System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting maritime data; means for using artificial intelligence algorithms to analyze the collected maritime data; means for identifying pollution hot spots based on the analysis results; means for visualizing location information of the identified pollution hot spots on a map; and means for suggesting cleanup activities based on the identified hot spots.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] Marine pollution has become a serious problem in modern society, significantly impacting marine ecosystems and biodiversity. The widespread nature of pollution sources makes effective cleanup efforts particularly challenging. Furthermore, traditional manual data collection and analysis methods make it difficult to quickly and accurately identify pollution hotspots, preventing the development of efficient countermeasures. This calls for the development of methods to effectively utilize limited resources to remove pollution. [Means for solving the problem]

[0005] The present invention provides a system including a means for collecting oceanographic data, a means for using an artificial intelligence algorithm to analyze the collected oceanographic data, a means for identifying pollution hotspots based on the analysis results, a means for visualizing the locations of the identified pollution hotspots on a map, and a means for proposing cleanup activities based on the identified hotspots. In particular, by implementing a strategy that complies with international maritime law and local environmental regulations and by using at least one of vessels, satellites, and sensors to improve data accuracy, it is possible to effectively address marine pollution. This system enables rapid and accurate identification of pollution sources and efficient cleanup activities, thereby maximizing the use of limited resources and contributing to the conservation of the marine environment.

[0006] "Ocean data collection" refers to the acquisition of data using vessels, satellites, sensors, etc. to gather information about the marine environment.

[0007] An "artificial intelligence algorithm" is a method that uses machine learning and data analysis techniques to extract useful information from large amounts of data and find patterns and trends.

[0008] "Identifying pollution hotspots" refers to identifying areas with particularly high levels of pollution based on collected and analyzed data.

[0009] "Visualizing on a map" means showing the location information of identified contamination hotspots on a map so that users can visually confirm them.

[0010] "Proposing cleanup actions" means showing how to carry out efficient cleanup and remediation efforts for identified contamination hotspots.

[0011] "International maritime law" is a general term for international laws and rules governing conduct and activities at sea.

[0012] "Local environmental regulations" means the laws and regulations relating to environmental protection that apply in a particular locality.

[0013] A "vessel" is a vehicle used for travel or work on the sea.

[0014] A "satellite" is an artificial celestial body that orbits the Earth and collects data.

[0015] A "sensor" is a device that senses environmental information and acquires it as data. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention is a system that collects marine data and uses artificial intelligence algorithms to identify pollution hotspots, analyzes the collected data, visualizes the pollution hotspots on a map, and suggests cleanup actions.

[0038] Data collection

[0039] The server first collects oceanographic data. Specifically, it obtains the necessary data from oceanographic data providers via API. Providers collect marine environmental data using ships, satellites, sensors, etc. For example, to obtain marine pollution data for a certain period of time, the server sets the API endpoint and parameters, sends the request, and collects the data.

[0040] Data analysis

[0041] Next, the server uses artificial intelligence algorithms to analyze the collected oceanographic data. Specifically, it uses machine learning algorithms to analyze information such as latitude, longitude, and pollution levels. This analysis makes it possible to identify pollution hotspots. For example, by using K-means clustering, pollution clusters are formed based on the features of the data, and hotspots are identified.

[0042] visualization

[0043] The contamination hotspots obtained as a result of the analysis are visualized on a map by the device. The device initializes the map and displays the location information of the identified hotspots as markers on the map. This allows the user to visually grasp the contamination situation. The map is saved as an HTML file and can be displayed through a browser.

[0044] Clean-up activity proposals

[0045] The server generates specific cleanup activity recommendations based on the identified hotspots. The recommendations include countermeasures and actions to be taken for each hotspot, such as how to deploy cleanup crews to specific hotspots and their priorities. This allows users to efficiently and effectively address marine pollution.

[0046] Specific examples

[0047] For example, the server sends an API request to collect marine pollution data from January 1, 2023 to January 31, 2023. The acquired data is analyzed and five pollution hotspots are identified based on K-means clustering. The identified hotspots are then displayed on a map, and users can check their locations. Furthermore, the server suggests high-priority cleanup actions, allowing users to take specific measures based on the suggestions.

[0048] The system will use vessels, satellites and / or sensors to improve the accuracy of oceanographic data, employing strategies consistent with international maritime law and local environmental regulations, thereby enabling rapid and accurate identification of pollution sources and facilitating efficient cleanup efforts.

[0049] The processing flow will be explained below.

[0050] Step 1:

[0051] The server sets API endpoints and parameters for collecting oceanographic data, such as the collection range date and ocean area.

[0052] Step 2:

[0053] The server sends an API request with the configured parameters to retrieve data from the ocean data provider, verifies the response status code, and extracts the data from the response if successful.

[0054] Step 3:

[0055] The server extracts the necessary information for analysis (latitude, longitude, pollution level) from the acquired oceanographic data, and prepares for further analysis based on this data.

[0056] Step 4:

[0057] The server then inputs the extracted data into an artificial intelligence algorithm and performs data analysis using machine learning techniques, specifically K-means clustering, to identify contamination hotspots based on the data features.

[0058] Step 5:

[0059] The server sends the location information of the pollution hotspots obtained as a result of the analysis to the device, which receives it and initializes the map.

[0060] Step 6:

[0061] The device maps the locations of identified contamination hotspots on a map, placing markers for visual identification, and saves the map as an HTML file for later viewing through a browser.

[0062] Step 7:

[0063] The server generates cleanup action proposals based on the identified hotspots, including specific actions for each hotspot and their priority.

[0064] Step 8:

[0065] The user checks the cleanup activity suggestions provided by the server, determines which hotspots should be prioritized, and creates a specific cleanup plan.

[0066] Step 9:

[0067] The cleanup activities decided by the user are carried out and the results are monitored. This information is fed back to the server and used for future data analysis and cleanup activities.

[0068] Example 1

[0069] 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."

[0070] Conventional marine pollution monitoring systems lack a unified process for data collection, analysis, visualization, and countermeasure proposals, making it difficult to implement efficient pollution countermeasures. Furthermore, the accuracy of data collection and reliability of analysis are low, leading to insufficient identification of pollution hotspots and the proposal of cleanup activities based on those hotspots, making it difficult to implement effective pollution countermeasures. As a result, marine pollution problems worsen and environmental protection efforts are delayed.

[0071] 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.

[0072] In this invention, the server includes means for collecting oceanographic data, means for using an artificial intelligence algorithm to analyze the collected oceanographic data, means for identifying pollution hotspots based on the analysis results, means for visualizing the location information of the identified pollution hotspots on a map, means for proposing cleanup activities based on the identified hotspots, means for preprocessing the collected data, configuring a machine learning algorithm to perform analysis, and means for displaying the analysis results as markers on a map using a map display component, thereby enabling highly accurate data collection, reliable analysis, visual visualization, and effective countermeasure proposals through a unified series of processes.

[0073] "Ocean data" refers to information about the marine environment, specifically including data on seawater pollution levels, temperature, salinity, currents, etc.

[0074] "Collection means" refers to methods and equipment for acquiring oceanographic data, and specifically includes mobile objects, remote sensing equipment, and sensor devices.

[0075] "Artificial intelligence algorithm" refers to a technology that uses a computer to analyze a wide range of data and find patterns and characteristics, and specifically includes machine learning algorithms.

[0076] "Analysis results" refers to the information obtained after processing marine data with artificial intelligence algorithms, including, in particular, the location of pollution hotspots.

[0077] A "pollution hotspot" is a location in a particular area where the concentration of a pollutant is particularly high.

[0078] "Map display components" refers to software components or libraries for displaying data on a map, including map libraries such as Leaflet.js.

[0079] "Cleanup activities" refer to the removal of contaminants and countermeasures implemented in response to identified contamination hotspots.

[0080] "Preprocessing" refers to a series of steps that convert collected raw data into an analyzable format, including, for example, data interpolation and normalization.

[0081] A "machine learning algorithm" refers to an algorithm that learns from experience and recognizes patterns from large amounts of data, and specific examples include K-means clustering.

[0082] A "marker" refers to a visual icon or symbol used to indicate a specific location on a map.

[0083] The present invention is a system for collecting oceanographic data and identifying pollution hotspots using artificial intelligence algorithms. The system analyzes the collected data, visualizes pollution hotspots on a map, and suggests cleanup actions. Specific embodiments of the system are described below.

[0084] Data collection

[0085] The server collects the necessary data from marine data providers via API. The providers collect marine environmental data using mobile objects, remote sensing equipment, sensor devices, etc. The server sets the provider's API endpoint, generates a request including parameters such as the period (e.g., January 1, 2023 to January 31, 2023) and location, and sends the API request. The server analyzes the received response data and extracts the necessary information. Specifically, it extracts data points including latitude, longitude, and pollution level from the data returned in JSON format.

[0086] Data analysis

[0087] The server uses machine learning algorithms to analyze the collected oceanographic data. At this stage, data preprocessing is performed, which includes missing data completion and data normalization. Next, a machine learning algorithm such as K-means clustering is set up to identify pollution hotspots based on the data features. The analysis results provide location information for pollution hotspots.

[0088] visualization

[0089] The pollution hotspots obtained as a result of the analysis are visualized on a map by the device. The device initializes a map display component (e.g., Leaflet.js) and displays the hotspot location information as markers on the map. This allows the user to visually grasp the pollution situation. The device saves the map as an HTML file, which can be displayed through a browser.

[0090] Clean-up activity proposals

[0091] The server generates cleanup activity recommendations based on the identified hotspots. The recommendations include countermeasures and actions to be taken for each hotspot, such as how and how to prioritize the deployment of cleanup crews to specific hotspots. This allows users to efficiently and effectively address marine pollution.

[0092] Specific examples

[0093] For example, the server sends an API request to collect "marine pollution data from January 1, 2023 to January 31, 2023." The data is analyzed and five pollution hotspots are identified using K-means clustering. The device displays these hotspots on a map, allowing users to visually confirm their locations. The server then suggests high-priority cleanup actions for specific hotspots. Users can then take efficient measures based on these suggestions.

[0094] Prompt Sentence Examples

[0095] "Collect marine pollution data from January 1, 2023 to January 31, 2023, and identify five pollution hotspots using K-means clustering. Visualize them on a map and propose cleanup actions for each hotspot."

[0096] Through this series of processes, the system achieves highly accurate data collection and analysis, visual visualization, and effective countermeasure proposals in a unified process, enabling rapid and accurate countermeasures against marine pollution.

[0097] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0098] Step 1:

[0099] Data collection

[0100] The server collects the necessary data from the API of the ocean data provider. As input, it sets the API endpoint and request parameters (e.g., period, location, data type). The server generates and sends an API request based on this input. It receives the response data to the sent request and extracts the necessary information (e.g., latitude, longitude, pollution level). Specifically, the server sends a request using a URL such as "https: / / api.ocean-data-provider.com / data?start=2023-01-01&end=2023-01-31&type=pollution". The output is the extracted ocean data.

[0101] Step 2:

[0102] Data Preprocessing

[0103] The server preprocesses the collected oceanographic data. It uses the oceanographic data obtained in step 1 as input. Preprocessing includes filling in missing data and normalizing the data. The server performs this preprocessing and formats the data in a format suitable for analysis. Specifically, the server fills in NaN values ​​and scales the dataset. The output is the formatted oceanographic data.

[0104] Step 3:

[0105] Data analysis

[0106] The server uses a machine learning algorithm to analyze the preprocessed data. It takes the oceanographic data from step 2 as input. The server configures the K-means clustering algorithm to perform data analysis. This process identifies pollution hotspots based on the data features. Specifically, the server performs K-means clustering to separate the data points into multiple clusters. The output is the location information of the identified hotspots.

[0107] Step 4:

[0108] visualization

[0109] The device visualizes the analysis results on a map. It uses the hotspot location information obtained in step 3 as input. The device initializes a map display component (e.g., Leaflet.js) and displays the hotspot location information as markers on the map. Specifically, the device saves the map as an HTML file and displays it through a browser. The output is a map showing the pollution hotspots.

[0110] Step 5:

[0111] Clean-up activity proposals

[0112] The server generates cleanup activity proposals based on the identified contamination hotspots. It uses the hotspot data obtained in step 3 as input. The server analyzes the contamination level and scale of each hotspot and generates a specific action plan that determines countermeasures and priorities. Specifically, the server generates a proposal such as "dispatch a five-person cleanup crew to a specific hotspot." The output is a documented cleanup activity proposal.

[0113] (Application example 1)

[0114] 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."

[0115] In conventional logistics facilities, there were insufficient means to grasp the contamination status within the facility in real time, which resulted in delays in effective cleanup activities.In addition, there was no system to identify contamination hotspots and propose specific countermeasures, which resulted in low efficiency and effectiveness of contamination countermeasures.

[0116] 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.

[0117] In this invention, the server includes means for collecting contamination data, means for using a machine learning algorithm to analyze the collected contamination data, means for visualizing the location information of identified hotspots on a map, and means for proposing cleanup activities based on the contamination hotspots within the logistics facility, thereby enabling real-time understanding of the contamination status within the logistics facility and the implementation of prompt and effective cleanup activities.

[0118] "Pollution data" refers to environmental information such as temperature, humidity, dust, and chemical levels within logistics facilities.

[0119] "Machine learning algorithms" are artificial intelligence techniques used to analyze collected data and identify contamination hotspots.

[0120] A "hot spot" is an area within a logistics facility where contamination is particularly concentrated.

[0121] "Visualizing on a map" means visually displaying the location information of the identified hotspots using a geographic information system.

[0122] "Cleanup Actions" are specific measures taken to reduce or eliminate contamination within a logistics facility.

[0123] A "sensor" is a device used to collect environmental data within a logistics facility.

[0124] A "network device" is a communication device that transmits data collected by a sensor to a server.

[0125] A "data collection device" is a device for aggregating data from sensors and network devices.

[0126] This invention is a system for monitoring the contamination status within a logistics facility in real time and effectively proposing cleanup activities. This system is specifically implemented as follows.

[0127] 1. Data Collection System

[0128] The server collects environmental data such as temperature, humidity, dust, and chemical levels from sensors installed throughout the logistics facility. The sensors are connected via Wi-Fi and transmit the data to the server in real time. General IoT devices and network equipment are used as data collection devices.

[0129] 2. Data analysis system

[0130] The server uses machine learning algorithms to analyze the collected environmental data. Specifically, it applies the K-means clustering algorithm to identify pollution hotspots within the logistics facility. Data features such as latitude, longitude, and pollution level are used. This allows the identification of areas with particularly high levels of pollution.

[0131] 3. Visualization System

[0132] The location information of hotspots obtained as a result of the analysis is visualized on a map. An application installed on a device (e.g., a smartphone) displays the identified hotspots as markers on the map. The map is visualized using HTML and JavaScript, and the location information is displayed using the Google Maps API.

[0133] 4. Cleanup activity suggestion system

[0134] The server then proposes specific cleanup actions based on the identified hotspots. An artificial intelligence algorithm generates countermeasures for each contamination hotspot (e.g., deploying cleaning robots, improving ventilation, etc.). The proposals are then sent to the user's device, allowing the user to implement the cleanup actions accordingly.

[0135] Examples of concrete examples and prompts

[0136] As a concrete example, we will explain a scenario in which contamination data within a logistics facility is collected and cleaning robots are automatically deployed to identified hotspots.

[0137] Examples:

[0138] Sensor location: Specific area in the warehouse

[0139] Data collection period: 1 week

[0140] Devices used: IoT sensors (temperature, humidity, chemical sensors), smartphones, network devices

[0141] Example prompt sentence:

[0142] Collect temperature, humidity, dust and chemical levels within your logistics facility to identify contamination hotspots, display them on a map and suggest specific cleanup actions.

[0143] This will enable us to grasp the contamination status within logistics facilities in real time and implement quick and effective cleanup activities.

[0144] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0145] Step 1:

[0146] The server collects environmental data from sensors within the logistics facility. Specifically, the sensors collect data on temperature, humidity, dust, chemical levels, and other factors in real time and transmit it to the server via Wi-Fi. The input is environmental data from the sensors, and the output is the storage of the collected data in a database.

[0147] Step 2:

[0148] The server preprocesses the collected data and converts it into an analyzable format. It also fills in missing values ​​and detects outliers. The input is the collected raw data, and the output is the preprocessed, clean data. Specific operations use Python data processing libraries (e.g., Pandas).

[0149] Step 3:

[0150] The server uses a machine learning algorithm to identify pollution hotspots based on the preprocessed data. Specifically, it applies the K-means clustering algorithm to form clusters based on pollution levels. The input is the preprocessed data, and the output is hotspot location information. Specific operations use a Python machine learning library (e.g., Scikit-learn).

[0151] Step 4:

[0152] The server visualizes the location information of the identified hotspots on a map. To do this, it uses HTML and JavaScript and utilizes the Google Maps API to display the hotspots as markers on the map. The input is the location information of the hotspots, and the output is the visualized map. Specifically, it uses the Folium library to generate an HTML file that can be displayed in a browser.

[0153] Step 5:

[0154] The server proposes cleanup activities based on the identified hotspots. An artificial intelligence algorithm generates countermeasures (e.g., deploying cleaning robots, improving ventilation, etc.) for each hotspot. The input is the hotspot location information, and the output is a proposal for a specific cleanup action. The proposal is then notified to the user through a user interface.

