] 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."

[0936] The present invention is a system including a data collection means, a preprocessing means, a data analysis means, a data reporting means, and an information sharing means, and by collecting data in real time from multiple sensors, preprocessing, analyzing, reporting, and sharing this data, it is possible to quickly and accurately collect, analyze, and report environmental data. Below, the processing of a specific program for implementing the present invention is explained in natural language.

[0937] 1. Data Collection

[0938] The server collects data from cameras, audio sensors, weather data sources, etc. For example, it acquires image data of birds and animals from outdoor cameras, receives audio recordings from audio sensors, and obtains weather information from weather data APIs.

[0939] 2. Data Preprocessing

[0940] The server preprocesses the collected data, applying contrast correction and noise reduction filters to image data and noise reduction algorithms to audio data, as well as normalizing meteorological data and imputing missing values.

[0941] 3. Data Analysis

[0942] The server performs analysis based on the preprocessed data. For image data, it uses a deep learning object detection model to identify the type and number of animals, converts audio data into a spectrogram to extract features, and uses a machine learning model to identify whale species. It also detects abnormal weather patterns from weather data.

[0943] 4. Data reporting

[0944] The server reports the results of the analysis to environmental organizations and government agencies by visualizing the data on a dashboard and displaying it in graphs and maps. It also sends email alerts when certain conditions are detected. Monthly reports are also automatically generated and sent to relevant parties.

[0945] 5. Information Sharing

[0946] The server provides data to the general public and educational institutions through an information-sharing platform. Specifically, devices (PCs and smartphones) can access a web portal, view analysis results and reports, and download necessary data. Users can also use publicly available educational resources to learn about ecosystem conservation. They can also provide feedback and suggest improvements and new features to the system.

[0947] This system will support ecosystem conservation activities and enable the rapid and accurate collection, analysis, and reporting of environmental data. Furthermore, by sharing information with the general public and educational institutions, it will contribute to raising environmental awareness and supporting education.

[0948] The processing flow will be explained below.

[0949] Step 1: Collect data

[0950] The server collects data from multiple cameras, audio sensors, and a weather database. Specifically, it periodically acquires data sent from each sensor and stores it in the database.

[0951] The server periodically acquires image data from a camera installed outdoors.

[0952] The server periodically acquires audio data from audio sensors installed in the ocean.

[0953] The server uses a weather data API to obtain real-time weather information.

[0954] Step 2: Preprocessing the data

[0955] The server pre-processes the collected data, which includes noise removal, data normalization, and outlier detection.

[0956] The server applies contrast enhancement and noise reduction filters to the collected image data.

[0957] The server applies a noise reduction algorithm to the acquired audio data to obtain clean audio data.

[0958] The server normalizes the weather data and imputes missing values ​​appropriately.

[0959] Step 3: Analyze the data

[0960] The server performs analysis based on the preprocessed data, using machine learning algorithms and deep learning models to analyze the data.

[0961] The server applies deep learning models to the image data to identify specific animal or plant species.

[0962] The server converts the audio data into a spectrogram and extracts features to identify the type and number of whales.

[0963] The server detects abnormal weather patterns from the weather data and evaluates their impact.

[0964] Step 4: Report the data

[0965] The server reports the analysis results to stakeholders, including dashboard displays, alert notifications, and report generation.

[0966] The server visualizes the analysis results on a dashboard and displays them in the form of maps and graphs.

[0967] The server sends email alerts based on certain conditions (e.g., when the presence of an endangered species is confirmed).

[0968] The server automatically generates periodic reports and sends them to the relevant parties by email.

[0969] Step 5: Share information

[0970] The server provides a platform for sharing information for the general public and educational institutions.

[0971] Devices (PCs or smartphones owned by the general public or educational institutions) access the AI ​​Eco-Monitor Network's web portal to view analysis results and reports.

[0972] The terminal can download the necessary data and obtain detailed information.

[0973] Users can learn about environmental protection by using educational resources made publicly available on the platform.

[0974] Users can provide feedback and suggest improvements and new features to the system.

[0975] Example 1

[0976] 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."

[0977] In conventional environmental data collection and analysis systems, the process from data collection to reporting was extremely slow and sometimes lacked accuracy. Furthermore, data sharing with the general public and educational institutions was limited, resulting in insufficient contribution to raising environmental awareness and supporting education. Furthermore, the lack of a feedback function made it difficult to propose system improvements or new functions.

[0978] 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.

[0979] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, a data reporting means, and an information sharing means. This allows data to be collected in real time from multiple sensors and the collected data to be subjected to noise removal and normalization. Furthermore, by including a feedback function for visualizing and reporting the analyzed data and for suggesting system improvements and new functions, this enables rapid and accurate data collection, analysis, and reporting, and contributes to raising environmental awareness and supporting education through information sharing with the general public and educational institutions.

