System

Abstract

To provide a system.SOLUTION: A system includes: means for analyzing various data including data relating to any one of the sea, on the sea, and fish; means for acquiring, by using a prompt sentence that gives instruction on generation of a behavior prediction for fish species to be caught and a generative AI model, a behavior prediction result of the fish species; means for displaying the acquired behavior prediction result of the fish species in real time on at least one of a nautical chart and location information on a fish finder; means for optimizing the navigation route of a self-driving vehicle based on the acquired behavior prediction result of the fish species; and means for acquiring and notifying the timing of fish catch based on the acquired behavior prediction result of the fish species.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] In conventional fishing, it was difficult to predict catch volumes and the behavior of fish species, making it difficult to conduct fishing efficiently. [Means for solving the problem]

[0005] The present invention analyzes various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, rate of temperature change due to global warming, etc.) to create predictions of the behavior of target fish species, etc. It predicts where the target fish species will be moving at a specific time period and displays the information in real time on the fish finder's nautical chart and GPS, improving the catch volume in the fishing industry. This makes it possible to predict the catch volume and the behavior of fish species, enabling more efficient fishing. [Brief description of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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. 2 is a sequence diagram showing a process flow of the data processing system in the first embodiment of the first form example. [Figure 12] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the application example 1 of the first embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second embodiment. [Figure 14] FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. [Figure 15] FIG. 13 is a sequence diagram showing a process flow of a data processing system in a third embodiment of the present invention. [Figure 16] FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third application example of the third embodiment. [Figure 17] FIG. 11 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0011] 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.

[0012] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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 wide area network (WAN) and / or a local area network (LAN).

[0018] 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.

[0019] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. 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.

[0020] 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 (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0023] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

[0024] 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.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] In one embodiment of the present invention, a fishing boat is equipped with sensors and data collection devices for collecting various data (such as nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, and rate of temperature change due to global warming). These data are sent to a central data processing device and analyzed using machine learning algorithms. The analysis results are generated as a behavior prediction of the target fish species, and predict where the target fish species will be moving at a specific time period. The prediction results are displayed in real time on the nautical charts and GPS on the fish finder, allowing fishermen to efficiently select fishing locations.

[0029] "Example 2"

[0030] As a specific example, consider a fishing boat that fishes for tuna. Various data on the ecology of tuna and ocean conditions are collected, and predictions of tuna behavior are made based on this data. For example, based on data such as seawater temperature, salinity, and tides, the areas that tuna prefer can be predicted, and the fishing boat can be moved to those areas. Also, based on data such as temperature, moon phase, and tide graphs, the times when tuna will be active can be predicted, and fishing can be carried out at those times. This makes it possible to significantly increase the catch.

[0031] The process flow of each embodiment will be described below.

[0032] "Example 1"

[0033] Step 1: Sensors and data collection devices are installed on the fishing boat to collect various data (nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar phase, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of temperature change due to global warming, etc.).

[0034] Step 2: The collected data is transmitted to a central data processing device.

[0035] Step 3: The data processor uses machine learning algorithms to analyze the data and generate behavioral predictions for the fish species being fished.

[0036] Step 4: Predict where the target fish species will be moving at a specific time and display this prediction in real time on the chart and GPS on the fish finder.

[0037] "Example 2"

[0038] Step 1: Sensors and data collection devices will be installed on tuna fishing boats to collect various data on tuna ecology and ocean conditions.

[0039] Step 2: The collected data is transmitted to a central data processing device.

[0040] Step 3: The data processor uses machine learning algorithms to analyze the data and generate predictions of tuna behavior.

[0041] Step 4: Using data on seawater temperature, salinity, tidal currents, etc., predict the areas preferred by tuna and move fishing boats to those areas.

[0042] Step 5: Using data such as temperature, moon phase, and tide graphs, predict the times when the tuna will be active and fish during those times.

[0043] Example 1

[0044] Next, a description will be given of Example 1 of the embodiment 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".

[0045] In conventional fishing, it was difficult for fishermen to accurately determine the location of schools of fish, making it difficult to increase catches. In addition, there was a lack of systems that could efficiently collect and analyze a wide variety of data, such as meteorological and oceanographic information, and provide it to fishermen in real time. This reduced the efficiency of fishing and made it difficult to predict catches.

[0046] 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.

[0047] In this invention, the server includes a means for collecting various data (map information, location information, weather information, ocean information, wind speed information, tidal current information, lunar age information, tide information, fishing information, fishing location information, marine life information, salinity concentration information, climate change information, etc.), a means for transmitting the collected data to a central data processing device, a means for receiving the transmitted data and performing preprocessing, a means for analyzing the preprocessed data using a machine learning algorithm, a means for generating a behavior prediction of fish species based on the analysis result, a means for transmitting the generated behavior prediction result to a terminal, and a means for displaying the prediction result on the terminal in real time. This enables fishermen to grasp the location of schools of fish in real time and efficiently select fishing spots.

[0048] "Various data" refers to map information, location information, weather information, ocean information, wind speed information, current information, lunar age information, tidal information, fishing information, fishing location information, marine life information, salinity concentration information, climate change information, etc.

[0049] "Means of collection" refers to the equipment and methods used to obtain various data using sensors and data collection devices installed on fishing vessels.

[0050] "Central Data Processing Unit" refers to a computer system for receiving, pre-processing and analyzing collected data.

[0051] "Transmitting means" refers to a device or method for transmitting collected data to a central data processing device using wireless or wired communication.

[0052] "Preprocessing means" refers to software or algorithms for filling in missing values ​​or correcting outliers in the received data.

[0053] "Machine learning algorithms" refers to artificial intelligence techniques for analyzing data and creating patterns and predictions.

[0054] "Means for generating a behavioral prediction" refers to software or algorithms for predicting behavioral patterns of fish species using machine learning algorithms.

[0055] "Terminal" refers to fish finders and other display devices installed on fishing vessels.

[0056] "Means for displaying in real time" refers to software or hardware for instantly displaying the generated behavior prediction results on a terminal.

[0057] "Means for improving catch" refers to methods and devices for increasing catch by accurately determining the location of fish schools and efficiently selecting fishing spots.

[0058] The present invention is a system for improving catches in the fishing industry, which collects various data, analyzes them using machine learning algorithms, and generates predictions of fish species behavior. A specific embodiment of the system will be described below.

[0059] Data collection

[0060] The user (fisherman) uses sensors and data collection devices installed on the fishing boat to collect various data such as map information, location information, weather information, ocean information, wind speed information, tidal current information, lunar age information, tide information, fishing catch information, fishing location information, marine life information, salinity concentration information, climate change information, etc. For example, an air temperature sensor measures 25°C and a seawater temperature sensor measures 20°C.

[0061] Data transmission

[0062] The terminal (data collection device on the fishing boat) transmits the collected data to the central data processing device using wireless communication (e.g., Wi-Fi (registered trademark) or satellite communication). For example, the data is transmitted using a Wi-Fi module.

[0063] Data reception and preprocessing

[0064] The server receives data sent from the terminal. For the received data, a data frame is created using the Python (registered trademark) pandas library, missing values ​​are complemented, and outliers are detected and corrected. For example, missing values ​​are complemented with the average value, and outliers are corrected with the median value.

[0065] Data analysis

[0066] The server inputs the preprocessed data into a machine learning algorithm (e.g., TENSORFLOW® or PyTorch®) for analysis. For example, a random forest model is used to predict the behavioral patterns of fish species.

[0067] Generate behavioral predictions

[0068] Based on the analysis results, the server generates a prediction of the behavior of fish species, for example, a prediction that mackerel will move to 35 degrees north latitude and 140 degrees east longitude during a specific time period.

[0069] Sending and viewing results

[0070] The server sends the generated behavior prediction results to the terminal. For example, it sends the prediction results in JSON format using the HTTP protocol. The terminal (fish finder) displays the received prediction results in real time. For example, it displays a nautical chart and GPS information on the fish finder display, overlaying them, and indicates the predicted location of the school of fish with a marker.

[0071] Examples

[0072] For example, a fisherman might collect the following data using sensors on his boat:

[0073] Nautical Chart Data GPS data Temperature: 25°C Sea water temperature: 20°C Wind speed: 5m / s Current: 1m / s Moon age: 15 days Tide Graph: High Tide Catch: 100kg Fishing location: 35 degrees north latitude, 139 degrees east longitude Ecology of fish and shellfish: Mackerel Salinity: 3.5% Rate of temperature change due to global warming: 0.02°C / year

[0074] This data is sent to a central data processor where it is analysed using machine learning algorithms, which generate predictions of when mackerel will move to 35 degrees north and 140 degrees east at a specific time, and which are then displayed in real time on the charts and GPS on the fish finder.