[0155] Step 6:

[0156] The device (e.g., a smartphone) receives a cleanup suggestion notification from the server and displays it to the user. The user can then take action based on the suggestion. The input is the cleanup suggestion from the server, and the output is the display and notification to the user. Specifically, the system displays a notification through a mobile application and prompts the user to take action.

[0157] These steps will result in a system that monitors contamination levels within logistics facilities in real time and suggests effective cleanup actions.

[0158] 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.

[0159] The present invention combines a system that collects oceanographic data, identifies pollution hotspots using artificial intelligence algorithms, and an emotion engine that recognizes user emotions. The system analyzes the collected data, visualizes pollution hotspots on a map, and suggests cleanup activities based on the user's emotions.

[0160] Data collection

[0161] The server first collects oceanographic data. Specifically, it obtains the necessary data from oceanographic data providers via API. Providers collect marine environmental data using ships, satellites, sensors, etc. For example, to obtain marine pollution data for a certain period of time, the server sets the API endpoint and parameters, sends the request, and collects the data.

[0162] Data analysis

[0163] Next, the server uses artificial intelligence algorithms to analyze the collected oceanographic data. Specifically, it uses machine learning algorithms to analyze information such as latitude, longitude, and pollution levels. This analysis makes it possible to identify pollution hotspots. For example, by using K-means clustering, pollution clusters are formed based on the features of the data, and hotspots are identified.

[0164] visualization

[0165] The contamination hotspots obtained as a result of the analysis are visualized on a map by the device. The device initializes the map and displays the location information of the identified hotspots as markers on the map. This allows the user to visually grasp the contamination situation. The map is saved as an HTML file and can be displayed through a browser.

[0166] Clean-up activity proposals

[0167] The server generates specific cleanup activity recommendations based on the identified hotspots, including countermeasures and actions to be taken for each hotspot, such as how to deploy cleanup crews at specific hotspots and their priorities.

[0168] Combining Emotion Engines

[0169] Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions. The device analyzes data such as the user's facial expressions and voice to recognize emotions and transmits that information to the server. The server then adjusts cleanup activity suggestions based on this emotion data. For example, if the user expresses strong interest or anxiety about a particular pollution situation, the server will suggest prioritizing cleanup in that area.

[0170] Specific examples

[0171] For example, the server sends an API request to collect marine pollution data from January 1, 2023 to January 31, 2023. The acquired data is analyzed and five pollution hotspots are identified based on K-means clustering. The identified hotspots are then displayed on a map, and the user can check their locations. Next, an emotion engine recognizes the user's emotional state, and the server tailors cleanup activity suggestions based on the emotion data. For example, high-priority cleanup suggestions are given to hotspots that the user is particularly interested in. Based on these suggestions, the user can create a specific cleanup plan.

[0172] The system uses vessels, satellites, and / or sensors to improve the accuracy of marine data, adopting strategies that comply with international maritime law and local environmental regulations, thereby enabling rapid and accurate identification of pollution sources, facilitating efficient cleanup efforts, and enabling effective countermeasures that are considerate of user feelings.

[0173] The processing flow will be explained below.

[0174] Step 1:

[0175] The server sets the API endpoint and parameters for collecting oceanographic data. For example, the endpoint "https: / / api.marinedata.org / ocean_data" is used, and the collection date and ocean area range are specified as parameters.

[0176] Step 2:

[0177] The server sends an API request based on the set parameters and retrieves oceanographic data from the data provider. At that time, it checks the response status code and extracts the data if it was received successfully.

[0178] Step 3:

[0179] The server extracts necessary information, such as latitude, longitude, and pollution level, from the acquired data and builds a dataset to be used for AI analysis. In this step, unnecessary data is removed and the data is formatted for analysis.

[0180] Step 4:

[0181] The server uses artificial intelligence algorithms to analyze the data, specifically applying K-means clustering to identify pollution hotspots based on latitude and longitude, thereby highlighting areas with particularly high concentrations of marine pollution.

[0182] Step 5:

[0183] The server sends the pollution hotspot data obtained as a result of the analysis to the device, which then receives it and initializes the map, specifically setting the map's default position and zoom level.

[0184] Step 6:

[0185] The device maps the location information of the identified pollution hotspots on a map and places markers on them, allowing the user to visually grasp the distribution of pollution. The generated map is saved as an HTML file and can be displayed in a browser.

[0186] Step 7:

[0187] The server acquires emotion data from the user's facial expressions and voice using an emotion engine that recognizes the user's emotions. The emotion engine analyzes the emotion data through the user-device interface and identifies the user's emotional state.

[0188] Step 8:

[0189] The server adjusts the cleanup suggestions based on the emotion data received from the emotion engine: for example, if a user expresses strong interest or concern about a particular hotspot, it may prioritize cleanup efforts in that area.

[0190] Step 9:

[0191] The server provides users with coordinated cleanup recommendations, including priority hotspots and specific cleanup actions, which they can use to develop and execute a detailed cleanup plan.

[0192] Step 10:

[0193] After the user performs the cleanup activity, the results are fed back to the server via the terminal. The server uses this feedback data to further improve the data analysis model and increase the accuracy of the next cleanup activity.

[0194] Example 2

[0195] 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."

[0196] Conventional ocean data analysis systems lack the accuracy to identify pollution hotspots, preventing efficient cleanup activities. Furthermore, because they make uniform recommendations without considering the user's feelings, pollution in areas of the user's priority may be overlooked. A system that solves these problems is needed.

[0197] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0198] In this invention, the server includes means for collecting oceanographic data, means for using an artificial intelligence algorithm to analyze the collected oceanographic data, means for identifying pollution hotspots based on the analysis results, means for visualizing the location information of the identified pollution hotspots on a map, means for suggesting cleanup activities based on the identified pollution hotspots, means for collecting and analyzing user emotion data, and means for adjusting the suggested cleanup activities based on the user emotion data, thereby enabling not only accurate identification of pollution hotspots and suggesting efficient cleanup activities but also effective countermeasures that reflect the user's emotion.

[0199] "Marine data" refers to various data related to the marine environment, including, for example, information such as latitude, longitude, pollution level, water temperature, salinity, and flow speed.

[0200] "Artificial intelligence algorithms" are computer programming technologies for performing data analysis, pattern recognition, predictions, etc., and include techniques such as machine learning and deep learning.

[0201] A "pollution hotspot" is an area of ​​concentrated pollution within a particular region.

[0202] "Location information" refers to geographic coordinate information, such as a combination of latitude and longitude that indicates a specific location.

[0203] "Visualization" is the visual display of data in the form of maps, graphs, tables, etc.

[0204] "Cleanup activities" refers to any measure or action taken to remove or reduce pollution of the marine environment.

[0205] "Emotion data" is data that expresses the user's emotional state as numerical values ​​or categories, and is collected through facial expression recognition and voice analysis.

[0206] "Adjusting suggestions" refers to changing or optimizing suggested cleanup activities based on the user's emotional data.

[0207] The present invention is a system that collects oceanographic data, identifies pollution hotspots using artificial intelligence algorithms, and analyzes users' sentiment data to tailor cleanup action recommendations. The system is implemented using a server and terminals as follows:

[0208] Data collection

[0209] The server uses APIs to collect ocean data. Specifically, it obtains data provided by ships, satellites, sensors, etc. For example, to obtain marine pollution data, it sets an API endpoint and parameters such as "https: / / api.oceandata.com / get_data?start_date=2023-01-01&end_date=2023-01-31" and sends a request to collect data.

[0210] Data analysis

[0211] The server uses artificial intelligence algorithms to analyze the acquired oceanographic data. Specifically, it uses machine learning algorithms (e.g., K-means clustering) to analyze information such as latitude, longitude, and pollution levels. This analysis identifies pollution hotspots.

[0212] visualization

[0213] The device visualizes the location information of the pollution hotspots obtained as a result of the analysis on a map. The device initializes the map using a map display library (e.g., Leaflet.js or Google Maps API) and displays the location information of the identified hotspots as markers. The user can check these markers through a browser and visually grasp the pollution situation.

[0214] Clean-up activity proposals

[0215] The server generates specific cleanup activity recommendations based on the identified hotspots, including countermeasures and actions to be taken for each hotspot, such as how to deploy cleanup crews to specific hotspots and their priorities.

[0216] Combining Emotion Engines

[0217] The device collects and analyzes the user's emotional data. Data collected through facial recognition and voice analysis expresses the user's emotional state as a numerical value or category. The device then transmits this emotional data to the server, which then adjusts its cleaning activity suggestions based on the data. For example, high-priority cleaning suggestions may be made for hotspots that the user is particularly interested in.

[0218] Specific examples

[0219] For example, the server sends an API request to collect marine pollution data from January 1, 2023 to January 31, 2023, and receives the marine pollution data in JSON format. This data is preprocessed and five pollution hotspots are identified using K-means clustering. The device initializes a map using Leaflet.js and displays the identified hotspots as markers. The user can view these hotspots on the map, and the emotion engine analyzes the user's emotional state. This emotion data is then sent to the server, which generates prioritized cleanup suggestions for hotspots of particular interest.

[0220] Prompt Sentence Examples

[0221] "Based on marine pollution data from January 1, 2023 to January 31, 2023, please identify pollution hotspots and propose cleanup activities that reflect user sentiment. Please give high priority to proposals for locations where users show particular interest."

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

[0223] Step 1:

[0224] The server collects oceanographic data. Specifically, it sends a request to the API endpoint "https: / / api.oceandata.com / get_data?start_date=2023-01-01&end_date=2023-01-31" to retrieve oceanographic data collected from ships, satellites, and sensors. The input is the API request, and the output is the retrieved oceanographic data (e.g., in JSON format).

[0225] Step 2:

[0226] The server preprocesses the collected oceanographic data. Specifically, it cleanses the data (processing missing values ​​and normalizing them). For example, it completes missing latitude and longitude data and standardizes pollution levels. The input of this step is the collected oceanographic data, and the output is the preprocessed, clean data.

[0227] Step 3:

[0228] The server applies a machine learning algorithm (e.g., K-means clustering) to the preprocessed data to identify pollution hotspots. Specifically, it performs clustering using latitude, longitude, and pollution level as features to extract areas where pollution is concentrated. The input of this step is the preprocessed data, and the output is a list of identified pollution hotspots.

[0229] Step 4:

[0230] The device visualizes the location information of the identified pollution hotspots on a map. Specifically, it initializes the map using Leaflet.js and Google Maps API and displays the hotspot locations as markers. The input of this step is the location information of the hotspots, and the output is the visualized map.

[0231] Step 5:

[0232] The server generates specific cleanup action proposals based on the identified hotspots, including the deployment of clean crews for each hotspot, the proposed equipment to use, and their priorities. The input to this step is the identified hotspots, and the output is the cleanup action proposals.

[0233] Step 6:

[0234] The device collects and analyzes the user's emotional data. Specifically, it uses a webcam and microphone to analyze the user's facial expressions and voice and estimates their emotional state. The input for this step is the user's facial and voice data, and the output is the emotional data resulting from the analysis.

[0235] Step 7:

[0236] The device sends the collected emotion data to the server, which then adjusts the cleaning activity suggestions based on the emotion data. Specifically, the suggestions are modified to prioritize cleaning hotspots that the user is particularly interested in. The input of this step is emotion data, and the output is the adjusted cleaning activity suggestions.

[0237] An example of a specific prompt is, "Based on marine pollution data from January 1, 2023 to January 31, 2023, please identify pollution hotspots and propose cleanup activities that reflect user sentiment. Please give high priority to suggestions for locations where users show particular interest."

[0238] (Application example 2)

[0239] 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."

[0240] This invention relates to a system for identifying pollution hotspots and proposing cleanup activities using marine data, and aims to solve the problem of providing a more effective method to increase participation by proposing cleanup activities that take user emotions into account. Specifically, the purpose of this invention is to solve the problem that conventional systems do not take user emotions into account and prioritize and propose cleanup activities in a uniform manner, which makes it difficult to respond flexibly to users' interests and concerns.

[0241] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0242] In this invention, the server includes means for collecting oceanographic data, means for using an artificial intelligence algorithm to analyze the collected oceanographic data, means for identifying pollution hotspots based on the analysis results, means for visualizing the location information of the identified pollution hotspots on a map, means for suggesting cleanup activities based on the identified hotspots, and means for recognizing a user's emotions and adjusting the suggested cleanup activities based on the emotion data, thereby enabling visualization of the pollution situation and flexible suggestions of cleanup activities that take the user's emotions into consideration.

[0243] "Marine data" refers to information about the marine environment, including, for example, water quality data, pollutant concentrations, weather information, and marine ecosystem data.

[0244] "Artificial intelligence algorithms" refer to computational processes for analyzing large amounts of data and extracting useful information and patterns from it, and include machine learning, deep learning, and clustering techniques.

[0245] A "pollution hotspot" is an area in a particular region where the level of pollution is significantly higher than in other surrounding areas.

[0246] "Visualization" refers to displaying data in a format that is intuitively easy to understand (for example, a map or graph), and visually representing data such as location information and pollution levels.

[0247] "Cleanup activities" refers to specific methods and means for removing or reducing discovered contamination, including, for example, cleaning operations and methods for removing contaminants.

[0248] "Emotion recognition" refers to the process of analyzing data such as a user's facial expressions and voice to identify their emotional state (e.g., excitement, sadness, anxiety, joy, etc.).

[0249] "Server" refers to a computer system for collecting, analyzing, storing, and managing data.

[0250] The system of the present invention collects oceanographic data, uses artificial intelligence algorithms to identify pollution hotspots, and then recognizes user sentiment to tailor cleanup recommendations. The system is implemented in the following steps:

[0251] First, the server collects oceanographic data. This collection is done by obtaining data from sources via API. Sources include ships, satellites, and sensors, and the server receives the highly accurate oceanographic data collected by these sources.

[0252] The server analyzes the collected data using artificial intelligence algorithms. This analysis uses machine learning techniques such as K-means clustering based on information such as latitude, longitude, and pollution level to identify pollution hotspots. Clusters are formed based on the characteristics of the data, and areas with particularly high levels of pollution are identified as hotspots.

[0253] Next, the device visualizes the location information of the identified pollution hotspots on a map. The device initializes the map and displays the location information of the identified hotspots as markers, allowing the user to visually grasp the pollution situation. The map is saved as an HTML file and can be displayed through a browser.

[0254] Additionally, the server generates specific cleanup action recommendations based on the identified hotspots, including recommendations on how and prioritizing cleanup crew deployment at specific hotspots.

[0255] A distinctive feature of the present invention is an emotion engine that recognizes a user's emotions. The device analyzes data such as the user's facial expressions and voice to identify the user's emotional state. The emotion engine can utilize, for example, facial recognition software or tone-of-voice analysis tools. The recognized emotion data is sent to a server, which then tailors cleanup activity suggestions based on the emotion data. For example, if the user expresses strong concern or anxiety about a particular pollution situation, suggestions to prioritize cleanup in that area are made.

[0256] As a specific example, a server sends an API request to collect marine pollution data from January 1, 2023 to January 31, 2023. The acquired data is analyzed and five pollution hotspots are identified based on K-means clustering. The identified hotspots are then displayed on a map, and the user can check their locations. Next, an emotion engine recognizes the user's emotional state, and the server tailors cleanup activity suggestions based on the emotion data. For example, high-priority cleanup suggestions are made for hotspots that the user is particularly interested in. Based on these suggestions, the user can create a specific cleanup plan.

[0257] An example of a prompt for a generative AI model is as follows:

[0258] "Collect marine pollution data from January 1, 2023 to January 31, 2023 and identify pollution hotspots using K-means clustering. Then collect user sentiment data, display the identified hotspots on a map, and generate cleanup action suggestions based on user sentiment."

[0259] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0260] Step 1:

[0261] The server collects oceanographic data via API. It sets the API endpoint and parameters and retrieves data from sources such as ships, satellites, and sensors. The input is the parameters included in the API request, and the output is the collected oceanographic data. This data includes information such as latitude, longitude, and pollution level.

[0262] Step 2:

[0263] The server applies an artificial intelligence algorithm to analyze the collected oceanographic data. Specifically, it uses K-means clustering to identify pollution hotspots based on the data's features. The input is the collected oceanographic data, and the output is cluster information for the identified pollution hotspots. Data processing involves clustering using latitude and longitude as features.

[0264] Step 3:

[0265] The terminal visualizes the location information of the identified pollution hotspots on a map. The input is the cluster information of the pollution hotspots sent from the server, and the output is markers of the hotspots displayed on the map. The operation is to initialize the map and place markers at the locations of the hotspots.

[0266] Step 4:

[0267] The server generates cleanup action proposals based on the identified hotspots. The input is the hotspot locations and their contamination levels, and the output is specific cleanup action proposals, including the location and priority of cleanup crews.

[0268] Step 5:

[0269] The device recognizes the user's emotions in real time. The input is the user's facial image and voice data, and the output is the recognized emotional state. In actual operation, the device uses emotion recognition software to analyze the user's emotions.