[0980] A "data collection means" is a device or mechanism for collecting data in real time from multiple sensors.

[0981] A "preprocessing means" is a device or mechanism for removing noise and normalizing data from collected data.

[0982] A "data analysis means" is a device or mechanism that performs analysis on pre-processed data.

[0983] "Data reporting means" refers to a device or mechanism for visualizing and reporting analytical results to relevant parties and organizations.

[0984] An "information sharing tool" is a device or mechanism for providing analysis results and related information to the public and educational institutions.

[0985] "Denoising" is the process of removing unnecessary information or noise from data.

[0986] "Data normalization" is the process of scaling and standardizing data to reduce variability and make it consistent.

[0987] "Visualization" is the process of transforming data into something visible, such as a graph, chart, or map.

[0988] The "feedback function" is a mechanism for collecting opinions and requests from users and reflecting them in improving the system and developing new functions.

[0989] The present invention is a system that includes a data collection means, a preprocessing means, a data analysis means, a data reporting means, and an information sharing means. The system aims to quickly and accurately collect, analyze, and report environmental data, and to share this information with the general public and educational institutions. Specific embodiments for implementing the present invention are described below.

[0990] 1. Data Collection Methods

[0991] The server collects data in real time from multiple sensors, including cameras, audio sensors, and weather data sources. For example, it acquires image data of birds and animals from outdoor cameras, receives audio recordings from audio sensors, and obtains weather information from a weather data API.

[0992] 2. Pretreatment Methods

[0993] The server preprocesses the collected data. For image data, contrast correction and noise reduction filters are applied using OpenCV, and for audio data, noise reduction algorithms are applied using Audacity or Apache Commons Math. For weather data, the Pandas library is used to normalize and impute missing values.

[0994] 3. Data Analysis Methods

[0995] The server performs analysis based on the preprocessed data. It uses TensorFlow to perform object detection on image data using a deep learning model to identify the type and number of animals. It converts audio data into spectrograms and uses a machine learning model to identify whale species. It uses SciPy to detect abnormal weather patterns from weather data.

[0996] 4. Data reporting methods

[0997] The server reports the analysis results to environmental organizations and government agencies. It uses Dash and Plotly to visualize the data on a dashboard, displaying it in graphs and maps. It also uses an SMTP server to send alert emails when certain conditions are detected. Monthly reports are automatically generated using LaTeX and sent to relevant parties in PDF format.

[0998] 5. Information sharing method

[0999] Devices (PCs and smartphones) can access a web portal to view analysis results and reports and download necessary data. Specifically, users can access data through a web portal developed with Django and Flask. Users can also learn about ecosystem conservation using publicly available educational resources, provide feedback, and suggest system improvements and new features.

[1000] This system will support ecosystem conservation activities and enable the rapid and accurate collection, analysis, and reporting of environmental data. Furthermore, by sharing information with the general public and educational institutions, it will contribute to raising environmental awareness and supporting education.

[1001] Examples of prompt statements

[1002] "Consider a Python program that uses image data from field cameras and audio recordings from audio sensors to analyze the current state of an ecosystem."

[1003] "Detail the data processing and analysis procedures used to collect weather data and detect unusual weather patterns."

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

[1005] Step 1:

[1006] Data collection

[1007] The server collects data from multiple sensors in real time.

[1008] Inputs: Signals from cameras, audio sensors, weather data sources, etc.

[1009] Data processing: saving image data from cameras, collecting audio data from audio sensors, and obtaining data from weather data APIs

[1010] Output: Collected image data, audio data, and meteorological data

[1011] Specific operations: The camera periodically takes still images and sends them to the server. The audio sensor records audio at specified intervals and uploads the data to the server. Weather information is obtained from the weather data source using an API and stored on the server.

[1012] Step 2:

[1013] Data Preprocessing

[1014] The server pre-processes the collected data.

[1015] Input: Collected image data, audio data, and meteorological data

[1016] Data processing: Apply contrast correction and noise reduction filters to image data, apply noise reduction algorithms to audio data, normalize weather data and fill missing values

[1017] Output: Preprocessed image data, audio data, and weather data

[1018] What it does: It uses OpenCV to correct image contrast and a Gaussian filter to remove noise. For audio data, it uses signal processing tools to reduce background noise and make the audio clearer. For weather data, it normalizes the data frame and fills in missing values.

[1019] Step 3:

[1020] Data analysis

[1021] The server performs analysis based on the preprocessed data.