[0075] Examples of prompt statements

[0076] Examples of prompts to be input to a generative AI model include:

[0077] "Please predict the behavior of mackerel based on the following data:

[0078] Nautical Chart Data GPS data Temperature: 25°C Sea water temperature: 20°C Wind speed: 5m / s Current: 1m / s Moon age: 15 days Tide Graph: High Tide Catch: 100kg Fishing location: 35 degrees north latitude, 139 degrees east longitude Ecology of fish and shellfish: Mackerel Salinity: 3.5% Rate of temperature change due to global warming: 0.02°C / year

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

[0080] Step 1: Data collection

[0081] Users (fishermen) use sensors and data collection devices installed on their fishing boats to collect various data such as map information, location information, weather information, ocean information, wind speed information, tidal current information, lunar phase information, tide information, fishing catch information, fishing location information, marine life information, salinity concentration information, and climate change information. For example, an air temperature sensor measures 25°C and a seawater temperature sensor measures 20°C. The input is data from various sensors, and the output is the collected data.

[0082] Step 2: Send data

[0083] The terminal (data collection device on the fishing boat) transmits the collected data to the central data processing device using wireless communication (e.g. Wi-Fi or satellite communication). For example, a Wi-Fi module is used to transmit the data. The input is the collected data and the output is the data transmitted to the central data processing device.

[0084] Step 3: Receiving data

[0085] The server receives data sent from the terminal. It opens a receiving port to wait for data and temporarily stores the received data. The input is the data sent from the terminal, and the output is the data stored in the server.

[0086] Step 4: Data Preprocessing

[0087] The server preprocesses the received data. Specifically, it uses the pandas library of Python (registered trademark) to create a data frame, impute missing values, and detect and correct outliers. For example, if there are missing values, they are imputed with the mean value, and if there are outliers, they are corrected with the median value. The input is the received data, and the output is the preprocessed data.

[0088] Step 5: Data analysis

[0089] The server inputs the preprocessed data into a machine learning algorithm (e.g., TensorFlow (registered trademark) or PyTorch (registered trademark)) and performs analysis. For example, a random forest model is used to predict the behavioral patterns of fish species. The input is the preprocessed data, and the output is the analysis result.

[0090] Step 6: Generate behavior predictions

[0091] The server generates a behavioral prediction for the fish species based on the analysis results. For example, it generates a prediction that mackerel will move to 35 degrees north latitude and 140 degrees east longitude during a specific time period. The input is the analysis results, and the output is the behavioral prediction results.

[0092] Step 7: Sending results

[0093] The server transmits the generated behavior prediction result to the terminal. For example, the prediction result is transmitted in JSON format using the HTTP protocol. The input is the behavior prediction result, and the output is the prediction result transmitted to the terminal.

[0094] Step 8: View the results

[0095] The terminal (fish finder) displays the received prediction results in real time. For example, a marine chart and GPS information are overlaid on the fish finder display, and the predicted locations of the schools of fish are indicated with markers. The input is the prediction results sent from the server, and the output is the prediction results displayed on the display.

[0096] (Application example 1)

[0097] Next, a description will be given of Application Example 1 of Form 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."

[0098] In traditional fishing, fishermen often relied on experience and intuition to select fishing spots, making it difficult to catch fish efficiently. In addition, fishing boats also required manual operation, which was labor-intensive and time-consuming. Furthermore, there was a lack of real-time data analysis to respond to changes in weather conditions and the marine environment, making it difficult to increase catches.

[0099] 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. In this invention, the server includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for creating a behavior prediction of the target fish species, etc., a means for predicting where the target fish species are moving in a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, a means for improving the catch in the fishing industry, a means for updating the navigation system of the autonomous fishing boat, a means for predicting the behavior of fish using data collected in real time, and a means for moving the autonomous fishing boat to the optimal fishing spot based on the prediction result. This allows not only fishers to efficiently select fishing spots, but also allows the autonomous fishing boat to automatically move to the optimal fishing spot.

[0100] "Various data" refers to information such as nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and the rate of temperature change due to global warming.

[0101] "Means for analyzing" refers to methods and devices for analyzing various collected data and extracting meaningful information.

[0102] "Means for creating a behavioral prediction" refers to a method or device that constructs a predictive model based on collected data and generates the results in order to predict the behavior of a target fish species.

[0103] "Means for displaying in real time" refers to a method or device for instantly displaying the prediction results on a chart or GPS on a fish finder.

[0104] "Measures to improve fishing yield" refers to methods or devices that increase fishing yield by assisting in the selection of efficient fishing sites and the operation of fishing vessels.

[0105] "Means for updating the navigation system of an autonomous fishing vessel" refers to a method or device for correcting and updating the route and operation plan of an autonomous fishing vessel in real time based on the prediction results.

[0106] "Means for predicting fish behavior using data collected in real time" refers to a method or device for instantly predicting fish behavior based on the latest data obtained from sensors and data collection devices.

[0107] "Means for moving an autonomous fishing vessel to an optimal fishing location based on prediction results" refers to a method or device for automatically moving an autonomous fishing vessel to the most efficient fishing location based on the results of behavioral prediction.

[0108] The system for carrying out this invention collects data obtained from various sensors and data collection devices mounted on fishing boats in real time, and analyzes the data in a central data processing device to predict the behavior of specific fish species. A specific embodiment of this system will be described below.

[0109] Hardware and Software Used

[0110] Hardware

[0111] Various sensors: GPS, temperature sensor, sea water temperature sensor, anemometer, tide gauge, salinity meter, etc.

[0112] Data collection equipment: A device that collects data from sensors and transmits it to a central data processing device.

[0113] Central Data Processing Unit: A computer equipped with a high-performance CPU / GPU.

[0114] software

[0115] Python(registered trademark): A programming language.

[0116] scikit-learn: A machine learning library.

[0117] pandas: A data processing library.

[0118] matplotlib: A data visualization library.

[0119] Data processing and calculation

[0120] Data collection

[0121] The sensors collect data in real time, including GPS location, air temperature, seawater temperature, wind speed, tides, moon phase, tide graphs, catch volume, fishing location, fish and shellfish ecology, salinity, and the rate of temperature change due to global warming.

[0122] Data Preprocessing

[0123] Convert the collected data into a data frame and impute missing values, thereby ensuring data consistency and accuracy.

[0124] Training the model

[0125] A random forest regression model is trained using historical data, which allows us to build a fish behavior prediction model.

[0126] Behavioral Prediction

[0127] The data collected in real time is used to predict fish behavior, and the prediction results are displayed in real time on the fish finder's nautical chart and GPS.

[0128] Navigation system updates

[0129] The prediction results are used to update the navigation system of autonomous fishing boats, allowing them to automatically navigate to the optimal fishing spots.

[0130] Examples

[0131] For example, if it is predicted that a fishing vessel needs to move 10km northeast from its current position, the navigation system will automatically move the vessel in that direction.

[0132] Examples of prompt statements

[0133] "Enter the current GPS location, air temperature, seawater temperature, wind speed, tides, moon phase, tide graph, catch volume, fishing location, fish and shellfish ecology, salinity, and rate of temperature change due to global warming, and predict the location with the best chance of catching fish within the next hour."

[0134] In this way, by applying the invention to the navigation system of an autonomous fishing boat, more efficient fishing becomes possible.

[0135] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0136] Step 1:

[0137] Collecting data from sensors

[0138] The server collects data in real time from various sensors (GPS, temperature sensor, seawater temperature sensor, anemometer, tide gauge, salinity meter, etc.). As input, it receives measurements from each sensor and sends them to the data collector. As output, the collected data is stored in data frame format.

[0139] Step 2:

[0140] Data Preprocessing

[0141] The server converts the collected data into a data frame and imputes missing values. As input, it takes the data collected in step 1 and converts it into a data frame. If there are missing values, it imputes them with the previous value. As output, it obtains a preprocessed data frame.

[0142] Step 3:

[0143] Training a machine learning model

[0144] The server trains a random forest regression model using historical data. As input, it receives a preprocessed data frame and separates it into features and target variables. The features include air temperature, seawater temperature, wind speed, and currents, while the target variables include fish location information. As output, it obtains a trained machine learning model.

[0145] Step 4:

[0146] Real-time data collection

[0147] The server collects new data from the sensors in real time. As input, it takes the latest measurements from each sensor and adds them to a data frame. As output, it gets a data frame with the latest data.

[0148] Step 5:

[0149] Predicting fish behavior

[0150] The server uses the collected data in real time to predict the fish behavior. As input, it receives the latest data frame obtained in step 4 and feeds it into the trained machine learning model. As output, it obtains the predicted fish behavior result.