[0270] Step 6:

[0271] The server adjusts cleanup activity suggestions based on the emotion data sent from the device. The input is emotion data and existing cleanup suggestions, and the output is new cleanup suggestions adjusted with the emotion data. If the user expresses strong interest or concern about a particular hotspot, the server will make suggestions that prioritize cleanup in that area.

[0272] 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.

[0273] 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.

[0274] 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.

[0275] [Second embodiment]

[0276] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0277] 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.

[0278] 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).

[0279] 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.

[0280] 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.

[0281] 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).

[0282] 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.

[0283] 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.

[0284] 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.

[0285] 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.

[0286] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0287] 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."

[0288] The present invention is a system that collects marine data and uses artificial intelligence algorithms to identify pollution hotspots, analyzes the collected data, visualizes the pollution hotspots on a map, and suggests cleanup actions.

[0289] Data collection

[0290] The server first collects oceanographic data. Specifically, it obtains the necessary data from oceanographic data providers via API. Providers collect marine environmental data using ships, satellites, sensors, etc. For example, to obtain marine pollution data for a certain period of time, the server sets the API endpoint and parameters, sends the request, and collects the data.

[0291] Data analysis

[0292] Next, the server uses artificial intelligence algorithms to analyze the collected oceanographic data. Specifically, it uses machine learning algorithms to analyze information such as latitude, longitude, and pollution levels. This analysis makes it possible to identify pollution hotspots. For example, by using K-means clustering, pollution clusters are formed based on the features of the data, and hotspots are identified.

[0293] visualization

[0294] The contamination hotspots obtained as a result of the analysis are visualized on a map by the device. The device initializes the map and displays the location information of the identified hotspots as markers on the map. This allows the user to visually grasp the contamination situation. The map is saved as an HTML file and can be displayed through a browser.

[0295] Clean-up activity proposals

[0296] The server generates specific cleanup activity recommendations based on the identified hotspots. The recommendations include countermeasures and actions to be taken for each hotspot, such as how to deploy cleanup crews to specific hotspots and their priorities. This allows users to efficiently and effectively address marine pollution.

[0297] Specific examples

[0298] For example, the server sends an API request to collect marine pollution data from January 1, 2023 to January 31, 2023. The acquired data is analyzed and five pollution hotspots are identified based on K-means clustering. The identified hotspots are then displayed on a map, and users can check their locations. Furthermore, the server suggests high-priority cleanup actions, allowing users to take specific measures based on the suggestions.

[0299] The system will use vessels, satellites and / or sensors to improve the accuracy of oceanographic data, employing strategies consistent with international maritime law and local environmental regulations, thereby enabling rapid and accurate identification of pollution sources and facilitating efficient cleanup efforts.

[0300] The processing flow will be explained below.

[0301] Step 1:

[0302] The server sets API endpoints and parameters for collecting oceanographic data, such as the collection range date and ocean area.

[0303] Step 2:

[0304] The server sends an API request with the configured parameters to retrieve data from the ocean data provider, verifies the response status code, and extracts the data from the response if successful.

[0305] Step 3:

[0306] The server extracts the necessary information for analysis (latitude, longitude, pollution level) from the acquired oceanographic data, and prepares for further analysis based on this data.

[0307] Step 4:

[0308] The server then inputs the extracted data into an artificial intelligence algorithm and performs data analysis using machine learning techniques, specifically K-means clustering, to identify contamination hotspots based on the data features.

[0309] Step 5:

[0310] The server sends the location information of the pollution hotspots obtained as a result of the analysis to the device, which receives it and initializes the map.

[0311] Step 6:

[0312] The device maps the locations of identified contamination hotspots on a map, placing markers for visual identification, and saves the map as an HTML file for later viewing through a browser.

[0313] Step 7:

[0314] The server generates cleanup action proposals based on the identified hotspots, including specific actions for each hotspot and their priority.

[0315] Step 8:

[0316] The user checks the cleanup activity suggestions provided by the server, determines which hotspots should be prioritized, and creates a specific cleanup plan.

[0317] Step 9:

[0318] The cleanup activities decided by the user are carried out and the results are monitored. This information is fed back to the server and used for future data analysis and cleanup activities.

[0319] Example 1

[0320] 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."

[0321] Conventional marine pollution monitoring systems lack a unified process for data collection, analysis, visualization, and countermeasure proposals, making it difficult to implement efficient pollution countermeasures. Furthermore, the accuracy of data collection and reliability of analysis are low, leading to insufficient identification of pollution hotspots and the proposal of cleanup activities based on those hotspots, making it difficult to implement effective pollution countermeasures. As a result, marine pollution problems worsen and environmental protection efforts are delayed.

[0322] 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.

[0323] In this invention, the server includes means for collecting oceanographic data, means for using an artificial intelligence algorithm to analyze the collected oceanographic data, means for identifying pollution hotspots based on the analysis results, means for visualizing the location information of the identified pollution hotspots on a map, means for proposing cleanup activities based on the identified hotspots, means for preprocessing the collected data, configuring a machine learning algorithm to perform analysis, and means for displaying the analysis results as markers on a map using a map display component, thereby enabling highly accurate data collection, reliable analysis, visual visualization, and effective countermeasure proposals through a unified series of processes.

[0324] "Ocean data" refers to information about the marine environment, specifically including data on seawater pollution levels, temperature, salinity, currents, etc.

[0325] "Collection means" refers to methods and equipment for acquiring oceanographic data, and specifically includes mobile objects, remote sensing equipment, and sensor devices.

[0326] "Artificial intelligence algorithm" refers to a technology that uses a computer to analyze a wide range of data and find patterns and characteristics, and specifically includes machine learning algorithms.

[0327] "Analysis results" refers to the information obtained after processing marine data with artificial intelligence algorithms, including, in particular, the location of pollution hotspots.

[0328] A "pollution hotspot" is a location in a particular area where the concentration of a pollutant is particularly high.

[0329] "Map display components" refers to software components or libraries for displaying data on a map, including map libraries such as Leaflet.js.

[0330] "Cleanup activities" refer to the removal of contaminants and countermeasures implemented in response to identified contamination hotspots.

[0331] "Preprocessing" refers to a series of steps that convert collected raw data into an analyzable format, including, for example, data interpolation and normalization.

[0332] A "machine learning algorithm" refers to an algorithm that learns from experience and recognizes patterns from large amounts of data, and specific examples include K-means clustering.

[0333] A "marker" refers to a visual icon or symbol used to indicate a specific location on a map.

[0334] The present invention is a system for collecting oceanographic data and identifying pollution hotspots using artificial intelligence algorithms. The system analyzes the collected data, visualizes pollution hotspots on a map, and suggests cleanup actions. Specific embodiments of the system are described below.

[0335] Data collection

[0336] The server collects the necessary data from marine data providers via API. The providers collect marine environmental data using mobile objects, remote sensing equipment, sensor devices, etc. The server sets the provider's API endpoint, generates a request including parameters such as the period (e.g., January 1, 2023 to January 31, 2023) and location, and sends the API request. The server analyzes the received response data and extracts the necessary information. Specifically, it extracts data points including latitude, longitude, and pollution level from the data returned in JSON format.

[0337] Data analysis

[0338] The server uses machine learning algorithms to analyze the collected oceanographic data. At this stage, data preprocessing is performed, which includes missing data completion and data normalization. Next, a machine learning algorithm such as K-means clustering is set up to identify pollution hotspots based on the data features. The analysis results provide location information for pollution hotspots.

[0339] visualization

[0340] The pollution hotspots obtained as a result of the analysis are visualized on a map by the device. The device initializes a map display component (e.g., Leaflet.js) and displays the hotspot location information as markers on the map. This allows the user to visually grasp the pollution situation. The device saves the map as an HTML file, which can be displayed through a browser.

[0341] Clean-up activity proposals

[0342] The server generates cleanup activity recommendations based on the identified hotspots. The recommendations include countermeasures and actions to be taken for each hotspot, such as how and how to prioritize the deployment of cleanup crews to specific hotspots. This allows users to efficiently and effectively address marine pollution.

[0343] Specific examples

[0344] For example, the server sends an API request to collect "marine pollution data from January 1, 2023 to January 31, 2023." The data is analyzed and five pollution hotspots are identified using K-means clustering. The device displays these hotspots on a map, allowing users to visually confirm their locations. The server then suggests high-priority cleanup actions for specific hotspots. Users can then take efficient measures based on these suggestions.

[0345] Prompt Sentence Examples

[0346] "Collect marine pollution data from January 1, 2023 to January 31, 2023, and identify five pollution hotspots using K-means clustering. Visualize them on a map and propose cleanup actions for each hotspot."

[0347] Through this series of processes, the system achieves highly accurate data collection and analysis, visual visualization, and effective countermeasure proposals in a unified process, enabling rapid and accurate countermeasures against marine pollution.

[0348] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0349] Step 1:

[0350] Data collection

[0351] The server collects the necessary data from the API of the ocean data provider. As input, it sets the API endpoint and request parameters (e.g., period, location, data type). The server generates and sends an API request based on this input. It receives the response data to the sent request and extracts the necessary information (e.g., latitude, longitude, pollution level). Specifically, the server sends a request using a URL such as "https: / / api.ocean-data-provider.com / data?start=2023-01-01&end=2023-01-31&type=pollution". The output is the extracted ocean data.

[0352] Step 2:

[0353] Data Preprocessing

[0354] The server preprocesses the collected oceanographic data. It uses the oceanographic data obtained in step 1 as input. Preprocessing includes filling in missing data and normalizing the data. The server performs this preprocessing and formats the data in a format suitable for analysis. Specifically, the server fills in NaN values ​​and scales the dataset. The output is the formatted oceanographic data.

[0355] Step 3:

[0356] Data analysis

[0357] The server uses a machine learning algorithm to analyze the preprocessed data. It takes the oceanographic data from step 2 as input. The server configures the K-means clustering algorithm to perform data analysis. This process identifies pollution hotspots based on the data features. Specifically, the server performs K-means clustering to separate the data points into multiple clusters. The output is the location information of the identified hotspots.

[0358] Step 4:

[0359] visualization

[0360] The device visualizes the analysis results on a map. It uses the hotspot location information obtained in step 3 as input. The device initializes a map display component (e.g., Leaflet.js) and displays the hotspot location information as markers on the map. Specifically, the device saves the map as an HTML file and displays it through a browser. The output is a map showing the pollution hotspots.

[0361] Step 5:

[0362] Clean-up activity proposals

[0363] The server generates cleanup activity proposals based on the identified contamination hotspots. It uses the hotspot data obtained in step 3 as input. The server analyzes the contamination level and scale of each hotspot and generates a specific action plan that determines countermeasures and priorities. Specifically, the server generates a proposal such as "dispatch a five-person cleanup crew to a specific hotspot." The output is a documented cleanup activity proposal.

[0364] (Application example 1)

[0365] 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."

[0366] In conventional logistics facilities, there were insufficient means to grasp the contamination status within the facility in real time, which resulted in delays in effective cleanup activities.In addition, there was no system to identify contamination hotspots and propose specific countermeasures, which resulted in low efficiency and effectiveness of contamination countermeasures.

[0367] 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.

[0368] In this invention, the server includes means for collecting contamination data, means for using a machine learning algorithm to analyze the collected contamination data, means for visualizing the location information of identified hotspots on a map, and means for proposing cleanup activities based on the contamination hotspots within the logistics facility, thereby enabling real-time understanding of the contamination status within the logistics facility and the implementation of prompt and effective cleanup activities.

[0369] "Pollution data" refers to environmental information such as temperature, humidity, dust, and chemical levels within logistics facilities.

[0370] "Machine learning algorithms" are artificial intelligence techniques used to analyze collected data and identify contamination hotspots.

[0371] A "hot spot" is an area within a logistics facility where contamination is particularly concentrated.

[0372] "Visualizing on a map" means visually displaying the location information of the identified hotspots using a geographic information system.

[0373] "Cleanup Actions" are specific measures taken to reduce or eliminate contamination within a logistics facility.

[0374] A "sensor" is a device used to collect environmental data within a logistics facility.

[0375] A "network device" is a communication device that transmits data collected by a sensor to a server.

[0376] A "data collection device" is a device for aggregating data from sensors and network devices.

[0377] This invention is a system for monitoring the contamination status within a logistics facility in real time and effectively proposing cleanup activities. This system is specifically implemented as follows.

[0378] 1. Data Collection System

[0379] The server collects environmental data such as temperature, humidity, dust, and chemical levels from sensors installed throughout the logistics facility. The sensors are connected via Wi-Fi and transmit the data to the server in real time. General IoT devices and network equipment are used as data collection devices.

[0380] 2. Data analysis system

[0381] The server uses machine learning algorithms to analyze the collected environmental data. Specifically, it applies the K-means clustering algorithm to identify pollution hotspots within the logistics facility. Data features such as latitude, longitude, and pollution level are used. This allows the identification of areas with particularly high levels of pollution.

[0382] 3. Visualization System

[0383] The location information of hotspots obtained as a result of the analysis is visualized on a map. An application installed on a device (e.g., a smartphone) displays the identified hotspots as markers on the map. The map is visualized using HTML and JavaScript, and the location information is displayed using the Google Maps API.

[0384] 4. Cleanup activity suggestion system

[0385] The server then proposes specific cleanup actions based on the identified hotspots. An artificial intelligence algorithm generates countermeasures for each contamination hotspot (e.g., deploying cleaning robots, improving ventilation, etc.). The proposals are then sent to the user's device, allowing the user to implement the cleanup actions accordingly.

[0386] Examples of concrete examples and prompts

[0387] As a concrete example, we will explain a scenario in which contamination data within a logistics facility is collected and cleaning robots are automatically deployed to identified hotspots.

[0388] Examples:

[0389] Sensor location: Specific area in the warehouse

[0390] Data collection period: 1 week

[0391] Devices used: IoT sensors (temperature, humidity, chemical sensors), smartphones, network devices

[0392] Example prompt sentence:

[0393] Collect temperature, humidity, dust and chemical levels within your logistics facility to identify contamination hotspots, display them on a map and suggest specific cleanup actions.

[0394] This will enable us to grasp the contamination status within logistics facilities in real time and implement quick and effective cleanup activities.

[0395] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0396] Step 1:

[0397] The server collects environmental data from sensors within the logistics facility. Specifically, the sensors collect data on temperature, humidity, dust, chemical levels, and other factors in real time and transmit it to the server via Wi-Fi. The input is environmental data from the sensors, and the output is the storage of the collected data in a database.

[0398] Step 2:

[0399] The server preprocesses the collected data and converts it into an analyzable format. It also fills in missing values ​​and detects outliers. The input is the collected raw data, and the output is the preprocessed, clean data. Specific operations use Python data processing libraries (e.g., Pandas).

[0400] Step 3:

[0401] The server uses a machine learning algorithm to identify pollution hotspots based on the preprocessed data. Specifically, it applies the K-means clustering algorithm to form clusters based on pollution levels. The input is the preprocessed data, and the output is hotspot location information. Specific operations use a Python machine learning library (e.g., Scikit-learn).

[0402] Step 4:

[0403] The server visualizes the location information of the identified hotspots on a map. To do this, it uses HTML and JavaScript and utilizes the Google Maps API to display the hotspots as markers on the map. The input is the location information of the hotspots, and the output is the visualized map. Specifically, it uses the Folium library to generate an HTML file that can be displayed in a browser.

[0404] Step 5:

[0405] The server proposes cleanup activities based on the identified hotspots. An artificial intelligence algorithm generates countermeasures (e.g., deploying cleaning robots, improving ventilation, etc.) for each hotspot. The input is the hotspot location information, and the output is a proposal for a specific cleanup action. The proposal is then notified to the user through a user interface.

[0406] Step 6:

[0407] The device (e.g., a smartphone) receives a cleanup suggestion notification from the server and displays it to the user. The user can then take action based on the suggestion. The input is the cleanup suggestion from the server, and the output is the display and notification to the user. Specifically, the system displays a notification through a mobile application and prompts the user to take action.

[0408] These steps will result in a system that monitors contamination levels within logistics facilities in real time and suggests effective cleanup actions.

[0409] 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.

[0410] The present invention combines a system that collects oceanographic data, identifies pollution hotspots using artificial intelligence algorithms, and an emotion engine that recognizes user emotions. The system analyzes the collected data, visualizes pollution hotspots on a map, and suggests cleanup activities based on the user's emotions.

[0411] Data collection

[0412] The server first collects oceanographic data. Specifically, it obtains the necessary data from oceanographic data providers via API. Providers collect marine environmental data using ships, satellites, sensors, etc. For example, to obtain marine pollution data for a certain period of time, the server sets the API endpoint and parameters, sends the request, and collects the data.

[0413] Data analysis

[0414] Next, the server uses artificial intelligence algorithms to analyze the collected oceanographic data. Specifically, it uses machine learning algorithms to analyze information such as latitude, longitude, and pollution levels. This analysis makes it possible to identify pollution hotspots. For example, by using K-means clustering, pollution clusters are formed based on the features of the data, and hotspots are identified.

[0415] visualization

[0416] The contamination hotspots obtained as a result of the analysis are visualized on a map by the device. The device initializes the map and displays the location information of the identified hotspots as markers on the map. This allows the user to visually grasp the contamination situation. The map is saved as an HTML file and can be displayed through a browser.