[1022] Input: Preprocessed image data, audio data, and meteorological data

[1023] Data processing: object detection from image data, feature extraction from audio data, and abnormal weather pattern detection from meteorological data

[1024] Output: Analysis results (species and numbers of animals, whale species, details of abnormal weather)

[1025] What it does: (TensorFlow) Uses deep learning models to detect and classify animals in images; converts audio data into spectrograms to extract features and uses machine learning models to estimate whale species; analyzes weather data for unusual weather patterns and detects anomalies.

[1026] Step 4:

[1027] Data reporting

[1028] The server reports the analysis results to the relevant organizations.

[1029] Input: Analysis results

[1030] Data manipulation: Visualize on dashboards, display in graphs and maps, send alerts, automatically generate reports

[1031] Output: Visualized data, alert emails, monthly reports (PDF format)

[1032] Specific tasks: Use Dash and Plotly to display analysis results in graphs and maps and create a dashboard that can be viewed by stakeholders. Use an SMTP server to send alert emails when certain conditions are met. Automatically generate monthly reports using LaTeX and send them to stakeholders in PDF format.

[1033] Step 5:

[1034] Information Sharing

[1035] The device allows the analysis results to be viewed through a web portal.

[1036] Input: Analysis results, reports, educational resources

[1037] Data processing: building a web portal, providing data, receiving feedback

[1038] Output: Displaying analysis results, downloading required data, and collecting feedback

[1039] What it does: Build a web portal using Django and Flask to allow users to easily view analysis results and reports. Users can use educational resources to learn more about ecosystem conservation and submit suggestions for improvements and requests for new features to the system through a feedback form.

[1040] This will improve the efficiency and accuracy of the entire system and enable a consistent flow of environmental data collection, analysis, reporting, and information sharing.

[1041] (Application example 1)

[1042] 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."

[1043] In conventional logistics systems, the collection, pre-processing, analysis, and reporting of data from each sensor were not integrated, resulting in inefficient inventory management, temperature monitoring, and weight analysis. This resulted in delayed detection of inventory shortages and abnormal weather, hindering operational efficiency.

[1044] 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.

[1045] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, a data reporting means, an information sharing means, an inventory management means, a temperature monitoring means, a weight analysis means, and an image processing means. This enables real-time monitoring of inventory and anomaly detection at the logistics center, enabling efficient business operations. In addition, the collected data is noise-removed and normalized to obtain highly reliable analysis results, enabling prompt and accurate information provision to managers and related parties.

[1046] "Data collection means" refers to a means for collecting necessary data in real time from multiple sensors.

[1047] "Preprocessing means" refers to means for removing noise and normalizing data in order to prepare collected data in a form that is easier to analyze.

[1048] "Data analysis means" refers to means for performing analysis according to a specific purpose based on preprocessed data.

[1049] "Data reporting means" refers to the means for reporting analysis results to users and related organizations.

[1050] "Information sharing means" refers to the means for sharing analysis results and related data among stakeholders.

[1051] "Inventory management means" refers to means for monitoring the inventory status at the logistics center in real time and detecting abnormalities.

[1052] "Temperature monitoring means" refers to a means for monitoring the temperature of the storage environment in real time and maintaining appropriate storage conditions.

[1053] The "weight analysis means" is a means for analyzing the weight data of each product and performing appropriate inventory management.

[1054] The "image processing means" is a means for preprocessing image data acquired from a camera and extracting necessary information.

[1055] This invention is a system for improving the efficiency of inventory management in a logistics center. The server collects data in real time from multiple sensors and includes various means for preprocessing, analyzing, reporting, and sharing information. Specifically, this system is configured as follows:

[1056] Data collection

[1057] The server collects data from weight sensors, temperature sensors, cameras, etc. The data collected includes weight data for incoming and outgoing products, temperature data for storage areas, and image data for products. This allows for a real-time understanding of all movements within the logistics center. Product location information can also be obtained using RFID tags and barcode scanners.

[1058] Data Preprocessing

[1059] The server performs noise reduction and normalization on the collected data. For example, weight data is normalized, and temperature data is also normalized. Contrast correction and noise reduction filters are applied to the image data. This allows for faster and more accurate data analysis later.

[1060] Data analysis

[1061] The server detects inventory anomalies based on the pre-processed data. A deep learning algorithm using a generative AI model is applied for analysis, identifying products from image data. Temperature data is used to detect abnormalities in the storage environment, and appropriate countermeasures are implemented. Weight data is analyzed for abnormal fluctuations, preventing shortages and overstocks.

[1062] Data reporting

[1063] The server reports the analysis results to administrators and business personnel by visualizing real-time data on a dashboard, sending alert emails, and automatically generating monthly reports, allowing relevant parties to take action based on prompt and accurate information.

[1064] Information Sharing

[1065] The server shares analysis results and related data with relevant parties through an information-sharing platform. For example, administrators and business personnel can check information in real time through a web portal. Users can also use the system's feedback function to suggest improvements and new functions.