[0151] Step 6:

[0152] Navigation system updates

[0153] The server updates the navigation system of the autonomous fishing vessel based on the prediction results. As input, it receives the fish behavior prediction results obtained in step 5 and calculates the optimal fishing spot. As output, it obtains the updated navigation system instructions.

[0154] Step 7:

[0155] Autonomous Driving of Fishing Boats

[0156] The terminal moves the autonomous fishing vessel to the optimal fishing spot according to the updated navigation system instructions. As input, it receives the navigation system instructions obtained in step 6 and reflects them in the fishing vessel's operation system. As output, the fishing vessel automatically moves to the optimal fishing spot.

[0157] In this way, efficient fishing can be achieved through each step.

[0158] Example 2

[0159] Next, a second embodiment of the second embodiment will be described. 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."

[0160] In conventional fishing, data collection and analysis to predict the location and behavior of fish schools was insufficient, making it difficult to increase catches. In addition, there was a problem that efficient fishing could not be carried out because predictions of fish species' behavior were inaccurate. This reduced the efficiency of fishing and often resulted in economic losses.

[0161] 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.

[0162] In this invention, the server includes a means for collecting various data (nautical charts, location information, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for transmitting the collected data to the server via a communication module, a means for storing the received data in a database, a means for analyzing the stored data, a means for predicting the behavior of fish species from the analyzed data using a generative AI model, a means for displaying the prediction results on a terminal, and a means for improving the catch in the fishing industry. This makes it possible to accurately predict the location and behavior of schools of fish and to conduct efficient fishing.

[0163] "Various data" refers to information such as nautical charts, location information, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of seafood, salinity concentration, and the rate of temperature change due to global warming.

[0164] "Means of collection" refers to the method of obtaining various data using sensors and data collection devices installed on fishing vessels.

[0165] "Communication module" refers to a communication device for transmitting collected data to a server.

[0166] "Database" refers to an information system for storing and managing received Data.

[0167] "Analysis means" refers to the methods and techniques used to process the stored data and convert it into meaningful information.

[0168] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to make predictions and classifications from data.

[0169] "Behavioral prediction" refers to predicting the movement and activity patterns of fish species based on analyzed data.

[0170] "Terminal" refers to a device for displaying prediction results.

[0171] "Measures to improve catches" refers to methods and technologies for fishing efficiently based on prediction results and increasing catches.

[0172] The present invention relates to a system for collecting and analyzing various data and predicting the behavior of fish species in order to improve catches in the fishing industry. A specific embodiment of this system will be described below.

[0173] Hardware and Software Used

[0174] Hardware: Sensors installed on fishing boats (seawater temperature sensor, salinity sensor, tide gauge, etc.), GPS, communication module

[0175] Software: Data collection software, data analysis software, generative AI models (e.g., using TensorFlow® or PyTorch®)

[0176] Data collection and transmission

[0177] The terminal uses various sensors installed on the fishing boat to collect data on seawater temperature, salinity, currents, etc. in real time. For example, the seawater temperature sensor measures the current seawater temperature, and the salinity sensor measures the salinity. The collected data is sent to a server via a communication module.

[0178] Data storage and analysis

[0179] The server saves the received data in a database. For example, the data is stored in a MySQL® database. The saved data is preprocessed using a Python® script. Specifically, missing values ​​of the data are complemented and normalization is performed.

[0180] Behavioral Prediction

[0181] The server uses a generative AI model to predict the behavior of fish species from the analyzed data. For example, the prediction is made using a TensorFlow (registered trademark) model. The behavior of fish species is predicted by inputting the following prompt sentence into the generative AI model.

[0182] Example prompt:

[0183] The current seawater temperature is 25 degrees, the salinity is 3.5%, the tide is 1.2 knots in the northeast direction, the air temperature is 20 degrees, the moon is a full moon, and the tide chart shows a rising tide. Under these conditions, please predict the preferred waters of the fish species and the time of day when they will be active.

[0184] Displaying the results and executing the fishery

[0185] The terminal displays the prediction results sent from the server on the fishing boat's terminal. For example, the display may show, "The preferred sea area for this fish species is 35 degrees north latitude and 140 degrees east longitude. The time period when they are active is from 2:00 pm to 4:00 pm." Based on this prediction result, the user (fisherman) moves the fishing boat to the preferred sea area for the fish species and fishes according to the time period when they are active.

[0186] In this way, by performing specific actions at each step, the system achieves efficient fishing based on predictions of fish species' behavior.

[0187] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0188] Step 1:

[0189] Data collection

[0190] The terminal uses various sensors installed on the fishing boat to collect data on seawater temperature, salinity, currents, etc. in real time. For example, the seawater temperature sensor measures the current seawater temperature, and the salinity sensor measures the salinity.

[0191] Input: Data from ocean temperature sensor, salinity sensor, and tide gauge

[0192] Output: Collected ocean temperature, salinity, and current data

[0193] Step 2:

[0194] Data transmission

[0195] The terminal transmits the collected data to a server via a communication module. For example, collected data on seawater temperature, salinity, and currents is sent as packets.

[0196] Input: Collected ocean temperature, salinity, and current data

[0197] Output: Data packet sent to the server

[0198] Step 3:

[0199] Data Storage

[0200] The server stores the received data in a database, for example a MySQL database.

[0201] Input: Data packet sent to the server

[0202] Output: Data stored in the database

[0203] Step 4:

[0204] 4. Data Analysis

[0205] The server analyzes the stored data, for example by using Python scripts to preprocess the data, such as by imputing missing values ​​and normalizing the data.

[0206] Input: Data stored in the database

[0207] Output: Preprocessed data

[0208] Step 5:

[0209] Behavioral Prediction

[0210] The server uses a generative AI model to predict the behavior of fish species from the analyzed data. For example, the prediction is made using a TensorFlow (registered trademark) model. The behavior of fish species is predicted by inputting the following prompt sentence into the generative AI model.

[0211] Input: Preprocessed data, prompt statement

[0212] Output: Fish species behavior prediction results

[0213] Example prompt:

[0214] The current seawater temperature is 25 degrees, the salinity is 3.5%, the tide is 1.2 knots in the northeast direction, the air temperature is 20 degrees, the moon is a full moon, and the tide chart shows a rising tide. Under these conditions, please predict the preferred waters of the fish species and the time of day when they will be active.

[0215] Step 6:

[0216] Results display

[0217] The terminal displays the prediction results sent from the server on the fishing boat's terminal. For example, the display might say, "The fish species' preferred sea area is 35 degrees north latitude and 140 degrees east longitude. They are most active between 2:00 and 4:00 p.m."

[0218] Input: Fish species behavior prediction results

[0219] Output: Prediction results displayed on the terminal

[0220] Step 7:

[0221] Fishing

[0222] Based on the prediction results, users (fishermen) can move their fishing boats to areas favored by fish species and fish during times when the fish species are most active.

[0223] Input: Prediction result displayed on the device

[0224] Output: Movement of fishing vessels and execution of fishing

[0225] (Application example 2)

[0226] Next, a description will be given of Application Example 2 of Form 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."

[0227] Conventional fishing systems had problems with low fishing efficiency due to insufficient data analysis and behavioral prediction to improve catches. In addition, optimization of fishing boat routes and notifications of fishing timing were done manually, which placed a heavy burden on fishermen and made it difficult to fish efficiently.

[0228] 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.

[0229] In this invention, the server includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, moon age, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, rate of temperature change due to global warming, etc.), a means for creating a behavior prediction for the target fish species, etc., a means for predicting where the target fish species are moving during a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, a means for improving the catch volume in the fishing industry, a means for optimizing the navigation route of the autonomous vehicle, a means for notifying the timing of fishing, a means for predicting behavior using a generative AI model, and a means for generating prompt sentences. This makes it possible to significantly improve the efficiency of the fishing industry.

[0230] "Various data" refers to information such as nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and the rate of temperature change due to global warming.

[0231] "Means for analysis" refers to methods and devices for analyzing various collected data and extracting meaningful information.

[0232] "Means for generating a behavioral prediction" refers to a method or device that uses the calculations and models necessary to predict the behavior of a target fish species.

[0233] "Means for displaying in real time" refers to a method or device for instantly reflecting the prediction results on a display device.

[0234] "Fishing yield enhancing measures" means any method or device used to increase the yield in a fishery.

[0235] "Means for optimizing the navigation route of an autonomous vehicle" refers to a method or device for an autonomous vehicle to select and navigate an optimal route.

[0236] "Fishing timing communication means" means a method or device that informs fishermen of the optimal time to fish.

[0237] A "generative AI model" refers to a model that uses artificial intelligence to make predictions and generate information from data.