[0417] Clean-up activity proposals

[0418] The server generates specific cleanup activity recommendations based on the identified hotspots, including countermeasures and actions to be taken for each hotspot, such as how to deploy cleanup crews at specific hotspots and their priorities.

[0419] Combining Emotion Engines

[0420] Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions. The device analyzes data such as the user's facial expressions and voice to recognize emotions and transmits that information to the server. The server then adjusts cleanup activity suggestions based on this emotion data. For example, if the user expresses strong interest or anxiety about a particular pollution situation, the server will suggest prioritizing cleanup in that area.

[0421] Specific examples

[0422] For example, the server sends an API request to collect marine pollution data from January 1, 2023 to January 31, 2023. The acquired data is analyzed and five pollution hotspots are identified based on K-means clustering. The identified hotspots are then displayed on a map, and the user can check their locations. Next, an emotion engine recognizes the user's emotional state, and the server tailors cleanup activity suggestions based on the emotion data. For example, high-priority cleanup suggestions are given to hotspots that the user is particularly interested in. Based on these suggestions, the user can create a specific cleanup plan.

[0423] The system uses vessels, satellites, and / or sensors to improve the accuracy of marine data, adopting strategies that comply with international maritime law and local environmental regulations, thereby enabling rapid and accurate identification of pollution sources, facilitating efficient cleanup efforts, and enabling effective countermeasures that are considerate of user feelings.

[0424] The processing flow will be explained below.

[0425] Step 1:

[0426] The server sets the API endpoint and parameters for collecting oceanographic data. For example, the endpoint "https: / / api.marinedata.org / ocean_data" is used, and the collection date and ocean area range are specified as parameters.

[0427] Step 2:

[0428] The server sends an API request based on the set parameters and retrieves oceanographic data from the data provider. At that time, it checks the response status code and extracts the data if it was received successfully.

[0429] Step 3:

[0430] The server extracts necessary information, such as latitude, longitude, and pollution level, from the acquired data and builds a dataset to be used for AI analysis. In this step, unnecessary data is removed and the data is formatted for analysis.

[0431] Step 4:

[0432] The server uses artificial intelligence algorithms to analyze the data, specifically applying K-means clustering to identify pollution hotspots based on latitude and longitude, thereby highlighting areas with particularly high concentrations of marine pollution.

[0433] Step 5:

[0434] The server sends the pollution hotspot data obtained as a result of the analysis to the device, which then receives it and initializes the map, specifically setting the map's default position and zoom level.

[0435] Step 6:

[0436] The device maps the location information of the identified pollution hotspots on a map and places markers on them, allowing the user to visually grasp the distribution of pollution. The generated map is saved as an HTML file and can be displayed in a browser.

[0437] Step 7:

[0438] The server acquires emotion data from the user's facial expressions and voice using an emotion engine that recognizes the user's emotions. The emotion engine analyzes the emotion data through the user-device interface and identifies the user's emotional state.

[0439] Step 8:

[0440] The server adjusts the cleanup suggestions based on the emotion data received from the emotion engine: for example, if a user expresses strong interest or concern about a particular hotspot, it may prioritize cleanup efforts in that area.

[0441] Step 9:

[0442] The server provides users with coordinated cleanup recommendations, including priority hotspots and specific cleanup actions, which they can use to develop and execute a detailed cleanup plan.

[0443] Step 10:

[0444] After the user performs the cleanup activity, the results are fed back to the server via the terminal. The server uses this feedback data to further improve the data analysis model and increase the accuracy of the next cleanup activity.

[0445] Example 2

[0446] 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."

[0447] Conventional ocean data analysis systems lack the accuracy to identify pollution hotspots, preventing efficient cleanup activities. Furthermore, because they make uniform recommendations without considering the user's feelings, pollution in areas of the user's priority may be overlooked. A system that solves these problems is needed.

[0448] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0449] In this invention, the server includes means for collecting oceanographic data, means for using an artificial intelligence algorithm to analyze the collected oceanographic data, means for identifying pollution hotspots based on the analysis results, means for visualizing the location information of the identified pollution hotspots on a map, means for suggesting cleanup activities based on the identified pollution hotspots, means for collecting and analyzing user emotion data, and means for adjusting the suggested cleanup activities based on the user emotion data, thereby enabling not only accurate identification of pollution hotspots and suggesting efficient cleanup activities but also effective countermeasures that reflect the user's emotion.

[0450] "Marine data" refers to various data related to the marine environment, including, for example, information such as latitude, longitude, pollution level, water temperature, salinity, and flow speed.

[0451] "Artificial intelligence algorithms" are computer programming technologies for performing data analysis, pattern recognition, predictions, etc., and include techniques such as machine learning and deep learning.

[0452] A "pollution hotspot" is an area of ​​concentrated pollution within a particular region.

[0453] "Location information" refers to geographic coordinate information, such as a combination of latitude and longitude that indicates a specific location.

[0454] "Visualization" is the visual display of data in the form of maps, graphs, tables, etc.

[0455] "Cleanup activities" refers to any measure or action taken to remove or reduce pollution of the marine environment.

[0456] "Emotion data" is data that expresses the user's emotional state as numerical values ​​or categories, and is collected through facial expression recognition and voice analysis.

[0457] "Adjusting suggestions" refers to changing or optimizing suggested cleanup activities based on the user's emotional data.

[0458] The present invention is a system that collects oceanographic data, identifies pollution hotspots using artificial intelligence algorithms, and analyzes users' sentiment data to tailor cleanup action recommendations. The system is implemented using a server and terminals as follows:

[0459] Data collection

[0460] The server uses APIs to collect ocean data. Specifically, it obtains data provided by ships, satellites, sensors, etc. For example, to obtain marine pollution data, it sets an API endpoint and parameters such as "https: / / api.oceandata.com / get_data?start_date=2023-01-01&end_date=2023-01-31" and sends a request to collect data.

[0461] Data analysis

[0462] The server uses artificial intelligence algorithms to analyze the acquired oceanographic data. Specifically, it uses machine learning algorithms (e.g., K-means clustering) to analyze information such as latitude, longitude, and pollution levels. This analysis identifies pollution hotspots.

[0463] visualization

[0464] The device visualizes the location information of the pollution hotspots obtained as a result of the analysis on a map. The device initializes the map using a map display library (e.g., Leaflet.js or Google Maps API) and displays the location information of the identified hotspots as markers. The user can check these markers through a browser and visually grasp the pollution situation.

[0465] Clean-up activity proposals

[0466] The server generates specific cleanup activity recommendations based on the identified hotspots, including countermeasures and actions to be taken for each hotspot, such as how to deploy cleanup crews to specific hotspots and their priorities.

[0467] Combining Emotion Engines

[0468] The device collects and analyzes the user's emotional data. Data collected through facial recognition and voice analysis expresses the user's emotional state as a numerical value or category. The device then transmits this emotional data to the server, which then adjusts its cleaning activity suggestions based on the data. For example, high-priority cleaning suggestions may be made for hotspots that the user is particularly interested in.

[0469] Specific examples

[0470] For example, the server sends an API request to collect marine pollution data from January 1, 2023 to January 31, 2023, and receives the marine pollution data in JSON format. This data is preprocessed and five pollution hotspots are identified using K-means clustering. The device initializes a map using Leaflet.js and displays the identified hotspots as markers. The user can view these hotspots on the map, and the emotion engine analyzes the user's emotional state. This emotion data is then sent to the server, which generates prioritized cleanup suggestions for hotspots of particular interest.

[0471] Prompt Sentence Examples

[0472] "Based on marine pollution data from January 1, 2023 to January 31, 2023, please identify pollution hotspots and propose cleanup activities that reflect user sentiment. Please give high priority to proposals for locations where users show particular interest."

[0473] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0474] Step 1:

[0475] The server collects oceanographic data. Specifically, it sends a request to the API endpoint "https: / / api.oceandata.com / get_data?start_date=2023-01-01&end_date=2023-01-31" to retrieve oceanographic data collected from ships, satellites, and sensors. The input is the API request, and the output is the retrieved oceanographic data (e.g., in JSON format).

[0476] Step 2:

[0477] The server preprocesses the collected oceanographic data. Specifically, it cleanses the data (processing missing values ​​and normalizing them). For example, it completes missing latitude and longitude data and standardizes pollution levels. The input of this step is the collected oceanographic data, and the output is the preprocessed, clean data.

[0478] Step 3:

[0479] The server applies a machine learning algorithm (e.g., K-means clustering) to the preprocessed data to identify pollution hotspots. Specifically, it performs clustering using latitude, longitude, and pollution level as features to extract areas where pollution is concentrated. The input of this step is the preprocessed data, and the output is a list of identified pollution hotspots.

[0480] Step 4:

[0481] The device visualizes the location information of the identified pollution hotspots on a map. Specifically, it initializes the map using Leaflet.js and Google Maps API and displays the hotspot locations as markers. The input of this step is the location information of the hotspots, and the output is the visualized map.

[0482] Step 5:

[0483] The server generates specific cleanup action proposals based on the identified hotspots, including the deployment of clean crews for each hotspot, the proposed equipment to use, and their priorities. The input to this step is the identified hotspots, and the output is the cleanup action proposals.

[0484] Step 6:

[0485] The device collects and analyzes the user's emotional data. Specifically, it uses a webcam and microphone to analyze the user's facial expressions and voice and estimates their emotional state. The input for this step is the user's facial and voice data, and the output is the emotional data resulting from the analysis.

[0486] Step 7:

[0487] The device sends the collected emotion data to the server, which then adjusts the cleaning activity suggestions based on the emotion data. Specifically, the suggestions are modified to prioritize cleaning hotspots that the user is particularly interested in. The input of this step is emotion data, and the output is the adjusted cleaning activity suggestions.

[0488] An example of a specific prompt is, "Based on marine pollution data from January 1, 2023 to January 31, 2023, please identify pollution hotspots and propose cleanup activities that reflect user sentiment. Please give high priority to suggestions for locations where users show particular interest."

[0489] (Application example 2)

[0490] 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."

[0491] This invention relates to a system for identifying pollution hotspots and proposing cleanup activities using marine data, and aims to solve the problem of providing a more effective method to increase participation by proposing cleanup activities that take user emotions into account. Specifically, the purpose of this invention is to solve the problem that conventional systems do not take user emotions into account and prioritize and propose cleanup activities in a uniform manner, which makes it difficult to respond flexibly to users' interests and concerns.

[0492] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0493] In this invention, the server includes means for collecting oceanographic data, means for using an artificial intelligence algorithm to analyze the collected oceanographic data, means for identifying pollution hotspots based on the analysis results, means for visualizing the location information of the identified pollution hotspots on a map, means for suggesting cleanup activities based on the identified hotspots, and means for recognizing a user's emotions and adjusting the suggested cleanup activities based on the emotion data, thereby enabling visualization of the pollution situation and flexible suggestions of cleanup activities that take the user's emotions into consideration.

[0494] "Marine data" refers to information about the marine environment, including, for example, water quality data, pollutant concentrations, weather information, and marine ecosystem data.

[0495] "Artificial intelligence algorithms" refer to computational processes for analyzing large amounts of data and extracting useful information and patterns from it, and include machine learning, deep learning, and clustering techniques.

[0496] A "pollution hotspot" is an area in a particular region where the level of pollution is significantly higher than in other surrounding areas.

[0497] "Visualization" refers to displaying data in a format that is intuitively easy to understand (for example, a map or graph), and visually representing data such as location information and pollution levels.

[0498] "Cleanup activities" refers to specific methods and means for removing or reducing discovered contamination, including, for example, cleaning operations and methods for removing contaminants.

[0499] "Emotion recognition" refers to the process of analyzing data such as a user's facial expressions and voice to identify their emotional state (e.g., excitement, sadness, anxiety, joy, etc.).

[0500] "Server" refers to a computer system for collecting, analyzing, storing, and managing data.

[0501] The system of the present invention collects oceanographic data, uses artificial intelligence algorithms to identify pollution hotspots, and then recognizes user sentiment to tailor cleanup recommendations. The system is implemented in the following steps:

[0502] First, the server collects oceanographic data. This collection is done by obtaining data from sources via API. Sources include ships, satellites, and sensors, and the server receives the highly accurate oceanographic data collected by these sources.

[0503] The server analyzes the collected data using artificial intelligence algorithms. This analysis uses machine learning techniques such as K-means clustering based on information such as latitude, longitude, and pollution level to identify pollution hotspots. Clusters are formed based on the characteristics of the data, and areas with particularly high levels of pollution are identified as hotspots.

[0504] Next, the device visualizes the location information of the identified pollution hotspots on a map. The device initializes the map and displays the location information of the identified hotspots as markers, allowing the user to visually grasp the pollution situation. The map is saved as an HTML file and can be displayed through a browser.

[0505] Additionally, the server generates specific cleanup action recommendations based on the identified hotspots, including recommendations on how and prioritizing cleanup crew deployment at specific hotspots.

[0506] A distinctive feature of the present invention is an emotion engine that recognizes a user's emotions. The device analyzes data such as the user's facial expressions and voice to identify the user's emotional state. The emotion engine can utilize, for example, facial recognition software or tone-of-voice analysis tools. The recognized emotion data is sent to a server, which then tailors cleanup activity suggestions based on the emotion data. For example, if the user expresses strong concern or anxiety about a particular pollution situation, suggestions to prioritize cleanup in that area are made.

[0507] As a specific example, a server sends an API request to collect marine pollution data from January 1, 2023 to January 31, 2023. The acquired data is analyzed and five pollution hotspots are identified based on K-means clustering. The identified hotspots are then displayed on a map, and the user can check their locations. Next, an emotion engine recognizes the user's emotional state, and the server tailors cleanup activity suggestions based on the emotion data. For example, high-priority cleanup suggestions are made for hotspots that the user is particularly interested in. Based on these suggestions, the user can create a specific cleanup plan.

[0508] An example of a prompt for a generative AI model is as follows:

[0509] "Collect marine pollution data from January 1, 2023 to January 31, 2023 and identify pollution hotspots using K-means clustering. Then collect user sentiment data, display the identified hotspots on a map, and generate cleanup action suggestions based on user sentiment."

[0510] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0511] Step 1:

[0512] The server collects oceanographic data via API. It sets the API endpoint and parameters and retrieves data from sources such as ships, satellites, and sensors. The input is the parameters included in the API request, and the output is the collected oceanographic data. This data includes information such as latitude, longitude, and pollution level.

[0513] Step 2:

[0514] The server applies an artificial intelligence algorithm to analyze the collected oceanographic data. Specifically, it uses K-means clustering to identify pollution hotspots based on the data's features. The input is the collected oceanographic data, and the output is cluster information for the identified pollution hotspots. Data processing involves clustering using latitude and longitude as features.

[0515] Step 3:

[0516] The terminal visualizes the location information of the identified pollution hotspots on a map. The input is the cluster information of the pollution hotspots sent from the server, and the output is markers of the hotspots displayed on the map. The operation is to initialize the map and place markers at the locations of the hotspots.

[0517] Step 4:

[0518] The server generates cleanup action proposals based on the identified hotspots. The input is the hotspot locations and their contamination levels, and the output is specific cleanup action proposals, including the location and priority of cleanup crews.

[0519] Step 5:

[0520] The device recognizes the user's emotions in real time. The input is the user's facial image and voice data, and the output is the recognized emotional state. In actual operation, the device uses emotion recognition software to analyze the user's emotions.

[0521] Step 6:

[0522] The server adjusts cleanup activity suggestions based on the emotion data sent from the device. The input is emotion data and existing cleanup suggestions, and the output is new cleanup suggestions adjusted with the emotion data. If the user expresses strong interest or concern about a particular hotspot, the server will make suggestions that prioritize cleanup in that area.

[0523] 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.

[0524] 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.

[0525] 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.

[0526] [Third embodiment]

[0527] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0528] 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.

[0529] 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).

[0530] 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.

[0531] 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.

[0532] 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).

[0533] 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.

[0534] 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.

[0535] 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.

[0536] 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.

[0537] 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.

[0538] 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."

[0539] The present invention is a system that collects marine data and uses artificial intelligence algorithms to identify pollution hotspots, analyzes the collected data, visualizes the pollution hotspots on a map, and suggests cleanup actions.

[0540] Data collection

[0541] The server first collects oceanographic data. Specifically, it obtains the necessary data from oceanographic data providers via API. Providers collect marine environmental data using ships, satellites, sensors, etc. For example, to obtain marine pollution data for a certain period of time, the server sets the API endpoint and parameters, sends the request, and collects the data.

[0542] Data analysis

[0543] Next, the server uses artificial intelligence algorithms to analyze the collected oceanographic data. Specifically, it uses machine learning algorithms to analyze information such as latitude, longitude, and pollution levels. This analysis makes it possible to identify pollution hotspots. For example, by using K-means clustering, pollution clusters are formed based on the features of the data, and hotspots are identified.

[0544] visualization

[0545] The contamination hotspots obtained as a result of the analysis are visualized on a map by the device. The device initializes the map and displays the location information of the identified hotspots as markers on the map. This allows the user to visually grasp the contamination situation. The map is saved as an HTML file and can be displayed through a browser.