[1066] Specific examples

[1067] For example, in an inventory management system, the server could instruct a generative AI model using the following prompt sentence:

[1068] "I'm thinking of designing an application that will collect data using weight sensors, temperature sensors, and cameras, and then preprocess, analyze, report, and share the information in order to improve the efficiency of inventory management at distribution centers. I'd like to make this available on smartphones, so please write a specific program for me."

[1069] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1070] Step 1:

[1071] The server collects data in real time from weight sensors, temperature sensors, and cameras. Product weight data is input from the weight sensor, storage area temperature data from the temperature sensor, and product image data from the camera. This allows environmental information within the logistics center to be collected in one place.

[1072] Step 2:

[1073] The server preprocesses the collected data. Specifically, it removes noise and normalizes the weight and temperature data, and applies contrast correction and a noise removal filter to the image data. This preprocessing improves the reliability of the data and increases the accuracy of the analysis. The input is the raw weight data, temperature data, and image data, and the output is the preprocessed data.

[1074] Step 3:

[1075] The server performs data analysis based on the preprocessed data. It applies a deep learning algorithm using a generative AI model to process the image data to identify products. It also detects abnormalities in the storage environment from temperature data and analyzes inventory abnormalities from weight data. This allows for real-time detection of inventory abnormalities. The input is the preprocessed data, and the output is the analysis results.

[1076] Step 4:

[1077] The server reports data based on the analysis results. It updates the dashboard and visualizes inventory status in real time. It also sends alert emails to relevant parties when certain conditions occur and automatically generates and sends monthly reports. This allows relevant parties to quickly obtain the information they need. The input is the data analysis results, and the output is visualized data and reports.

[1078] Step 5:

[1079] The server shares data with relevant parties through an information-sharing platform. Managers and business personnel can access a web portal and check information in real time. The system also has a function that allows users to provide feedback, collecting requests for system improvements and suggestions for new functions. This enables continuous improvement of the system. The inputs are analysis results and feedback, and the outputs are shared information and improvement suggestions.

[1080] 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.

[1081] The present invention includes a system including a data collection means, a preprocessing means, a data analysis means, a data reporting means, and an information sharing means, as well as an emotion engine that can recognize a user's emotion and adjust the information provided based on that emotion. Below, the processing of a specific program for implementing the present invention will be described in natural language.

[1082] 1. Data Collection

[1083] The server collects data from multiple cameras, audio sensors, and a weather database, for example, capturing bird and animal image data from outdoor cameras, receiving audio recordings from audio sensors, and retrieving weather information from a weather data API.

[1084] 2. Data Preprocessing

[1085] The server pre-processes the collected data, which includes noise removal, data normalization, and outlier detection.

[1086] The server applies contrast enhancement and noise reduction filters to the collected image data.

[1087] The server applies a noise reduction algorithm to the acquired audio data to obtain clean audio data.

[1088] The server normalizes the weather data and imputes missing values ​​appropriately.

[1089] 3. Data Analysis

[1090] The server performs analysis based on the preprocessed data, using machine learning algorithms and deep learning models to analyze the data.

[1091] The server applies deep learning models to the image data to identify specific animal or plant species.

[1092] The server converts the audio data into a spectrogram and extracts features to identify the type and number of whales.

[1093] The server detects abnormal weather patterns from the weather data and evaluates their impact.

[1094] 4. Analysis by Emotion Engine

[1095] The server recognizes the user's emotions using an emotion engine, which analyzes the user's usage patterns, input data, and real-time sensor information to identify emotions.

[1096] The server may, for example, utilize facial recognition software or voice tone analysis tools to identify the user's emotional state (happiness, anxiety, surprise, etc.).

[1097] 5. Data reporting and personalization of information

[1098] The server reports the analysis results to stakeholders, including dashboard displays, alert notifications, and report generation.

[1099] The server visualizes the analysis results on a dashboard, displaying them in the form of maps and graphs, and also sends email alerts based on specific conditions (e.g., if an endangered species is detected).

[1100] The server automatically generates periodic reports and sends them to the relevant parties by email.

[1101] Based on the analysis results of the emotion engine, the server adjusts the information provided to suit the user's emotional state and provides optimal content.

[1102] 6. Information sharing

[1103] The server provides a platform for sharing information for the general public and educational institutions.

[1104] Devices (PCs or smartphones owned by the general public or educational institutions) access the AI ​​Eco-Monitor Network's web portal to view analysis results and reports.

[1105] The terminal can download the necessary data and obtain detailed information.

[1106] Users can learn about environmental protection through educational resources published on the platform, and the content is personalized based on the user's emotional state.

[1107] Users can provide feedback and suggest improvements and new features to the system.