[0238] "Means for generating prompt sentences" refers to a method or device for creating instruction sentences to be input into a generative AI model.

[0239] The system for carrying out the present invention collects and analyzes various data, predicts behavior, optimizes the navigation route of an autonomous vehicle based on the results, and notifies the timing of fishing. A specific embodiment of this system will be described below.

[0240] System Configuration

[0241] The system consists of the following main components:

[0242] 1. Data collection module:

[0243] Various data are collected, such as nautical charts, GPS, air temperature, sea water temperature, wind speed, currents, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and the rate of temperature change due to global warming.

[0244] Sensors and satellite communications are used to collect data.

[0245] 2. Data Analysis Module:

[0246] Analyze the collected data and extract meaningful information.

[0247] Analyze the data using machine learning algorithms.

[0248] 3. Behavioral Prediction Module:

[0249] Generative AI models are used to predict the behavior of target fish species.

[0250] Based on the prediction results, the results are displayed in real time on the fish finder's nautical chart and GPS.

[0251] 4. Route Optimization Module:

[0252] Based on the prediction results, the optimal route for the autonomous vehicle is calculated.

[0253] It issues instructions to the autonomous driving system to move fishing boats to the optimal sea area.

[0254] 5. Catch Timing Notification Module:

[0255] It notifies you of the times when tuna are active.

[0256] Optimize fishing timing and improve catches.

[0257] 6. Prompt generation module:

[0258] Create a prompt to input to the generative AI model.

[0259] Processing flow

[0260] The server first collects various data using a data collection module. Next, the data analysis module analyzes the collected data, and the behavior prediction module predicts the behavior of fish species using a generative AI model. The prediction results are displayed in real time, and the navigation route optimization module calculates the optimal navigation route and issues instructions to the autonomous driving system. In addition, the fishing timing notification module notifies the optimal fishing timing. The prompt generation module creates prompt sentences to input into the generative AI model.

[0261] Hardware and Software Used

[0262] Hardware: Sensors, satellite communication devices, autonomous driving systems, fish finders, GPS devices

[0263] Software: Machine learning algorithms, generative AI models, data analysis tools

[0264] Examples

[0265] For example, the following prompt sentence could be input to a generative AI model:

[0266] Predict the behavior of tuna when the sea water temperature is 25 degrees, the salinity is 35, the current is 1.5 m / s, the air temperature is 28 degrees, the moon phase is 0.5, and the tide graph is 1.2.

[0267] By inputting this prompt into the generative AI model, it is possible to predict the tuna's behavior and calculate the optimal navigation route.

[0268] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0269] Step 1:

[0270] The server uses a data collection module to collect various data, such as nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, and the rate of temperature change due to global warming, through sensors and satellite communications. The input is data from various sensors and satellite communications, and the output is the collected data set.

[0271] Step 2:

[0272] The server analyzes the collected data using a data analysis module, which uses machine learning algorithms to pre-process the data and extract meaningful information. The input is the dataset collected in step 1, and the output is the analyzed data.

[0273] Step 3:

[0274] The server inputs a prompt sentence into the generative AI model using the behavior prediction module to predict the behavior of the target fish species. Specifically, the server inputs the prompt sentence created by the prompt generation module into the generative AI model to obtain the prediction result. The input is the analyzed data and the prompt sentence, and the output is the predicted behavior result of the fish species.

[0275] Step 4:

[0276] The server displays the prediction results on the fish finder's chart and GPS in real time. Specifically, the prediction results are visualized and reflected on the display device so that the user can check them. The input is the predicted behavior of the fish species, and the output is the predicted results displayed in real time.

[0277] Step 5:

[0278] The server uses the navigation route optimization module to calculate the optimal navigation route for the autonomous vehicle. Specifically, it calculates the optimal route based on the prediction results and issues instructions to the autonomous driving system. The input is the behavior prediction results of the fish species, and the output is the optimal navigation route.

[0279] Step 6:

[0280] The server uses a fishing timing notification module to notify the user of the optimal fishing timing. Specifically, it calculates the time periods when tuna are active and notifies the user. The input is the predicted behavior of the fish species, and the output is a notification of the fishing timing.

[0281] Step 7:

[0282] The server uses the prompt generation module to create a prompt sentence to be input to the generative AI model. Specifically, the server generates a prompt sentence based on the collected data and passes it to the behavior prediction module. The input is the collected data, and the output is the prompt sentence.

[0283] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0284] "Example 1"

[0285] As one embodiment of the present invention, there is a system that combines an emotion engine. This system includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for creating a behavior prediction of target fish species, etc., a means for predicting where the target fish species are moving at a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, and a means for improving the catch volume in the fishing industry. In addition, an emotion engine that recognizes the user's emotions is combined. This emotion engine recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. It is possible to adjust the behavior prediction of the target fish species using the output of the emotion engine. Specifically, when the user is feeling stressed, the emotion engine captures that information and adjusts the behavior prediction. This makes it possible to propose a more appropriate fishing method according to the user's emotional state.

[0286] "Example 2"

[0287] As one embodiment of the present invention, there is a system that combines an emotion engine. This system includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for creating a behavior prediction of target fish species, etc., a means for predicting where the target fish species are moving at a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, and a means for improving the catch volume in the fishing industry. In addition, an emotion engine that recognizes the user's emotions is combined. This emotion engine recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. It is possible to adjust the behavior prediction of the target fish species using the output of the emotion engine. Specifically, when the user is feeling stressed, the emotion engine captures that information and adjusts the behavior prediction. This makes it possible to propose a more appropriate fishing method according to the user's emotional state.

[0288] The process flow of each embodiment will be described below.

[0289] "Example 1"

[0290] Step 1: The system collects various data (nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, rate of temperature change due to global warming, etc.).

[0291] Step 2: Analyze the collected data and create predictions for the behavior of target fish species, etc.

[0292] Step 3: Predict where the target fish species will be moving at a specific time and display it in real time on the fish finder's chart and GPS.

[0293] Step 4: Recognize the user's emotions with the emotion engine. The emotion engine recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc.

[0294] Step 5: Use the emotion engine's output to adjust the behavioral predictions of the target fish species. Specifically, when the user is stressed, the emotion engine captures that information and adjusts its behavioral predictions.

[0295] Step 6: Based on the adjusted behavioral predictions, propose optimal fishing strategies to improve catches in the fishery.

[0296] Example 1

[0297] Next, a description will be given of Example 1 of the embodiment 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".

[0298] In conventional fishing systems, data analysis and behavior prediction to improve catches were not sufficiently performed, making it difficult for fishermen to efficiently select fishing spots. In addition, there was a problem of increased stress and fatigue for fishermen because fishing methods were not proposed taking into account the user's emotional state. To solve these issues, a system that collects and analyzes various data and predicts behavior in real time is required. In addition, a function to recognize the user's emotional state and adjust behavior predictions based on that is also required.

[0299] 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.

[0300] In this invention, the server includes a means for collecting various data (such as a nautical chart, location information, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graph, catch volume, fishing location, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for transmitting the collected data to a central data processing device, a means for analyzing the data using a machine learning algorithm, a means for creating a behavior prediction for the target fish species, a means for predicting where the target fish species are moving during a specific time period and displaying the prediction in real time on the nautical chart and location information on the fish finder, a means for recognizing the user's emotions and adjusting the behavior prediction based on the emotion data, and a means for improving the catch in the fishing industry. This allows fishermen to efficiently select fishing spots and also makes it possible to suggest more appropriate fishing methods according to the user's emotional state.

[0301] "Various data" refers to information such as nautical charts, location information, air temperature, sea water temperature, wind speed, currents, lunar age, tide graphs, catch volume, fishing locations, ecology of seafood, salinity, and the rate of temperature change due to global warming.

[0302] "Means of collection" refers to the method of obtaining various data using sensors and data collection devices installed on fishing vessels.

[0303] "Central Data Processing Unit" refers to a computer system that receives, analyzes, and processes collected data.

[0304] A "machine learning algorithm" is a mathematical model that learns patterns and rules from data to make predictions and classifications.

[0305] "Means for generating behavioral predictions" refers to methods that use machine learning algorithms to predict the migration patterns and behavior of targeted fish species.

[0306] "Means of displaying in real time" refers to a method of instantly reflecting the prediction results on the nautical chart and location information on the fish finder.

[0307] "Means of recognizing emotions" refers to methods for analyzing a user's emotional state from facial expressions, tone of voice, choice of words, etc.

[0308] "Means for adjusting behavioral prediction based on emotional data" refers to a method for modifying the results of behavioral prediction by taking into account the emotional state of the user.