[0546] Clean-up activity proposals

[0547] The server generates specific cleanup activity recommendations based on the identified hotspots. The recommendations include countermeasures and actions to be taken for each hotspot, such as how to deploy cleanup crews to specific hotspots and their priorities. This allows users to efficiently and effectively address marine pollution.

[0548] Specific examples

[0549] For example, the server sends an API request to collect marine pollution data from January 1, 2023 to January 31, 2023. The acquired data is analyzed and five pollution hotspots are identified based on K-means clustering. The identified hotspots are then displayed on a map, and users can check their locations. Furthermore, the server suggests high-priority cleanup actions, allowing users to take specific measures based on the suggestions.

[0550] The system will use vessels, satellites and / or sensors to improve the accuracy of oceanographic data, employing strategies consistent with international maritime law and local environmental regulations, thereby enabling rapid and accurate identification of pollution sources and facilitating efficient cleanup efforts.

[0551] The processing flow will be explained below.

[0552] Step 1:

[0553] The server sets API endpoints and parameters for collecting oceanographic data, such as the collection range date and ocean area.

[0554] Step 2:

[0555] The server sends an API request with the configured parameters to retrieve data from the ocean data provider, verifies the response status code, and extracts the data from the response if successful.

[0556] Step 3:

[0557] The server extracts the necessary information for analysis (latitude, longitude, pollution level) from the acquired oceanographic data, and prepares for further analysis based on this data.

[0558] Step 4:

[0559] The server then inputs the extracted data into an artificial intelligence algorithm and performs data analysis using machine learning techniques, specifically K-means clustering, to identify contamination hotspots based on the data features.

[0560] Step 5:

[0561] The server sends the location information of the pollution hotspots obtained as a result of the analysis to the device, which receives it and initializes the map.

[0562] Step 6:

[0563] The device maps the locations of identified contamination hotspots on a map, placing markers for visual identification, and saves the map as an HTML file for later viewing through a browser.

[0564] Step 7:

[0565] The server generates cleanup action proposals based on the identified hotspots, including specific actions for each hotspot and their priority.

[0566] Step 8:

[0567] The user checks the cleanup activity suggestions provided by the server, determines which hotspots should be prioritized, and creates a specific cleanup plan.

[0568] Step 9:

[0569] The cleanup activities decided by the user are carried out and the results are monitored. This information is fed back to the server and used for future data analysis and cleanup activities.

[0570] Example 1

[0571] 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."

[0572] Conventional marine pollution monitoring systems lack a unified process for data collection, analysis, visualization, and countermeasure proposals, making it difficult to implement efficient pollution countermeasures. Furthermore, the accuracy of data collection and reliability of analysis are low, leading to insufficient identification of pollution hotspots and the proposal of cleanup activities based on those hotspots, making it difficult to implement effective pollution countermeasures. As a result, marine pollution problems worsen and environmental protection efforts are delayed.

[0573] 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.

[0574] In this invention, the server includes means for collecting oceanographic data, means for using an artificial intelligence algorithm to analyze the collected oceanographic data, means for identifying pollution hotspots based on the analysis results, means for visualizing the location information of the identified pollution hotspots on a map, means for proposing cleanup activities based on the identified hotspots, means for preprocessing the collected data, configuring a machine learning algorithm to perform analysis, and means for displaying the analysis results as markers on a map using a map display component, thereby enabling highly accurate data collection, reliable analysis, visual visualization, and effective countermeasure proposals through a unified series of processes.

[0575] "Ocean data" refers to information about the marine environment, specifically including data on seawater pollution levels, temperature, salinity, currents, etc.

[0576] "Collection means" refers to methods and equipment for acquiring oceanographic data, and specifically includes mobile objects, remote sensing equipment, and sensor devices.

[0577] "Artificial intelligence algorithm" refers to a technology that uses a computer to analyze a wide range of data and find patterns and characteristics, and specifically includes machine learning algorithms.

[0578] "Analysis results" refers to the information obtained after processing marine data with artificial intelligence algorithms, including, in particular, the location of pollution hotspots.

[0579] A "pollution hotspot" is a location in a particular area where the concentration of a pollutant is particularly high.

[0580] "Map display components" refers to software components or libraries for displaying data on a map, including map libraries such as Leaflet.js.

[0581] "Cleanup activities" refer to the removal of contaminants and countermeasures implemented in response to identified contamination hotspots.

[0582] "Preprocessing" refers to a series of steps that convert collected raw data into an analyzable format, including, for example, data interpolation and normalization.

[0583] A "machine learning algorithm" refers to an algorithm that learns from experience and recognizes patterns from large amounts of data, and specific examples include K-means clustering.

[0584] A "marker" refers to a visual icon or symbol used to indicate a specific location on a map.

[0585] The present invention is a system for collecting oceanographic data and identifying pollution hotspots using artificial intelligence algorithms. The system analyzes the collected data, visualizes pollution hotspots on a map, and suggests cleanup actions. Specific embodiments of the system are described below.

[0586] Data collection

[0587] The server collects the necessary data from marine data providers via API. The providers collect marine environmental data using mobile objects, remote sensing equipment, sensor devices, etc. The server sets the provider's API endpoint, generates a request including parameters such as the period (e.g., January 1, 2023 to January 31, 2023) and location, and sends the API request. The server analyzes the received response data and extracts the necessary information. Specifically, it extracts data points including latitude, longitude, and pollution level from the data returned in JSON format.

[0588] Data analysis

[0589] The server uses machine learning algorithms to analyze the collected oceanographic data. At this stage, data preprocessing is performed, which includes missing data completion and data normalization. Next, a machine learning algorithm such as K-means clustering is set up to identify pollution hotspots based on the data features. The analysis results provide location information for pollution hotspots.

[0590] visualization

[0591] The pollution hotspots obtained as a result of the analysis are visualized on a map by the device. The device initializes a map display component (e.g., Leaflet.js) and displays the hotspot location information as markers on the map. This allows the user to visually grasp the pollution situation. The device saves the map as an HTML file, which can be displayed through a browser.

[0592] Clean-up activity proposals

[0593] The server generates cleanup activity recommendations based on the identified hotspots. The recommendations include countermeasures and actions to be taken for each hotspot, such as how and how to prioritize the deployment of cleanup crews to specific hotspots. This allows users to efficiently and effectively address marine pollution.

[0594] Specific examples

[0595] For example, the server sends an API request to collect "marine pollution data from January 1, 2023 to January 31, 2023." The data is analyzed and five pollution hotspots are identified using K-means clustering. The device displays these hotspots on a map, allowing users to visually confirm their locations. The server then suggests high-priority cleanup actions for specific hotspots. Users can then take efficient measures based on these suggestions.

[0596] Prompt Sentence Examples

[0597] "Collect marine pollution data from January 1, 2023 to January 31, 2023, and identify five pollution hotspots using K-means clustering. Visualize them on a map and propose cleanup actions for each hotspot."

[0598] Through this series of processes, the system achieves highly accurate data collection and analysis, visual visualization, and effective countermeasure proposals in a unified process, enabling rapid and accurate countermeasures against marine pollution.

[0599] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0600] Step 1:

[0601] Data collection

[0602] The server collects the necessary data from the API of the ocean data provider. As input, it sets the API endpoint and request parameters (e.g., period, location, data type). The server generates and sends an API request based on this input. It receives the response data to the sent request and extracts the necessary information (e.g., latitude, longitude, pollution level). Specifically, the server sends a request using a URL such as "https: / / api.ocean-data-provider.com / data?start=2023-01-01&end=2023-01-31&type=pollution". The output is the extracted ocean data.

[0603] Step 2:

[0604] Data Preprocessing

[0605] The server preprocesses the collected oceanographic data. It uses the oceanographic data obtained in step 1 as input. Preprocessing includes filling in missing data and normalizing the data. The server performs this preprocessing and formats the data in a format suitable for analysis. Specifically, the server fills in NaN values ​​and scales the dataset. The output is the formatted oceanographic data.

[0606] Step 3:

[0607] Data analysis

[0608] The server uses a machine learning algorithm to analyze the preprocessed data. It takes the oceanographic data from step 2 as input. The server configures the K-means clustering algorithm to perform data analysis. This process identifies pollution hotspots based on the data features. Specifically, the server performs K-means clustering to separate the data points into multiple clusters. The output is the location information of the identified hotspots.

[0609] Step 4:

[0610] visualization

[0611] The device visualizes the analysis results on a map. It uses the hotspot location information obtained in step 3 as input. The device initializes a map display component (e.g., Leaflet.js) and displays the hotspot location information as markers on the map. Specifically, the device saves the map as an HTML file and displays it through a browser. The output is a map showing the pollution hotspots.

[0612] Step 5:

[0613] Clean-up activity proposals

[0614] The server generates cleanup activity proposals based on the identified contamination hotspots. It uses the hotspot data obtained in step 3 as input. The server analyzes the contamination level and scale of each hotspot and generates a specific action plan that determines countermeasures and priorities. Specifically, the server generates a proposal such as "dispatch a five-person cleanup crew to a specific hotspot." The output is a documented cleanup activity proposal.

[0615] (Application example 1)

[0616] 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."

[0617] In conventional logistics facilities, there were insufficient means to grasp the contamination status within the facility in real time, which resulted in delays in effective cleanup activities.In addition, there was no system to identify contamination hotspots and propose specific countermeasures, which resulted in low efficiency and effectiveness of contamination countermeasures.

[0618] 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.

[0619] In this invention, the server includes means for collecting contamination data, means for using a machine learning algorithm to analyze the collected contamination data, means for visualizing the location information of identified hotspots on a map, and means for proposing cleanup activities based on the contamination hotspots within the logistics facility, thereby enabling real-time understanding of the contamination status within the logistics facility and the implementation of prompt and effective cleanup activities.

[0620] "Pollution data" refers to environmental information such as temperature, humidity, dust, and chemical levels within logistics facilities.

[0621] "Machine learning algorithms" are artificial intelligence techniques used to analyze collected data and identify contamination hotspots.

[0622] A "hot spot" is an area within a logistics facility where contamination is particularly concentrated.

[0623] "Visualizing on a map" means visually displaying the location information of the identified hotspots using a geographic information system.

[0624] "Cleanup Actions" are specific measures taken to reduce or eliminate contamination within a logistics facility.

[0625] A "sensor" is a device used to collect environmental data within a logistics facility.

[0626] A "network device" is a communication device that transmits data collected by a sensor to a server.

[0627] A "data collection device" is a device for aggregating data from sensors and network devices.

[0628] This invention is a system for monitoring the contamination status within a logistics facility in real time and effectively proposing cleanup activities. This system is specifically implemented as follows.

[0629] 1. Data Collection System

[0630] The server collects environmental data such as temperature, humidity, dust, and chemical levels from sensors installed throughout the logistics facility. The sensors are connected via Wi-Fi and transmit the data to the server in real time. General IoT devices and network equipment are used as data collection devices.

[0631] 2. Data analysis system

[0632] The server uses machine learning algorithms to analyze the collected environmental data. Specifically, it applies the K-means clustering algorithm to identify pollution hotspots within the logistics facility. Data features such as latitude, longitude, and pollution level are used. This allows the identification of areas with particularly high levels of pollution.

[0633] 3. Visualization System

[0634] The location information of hotspots obtained as a result of the analysis is visualized on a map. An application installed on a device (e.g., a smartphone) displays the identified hotspots as markers on the map. The map is visualized using HTML and JavaScript, and the location information is displayed using the Google Maps API.

[0635] 4. Cleanup activity suggestion system

[0636] The server then proposes specific cleanup actions based on the identified hotspots. An artificial intelligence algorithm generates countermeasures for each contamination hotspot (e.g., deploying cleaning robots, improving ventilation, etc.). The proposals are then sent to the user's device, allowing the user to implement the cleanup actions accordingly.

[0637] Examples of concrete examples and prompts

[0638] As a concrete example, we will explain a scenario in which contamination data within a logistics facility is collected and cleaning robots are automatically deployed to identified hotspots.

[0639] Examples:

[0640] Sensor location: Specific area in the warehouse

[0641] Data collection period: 1 week

[0642] Devices used: IoT sensors (temperature, humidity, chemical sensors), smartphones, network devices

[0643] Example prompt sentence:

[0644] Collect temperature, humidity, dust and chemical levels within your logistics facility to identify contamination hotspots, display them on a map and suggest specific cleanup actions.

[0645] This will enable us to grasp the contamination status within logistics facilities in real time and implement quick and effective cleanup activities.

[0646] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0647] Step 1:

[0648] The server collects environmental data from sensors within the logistics facility. Specifically, the sensors collect data on temperature, humidity, dust, chemical levels, and other factors in real time and transmit it to the server via Wi-Fi. The input is environmental data from the sensors, and the output is the storage of the collected data in a database.

[0649] Step 2:

[0650] The server preprocesses the collected data and converts it into an analyzable format. It also fills in missing values ​​and detects outliers. The input is the collected raw data, and the output is the preprocessed, clean data. Specific operations use Python data processing libraries (e.g., Pandas).

[0651] Step 3:

[0652] The server uses a machine learning algorithm to identify pollution hotspots based on the preprocessed data. Specifically, it applies the K-means clustering algorithm to form clusters based on pollution levels. The input is the preprocessed data, and the output is hotspot location information. Specific operations use a Python machine learning library (e.g., Scikit-learn).

[0653] Step 4:

[0654] The server visualizes the location information of the identified hotspots on a map. To do this, it uses HTML and JavaScript and utilizes the Google Maps API to display the hotspots as markers on the map. The input is the location information of the hotspots, and the output is the visualized map. Specifically, it uses the Folium library to generate an HTML file that can be displayed in a browser.

[0655] Step 5:

[0656] The server proposes cleanup activities based on the identified hotspots. An artificial intelligence algorithm generates countermeasures (e.g., deploying cleaning robots, improving ventilation, etc.) for each hotspot. The input is the hotspot location information, and the output is a proposal for a specific cleanup action. The proposal is then notified to the user through a user interface.

[0657] Step 6:

[0658] The device (e.g., a smartphone) receives a cleanup suggestion notification from the server and displays it to the user. The user can then take action based on the suggestion. The input is the cleanup suggestion from the server, and the output is the display and notification to the user. Specifically, the system displays a notification through a mobile application and prompts the user to take action.

[0659] These steps will result in a system that monitors contamination levels within logistics facilities in real time and suggests effective cleanup actions.

[0660] 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.

[0661] The present invention combines a system that collects oceanographic data, identifies pollution hotspots using artificial intelligence algorithms, and an emotion engine that recognizes user emotions. The system analyzes the collected data, visualizes pollution hotspots on a map, and suggests cleanup activities based on the user's emotions.

[0662] Data collection

[0663] The server first collects oceanographic data. Specifically, it obtains the necessary data from oceanographic data providers via API. Providers collect marine environmental data using ships, satellites, sensors, etc. For example, to obtain marine pollution data for a certain period of time, the server sets the API endpoint and parameters, sends the request, and collects the data.

[0664] Data analysis

[0665] Next, the server uses artificial intelligence algorithms to analyze the collected oceanographic data. Specifically, it uses machine learning algorithms to analyze information such as latitude, longitude, and pollution levels. This analysis makes it possible to identify pollution hotspots. For example, by using K-means clustering, pollution clusters are formed based on the features of the data, and hotspots are identified.

[0666] visualization

[0667] The contamination hotspots obtained as a result of the analysis are visualized on a map by the device. The device initializes the map and displays the location information of the identified hotspots as markers on the map. This allows the user to visually grasp the contamination situation. The map is saved as an HTML file and can be displayed through a browser.

[0668] Clean-up activity proposals

[0669] The server generates specific cleanup activity recommendations based on the identified hotspots, including countermeasures and actions to be taken for each hotspot, such as how to deploy cleanup crews at specific hotspots and their priorities.

[0670] Combining Emotion Engines

[0671] Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions. The device analyzes data such as the user's facial expressions and voice to recognize emotions and transmits that information to the server. The server then adjusts cleanup activity suggestions based on this emotion data. For example, if the user expresses strong interest or anxiety about a particular pollution situation, the server will suggest prioritizing cleanup in that area.

[0672] Specific examples

[0673] For example, the server sends an API request to collect marine pollution data from January 1, 2023 to January 31, 2023. The acquired data is analyzed and five pollution hotspots are identified based on K-means clustering. The identified hotspots are then displayed on a map, and the user can check their locations. Next, an emotion engine recognizes the user's emotional state, and the server tailors cleanup activity suggestions based on the emotion data. For example, high-priority cleanup suggestions are given to hotspots that the user is particularly interested in. Based on these suggestions, the user can create a specific cleanup plan.

[0674] The system uses vessels, satellites, and / or sensors to improve the accuracy of marine data, adopting strategies that comply with international maritime law and local environmental regulations, thereby enabling rapid and accurate identification of pollution sources, facilitating efficient cleanup efforts, and enabling effective countermeasures that are considerate of user feelings.

[0675] The processing flow will be explained below.

[0676] Step 1:

[0677] The server sets the API endpoint and parameters for collecting oceanographic data. For example, the endpoint "https: / / api.marinedata.org / ocean_data" is used, and the collection date and ocean area range are specified as parameters.