[1108] By combining this system with an emotion engine, it is possible to provide personalized information tailored to the user's emotional state, making a significant contribution to raising environmental awareness and supporting education.

[1109] The processing flow will be explained below.

[1110] Step 1: Collect data

[1111] The server collects data from multiple cameras, audio sensors, and a weather database. Specifically, it periodically acquires data sent from each sensor and stores it in the database.

[1112] The server periodically acquires image data from a camera installed outdoors.

[1113] The server periodically acquires audio data from audio sensors installed in the ocean.

[1114] The server uses a weather data API to obtain real-time weather information.

[1115] Step 2: Preprocessing the data

[1116] The server pre-processes the collected data, which includes noise removal, data normalization, and outlier detection.

[1117] The server applies contrast enhancement and noise reduction filters to the collected image data.

[1118] The server applies a noise reduction algorithm to the acquired audio data to obtain clean audio data.

[1119] The server normalizes the weather data and imputes missing values ​​appropriately.

[1120] Step 3: Analyze the data

[1121] The server performs analysis based on the preprocessed data, using machine learning algorithms and deep learning models to analyze the data.

[1122] The server applies deep learning models to the image data to identify specific animal or plant species.

[1123] The server converts the audio data into a spectrogram and extracts features to identify the type and number of whales.

[1124] The server detects abnormal weather patterns from the weather data and evaluates their impact.

[1125] Step 4: Analysis by the Emotion Engine

[1126] The server recognizes the user's emotions using an emotion engine, which analyzes the user's usage patterns, input data, and real-time sensor information to identify emotions.

[1127] The server collects, for example, camera data to recognize the user's face and audio data to analyze the user's voice.

[1128] The server uses facial recognition software to analyze facial expressions and determine whether the user is happy or sad.

[1129] The server analyzes the tone of the voice using a voice tone analysis tool to determine whether the user is excited or relaxed.

[1130] Step 5: Reporting data and personalizing information

[1131] The server reports the results of the analysis to stakeholders, including dashboard displays, alert notifications, and report generation, and tailors the information provided to the user's emotional state based on the analysis results of the emotion engine.

[1132] The server visualizes the analysis results on a dashboard and displays them in the form of maps and graphs.

[1133] The server sends email alerts based on certain conditions (e.g., when the presence of an endangered species is confirmed).

[1134] The server automatically generates periodic reports and sends them to the relevant parties by email.

[1135] The server personalizes educational content or environmental information based on the user's emotional state: for example, if the user is excited, it will show simple infographics rather than detailed technical information.

[1136] Step 6: Information sharing

[1137] The server provides a platform for sharing information for the general public and educational institutions.

[1138] Devices (PCs or smartphones owned by the general public or educational institutions) access the AI ​​Eco-Monitor Network's web portal to view analysis results and reports.

[1139] The terminal can download the necessary data and obtain detailed information.

[1140] Users can learn about environmental protection through educational resources published on the platform, and the content is personalized based on the user's emotional state.

[1141] Users can provide feedback and suggest improvements and new features to the system.

[1142] Example 2

[1143] 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."

[1144] Conventional data collection and analysis systems provide information without considering the user's emotional state. This creates a gap between the content users want and the information they receive, resulting in problems such as insufficient environmental awareness and educational support. Furthermore, the quality and reliability of the collected data are often insufficient.

[1145] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, a sentiment analysis means, a data reporting means, and an information provision means. This makes it possible to provide information tailored to the emotional state of the user, which greatly contributes to improving environmental awareness and supporting education. Furthermore, by improving the quality and reliability of the data, more accurate analysis results can be obtained.

[1146] A "data collection means" is a combination of hardware and software for collecting necessary information in real time from multiple sensors and databases.

[1147] "Preprocessing means" is a function that performs processes such as noise removal, data normalization, and outlier detection on collected data to improve the quality of analysis.

[1148] A "data analysis tool" is a system that uses machine learning algorithms or deep learning models to analyze data based on pre-processed data and identify specific patterns or features.

[1149] The "emotion analysis means" is a system for identifying the user's emotional state through facial recognition, voice tone analysis, etc., and adjusting the information provided based on that.

[1150] "Data reporting means" is a function for providing information by means of dashboard display, alert notification, report generation, etc. in order to report the results of data analysis to relevant parties.

[1151] "Information provision means" refers to a platform for providing analysis results and related information to the general public and educational institutions, making them accessible.

[1152] The present invention provides a system including a data collection means, a pre-processing means, a data analysis means, a sentiment analysis means, a data reporting means, and an information providing means, the system being capable of recognizing a user's sentiment state and adjusting the information provided based on the sentiment state.