[0309] "Measures to improve fishing yield" refers to methods to improve fishing performance through the selection of efficient fishing sites and the proposal of appropriate fishing methods.

[0310] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0311] This invention is a system for achieving efficient fishing in the fishing industry. It collects and analyzes various data, predicts the behavior of fish species, and has the ability to adjust the prediction results taking into account the emotional state of the user.

[0312] Data collection

[0313] Fishing boats are equipped with sensors and data collection devices to collect various data such as nautical charts, location information, air temperature, seawater temperature, wind speed, tides, moon phase, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, rate of temperature change due to global warming, etc. This data is transmitted in real time to a central data processing device (server) using wireless communication technology (e.g. Wi-Fi (registered trademark), LTE).

[0314] Data analysis

[0315] The server preprocesses the received data, complementing missing values, removing outliers, normalizing the data, etc. Specifically, it uses Python's Pandas library. Features are extracted from the preprocessed data, and the Scikit-learn library is used to extract features such as fluctuation patterns of air and seawater temperature, and the direction and speed of tidal currents. Next, a machine learning algorithm (e.g. TensorFlow (registered trademark), PyTorch (registered trademark)) is used to train a model to predict the behavior of fish species.

[0316] Generate behavioral predictions

[0317] The server uses the trained model to predict the behavior of target fish species, for example, where they will move at a certain time of day, and displays the prediction results in real time on the fish finder's chart and location information.

[0318] Combining emotion engines

[0319] To recognize the user's emotions, the fishing boat is equipped with cameras and microphones. The terminal uses these devices to collect emotion data from the user's facial expressions, tone of voice, choice of words, etc. The server analyzes the emotion data using OpenCV and Google Cloud Speech-to-Text API to recognize the user's emotional state. Based on the analyzed emotion data, it adjusts behavior predictions and suggests more appropriate fishing methods according to the user's emotional state.

[0320] Examples

[0321] For example, when a fisherman goes fishing, he can input the following prompt sentence into the generative AI model to check how the system works:

[0322] "The current air temperature is 25 degrees, the sea temperature is 20 degrees, the wind speed is 5 m / s, and the tide is flowing northeast. The moon is full, and according to the tide graph, the tide is rising. The catch has been declining recently, and fishing is mainly taking place along the coast. According to the ecology data of fish and shellfish, the migration patterns of the target fish species are changing due to global warming. The user seems to be stressed. Please predict and suggest the best fishing spot under these conditions."

[0323] By inputting this prompt, the system can predict the best fishing spots in real time based on the collected data and the user's emotional state and display it on the fish finder.

[0324] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0325] Step 1:

[0326] The terminal uses sensors and data collection devices installed on the fishing boat to collect various data such as nautical charts, location information, air temperature, seawater temperature, wind speed, tides, moon phase, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, and the rate of change in air temperature due to global warming. The input is data from the various sensors, and the output is the collected data. In concrete terms, the sensors acquire data in real time and send it to the terminal.

[0327] Step 2:

[0328] The terminal transmits the collected data to the server in real time using wireless communication technology (e.g., Wi-Fi, LTE). The input is the collected data, and the output is the data transmitted to the server. In concrete terms, the terminal divides the data into packets and transmits them to the server via wireless communication.

[0329] Step 3:

[0330] The server preprocesses the received data. The input is the data sent from the terminal, and the output is the preprocessed data. Specifically, it uses the Pandas library of Python (registered trademark) to complement missing values, remove outliers, and normalize the data.

[0331] Step 4:

[0332] The server extracts features from the preprocessed data. The input is the preprocessed data, and the output is the extracted features. Specifically, the server uses the Scikit-learn (registered trademark) library to extract features such as fluctuation patterns of air and seawater temperature, and the direction and speed of tidal currents.

[0333] Step 5:

[0334] The server trains a machine learning model using the extracted features. The input is the extracted features, and the output is the trained model. Specifically, the server uses TensorFlow (registered trademark) and PyTorch (registered trademark) to build a fish species behavior prediction model.

[0335] Step 6:

[0336] The server uses the trained model to predict the behavior of the fish species that are the target of fishing. The input is the trained model and real-time data, and the output is the behavior prediction result. Specifically, the server inputs data into the model and generates a prediction result.

[0337] Step 7:

[0338] The server transmits the prediction result to the terminal. The input is the behavior prediction result, and the output is the prediction result transmitted to the terminal. In particular, the server formats the prediction result and transmits it to the terminal via wireless communication.

[0339] Step 8:

[0340] The terminal displays the prediction results in real time on the marine chart and location information on the fish finder. The input is the prediction results sent from the server, and the output is the displayed prediction results. The specific operation is to display the prediction results on the fish finder display.

[0341] Step 9:

[0342] The device collects emotion data from the user's facial expressions, tone of voice, choice of words, etc. The input is data from the camera and microphone, and the output is the collected emotion data. Specifically, the device uses the camera and microphone to capture the user's emotional state in real time.

[0343] Step 10:

[0344] The server analyzes the collected emotion data. The input is the emotion data sent from the terminal, and the output is the analyzed emotion state. Specifically, it uses OpenCV and Google Cloud Speech-to-Text (registered trademark) API to recognize the user's emotion state.

[0345] Step 11:

[0346] The server adjusts the behavior prediction based on the analyzed emotion data. The input is the analyzed emotion state and the behavior prediction result, and the output is the adjusted behavior prediction result. The specific operation is to revise the prediction result according to the emotion state and propose a more appropriate fishing method.

[0347] Step 12:

[0348] The server sends the adjusted behavior prediction result to the terminal, where the input is the adjusted behavior prediction result and the output is the adjustment result sent to the terminal. In particular, the server formats the adjustment result and sends it to the terminal through wireless communication.

[0349] Step 13:

[0350] The terminal displays the adjusted behavior prediction results on the marine chart and position information on the fish finder in real time. The input is the adjustment result sent from the server, and the output is the displayed adjustment result. The specific operation is to display the adjustment result on the fish finder display.

[0351] (Application example 1)

[0352] Next, a description will be given of Application Example 1 of Form 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."

[0353] In conventional fishing, fishermen have to spend a lot of time and effort to identify the location of fish schools, which reduces fishing efficiency. In addition, the emotional state of fishermen can affect fishing results, and the efficiency of fishing activities can further decrease due to accumulated stress and fatigue. In addition, there is a problem that it is difficult to improve the catch because the navigation of fishing boats and suggestions on fishing methods are not performed in real time.

[0354] 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.

[0355] In this invention, the server includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for creating a behavior prediction of the target fish species, etc., a means for predicting where the target fish species are moving during a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, a means for suggesting a fishing method according to the user's emotional state using an emotion engine that recognizes the user's emotions, a means for improving the navigation and fishing efficiency of the fishing boat that is installed on the autonomous fishing boat, and a means for receiving the location of the school of fish and the proposed fishing method in real time through the smart device. This enables fishermen to efficiently identify the location of the school of fish and increase the amount of catch. In addition, the proposed fishing method according to the user's emotional state can reduce the fishermen's stress and fatigue and improve the efficiency of fishing activities.

[0356] "Various data" refers to information such as nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and the rate of temperature change due to global warming.

[0357] "Means of analysis" refers to devices and algorithms used to analyze various collected data and predict the behavior of schools of fish.

[0358] "Means for creating behavioral predictions" refers to devices and algorithms that use the analyzed data to predict the behavior of targeted fish species.

[0359] "Means for displaying in real time" refers to devices or software for instantly displaying the predicted location information of schools of fish on a fish finder or GPS.

[0360] "Means to improve catches" refers to devices and algorithms that propose efficient fishing methods based on information on the location and behavioral predictions of fish schools, thereby increasing catches.

[0361] An "emotion engine" refers to a device or software that recognizes emotions from a user's facial expressions, tone of voice, choice of words, etc., and adjusts fishing methods based on that information.

[0362] An "autonomous fishing vessel" refers to a fishing vessel that is designed to navigate and conduct fishing activities automatically.

[0363] "Measures to improve navigation and fishing efficiency" refers to devices and algorithms that enable autonomous fishing vessels to navigate and fish efficiently.

[0364] "Smart devices" refers to portable information terminals such as smartphones, tablets, smart glasses, and head-mounted displays.

[0365] "Means of receiving real-time information on the location of schools of fish and suggestions on efficient fishing methods" refers to equipment or software that allows a smart device to instantly receive information on the location of schools of fish and suggestions on efficient fishing methods.

[0366] The following system configuration will be described as an embodiment of the present invention.

[0367] System Configuration

[0368] Hardware Configuration

[0369] 1. Sensors installed on fishing boats: Various sensors to collect data such as nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and rate of temperature change due to global warming.