[0678] Step 2:

[0679] The server sends an API request based on the set parameters and retrieves oceanographic data from the data provider. At that time, it checks the response status code and extracts the data if it was received successfully.

[0680] Step 3:

[0681] The server extracts necessary information, such as latitude, longitude, and pollution level, from the acquired data and builds a dataset to be used for AI analysis. In this step, unnecessary data is removed and the data is formatted for analysis.

[0682] Step 4:

[0683] The server uses artificial intelligence algorithms to analyze the data, specifically applying K-means clustering to identify pollution hotspots based on latitude and longitude, thereby highlighting areas with particularly high concentrations of marine pollution.

[0684] Step 5:

[0685] The server sends the pollution hotspot data obtained as a result of the analysis to the device, which then receives it and initializes the map, specifically setting the map's default position and zoom level.

[0686] Step 6:

[0687] The device maps the location information of the identified pollution hotspots on a map and places markers on them, allowing the user to visually grasp the distribution of pollution. The generated map is saved as an HTML file and can be displayed in a browser.

[0688] Step 7:

[0689] The server acquires emotion data from the user's facial expressions and voice using an emotion engine that recognizes the user's emotions. The emotion engine analyzes the emotion data through the user-device interface and identifies the user's emotional state.

[0690] Step 8:

[0691] The server adjusts the cleanup suggestions based on the emotion data received from the emotion engine: for example, if a user expresses strong interest or concern about a particular hotspot, it may prioritize cleanup efforts in that area.

[0692] Step 9:

[0693] The server provides users with coordinated cleanup recommendations, including priority hotspots and specific cleanup actions, which they can use to develop and execute a detailed cleanup plan.

[0694] Step 10:

[0695] After the user performs the cleanup activity, the results are fed back to the server via the terminal. The server uses this feedback data to further improve the data analysis model and increase the accuracy of the next cleanup activity.

[0696] Example 2

[0697] 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."

[0698] Conventional ocean data analysis systems lack the accuracy to identify pollution hotspots, preventing efficient cleanup activities. Furthermore, because they make uniform recommendations without considering the user's feelings, pollution in areas of the user's priority may be overlooked. A system that solves these problems is needed.

[0699] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0700] In this invention, the server includes means for collecting oceanographic data, means for using an artificial intelligence algorithm to analyze the collected oceanographic data, means for identifying pollution hotspots based on the analysis results, means for visualizing the location information of the identified pollution hotspots on a map, means for suggesting cleanup activities based on the identified pollution hotspots, means for collecting and analyzing user emotion data, and means for adjusting the suggested cleanup activities based on the user emotion data, thereby enabling not only accurate identification of pollution hotspots and suggesting efficient cleanup activities but also effective countermeasures that reflect the user's emotion.

[0701] "Marine data" refers to various data related to the marine environment, including, for example, information such as latitude, longitude, pollution level, water temperature, salinity, and flow speed.

[0702] "Artificial intelligence algorithms" are computer programming technologies for performing data analysis, pattern recognition, predictions, etc., and include techniques such as machine learning and deep learning.

[0703] A "pollution hotspot" is an area of ​​concentrated pollution within a particular region.

[0704] "Location information" refers to geographic coordinate information, such as a combination of latitude and longitude that indicates a specific location.

[0705] "Visualization" is the visual display of data in the form of maps, graphs, tables, etc.

[0706] "Cleanup activities" refers to any measure or action taken to remove or reduce pollution of the marine environment.

[0707] "Emotion data" is data that expresses the user's emotional state as numerical values ​​or categories, and is collected through facial expression recognition and voice analysis.

[0708] "Adjusting suggestions" refers to changing or optimizing suggested cleanup activities based on the user's emotional data.

[0709] The present invention is a system that collects oceanographic data, identifies pollution hotspots using artificial intelligence algorithms, and analyzes users' sentiment data to tailor cleanup action recommendations. The system is implemented using a server and terminals as follows:

[0710] Data collection

[0711] The server uses APIs to collect ocean data. Specifically, it obtains data provided by ships, satellites, sensors, etc. For example, to obtain marine pollution data, it sets an API endpoint and parameters such as "https: / / api.oceandata.com / get_data?start_date=2023-01-01&end_date=2023-01-31" and sends a request to collect data.

[0712] Data analysis

[0713] The server uses artificial intelligence algorithms to analyze the acquired oceanographic data. Specifically, it uses machine learning algorithms (e.g., K-means clustering) to analyze information such as latitude, longitude, and pollution levels. This analysis identifies pollution hotspots.

[0714] visualization

[0715] The device visualizes the location information of the pollution hotspots obtained as a result of the analysis on a map. The device initializes the map using a map display library (e.g., Leaflet.js or Google Maps API) and displays the location information of the identified hotspots as markers. The user can check these markers through a browser and visually grasp the pollution situation.

[0716] Clean-up activity proposals

[0717] The server generates specific cleanup activity recommendations based on the identified hotspots, including countermeasures and actions to be taken for each hotspot, such as how to deploy cleanup crews to specific hotspots and their priorities.

[0718] Combining Emotion Engines

[0719] The device collects and analyzes the user's emotional data. Data collected through facial recognition and voice analysis expresses the user's emotional state as a numerical value or category. The device then transmits this emotional data to the server, which then adjusts its cleaning activity suggestions based on the data. For example, high-priority cleaning suggestions may be made for hotspots that the user is particularly interested in.

[0720] Specific examples

[0721] For example, the server sends an API request to collect marine pollution data from January 1, 2023 to January 31, 2023, and receives the marine pollution data in JSON format. This data is preprocessed and five pollution hotspots are identified using K-means clustering. The device initializes a map using Leaflet.js and displays the identified hotspots as markers. The user can view these hotspots on the map, and the emotion engine analyzes the user's emotional state. This emotion data is then sent to the server, which generates prioritized cleanup suggestions for hotspots of particular interest.

[0722] Prompt Sentence Examples

[0723] "Based on marine pollution data from January 1, 2023 to January 31, 2023, please identify pollution hotspots and propose cleanup activities that reflect user sentiment. Please give high priority to proposals for locations where users show particular interest."

[0724] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0725] Step 1:

[0726] The server collects oceanographic data. Specifically, it sends a request to the API endpoint "https: / / api.oceandata.com / get_data?start_date=2023-01-01&end_date=2023-01-31" to retrieve oceanographic data collected from ships, satellites, and sensors. The input is the API request, and the output is the retrieved oceanographic data (e.g., in JSON format).

[0727] Step 2:

[0728] The server preprocesses the collected oceanographic data. Specifically, it cleanses the data (processing missing values ​​and normalizing them). For example, it completes missing latitude and longitude data and standardizes pollution levels. The input of this step is the collected oceanographic data, and the output is the preprocessed, clean data.

[0729] Step 3:

[0730] The server applies a machine learning algorithm (e.g., K-means clustering) to the preprocessed data to identify pollution hotspots. Specifically, it performs clustering using latitude, longitude, and pollution level as features to extract areas where pollution is concentrated. The input of this step is the preprocessed data, and the output is a list of identified pollution hotspots.

[0731] Step 4:

[0732] The device visualizes the location information of the identified pollution hotspots on a map. Specifically, it initializes the map using Leaflet.js and Google Maps API and displays the hotspot locations as markers. The input of this step is the location information of the hotspots, and the output is the visualized map.

[0733] Step 5:

[0734] The server generates specific cleanup action proposals based on the identified hotspots, including the deployment of clean crews for each hotspot, the proposed equipment to use, and their priorities. The input to this step is the identified hotspots, and the output is the cleanup action proposals.

[0735] Step 6:

[0736] The device collects and analyzes the user's emotional data. Specifically, it uses a webcam and microphone to analyze the user's facial expressions and voice and estimates their emotional state. The input for this step is the user's facial and voice data, and the output is the emotional data resulting from the analysis.

[0737] Step 7:

[0738] The device sends the collected emotion data to the server, which then adjusts the cleaning activity suggestions based on the emotion data. Specifically, the suggestions are modified to prioritize cleaning hotspots that the user is particularly interested in. The input of this step is emotion data, and the output is the adjusted cleaning activity suggestions.

[0739] An example of a specific prompt is, "Based on marine pollution data from January 1, 2023 to January 31, 2023, please identify pollution hotspots and propose cleanup activities that reflect user sentiment. Please give high priority to suggestions for locations where users show particular interest."

[0740] (Application example 2)

[0741] 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."

[0742] This invention relates to a system for identifying pollution hotspots and proposing cleanup activities using marine data, and aims to solve the problem of providing a more effective method to increase participation by proposing cleanup activities that take user emotions into account. Specifically, the purpose of this invention is to solve the problem that conventional systems do not take user emotions into account and prioritize and propose cleanup activities in a uniform manner, which makes it difficult to respond flexibly to users' interests and concerns.

[0743] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0744] In this invention, the server includes means for collecting oceanographic data, means for using an artificial intelligence algorithm to analyze the collected oceanographic data, means for identifying pollution hotspots based on the analysis results, means for visualizing the location information of the identified pollution hotspots on a map, means for suggesting cleanup activities based on the identified hotspots, and means for recognizing a user's emotions and adjusting the suggested cleanup activities based on the emotion data, thereby enabling visualization of the pollution situation and flexible suggestions of cleanup activities that take the user's emotions into consideration.

[0745] "Marine data" refers to information about the marine environment, including, for example, water quality data, pollutant concentrations, weather information, and marine ecosystem data.

[0746] "Artificial intelligence algorithms" refer to computational processes for analyzing large amounts of data and extracting useful information and patterns from it, and include machine learning, deep learning, and clustering techniques.

[0747] A "pollution hotspot" is an area in a particular region where the level of pollution is significantly higher than in other surrounding areas.

[0748] "Visualization" refers to displaying data in a format that is intuitively easy to understand (for example, a map or graph), and visually representing data such as location information and pollution levels.

[0749] "Cleanup activities" refers to specific methods and means for removing or reducing discovered contamination, including, for example, cleaning operations and methods for removing contaminants.

[0750] "Emotion recognition" refers to the process of analyzing data such as a user's facial expressions and voice to identify their emotional state (e.g., excitement, sadness, anxiety, joy, etc.).

[0751] "Server" refers to a computer system for collecting, analyzing, storing, and managing data.

[0752] The system of the present invention collects oceanographic data, uses artificial intelligence algorithms to identify pollution hotspots, and then recognizes user sentiment to tailor cleanup recommendations. The system is implemented in the following steps:

[0753] First, the server collects oceanographic data. This collection is done by obtaining data from sources via API. Sources include ships, satellites, and sensors, and the server receives the highly accurate oceanographic data collected by these sources.

[0754] The server analyzes the collected data using artificial intelligence algorithms. This analysis uses machine learning techniques such as K-means clustering based on information such as latitude, longitude, and pollution level to identify pollution hotspots. Clusters are formed based on the characteristics of the data, and areas with particularly high levels of pollution are identified as hotspots.

[0755] Next, the device visualizes the location information of the identified pollution hotspots on a map. The device initializes the map and displays the location information of the identified hotspots as markers, allowing the user to visually grasp the pollution situation. The map is saved as an HTML file and can be displayed through a browser.

[0756] Additionally, the server generates specific cleanup action recommendations based on the identified hotspots, including recommendations on how and prioritizing cleanup crew deployment at specific hotspots.

[0757] A distinctive feature of the present invention is an emotion engine that recognizes a user's emotions. The device analyzes data such as the user's facial expressions and voice to identify the user's emotional state. The emotion engine can utilize, for example, facial recognition software or tone-of-voice analysis tools. The recognized emotion data is sent to a server, which then tailors cleanup activity suggestions based on the emotion data. For example, if the user expresses strong concern or anxiety about a particular pollution situation, suggestions to prioritize cleanup in that area are made.

[0758] As a specific example, a server sends an API request to collect marine pollution data from January 1, 2023 to January 31, 2023. The acquired data is analyzed and five pollution hotspots are identified based on K-means clustering. The identified hotspots are then displayed on a map, and the user can check their locations. Next, an emotion engine recognizes the user's emotional state, and the server tailors cleanup activity suggestions based on the emotion data. For example, high-priority cleanup suggestions are made for hotspots that the user is particularly interested in. Based on these suggestions, the user can create a specific cleanup plan.

[0759] An example of a prompt for a generative AI model is as follows:

[0760] "Collect marine pollution data from January 1, 2023 to January 31, 2023 and identify pollution hotspots using K-means clustering. Then collect user sentiment data, display the identified hotspots on a map, and generate cleanup action suggestions based on user sentiment."

[0761] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0762] Step 1:

[0763] The server collects oceanographic data via API. It sets the API endpoint and parameters and retrieves data from sources such as ships, satellites, and sensors. The input is the parameters included in the API request, and the output is the collected oceanographic data. This data includes information such as latitude, longitude, and pollution level.

[0764] Step 2:

[0765] The server applies an artificial intelligence algorithm to analyze the collected oceanographic data. Specifically, it uses K-means clustering to identify pollution hotspots based on the data's features. The input is the collected oceanographic data, and the output is cluster information for the identified pollution hotspots. Data processing involves clustering using latitude and longitude as features.

[0766] Step 3:

[0767] The terminal visualizes the location information of the identified pollution hotspots on a map. The input is the cluster information of the pollution hotspots sent from the server, and the output is markers of the hotspots displayed on the map. The operation is to initialize the map and place markers at the locations of the hotspots.

[0768] Step 4:

[0769] The server generates cleanup action proposals based on the identified hotspots. The input is the hotspot locations and their contamination levels, and the output is specific cleanup action proposals, including the location and priority of cleanup crews.

[0770] Step 5:

[0771] The device recognizes the user's emotions in real time. The input is the user's facial image and voice data, and the output is the recognized emotional state. In actual operation, the device uses emotion recognition software to analyze the user's emotions.

[0772] Step 6:

[0773] The server adjusts cleanup activity suggestions based on the emotion data sent from the device. The input is emotion data and existing cleanup suggestions, and the output is new cleanup suggestions adjusted with the emotion data. If the user expresses strong interest or concern about a particular hotspot, the server will make suggestions that prioritize cleanup in that area.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] [Fourth embodiment]

[0778] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0779] 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.

[0780] 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).

[0781] 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.

[0782] 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.

[0783] 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).

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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."

[0791] The present invention is a system that collects marine data and uses artificial intelligence algorithms to identify pollution hotspots, analyzes the collected data, visualizes the pollution hotspots on a map, and suggests cleanup actions.

[0792] Data collection

[0793] The server first collects oceanographic data. Specifically, it obtains the necessary data from oceanographic data providers via API. Providers collect marine environmental data using ships, satellites, sensors, etc. For example, to obtain marine pollution data for a certain period of time, the server sets the API endpoint and parameters, sends the request, and collects the data.

[0794] Data analysis

[0795] Next, the server uses artificial intelligence algorithms to analyze the collected oceanographic data. Specifically, it uses machine learning algorithms to analyze information such as latitude, longitude, and pollution levels. This analysis makes it possible to identify pollution hotspots. For example, by using K-means clustering, pollution clusters are formed based on the features of the data, and hotspots are identified.

[0796] visualization

[0797] The contamination hotspots obtained as a result of the analysis are visualized on a map by the device. The device initializes the map and displays the location information of the identified hotspots as markers on the map. This allows the user to visually grasp the contamination situation. The map is saved as an HTML file and can be displayed through a browser.

[0798] Clean-up activity proposals

[0799] The server generates specific cleanup activity recommendations based on the identified hotspots. The recommendations include countermeasures and actions to be taken for each hotspot, such as how to deploy cleanup crews to specific hotspots and their priorities. This allows users to efficiently and effectively address marine pollution.

[0800] Specific examples

[0801] For example, the server sends an API request to collect marine pollution data from January 1, 2023 to January 31, 2023. The acquired data is analyzed and five pollution hotspots are identified based on K-means clustering. The identified hotspots are then displayed on a map, and users can check their locations. Furthermore, the server suggests high-priority cleanup actions, allowing users to take specific measures based on the suggestions.

[0802] The system will use vessels, satellites and / or sensors to improve the accuracy of oceanographic data, employing strategies consistent with international maritime law and local environmental regulations, thereby enabling rapid and accurate identification of pollution sources and facilitating efficient cleanup efforts.

[0803] The processing flow will be explained below.

[0804] Step 1:

[0805] The server sets API endpoints and parameters for collecting oceanographic data, such as the collection range date and ocean area.

[0806] Step 2:

[0807] The server sends an API request with the configured parameters to retrieve data from the ocean data provider, verifies the response status code, and extracts the data from the response if successful.

[0808] Step 3:

[0809] The server extracts the necessary information for analysis (latitude, longitude, pollution level) from the acquired oceanographic data, and prepares for further analysis based on this data.

[0810] Step 4:

[0811] The server then inputs the extracted data into an artificial intelligence algorithm and performs data analysis using machine learning techniques, specifically K-means clustering, to identify contamination hotspots based on the data features.

[0812] Step 5:

[0813] The server sends the location information of the pollution hotspots obtained as a result of the analysis to the device, which receives it and initializes the map.

[0814] Step 6:

[0815] The device maps the locations of identified contamination hotspots on a map, placing markers for visual identification, and saves the map as an HTML file for later viewing through a browser.