[1153] Data collection

[1154] The server collects data from multiple cameras, audio sensors, and a weather database. For example, it uses outdoor cameras to capture image data of birds and animals, audio sensors to receive recorded calls and environmental sounds, and weather data APIs to obtain the latest weather information.

[1155] Pretreatment

[1156] The server preprocesses the collected data, which includes applying contrast correction and noise reduction filters to image data using the OpenCV library, denoising audio data using the Librosa library, normalizing meteorological data, and imputing missing data.

[1157] Data analysis

[1158] The server then applies machine learning algorithms and deep learning models to the preprocessed data and analyzes it. For example, a deep learning model trained with TensorFlow or PyTorch can be applied to image data to identify specific plant or animal species. Audio data can be converted into spectrograms to extract the features needed to identify whale species and numbers. Weather data can be used to detect abnormal weather patterns and assess their impact.

[1159] Emotion analysis

[1160] The server recognizes the user's emotions using an emotion engine that uses facial recognition software and voice analysis tools to perform real-time facial recognition and voice tone analysis of the user and identify the user's emotional state (e.g., joy, anxiety, surprise).

[1161] Data reporting and information provision

[1162] The server reports the analysis results to relevant parties. The analysis results are visualized on a dashboard and displayed in the form of maps and graphs. If certain conditions are met, an alert email is sent. In addition, based on the results of the emotion analysis, the information provided is adjusted to match the user's emotional state, providing optimal content.

[1163] Information sharing

[1164] The server provides a platform for sharing information with the general public and educational institutions. Devices (PCs and smartphones of the general public and educational institutions) can access the web portal to view analysis results and reports. They can also download necessary data and obtain detailed information. Users can use publicly available educational resources to learn about environmental protection. Personalized content is also provided based on the user's emotional state. A feedback function allows users to suggest improvements to the system and new functions.

[1165] Examples and prompts:

[1166] When a user inputs a prompt such as "Tell me the types of birds you have observed in the mountains," the server first processes the data obtained from the camera and audio sensors. Then, based on the preprocessed image data, it applies a deep learning model to identify the bird species. The analysis results are then visualized on a dashboard for the user to access. Finally, it uses sentiment analysis to recognize that the user is excited, and provides detailed information and additional observation points according to that excitement. Specifically, the following prompt is used:

[1167] Prompt: "What types of birds have you seen in the mountains?"

[1168] By working in conjunction with an emotion engine, this system provides personalized information tailored to the user's emotional state, making a significant contribution to improving environmental awareness and supporting education.

[1169] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1170] Step 1: Data collection

[1171] The server collects data from multiple cameras, audio sensors, and a weather database. Input data includes image data, audio data, and weather information. Specifically, it uses cameras installed outdoors to obtain image data of birds and animals, and audio sensors to receive recorded calls and environmental sounds. It also uses a weather data API to obtain the latest weather information. As output, this data is aggregated on the server.

[1172] Step 2: Preprocessing the data

[1173] The server preprocesses the collected data. The input data are the image data, audio data, and weather information collected in step 1. Specific operations include contrast correction and noise reduction filter application to the image data using the OpenCV library, noise reduction to the audio data using the Librosa library, normalization of the weather data, and completion of missing data. The output is preprocessed image data, audio data, and normalized weather data.

[1174] Step 3: Data analysis

[1175] The server analyzes the preprocessed data by applying machine learning algorithms and deep learning models. The input data is the image data, audio data, and weather information preprocessed in step 2. Specifically, a deep learning model trained using TensorFlow or PyTorch is applied to the image data to identify specific types of plants and animals. The audio data is converted into a spectrogram, and the features needed to identify the type and number of whales are extracted. The weather data is used to detect abnormal weather patterns and evaluate their impact. The analysis results are obtained as output.

[1176] Step 4: Sentiment Analysis

[1177] The server uses an emotion engine to recognize the user's emotions. The input data is the user's real-time facial recognition data and voice data. Specifically, it uses facial recognition software and voice tone analysis tools to identify the user's emotional state (e.g., joy, anxiety, surprise) from their facial expressions and voice tone. The output is the user's emotional state.

[1178] Step 5: Data reporting and information provision

[1179] The server reports the analysis results to the relevant parties. The input data are the analysis results from step 3 and the sentiment analysis results from step 4. Specific operations include visualizing the analysis results on a dashboard and displaying them in the form of maps and graphs. Additionally, an alert email is sent when certain conditions are met. The visualized analysis results and the sent alert are obtained as outputs.

[1180] Step 6: Information sharing

[1181] Terminals (PCs or smartphones of the general public or educational institutions) access the platform provided by the server to view analysis results and reports. The input data are the analysis results visualized in step 5. Users can download the necessary data from the web portal and obtain more detailed information. They can also use publicly available educational resources to learn about environmental protection. They can also suggest improvements to the system or new functions through the feedback function. The output includes the data used, educational resources, and submitted feedback.