[0370] 2. Central Data Processing Unit: A computer capable of high-speed data processing, such as a server equipped with an NVIDIA (registered trademark) GPU.

[0371] 3. Smart devices: Portable information terminals such as smartphones, tablets, smart glasses, and head-mounted displays.

[0372] Software Configuration

[0373] 1. Data collection software: Software for collecting data from various sensors and transmitting it to a central data processing device.

[0374] 2. Data analysis software: Software that analyzes collected data using machine learning algorithms such as TensorFlow (registered trademark) and PyTorch (registered trademark).

[0375] 3. Behavioral prediction software: Software that predicts the behavior of fish species being targeted for fishing based on analyzed data.

[0376] 4. Real-time display software: Software that displays the predicted locations of fish schools in real time on a fish finder or GPS.

[0377] 5. Emotion engine software: Software that recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. and adjusts fishing methods based on that information.

[0378] 6. Navigation software: Software that enables autonomous fishing vessels to navigate and fish efficiently.

[0379] 7. Application for smart devices: An application to receive real-time information on fish locations and fishing method suggestions via smart devices.

[0380] Processing flow

[0381] 1. Data collection: Various sensors installed on fishing boats collect data such as nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, moon phase, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, rate of temperature change due to global warming, etc. This data is sent to a central data processing unit through data collection software.

[0382] 2. Data Analysis: The central data processing unit analyses the collected data using data analysis software, which uses machine learning algorithms such as TensorFlow® and PyTorch®.

[0383] 3. Behavioral prediction: Based on the analyzed data, behavioral prediction software predicts the behavior of the targeted fish species, thereby predicting where schools of fish will be moving at a particular time.

[0384] 4. Real-time display: The prediction results are displayed on fish finders and GPS through real-time display software, which helps fishermen to efficiently select fishing spots.

[0385] 5. Emotion Recognition and Adjustment: The emotion engine software recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. and adjusts its fishing strategy based on that information. For example, if the user is stressed, the emotion engine will pick up on that information and adjust its behavior predictions.

[0386] 6. Improved navigation and fishing efficiency: Navigation software will help autonomous fishing vessels navigate and fish more efficiently, which will improve fishing efficiency.

[0387] 7. Notifications on smart devices: Through a smart device application, fishermen can receive real-time information on the location of fish schools and suggestions on how to catch them.

[0388] Examples

[0389] For example, if a fisherman is wearing smart glasses, he can input prompt sentences like the following into the generative AI model and receive real-time information about the location of fish schools and suggestions on how to catch them.

[0390] Examples of prompt statements

[0391] "The current seawater temperature is 25 degrees, the wind speed is 5 m / s, and the current is flowing northeast. Please tell me where we can expect to catch the most fish in the next hour."

[0392] By feeding this prompt into a generative AI model, the AI ​​will suggest optimal fishing locations based on the collected data.

[0393] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0394] Step 1:

[0395] Various sensors installed on fishing boats collect data such as nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, and the rate of temperature change due to global warming. This data is sent to a central data processing device through data collection software. The input is real-time data from the various sensors, and the output is the data sent to the central data processing device.

[0396] Step 2:

[0397] The central data processing unit analyzes the collected data using data analysis software. Machine learning algorithms such as TensorFlow (registered trademark) and PyTorch (registered trademark) are used for the analysis. The input is the data collected in step 1, and the output is the analysis result. Specific operations include data preprocessing, feature extraction, and application of machine learning models.

[0398] Step 3:

[0399] Based on the analyzed data, the behavioral prediction software predicts the behavior of the target fish species. This allows it to predict where fish schools will be moving at a specific time. The input is the analysis result from step 2, and the output is the predicted behavioral data of the fish schools. Specific operations include applying a predictive model and generating a prediction result.

[0400] Step 4:

[0401] The prediction results are displayed on the fish finder or GPS through real-time display software. This allows fishermen to efficiently select fishing locations. The input is the behavior prediction data from step 3, and the output is the display data on the fish finder or GPS. Specific operations include data visualization and real-time display.

[0402] Step 5:

[0403] The emotion engine software recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc., and adjusts its fishing methods based on that information. For example, if the user is feeling stressed, the emotion engine captures that information and adjusts its behavior predictions. The input is the user's emotion data, and the output is adjusted behavior prediction data. Specific operations include applying emotion recognition algorithms and recalibrating the prediction model.

[0404] Step 6:

[0405] The navigation software efficiently navigates the autonomous fishing vessel and performs fishing activities, thereby improving fishing efficiency. The input is adjusted behavior prediction data, and the output is navigation data for the autonomous fishing vessel. Specific operations include calculation of navigation routes and autonomous driving control.

[0406] Step 7:

[0407] Through the smart device application, fishermen can receive real-time fish location and fishing method suggestions. The input is the navigation data and coordinated behavior prediction data of the autonomous fishing boat, and the output is notification data on the smart device. Specific operations include transmitting data and generating notifications.

[0408] Example 2

[0409] Next, a second embodiment of the second embodiment will be described. 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."

[0410] In conventional fishing systems, data analysis and behavioral prediction to improve catches were not sufficiently performed, making efficient fishing difficult. In addition, there were no proposals for fishing methods that took into account the emotional state of fishermen, which led to problems with increased stress and fatigue among fishermen. This has led to a demand for simultaneously improving the efficiency of fishing and the satisfaction of fishermen.

[0411] 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.

[0412] In this invention, the server includes a means for analyzing various data (map information, location information, weather information, ocean information, tide information, lunar age information, tide information, fishing information, fishing location information, fish ecology information, salinity information, climate change information, etc.), a means for creating a behavior prediction for the target fish to be caught, a means for predicting where the target fish will move during a specific time period and displaying this in real time on the map information and location information on the fish finder, a means for improving the catch in the fishing industry, and a means including an emotion engine that recognizes the user's emotions and adjusting the behavior prediction using the output of the emotion engine. This makes it possible to make highly accurate behavior predictions based on collected data and to suggest appropriate fishing methods according to the user's emotional state.

[0413] "Map information" is data that shows the topography and location relationships of oceans and land.

[0414] "Location information" is data that indicates the latitude and longitude of a specific point using technology such as GPS.

[0415] "Weather information" is data that indicates atmospheric conditions such as temperature, wind speed, and precipitation.

[0416] "Ocean information" refers to data that indicates ocean conditions, such as seawater temperature, salinity, and tidal currents.

[0417] "Tidal current information" is data that indicates the direction and speed of ocean water flow.

[0418] "Moon age information" is data that indicates the phases of the moon.

[0419] "Tidal information" is data that indicates the up and down movement of the sea surface.

[0420] "Catch information" is data that indicates the type and quantity of fish caught.

[0421] "Fishing location information" is data that indicates the specific location where the fishing took place.

[0422] "Fish ecological information" is data that indicates fish behavior patterns and habitats.

[0423] "Salinity concentration information" is data that indicates the percentage of salinity in seawater.

[0424] "Climate change information" is data showing long-term changes in temperature and precipitation.

[0425] An "emotion engine" is a system that recognizes emotions from a user's facial expressions, tone of voice, choice of words, etc.

[0426] A "machine learning algorithm" is a computational method for making predictions and classifications based on data.

[0427] This invention is a system for improving catches in the fishing industry, which collects and analyzes various data, predicts fish behavior, and suggests appropriate fishing methods according to the user's emotional state.

[0428] The server collects various data such as map information, location information, weather information, ocean information, tide information, lunar phase information, tide information, fishing information, fishing location information, fish ecology information, salinity information, and climate change information. These data are obtained from dedicated sensors and databases. For example, the latest seawater temperature, salinity, and tide data is obtained from the ocean database, and temperature, wind speed, lunar phase, and tide information is obtained from the weather database. In addition, real-time location information and catch volume data are collected from the GPS and fish finder installed on the fishing boat.

[0429] The server analyzes the collected data and creates predictions for the behavior of tuna and other fish. Using machine learning algorithms, it analyzes data such as seawater temperature, salinity, and currents to predict the areas that fish prefer. It also predicts the times when fish will be active based on data such as temperature, moon phase, and tide information. This allows fishing boats to fish more efficiently.

[0430] The server displays the prediction results on the map information on the fish finder and on the GPS in real time. This allows fishing boats to move to areas where fish are predicted to be present and fish more efficiently. The prediction results are converted into a data format for display on the fish finder display and sent to the GPS device.

[0431] It is combined with an emotion engine that recognizes the user's emotions. The emotion engine recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. For example, the emotion engine captures the user's facial expressions with a camera and performs image analysis. It also collects the user's tone of voice with a microphone and performs audio analysis. The server receives the output data from the emotion engine and adjusts the parameters of the behavior prediction model if the user is feeling stressed.