[0816] Step 7:

[0817] The server generates cleanup action proposals based on the identified hotspots, including specific actions for each hotspot and their priority.

[0818] Step 8:

[0819] The user checks the cleanup activity suggestions provided by the server, determines which hotspots should be prioritized, and creates a specific cleanup plan.

[0820] Step 9:

[0821] The cleanup activities decided by the user are carried out and the results are monitored. This information is fed back to the server and used for future data analysis and cleanup activities.

[0822] Example 1

[0823] 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."

[0824] Conventional marine pollution monitoring systems lack a unified process for data collection, analysis, visualization, and countermeasure proposals, making it difficult to implement efficient pollution countermeasures. Furthermore, the accuracy of data collection and reliability of analysis are low, leading to insufficient identification of pollution hotspots and the proposal of cleanup activities based on those hotspots, making it difficult to implement effective pollution countermeasures. As a result, marine pollution problems worsen and environmental protection efforts are delayed.

[0825] 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.

[0826] In this invention, the server includes means for collecting oceanographic data, means for using an artificial intelligence algorithm to analyze the collected oceanographic data, means for identifying pollution hotspots based on the analysis results, means for visualizing the location information of the identified pollution hotspots on a map, means for proposing cleanup activities based on the identified hotspots, means for preprocessing the collected data, configuring a machine learning algorithm to perform analysis, and means for displaying the analysis results as markers on a map using a map display component, thereby enabling highly accurate data collection, reliable analysis, visual visualization, and effective countermeasure proposals through a unified series of processes.

[0827] "Ocean data" refers to information about the marine environment, specifically including data on seawater pollution levels, temperature, salinity, currents, etc.

[0828] "Collection means" refers to methods and equipment for acquiring oceanographic data, and specifically includes mobile objects, remote sensing equipment, and sensor devices.

[0829] "Artificial intelligence algorithm" refers to a technology that uses a computer to analyze a wide range of data and find patterns and characteristics, and specifically includes machine learning algorithms.

[0830] "Analysis results" refers to the information obtained after processing marine data with artificial intelligence algorithms, including, in particular, the location of pollution hotspots.

[0831] A "pollution hotspot" is a location in a particular area where the concentration of a pollutant is particularly high.

[0832] "Map display components" refers to software components or libraries for displaying data on a map, including map libraries such as Leaflet.js.

[0833] "Cleanup activities" refer to the removal of contaminants and countermeasures implemented in response to identified contamination hotspots.

[0834] "Preprocessing" refers to a series of steps that convert collected raw data into an analyzable format, including, for example, data interpolation and normalization.

[0835] A "machine learning algorithm" refers to an algorithm that learns from experience and recognizes patterns from large amounts of data, and specific examples include K-means clustering.

[0836] A "marker" refers to a visual icon or symbol used to indicate a specific location on a map.

[0837] The present invention is a system for collecting oceanographic data and identifying pollution hotspots using artificial intelligence algorithms. The system analyzes the collected data, visualizes pollution hotspots on a map, and suggests cleanup actions. Specific embodiments of the system are described below.

[0838] Data collection

[0839] The server collects the necessary data from marine data providers via API. The providers collect marine environmental data using mobile objects, remote sensing equipment, sensor devices, etc. The server sets the provider's API endpoint, generates a request including parameters such as the period (e.g., January 1, 2023 to January 31, 2023) and location, and sends the API request. The server analyzes the received response data and extracts the necessary information. Specifically, it extracts data points including latitude, longitude, and pollution level from the data returned in JSON format.

[0840] Data analysis

[0841] The server uses machine learning algorithms to analyze the collected oceanographic data. At this stage, data preprocessing is performed, which includes missing data completion and data normalization. Next, a machine learning algorithm such as K-means clustering is set up to identify pollution hotspots based on the data features. The analysis results provide location information for pollution hotspots.

[0842] visualization

[0843] The pollution hotspots obtained as a result of the analysis are visualized on a map by the device. The device initializes a map display component (e.g., Leaflet.js) and displays the hotspot location information as markers on the map. This allows the user to visually grasp the pollution situation. The device saves the map as an HTML file, which can be displayed through a browser.

[0844] Clean-up activity proposals

[0845] The server generates cleanup activity recommendations based on the identified hotspots. The recommendations include countermeasures and actions to be taken for each hotspot, such as how and how to prioritize the deployment of cleanup crews to specific hotspots. This allows users to efficiently and effectively address marine pollution.

[0846] Specific examples

[0847] For example, the server sends an API request to collect "marine pollution data from January 1, 2023 to January 31, 2023." The data is analyzed and five pollution hotspots are identified using K-means clustering. The device displays these hotspots on a map, allowing users to visually confirm their locations. The server then suggests high-priority cleanup actions for specific hotspots. Users can then take efficient measures based on these suggestions.

[0848] Prompt Sentence Examples

[0849] "Collect marine pollution data from January 1, 2023 to January 31, 2023, and identify five pollution hotspots using K-means clustering. Visualize them on a map and propose cleanup actions for each hotspot."

[0850] Through this series of processes, the system achieves highly accurate data collection and analysis, visual visualization, and effective countermeasure proposals in a unified process, enabling rapid and accurate countermeasures against marine pollution.

[0851] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0852] Step 1:

[0853] Data collection

[0854] The server collects the necessary data from the API of the ocean data provider. As input, it sets the API endpoint and request parameters (e.g., period, location, data type). The server generates and sends an API request based on this input. It receives the response data to the sent request and extracts the necessary information (e.g., latitude, longitude, pollution level). Specifically, the server sends a request using a URL such as "https: / / api.ocean-data-provider.com / data?start=2023-01-01&end=2023-01-31&type=pollution". The output is the extracted ocean data.

[0855] Step 2:

[0856] Data Preprocessing

[0857] The server preprocesses the collected oceanographic data. It uses the oceanographic data obtained in step 1 as input. Preprocessing includes filling in missing data and normalizing the data. The server performs this preprocessing and formats the data in a format suitable for analysis. Specifically, the server fills in NaN values ​​and scales the dataset. The output is the formatted oceanographic data.

[0858] Step 3:

[0859] Data analysis

[0860] The server uses a machine learning algorithm to analyze the preprocessed data. It takes the oceanographic data from step 2 as input. The server configures the K-means clustering algorithm to perform data analysis. This process identifies pollution hotspots based on the data features. Specifically, the server performs K-means clustering to separate the data points into multiple clusters. The output is the location information of the identified hotspots.

[0861] Step 4:

[0862] visualization

[0863] The device visualizes the analysis results on a map. It uses the hotspot location information obtained in step 3 as input. The device initializes a map display component (e.g., Leaflet.js) and displays the hotspot location information as markers on the map. Specifically, the device saves the map as an HTML file and displays it through a browser. The output is a map showing the pollution hotspots.

[0864] Step 5:

[0865] Clean-up activity proposals

[0866] The server generates cleanup activity proposals based on the identified contamination hotspots. It uses the hotspot data obtained in step 3 as input. The server analyzes the contamination level and scale of each hotspot and generates a specific action plan that determines countermeasures and priorities. Specifically, the server generates a proposal such as "dispatch a five-person cleanup crew to a specific hotspot." The output is a documented cleanup activity proposal.

[0867] (Application example 1)

[0868] 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."

[0869] In conventional logistics facilities, there were insufficient means to grasp the contamination status within the facility in real time, which resulted in delays in effective cleanup activities.In addition, there was no system to identify contamination hotspots and propose specific countermeasures, which resulted in low efficiency and effectiveness of contamination countermeasures.

[0870] 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.

[0871] In this invention, the server includes means for collecting contamination data, means for using a machine learning algorithm to analyze the collected contamination data, means for visualizing the location information of identified hotspots on a map, and means for proposing cleanup activities based on the contamination hotspots within the logistics facility, thereby enabling real-time understanding of the contamination status within the logistics facility and the implementation of prompt and effective cleanup activities.

[0872] "Pollution data" refers to environmental information such as temperature, humidity, dust, and chemical levels within logistics facilities.

[0873] "Machine learning algorithms" are artificial intelligence techniques used to analyze collected data and identify contamination hotspots.

[0874] A "hot spot" is an area within a logistics facility where contamination is particularly concentrated.

[0875] "Visualizing on a map" means visually displaying the location information of the identified hotspots using a geographic information system.

[0876] "Cleanup Actions" are specific measures taken to reduce or eliminate contamination within a logistics facility.

[0877] A "sensor" is a device used to collect environmental data within a logistics facility.

[0878] A "network device" is a communication device that transmits data collected by a sensor to a server.

[0879] A "data collection device" is a device for aggregating data from sensors and network devices.

[0880] This invention is a system for monitoring the contamination status within a logistics facility in real time and effectively proposing cleanup activities. This system is specifically implemented as follows.

[0881] 1. Data Collection System

[0882] The server collects environmental data such as temperature, humidity, dust, and chemical levels from sensors installed throughout the logistics facility. The sensors are connected via Wi-Fi and transmit the data to the server in real time. General IoT devices and network equipment are used as data collection devices.

[0883] 2. Data analysis system

[0884] The server uses machine learning algorithms to analyze the collected environmental data. Specifically, it applies the K-means clustering algorithm to identify pollution hotspots within the logistics facility. Data features such as latitude, longitude, and pollution level are used. This allows the identification of areas with particularly high levels of pollution.

[0885] 3. Visualization System

[0886] The location information of hotspots obtained as a result of the analysis is visualized on a map. An application installed on a device (e.g., a smartphone) displays the identified hotspots as markers on the map. The map is visualized using HTML and JavaScript, and the location information is displayed using the Google Maps API.

[0887] 4. Cleanup activity suggestion system

[0888] The server then proposes specific cleanup actions based on the identified hotspots. An artificial intelligence algorithm generates countermeasures for each contamination hotspot (e.g., deploying cleaning robots, improving ventilation, etc.). The proposals are then sent to the user's device, allowing the user to implement the cleanup actions accordingly.

[0889] Examples of concrete examples and prompts

[0890] As a concrete example, we will explain a scenario in which contamination data within a logistics facility is collected and cleaning robots are automatically deployed to identified hotspots.

[0891] Examples:

[0892] Sensor location: Specific area in the warehouse

[0893] Data collection period: 1 week

[0894] Devices used: IoT sensors (temperature, humidity, chemical sensors), smartphones, network devices

[0895] Example prompt sentence:

[0896] Collect temperature, humidity, dust and chemical levels within your logistics facility to identify contamination hotspots, display them on a map and suggest specific cleanup actions.

[0897] This will enable us to grasp the contamination status within logistics facilities in real time and implement quick and effective cleanup activities.

[0898] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0899] Step 1:

[0900] The server collects environmental data from sensors within the logistics facility. Specifically, the sensors collect data on temperature, humidity, dust, chemical levels, and other factors in real time and transmit it to the server via Wi-Fi. The input is environmental data from the sensors, and the output is the storage of the collected data in a database.

[0901] Step 2:

[0902] The server preprocesses the collected data and converts it into an analyzable format. It also fills in missing values ​​and detects outliers. The input is the collected raw data, and the output is the preprocessed, clean data. Specific operations use Python data processing libraries (e.g., Pandas).

[0903] Step 3:

[0904] The server uses a machine learning algorithm to identify pollution hotspots based on the preprocessed data. Specifically, it applies the K-means clustering algorithm to form clusters based on pollution levels. The input is the preprocessed data, and the output is hotspot location information. Specific operations use a Python machine learning library (e.g., Scikit-learn).

[0905] Step 4:

[0906] The server visualizes the location information of the identified hotspots on a map. To do this, it uses HTML and JavaScript and utilizes the Google Maps API to display the hotspots as markers on the map. The input is the location information of the hotspots, and the output is the visualized map. Specifically, it uses the Folium library to generate an HTML file that can be displayed in a browser.

[0907] Step 5:

[0908] The server proposes cleanup activities based on the identified hotspots. An artificial intelligence algorithm generates countermeasures (e.g., deploying cleaning robots, improving ventilation, etc.) for each hotspot. The input is the hotspot location information, and the output is a proposal for a specific cleanup action. The proposal is then notified to the user through a user interface.

[0909] Step 6:

[0910] The device (e.g., a smartphone) receives a cleanup suggestion notification from the server and displays it to the user. The user can then take action based on the suggestion. The input is the cleanup suggestion from the server, and the output is the display and notification to the user. Specifically, the system displays a notification through a mobile application and prompts the user to take action.

[0911] These steps will result in a system that monitors contamination levels within logistics facilities in real time and suggests effective cleanup actions.

[0912] 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.

[0913] The present invention combines a system that collects oceanographic data, identifies pollution hotspots using artificial intelligence algorithms, and an emotion engine that recognizes user emotions. The system analyzes the collected data, visualizes pollution hotspots on a map, and suggests cleanup activities based on the user's emotions.

[0914] Data collection

[0915] The server first collects oceanographic data. Specifically, it obtains the necessary data from oceanographic data providers via API. Providers collect marine environmental data using ships, satellites, sensors, etc. For example, to obtain marine pollution data for a certain period of time, the server sets the API endpoint and parameters, sends the request, and collects the data.

[0916] Data analysis

[0917] Next, the server uses artificial intelligence algorithms to analyze the collected oceanographic data. Specifically, it uses machine learning algorithms to analyze information such as latitude, longitude, and pollution levels. This analysis makes it possible to identify pollution hotspots. For example, by using K-means clustering, pollution clusters are formed based on the features of the data, and hotspots are identified.

[0918] visualization

[0919] The contamination hotspots obtained as a result of the analysis are visualized on a map by the device. The device initializes the map and displays the location information of the identified hotspots as markers on the map. This allows the user to visually grasp the contamination situation. The map is saved as an HTML file and can be displayed through a browser.

[0920] Clean-up activity proposals

[0921] The server generates specific cleanup activity recommendations based on the identified hotspots, including countermeasures and actions to be taken for each hotspot, such as how to deploy cleanup crews at specific hotspots and their priorities.

[0922] Combining Emotion Engines

[0923] Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions. The device analyzes data such as the user's facial expressions and voice to recognize emotions and transmits that information to the server. The server then adjusts cleanup activity suggestions based on this emotion data. For example, if the user expresses strong interest or anxiety about a particular pollution situation, the server will suggest prioritizing cleanup in that area.

[0924] Specific examples

[0925] For example, the server sends an API request to collect marine pollution data from January 1, 2023 to January 31, 2023. The acquired data is analyzed and five pollution hotspots are identified based on K-means clustering. The identified hotspots are then displayed on a map, and the user can check their locations. Next, an emotion engine recognizes the user's emotional state, and the server tailors cleanup activity suggestions based on the emotion data. For example, high-priority cleanup suggestions are given to hotspots that the user is particularly interested in. Based on these suggestions, the user can create a specific cleanup plan.

[0926] The system uses vessels, satellites, and / or sensors to improve the accuracy of marine data, adopting strategies that comply with international maritime law and local environmental regulations, thereby enabling rapid and accurate identification of pollution sources, facilitating efficient cleanup efforts, and enabling effective countermeasures that are considerate of user feelings.

[0927] The processing flow will be explained below.

[0928] Step 1:

[0929] The server sets the API endpoint and parameters for collecting oceanographic data. For example, the endpoint "https: / / api.marinedata.org / ocean_data" is used, and the collection date and ocean area range are specified as parameters.

[0930] Step 2:

[0931] The server sends an API request based on the set parameters and retrieves oceanographic data from the data provider. At that time, it checks the response status code and extracts the data if it was received successfully.

[0932] Step 3:

[0933] The server extracts necessary information, such as latitude, longitude, and pollution level, from the acquired data and builds a dataset to be used for AI analysis. In this step, unnecessary data is removed and the data is formatted for analysis.

[0934] Step 4:

[0935] The server uses artificial intelligence algorithms to analyze the data, specifically applying K-means clustering to identify pollution hotspots based on latitude and longitude, thereby highlighting areas with particularly high concentrations of marine pollution.

[0936] Step 5:

[0937] The server sends the pollution hotspot data obtained as a result of the analysis to the device, which then receives it and initializes the map, specifically setting the map's default position and zoom level.

[0938] Step 6:

[0939] The device maps the location information of the identified pollution hotspots on a map and places markers on them, allowing the user to visually grasp the distribution of pollution. The generated map is saved as an HTML file and can be displayed in a browser.

[0940] Step 7:

[0941] The server acquires emotion data from the user's facial expressions and voice using an emotion engine that recognizes the user's emotions. The emotion engine analyzes the emotion data through the user-device interface and identifies the user's emotional state.

[0942] Step 8:

[0943] The server adjusts the cleanup suggestions based on the emotion data received from the emotion engine: for example, if a user expresses strong interest or concern about a particular hotspot, it may prioritize cleanup efforts in that area.

[0944] Step 9:

[0945] The server provides users with coordinated cleanup recommendations, including priority hotspots and specific cleanup actions, which they can use to develop and execute a detailed cleanup plan.

[0946] Step 10:

[0947] After the user performs the cleanup activity, the results are fed back to the server via the terminal. The server uses this feedback data to further improve the data analysis model and increase the accuracy of the next cleanup activity.

[0948] Example 2

[0949] 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."