[1182] An example of a specific prompt: "Tell me what kinds of birds you saw in the mountains."

[1183] In this way, this system has a consistent process from data collection to analysis and provision of information based on the user's emotional state, thereby providing advanced information tailored to the user's needs.

[1184] (Application example 2)

[1185] 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."

[1186] Conventional systems have had difficulty providing information according to a user's emotions, making it difficult to realize personalized services. This has prevented users from improving their satisfaction and engagement. The present invention aims to solve these problems by providing a system that recognizes a user's emotions and adjusts the information provided based on those emotions.

[1187] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, a means for analyzing a user's emotions using an emotion engine, a means for adjusting information to be provided based on the emotion analysis, a data reporting means, and an information sharing means. This makes it possible to provide personalized information according to the user's emotional state.

[1188] "Data collection means" refers to a device or method for collecting data in real time from multiple sensors.

[1189] "Preprocessing means" refers to devices or methods that normalize collected data, remove noise, and otherwise prepare the data in a form that is easier to analyze.

[1190] "Data analysis means" refers to devices or methods that use machine learning algorithms or deep learning models to analyze data and extract useful information.

[1191] "Means for analyzing a user's emotions using an emotion engine" refers to a device or method that utilizes an emotion engine to identify and assess a user's emotional state in real time.

[1192] "Means for adjusting provided information based on emotion analysis" refers to a device or method for personalizing and adjusting provided information or content based on the user's emotion data.

[1193] "Data reporting means" refers to devices or methods for visualizing analysis results as dashboards or reports and sharing them with stakeholders.

[1194] "Information sharing means" refers to devices and methods for sharing analysis results and useful information with the general public, educational institutions, and other stakeholders.

[1195] The present invention provides a system for analyzing user emotions and providing personalized information based on the analyzed emotions. The system includes a data collection unit, a preprocessing unit, a data analysis unit, an emotion engine, a unit for adjusting information provided based on the emotion analysis, a data reporting unit, and an information sharing unit.

[1196] First, the server collects data in real time from multiple sensors such as cameras and microphones through data collection means, including the user's facial expressions, voice tone, and other vital data.

[1197] The preprocessing means denoises and normalizes the collected data to prepare it for analysis, for example, by normalizing facial expression data and denoising voice data.

[1198] The data analysis means then uses machine learning algorithms and deep learning models to analyze the pre-processed data and identify the user's emotions. An emotion engine is used to analyze the user's emotional state (e.g., joy, anxiety, surprise, etc.).

[1199] The information provision adjustment means based on emotion analysis personalizes the information provided according to the user's emotional state. For example, if the user is smiling, it suggests products that may be needed for relaxation, and if the user is feeling stressed, it recommends stress relief products.

[1200] The data reporting tool allows analysis results to be visualized in the form of dashboards and reports, which can be shared with stakeholders. It also allows alert notifications to be sent based on specific conditions.

[1201] Analysis results and reports are provided to general users and educational institutions through information sharing channels, allowing users to easily access interesting products and content and provide feedback.

[1202] With the above functions, the present invention can provide personalized information according to the user's emotional state, thereby improving customer satisfaction and engagement.

[1203] For example, a smartphone or smart glasses can be used to scan the user's facial expression and suggest relaxation items to smiling users. Also, if a user's voice tone indicates that they are feeling stressed, relaxation music or stress relief goods can be recommended.

[1204] Example prompt sentence:

[1205] "What products do you recommend when a user smiles?"

[1206] "What content should I recommend if the user has a calm voice tone?"

[1207] "Recommend optimal products based on user emotional data and purchase history."

[1208] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1209] Step 1: Data collection

[1210] The server collects real-time data from cameras, microphones, and other sensors, such as the user's facial expression data, voice tone, and heart rate. The input data is the user's real-time sensor information, and the output is the collected raw data, which is used in the next pre-processing step.

[1211] Step 2: Data Preprocessing

[1212] The server performs noise removal and normalization on the collected data. The input is the raw data collected in step 1, and the output is clean, normalized data with noise removed. Specifically, it normalizes facial expression data and removes noise from voice data to prepare it for analysis.

[1213] Step 3: Data analysis

[1214] The server uses the preprocessed data to run machine learning algorithms or deep learning models to identify the user's emotions. The input data is denoised and normalized data, and the output is the user's emotional state (e.g., joy, anxiety, surprise). As a specific example, a deep learning model is used to classify emotions from the user's facial expressions.

[1215] Step 4: Analysis by the Emotion Engine

[1216] The server uses an emotion engine to analyze the user's emotions. The input data is the user's emotional state obtained in step 3, and the output is a more precise emotion analysis result. Specifically, the server evaluates the user's emotional state in detail and quantifies the degree of joy or anxiety the user feels.