[0432] The server generates the optimal fishing method based on the adjusted behavior prediction results. The generated proposal is displayed on the terminal display and notified to the user. This makes it possible to propose a more appropriate fishing method according to the user's emotional state.

[0433] As a concrete example, if the seawater temperature on a certain day is 25 degrees, the salinity is 3.5%, and the tidal current is flowing northeast, the server will use this data to predict the areas where tuna prefer and move fishing boats to those areas.Also, if the air temperature is 20 degrees, the moon is a full moon, and the tidal information shows a rising tide, the server will predict the times when tuna will be active and give instructions to fish during those times.

[0434] An example of a prompt sentence is as follows:

[0435] "Predict the areas where tuna prefer to fish if the seawater temperature is 25 degrees, the salinity is 3.5%, and the current is flowing northeast. Also, if the air temperature is 20 degrees, the moon is a full moon, and the tidal information shows a rising tide, predict the time of day when tuna will be active."

[0436] In this way, the system can predict fish behavior based on collected data and improve catches. In addition, by using an emotion engine, the system can suggest more appropriate fishing methods according to the user's emotional state.

[0437] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0438] Step 1:

[0439] The server collects various data such as map information, location information, weather information, ocean information, tidal current information, lunar phase information, tide information, fishing information, fishing location information, fish ecology information, salinity concentration information, and climate change information.

[0440] Input: Various data from dedicated sensors and databases

[0441] Output: Various data collected

[0442] Specific behavior:

[0443] The server accesses an oceanographic database to obtain the latest ocean temperature, salinity, and current data.

[0444] The server retrieves temperature, wind speed, lunar age, and tide information from a weather database.

[0445] The server collects real-time location and catch data from the GPS and fish finders installed on the fishing boats.

[0446] Step 2:

[0447] The server analyzes the collected data and creates predictions of fish behavior.

[0448] Input: Various data collected

[0449] Output: Fish behavior prediction results

[0450] Specific behavior:

[0451] The server inputs the collected seawater temperature, salinity, and current data and applies it to a model to predict which marine areas fish prefer.

[0452] The server uses data on temperature, lunar phase, and tide information to run models to predict when fish will be active.

[0453] Step 3:

[0454] The server displays the prediction results in real time on the fish finder's map information and GPS.

[0455] Input: Fish behavior prediction results

[0456] Output: Display data to fishfinder and GPS devices

[0457] Specific behavior:

[0458] The server converts the prediction results into a data format for display on the fish finder display.

[0459] The server sends the prediction results to the GPS device and displays them in real time.

[0460] Step 4:

[0461] It is combined with an emotion engine that recognizes the user's emotions from facial expressions, tone of voice, choice of words, etc.

[0462] Input: User facial expressions, tone of voice, and word choice

[0463] Output: The user's emotional state.

[0464] Specific behavior:

[0465] The emotion engine captures the user's facial expressions with a camera and performs image analysis.

[0466] The emotion engine collects the user's voice tone through a microphone and performs voice analysis.

[0467] Step 5:

[0468] The server uses the output of the emotion engine to refine the behavior predictions of the fish.

[0469] Input: User's emotional state, fish behavior prediction results

[0470] Output: Adjusted fish behavior prediction results

[0471] Specific behavior:

[0472] The server receives the output data from the emotion engine and adjusts the parameters of the behavior prediction model if the user is feeling stressed.

[0473] Step 6:

[0474] The server generates the optimal fishing method based on the adjusted behavior prediction results, and the generated proposal is displayed on the terminal display and notified to the user.

[0475] Input: Adjusted fish behavior prediction results

[0476] Output: Recommendations for optimal fishing methods

[0477] Specific behavior:

[0478] The server generates an optimal fishing method based on the adjusted behavior prediction results.

[0479] The server displays the generated proposal on the display of the terminal and notifies the user.

[0480] (Application example 2)

[0481] Next, a description will be given of Application Example 2 of Form 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."

[0482] Conventional fishing systems generally catch fish based on ocean conditions and fish school behavior predictions, but there was no system that took the user's emotional state into account. As a result, it was not possible to suggest the optimal fishing method depending on whether the user was stressed or relaxed, which could lead to reduced fishing efficiency. In addition, these systems were rarely applied to autonomous vehicles, and the automation and efficiency of fishing had not progressed sufficiently.

[0483] 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.

[0484] In this invention, the server includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, rate of temperature change due to global warming, etc.), a means for creating a behavior prediction for target fish species, etc., a means for predicting where the target fish species are moving during a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, a means for improving the catch volume in fishing, a means for recognizing the user's emotional state, a means for adjusting the behavior prediction based on the user's emotional state, and a means for being installed in the autonomous vehicle. This makes it possible to propose an optimal fishing method according to the user's emotional state and improve fishing efficiency.

[0485] "Various data" refers to information such as nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and the rate of temperature change due to global warming.

[0486] "Means of analysis" refers to methods and equipment for analyzing various types of data and understanding fish behavior and oceanographic conditions.

[0487] "Means for generating behavioral predictions" refers to methods or devices for predicting the behavior of target fish species based on collected data.

[0488] "Means for displaying in real time" refers to a method or device for instantly displaying predicted fish school location information on a marine chart or GPS on a fish finder.

[0489] "Means for improving catches" refers to methods and devices for fishing efficiently and increasing catches based on predicted fish school location information.

[0490] "Means for recognizing a user's emotional state" refers to a method or device for identifying emotions from a user's facial expressions, tone of voice, choice of words, etc.

[0491] "Means for adjusting behavior prediction" refers to a method or device for modifying the behavior prediction of the school of fish based on the emotional state of the user.

[0492] "Means installed in an autonomous vehicle" refers to a method or apparatus for mounting and operating each of the means described above on an autonomous vehicle.

[0493] A system for implementing this invention is configured as follows: First, the server collects various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.) and analyzes this data. Software such as Python (registered trademark), Pandas, and Scikit-learn (registered trademark) are used for the analysis.

[0494] The server then uses machine learning algorithms to generate predictions of the behavior of the target fish species, based on ecological knowledge of the target species, and displays the predicted fish locations in real time on the chart and GPS on the fish finder.

[0495] In addition, the server uses emotion recognition software such as EmotionEngine® to recognize the user's emotional state. It identifies emotions from the user's facial expressions, tone of voice, choice of words, etc., and adjusts behavior predictions based on the user's emotional state. For example, if the user is stressed, it predicts the location of schools of fish by emphasizing the influence of tides. Conversely, if the user is relaxed, it predicts the location of schools of fish by reducing the influence of tides.

[0496] This system will be installed in autonomous vehicles, which will be able to move automatically based on the predicted location information of fish schools and fish more efficiently, thereby improving catches.

[0497] As a concrete example, the operation of the system can be confirmed by inputting the following prompt sentence into the generative AI model.

[0498] Example prompt:

[0499] Create a Python (registered trademark) program that predicts the location of schools of fish based on oceanographic condition data and fish behavior data. Add a function to adjust the parameters of the prediction model according to the user's emotional state. There are two types of emotional state: "stressed" and "relaxed," and the influence of the tides should be adjusted according to each state.

[0500] In this way, the server, terminals, and users can work together to operate the system, making it possible to streamline and automate fishing.

[0501] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0502] Step 1:

[0503] The server collects various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, rate of temperature change due to global warming, etc.). This data is obtained from sensors and external databases. The input is data from various sensors and databases, and the output is a set of collected data.

[0504] Step 2:

[0505] The server analyzes the collected data. Specifically, it preprocesses the data using Python (registered trademark) and Pandas, and performs missing value completion and outlier removal. The input is the collected data set, and the output is the preprocessed data.

[0506] Step 3:

[0507] The server uses machine learning algorithms (e.g., Scikit-learn® random forest regression models) to generate behavioral predictions for the fish species being fished. The input is the pre-processed data, and the output is the predicted location of the fish schools.

[0508] Step 4:

[0509] The server displays the predicted fish school location information on the fish finder's nautical chart or GPS in real time. The input is the fish school location prediction, and the output is the displayed location information. The specific operation is to plot the location information on the fish finder's display.

[0510] Step 5:

[0511] The server uses the EmotionEngine® to recognize the user's emotional state: the input is data such as the user's facial expression, tone of voice, and choice of words, and the output is the user's emotional state (e.g., stressed, relaxed).

[0512] Step 6:

[0513] The server adjusts the action prediction based on the user's emotional state. For example, if the user is stressed, the server re-predicts the fish school's location by emphasizing the influence of tides. The inputs are the user's emotional state and the predicted fish school location, and the output is the adjusted predicted fish school location.