[0950] Conventional ocean data analysis systems lack the accuracy to identify pollution hotspots, preventing efficient cleanup activities. Furthermore, because they make uniform recommendations without considering the user's feelings, pollution in areas of the user's priority may be overlooked. A system that solves these problems is needed.

[0951] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0952] In this invention, the server includes means for collecting oceanographic data, means for using an artificial intelligence algorithm to analyze the collected oceanographic data, means for identifying pollution hotspots based on the analysis results, means for visualizing the location information of the identified pollution hotspots on a map, means for suggesting cleanup activities based on the identified pollution hotspots, means for collecting and analyzing user emotion data, and means for adjusting the suggested cleanup activities based on the user emotion data, thereby enabling not only accurate identification of pollution hotspots and suggesting efficient cleanup activities but also effective countermeasures that reflect the user's emotion.

[0953] "Marine data" refers to various data related to the marine environment, including, for example, information such as latitude, longitude, pollution level, water temperature, salinity, and flow speed.

[0954] "Artificial intelligence algorithms" are computer programming technologies for performing data analysis, pattern recognition, predictions, etc., and include techniques such as machine learning and deep learning.

[0955] A "pollution hotspot" is an area of ​​concentrated pollution within a particular region.

[0956] "Location information" refers to geographic coordinate information, such as a combination of latitude and longitude that indicates a specific location.

[0957] "Visualization" is the visual display of data in the form of maps, graphs, tables, etc.

[0958] "Cleanup activities" refers to any measure or action taken to remove or reduce pollution of the marine environment.

[0959] "Emotion data" is data that expresses the user's emotional state as numerical values ​​or categories, and is collected through facial expression recognition and voice analysis.

[0960] "Adjusting suggestions" refers to changing or optimizing suggested cleanup activities based on the user's emotional data.

[0961] The present invention is a system that collects oceanographic data, identifies pollution hotspots using artificial intelligence algorithms, and analyzes users' sentiment data to tailor cleanup action recommendations. The system is implemented using a server and terminals as follows:

[0962] Data collection

[0963] The server uses APIs to collect ocean data. Specifically, it obtains data provided by ships, satellites, sensors, etc. For example, to obtain marine pollution data, it sets an API endpoint and parameters such as "https: / / api.oceandata.com / get_data?start_date=2023-01-01&end_date=2023-01-31" and sends a request to collect data.

[0964] Data analysis

[0965] The server uses artificial intelligence algorithms to analyze the acquired oceanographic data. Specifically, it uses machine learning algorithms (e.g., K-means clustering) to analyze information such as latitude, longitude, and pollution levels. This analysis identifies pollution hotspots.

[0966] visualization

[0967] The device visualizes the location information of the pollution hotspots obtained as a result of the analysis on a map. The device initializes the map using a map display library (e.g., Leaflet.js or Google Maps API) and displays the location information of the identified hotspots as markers. The user can check these markers through a browser and visually grasp the pollution situation.

[0968] Clean-up activity proposals

[0969] The server generates specific cleanup activity recommendations based on the identified hotspots, including countermeasures and actions to be taken for each hotspot, such as how to deploy cleanup crews to specific hotspots and their priorities.

[0970] Combining Emotion Engines

[0971] The device collects and analyzes the user's emotional data. Data collected through facial recognition and voice analysis expresses the user's emotional state as a numerical value or category. The device then transmits this emotional data to the server, which then adjusts its cleaning activity suggestions based on the data. For example, high-priority cleaning suggestions may be made for hotspots that the user is particularly interested in.

[0972] Specific examples

[0973] For example, the server sends an API request to collect marine pollution data from January 1, 2023 to January 31, 2023, and receives the marine pollution data in JSON format. This data is preprocessed and five pollution hotspots are identified using K-means clustering. The device initializes a map using Leaflet.js and displays the identified hotspots as markers. The user can view these hotspots on the map, and the emotion engine analyzes the user's emotional state. This emotion data is then sent to the server, which generates prioritized cleanup suggestions for hotspots of particular interest.

[0974] Prompt Sentence Examples

[0975] "Based on marine pollution data from January 1, 2023 to January 31, 2023, please identify pollution hotspots and propose cleanup activities that reflect user sentiment. Please give high priority to proposals for locations where users show particular interest."

[0976] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0977] Step 1:

[0978] The server collects oceanographic data. Specifically, it sends a request to the API endpoint "https: / / api.oceandata.com / get_data?start_date=2023-01-01&end_date=2023-01-31" to retrieve oceanographic data collected from ships, satellites, and sensors. The input is the API request, and the output is the retrieved oceanographic data (e.g., in JSON format).

[0979] Step 2:

[0980] The server preprocesses the collected oceanographic data. Specifically, it cleanses the data (processing missing values ​​and normalizing them). For example, it completes missing latitude and longitude data and standardizes pollution levels. The input of this step is the collected oceanographic data, and the output is the preprocessed, clean data.

[0981] Step 3:

[0982] The server applies a machine learning algorithm (e.g., K-means clustering) to the preprocessed data to identify pollution hotspots. Specifically, it performs clustering using latitude, longitude, and pollution level as features to extract areas where pollution is concentrated. The input of this step is the preprocessed data, and the output is a list of identified pollution hotspots.

[0983] Step 4:

[0984] The device visualizes the location information of the identified pollution hotspots on a map. Specifically, it initializes the map using Leaflet.js and Google Maps API and displays the hotspot locations as markers. The input of this step is the location information of the hotspots, and the output is the visualized map.

[0985] Step 5:

[0986] The server generates specific cleanup action proposals based on the identified hotspots, including the deployment of clean crews for each hotspot, the proposed equipment to use, and their priorities. The input to this step is the identified hotspots, and the output is the cleanup action proposals.

[0987] Step 6:

[0988] The device collects and analyzes the user's emotional data. Specifically, it uses a webcam and microphone to analyze the user's facial expressions and voice and estimates their emotional state. The input for this step is the user's facial and voice data, and the output is the emotional data resulting from the analysis.

[0989] Step 7:

[0990] The device sends the collected emotion data to the server, which then adjusts the cleaning activity suggestions based on the emotion data. Specifically, the suggestions are modified to prioritize cleaning hotspots that the user is particularly interested in. The input of this step is emotion data, and the output is the adjusted cleaning activity suggestions.

[0991] An example of a specific prompt is, "Based on marine pollution data from January 1, 2023 to January 31, 2023, please identify pollution hotspots and propose cleanup activities that reflect user sentiment. Please give high priority to suggestions for locations where users show particular interest."

[0992] (Application example 2)

[0993] 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."

[0994] This invention relates to a system for identifying pollution hotspots and proposing cleanup activities using marine data, and aims to solve the problem of providing a more effective method to increase participation by proposing cleanup activities that take user emotions into account. Specifically, the purpose of this invention is to solve the problem that conventional systems do not take user emotions into account and prioritize and propose cleanup activities in a uniform manner, which makes it difficult to respond flexibly to users' interests and concerns.

[0995] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0996] In this invention, the server includes means for collecting oceanographic data, means for using an artificial intelligence algorithm to analyze the collected oceanographic data, means for identifying pollution hotspots based on the analysis results, means for visualizing the location information of the identified pollution hotspots on a map, means for suggesting cleanup activities based on the identified hotspots, and means for recognizing a user's emotions and adjusting the suggested cleanup activities based on the emotion data, thereby enabling visualization of the pollution situation and flexible suggestions of cleanup activities that take the user's emotions into consideration.

[0997] "Marine data" refers to information about the marine environment, including, for example, water quality data, pollutant concentrations, weather information, and marine ecosystem data.

[0998] "Artificial intelligence algorithms" refer to computational processes for analyzing large amounts of data and extracting useful information and patterns from it, and include machine learning, deep learning, and clustering techniques.

[0999] A "pollution hotspot" is an area in a particular region where the level of pollution is significantly higher than in other surrounding areas.

[1000] "Visualization" refers to displaying data in a format that is intuitively easy to understand (for example, a map or graph), and visually representing data such as location information and pollution levels.

[1001] "Cleanup activities" refers to specific methods and means for removing or reducing discovered contamination, including, for example, cleaning operations and methods for removing contaminants.

[1002] "Emotion recognition" refers to the process of analyzing data such as a user's facial expressions and voice to identify their emotional state (e.g., excitement, sadness, anxiety, joy, etc.).

[1003] "Server" refers to a computer system for collecting, analyzing, storing, and managing data.

[1004] The system of the present invention collects oceanographic data, uses artificial intelligence algorithms to identify pollution hotspots, and then recognizes user sentiment to tailor cleanup recommendations. The system is implemented in the following steps:

[1005] First, the server collects oceanographic data. This collection is done by obtaining data from sources via API. Sources include ships, satellites, and sensors, and the server receives the highly accurate oceanographic data collected by these sources.

[1006] The server analyzes the collected data using artificial intelligence algorithms. This analysis uses machine learning techniques such as K-means clustering based on information such as latitude, longitude, and pollution level to identify pollution hotspots. Clusters are formed based on the characteristics of the data, and areas with particularly high levels of pollution are identified as hotspots.

[1007] Next, the device visualizes the location information of the identified pollution hotspots on a map. The device initializes the map and displays the location information of the identified hotspots as markers, allowing the user to visually grasp the pollution situation. The map is saved as an HTML file and can be displayed through a browser.

[1008] Additionally, the server generates specific cleanup action recommendations based on the identified hotspots, including recommendations on how and prioritizing cleanup crew deployment at specific hotspots.

[1009] A distinctive feature of the present invention is an emotion engine that recognizes a user's emotions. The device analyzes data such as the user's facial expressions and voice to identify the user's emotional state. The emotion engine can utilize, for example, facial recognition software or tone-of-voice analysis tools. The recognized emotion data is sent to a server, which then tailors cleanup activity suggestions based on the emotion data. For example, if the user expresses strong concern or anxiety about a particular pollution situation, suggestions to prioritize cleanup in that area are made.

[1010] As a specific example, a server sends an API request to collect marine pollution data from January 1, 2023 to January 31, 2023. The acquired data is analyzed and five pollution hotspots are identified based on K-means clustering. The identified hotspots are then displayed on a map, and the user can check their locations. Next, an emotion engine recognizes the user's emotional state, and the server tailors cleanup activity suggestions based on the emotion data. For example, high-priority cleanup suggestions are made for hotspots that the user is particularly interested in. Based on these suggestions, the user can create a specific cleanup plan.

[1011] An example of a prompt for a generative AI model is as follows:

[1012] "Collect marine pollution data from January 1, 2023 to January 31, 2023 and identify pollution hotspots using K-means clustering. Then collect user sentiment data, display the identified hotspots on a map, and generate cleanup action suggestions based on user sentiment."

[1013] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1014] Step 1:

[1015] The server collects oceanographic data via API. It sets the API endpoint and parameters and retrieves data from sources such as ships, satellites, and sensors. The input is the parameters included in the API request, and the output is the collected oceanographic data. This data includes information such as latitude, longitude, and pollution level.

[1016] Step 2:

[1017] The server applies an artificial intelligence algorithm to analyze the collected oceanographic data. Specifically, it uses K-means clustering to identify pollution hotspots based on the data's features. The input is the collected oceanographic data, and the output is cluster information for the identified pollution hotspots. Data processing involves clustering using latitude and longitude as features.

[1018] Step 3:

[1019] The terminal visualizes the location information of the identified pollution hotspots on a map. The input is the cluster information of the pollution hotspots sent from the server, and the output is markers of the hotspots displayed on the map. The operation is to initialize the map and place markers at the locations of the hotspots.

[1020] Step 4:

[1021] The server generates cleanup action proposals based on the identified hotspots. The input is the hotspot locations and their contamination levels, and the output is specific cleanup action proposals, including the location and priority of cleanup crews.

[1022] Step 5:

[1023] The device recognizes the user's emotions in real time. The input is the user's facial image and voice data, and the output is the recognized emotional state. In actual operation, the device uses emotion recognition software to analyze the user's emotions.

[1024] Step 6:

[1025] The server adjusts cleanup activity suggestions based on the emotion data sent from the device. The input is emotion data and existing cleanup suggestions, and the output is new cleanup suggestions adjusted with the emotion data. If the user expresses strong interest or concern about a particular hotspot, the server will make suggestions that prioritize cleanup in that area.

[1026] 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.

[1027] 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.

[1028] 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 robot 414.

[1029] 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.

[1030] 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.

[1031] 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.

[1032] 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).

[1033] 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, motorcycles, and other devices, 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.

[1034] 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."

[1035] 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.

[1036] 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).

[1037] 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.

[1038] 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.

[1039] 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.

[1040] 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.

[1041] 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.

[1042] 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.

[1043] 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.

[1044] 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.

[1045] 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.

[1046] 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.

[1047] The following is further disclosed regarding the above embodiment.

[1048] (Claim 1)

[1049] a means for collecting oceanographic data;

[1050] means for using artificial intelligence algorithms to analyze the collected oceanographic data;

[1051] A means of identifying contamination hotspots based on the analysis results;

[1052] A means for visualizing the location information of identified contamination hotspots on a map;

[1053] a means of suggesting cleanup activities based on identified hotspots;

[1054] A system including:

[1055] (Claim 2)

[1056] 10. The system of claim 1, which implements a strategy to comply with international maritime law and local environmental regulations.

[1057] (Claim 3)

[1058] 10. The system of claim 1, wherein the collection means comprises at least one of a vessel, a satellite, and a sensor to improve the accuracy of the collected oceanographic data.

[1059] "Example 1"

[1060] (Claim 1)

[1061] a means for collecting oceanographic data;

[1062] means for using artificial intelligence algorithms to analyze the collected oceanographic data;

[1063] A means of identifying contamination hotspots based on the analysis results;

[1064] A means for visualizing the location information of identified contamination hotspots on a map;

[1065] a means of suggesting cleanup activities based on identified hotspots;

[1066] A means to preprocess the collected data and configure machine learning algorithms to perform the analysis;

[1067] A means for displaying the analysis results as markers on a map using a map display component;

[1068] A system including:

[1069] (Claim 2)

[1070] 10. The system of claim 1, which implements strategies that comply with international standards and local regulations.

[1071] (Claim 3)

[1072] 2. The system according to claim 1, wherein the collection means comprises at least one of a mobile object, a remote sensing device, and a sensor device to improve the accuracy of the collected data.

[1073] "Application Example 1"

[1074] (Claim 1)

[1075] a means for collecting contamination data;

[1076] a means for using machine learning algorithms to analyze the collected contamination data;

[1077] A means of identifying hotspots based on the analysis results;

[1078] A means for visualizing the location information of the identified hotspots on a map;

[1079] A means of proposing cleanup activities based on contamination hotspots within logistics facilities;

[1080] A system including:

[1081] (Claim 2)

[1082] 10. The system of claim 1, which implements strategies that comply with international standards and local environmental regulations.

[1083] (Claim 3)

[1084] The system of claim 1, wherein the collection means comprises at least one of a sensor, a network device, and a data collection device to improve the accuracy of the collected pollution data.

[1085] "Example 2: Combining Emotion Engines"

[1086] (Claim 1)

[1087] a means for collecting oceanographic data;

[1088] means for using artificial intelligence algorithms to analyze the collected oceanographic data;

[1089] A means of identifying contamination hotspots based on the analysis results;

[1090] A means for visualizing the location information of identified contamination hotspots on a map;

[1091] a means of suggesting cleanup activities based on identified hotspots;

[1092] means for collecting and analyzing user emotion data;

[1093] means for tailoring suggested cleanup activities based on the user's sentiment data;

[1094] A system including:

[1095] (Claim 2)

[1096] 10. The system of claim 1, which implements a strategy to comply with international maritime law and local environmental regulations.

[1097] (Claim 3)

[1098] 10. The system of claim 1, wherein the collection means comprises at least one of a vessel, a satellite, and a sensor to improve the accuracy of the collected oceanographic data.

[1099] "Application example 2 when combining emotion engines"

[1100] New Claims

[1101] (Claim 1)

[1102] a means for collecting oceanographic data;

[1103] means for using artificial intelligence algorithms to analyze the collected oceanographic data;

[1104] A means of identifying contamination hotspots based on the analysis results;

[1105] A means for visualizing the location information of identified contamination hotspots on a map;

[1106] a means of suggesting cleanup activities based on identified hotspots;

[1107] means for recognizing a user's emotions and tailoring suggested cleanup activities based on the emotion data;

[1108] A system including:

[1109] (Claim 2)

[1110] 10. The system of claim 1, which implements a strategy to comply with international maritime law and local environmental regulations.

[1111] (Claim 3)

[1112] 10. The system of claim 1, wherein the collection means comprises at least one of a vessel, a satellite, and a sensor to improve the accuracy of the collected oceanographic data. [Explanation of symbols]

[1113] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting oceanographic data; means for using artificial intelligence algorithms to analyze the collected oceanographic data; A means of identifying contamination hotspots based on the analysis results; A means for visualizing the location information of identified contamination hotspots on a map; a means of suggesting cleanup activities based on identified hotspots; A system including:

2. 10. The system of claim 1, which implements a strategy to comply with international maritime laws and local environmental regulations.

3. 10. The system of claim 1, wherein the collection means comprises at least one of a vessel, a satellite, and a sensor to improve the accuracy of the collected oceanographic data.

Images