[1217] Step 5: Reporting data and personalizing information

[1218] The server personalizes the information it provides based on the analysis results of the emotion engine. The input data is the emotion analysis results obtained in step 4, and the output is a personalized list of recommended products and content. For example, if the user is smiling, it will recommend relaxation items, and if they are feeling stressed, it will recommend stress relief products.

[1219] Step 6: Information sharing

[1220] The server and device share the analysis results and recommendation list with the user and other relevant parties. The input data is the personalized information obtained in step 5, and the output is notifications and dashboard displays for the user. Specifically, the personalized product list is sent to the user via a web portal or email.

[1221] 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.

[1222] 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.

[1223] 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.

[1224] 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.

[1225] 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.

[1226] 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.

[1227] 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).

[1228] 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.

[1229] 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."

[1230] 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.

[1231] 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).

[1232] 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.

[1233] 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.

[1234] 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.

[1235] 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.

[1236] 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.

[1237] 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.

[1238] 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.

[1239] 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.

[1240] 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.

[1241] 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.

[1242] The following is further disclosed regarding the above embodiment.

[1243] (Claim 1)

[1244] data collection means;

[1245] A pre-processing means;

[1246] data analysis means;

[1247] a data reporting means;

[1248] Information sharing means;

[1249] A system including:

[1250] (Claim 2)

[1251] 10. The system of claim 1, wherein the system collects data in real time from multiple sensors.

[1252] (Claim 3)

[1253] 10. The system of claim 1, wherein preprocessing of the collected data includes noise removal and data normalization.

[1254] "Example 1"

[1255] (Claim 1)

[1256] data collection means;

[1257] A pre-processing means;

[1258] data analysis means;

[1259] a data reporting means;

[1260] Information sharing means;

[1261] A system comprising:

[1262] Collecting data in real time from multiple sensors,

[1263] The collected data is denoised and normalised,

[1264] Visualize and report the analyzed data,

[1265] A feedback system that allows you to improve the system or suggest new features.

[1266] (Claim 2)

[1267] 2. The system of claim 1, wherein the preprocessing means applies a contrast enhancement and noise reduction filter to the image data and a noise reduction algorithm to the audio data.

[1268] (Claim 3)

[1269] 2. The system according to claim 1, wherein the information sharing means provides the analysis results to the general public and educational institutions through a web portal, and uses educational resources to learn about ecosystem protection.

[1270] "Application Example 1"

[1271] Rewriting of claims

[1272] (Claim 1)

[1273] data collection means;

[1274] A pre-processing means;

[1275] data analysis means;

[1276] a data reporting means;

[1277] Information sharing means;

[1278] Inventory control measures;

[1279] temperature monitoring means;

[1280] a weight analysis means;

[1281] image processing means;

[1282] A system including:

[1283] (Claim 2)

[1284] 10. The system of claim 1, wherein the system collects data in real time from multiple sensors.

[1285] (Claim 3)

[1286] The system according to claim 1, wherein the collected data is preprocessed by performing noise removal and data normalization to detect abnormalities in inventory status.

[1287] "Example 2: Combining Emotion Engines"

[1288] (Claim 1)

[1289] data collection means;

[1290] A pre-processing means;

[1291] data analysis means;

[1292] A sentiment analysis means;

[1293] a data reporting means;

[1294] Means of providing information;

[1295] A system including:

[1296] (Claim 2)

[1297] 10. The system of claim 1, wherein the system collects data in real time from multiple sensors.

[1298] (Claim 3)

[1299] 10. The system of claim 1, wherein preprocessing of the collected data includes noise removal and data normalization.

[1300] "Application example 2 when combining emotion engines"

[1301] (Claim 1)

[1302] data collection means;

[1303] A pre-processing means;

[1304] data analysis means;

[1305] means for analyzing a user's emotions using an emotion engine;

[1306] means for tailoring the information provided based on sentiment analysis;

[1307] a data reporting means;

[1308] Information sharing means;

[1309] A system including:

[1310] (Claim 2)

[1311] 10. The system of claim 1, wherein the system collects data in real time from multiple sensors and provides suggestions based on the user's emotional state.

[1312] (Claim 3)

[1313] The system of claim 1, wherein the collected data is preprocessed by noise removal and data normalization, and personalized information is provided based on the user's emotions. [Explanation of symbols]

[1314] 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. data collection means; A pre-processing means; data analysis means; a data reporting means; Information sharing means; A system including:

2. 10. The system of claim 1, wherein data is collected in real time from multiple sensors.

3. 10. The system of claim 1, wherein preprocessing of the collected data includes noise removal and data normalization.

Images