[0514] Step 7:

[0515] The autonomous vehicle moves automatically based on the adjusted fish school position information. The input is the adjusted fish school position prediction, and the output is the autonomous vehicle's movement path. Specifically, the vehicle's navigation system calculates a new path and moves the vehicle according to the new path.

[0516] Step 8:

[0517] The user fishes based on the information provided by the system. The input is the location information and fishing method suggestions from the system, and the output is the actual fishing results. In concrete terms, the user fishes at the specified location and checks the amount of catch.

[0518] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0519] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0520] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0521] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0522] [Second embodiment]

[0523] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0524] 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.

[0525] 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.

[0526] 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 wide area network (WAN) and / or a local area network (LAN).

[0527] 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.

[0528] 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 the voice according to instructions from the processor 46.

[0529] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0530] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0531] Fig. 4 shows an example of 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.

[0532] 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.

[0533] 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.

[0534] 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.

[0535] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0536] "Example 1"

[0537] In one embodiment of the present invention, a fishing boat is equipped with sensors and data collection devices for collecting various data (such as nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, and rate of temperature change due to global warming). These data are sent to a central data processing device and analyzed using machine learning algorithms. The analysis results are generated as a behavior prediction of the target fish species, and predict where the target fish species will be moving at a specific time period. The prediction results are displayed in real time on the nautical charts and GPS on the fish finder, allowing fishermen to efficiently select fishing locations.

[0538] "Example 2"

[0539] As a specific example, consider a fishing boat that fishes for tuna. Various data on the ecology of tuna and ocean conditions are collected, and predictions of tuna behavior are made based on this data. For example, based on data such as seawater temperature, salinity, and tides, the areas that tuna prefer can be predicted, and the fishing boat can be moved to those areas. Also, based on data such as temperature, moon phase, and tide graphs, the times when tuna will be active can be predicted, and fishing can be carried out at those times. This makes it possible to significantly increase the catch.

[0540] The process flow of each embodiment will be described below.

[0541] "Example 1"

[0542] Step 1: Sensors and data collection devices are installed on the fishing boat to collect various data (nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar phase, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of temperature change due to global warming, etc.).

[0543] Step 2: The collected data is transmitted to a central data processing device.

[0544] Step 3: The data processor uses machine learning algorithms to analyze the data and generate behavioral predictions for the fish species being fished.

[0545] Step 4: Predict where the target fish species will be moving at a specific time and display this prediction in real time on the chart and GPS on the fish finder.

[0546] "Example 2"

[0547] Step 1: Sensors and data collection devices will be installed on tuna fishing boats to collect various data on tuna ecology and ocean conditions.

[0548] Step 2: The collected data is transmitted to a central data processing device.

[0549] Step 3: The data processor uses machine learning algorithms to analyze the data and generate predictions of tuna behavior.

[0550] Step 4: Using data on seawater temperature, salinity, tidal currents, etc., predict the areas preferred by tuna and move fishing boats to those areas.

[0551] Step 5: Using data such as temperature, moon phase, and tide graphs, predict the times when the tuna will be active and fish during those times.

[0552] Example 1

[0553] Next, a description will be given of Example 1 of Form 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".

[0554] In conventional fishing, it was difficult for fishermen to accurately determine the location of schools of fish, making it difficult to increase catches. In addition, there was a lack of systems that could efficiently collect and analyze a wide variety of data, such as meteorological and oceanographic information, and provide it to fishermen in real time. This reduced the efficiency of fishing and made it difficult to predict catches.

[0555] 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.

[0556] In this invention, the server includes a means for collecting various data (map information, location information, weather information, ocean information, wind speed information, tidal current information, lunar age information, tide information, fishing information, fishing location information, marine life information, salinity concentration information, climate change information, etc.), a means for transmitting the collected data to a central data processing device, a means for receiving the transmitted data and performing preprocessing, a means for analyzing the preprocessed data using a machine learning algorithm, a means for generating a behavior prediction of fish species based on the analysis result, a means for transmitting the generated behavior prediction result to a terminal, and a means for displaying the prediction result on the terminal in real time. This enables fishermen to grasp the location of schools of fish in real time and efficiently select fishing spots.

[0557] "Various data" refers to map information, location information, weather information, ocean information, wind speed information, current information, lunar age information, tidal information, fishing information, fishing location information, marine life information, salinity concentration information, climate change information, etc.

[0558] "Means of collection" refers to the equipment and methods used to obtain various data using sensors and data collection devices installed on fishing vessels.

[0559] "Central Data Processing Unit" refers to a computer system for receiving, pre-processing and analyzing collected data.

[0560] "Transmitting means" refers to a device or method for transmitting collected data to a central data processing device using wireless or wired communication.

[0561] "Preprocessing means" refers to software or algorithms for filling in missing values ​​or correcting outliers in the received data.

[0562] "Machine learning algorithms" refers to artificial intelligence techniques for analyzing data and creating patterns and predictions.

[0563] "Means for generating a behavioral prediction" refers to software or algorithms for predicting behavioral patterns of fish species using machine learning algorithms.

[0564] "Terminal" refers to fish finders and other display devices installed on fishing vessels.

[0565] "Means for displaying in real time" refers to software or hardware for instantly displaying the generated behavior prediction results on a terminal.

[0566] "Means for improving catch" refers to methods and devices for increasing catch by accurately determining the location of fish schools and efficiently selecting fishing spots.

[0567] The present invention is a system for improving catches in the fishing industry, which collects various data, analyzes them using machine learning algorithms, and generates predictions of fish species behavior. A specific embodiment of the system will be described below.

[0568] Data collection

[0569] The user (fisherman) uses sensors and data collection devices installed on the fishing boat to collect various data such as map information, location information, weather information, ocean information, wind speed information, tidal current information, lunar age information, tide information, fishing catch information, fishing location information, marine life information, salinity concentration information, climate change information, etc. For example, an air temperature sensor measures 25°C and a seawater temperature sensor measures 20°C.

[0570] Data transmission

[0571] The terminal (data collection device on the fishing boat) transmits the collected data to the central data processing device using wireless communication (e.g., Wi-Fi (registered trademark) or satellite communication). For example, the data is transmitted using a Wi-Fi module.

[0572] Data reception and preprocessing

[0573] The server receives data sent from the terminal. For the received data, a data frame is created using the Python (registered trademark) pandas library, missing values ​​are complemented, and outliers are detected and corrected. For example, missing values ​​are complemented with the average value, and outliers are corrected with the median value.

[0574] Data analysis

[0575] The server inputs the preprocessed data into a machine learning algorithm (e.g., TensorFlow® or PyTorch®) for analysis. For example, it uses a random forest model to predict the behavioral patterns of fish species.

[0576] Generate behavioral predictions

[0577] Based on the analysis results, the server generates a prediction of the behavior of fish species, for example, a prediction that mackerel will move to 35 degrees north latitude and 140 degrees east longitude during a specific time period.

[0578] Sending and viewing results

[0579] The server sends the generated behavior prediction results to the terminal. For example, it sends the prediction results in JSON format using the HTTP protocol. The terminal (fish finder) displays the received prediction results in real time. For example, it displays a nautical chart and GPS information on the fish finder display, overlaying them, and indicates the predicted location of the school of fish with a marker.

[0580] Examples

[0581] For example, a fisherman might collect the following data using sensors on his boat:

[0582] Nautical Chart Data GPS data Temperature: 25°C Sea water temperature: 20°C Wind speed: 5m / s Current: 1m / s Moon age: 15 days Tide Graph: High Tide Catch: 100kg Fishing location: 35 degrees north latitude, 139 degrees east longitude Ecology of fish and shellfish: Mackerel Salinity: 3.5% Rate of temperature change due to global warming: 0.02°C / year

[0583] This data is sent to a central data processor where it is analysed using machine learning algorithms, which generate predictions of when mackerel will move to 35 degrees north and 140 degrees east at a specific time, and which are then displayed in real time on the charts and GPS on the fish finder.

[0584] Examples of prompt statements

[0585] Examples of prompts to be input to a generative AI model include:

[0586] "Please predict the behavior of mackerel based on the following data:

[0587] Nautical Chart Data GPS data Temperature: 25°C Sea water temperature: 20°C Wind speed: 5m / s Current: 1m / s Moon age: 15 days Tide Graph: High Tide Catch: 100kg Fishing location: 35 degrees north latitude, 139 degrees east longitude Ecology of fish and shellfish: Mackerel Salinity: 3.5% Rate of temperature change due to global warming: 0.02°C / year

[0588] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0589] Step 1: Data collection

[0590] Users (fishermen) use sensors and data collection devices installed on their fishing boats to collect various data such as map information, location information, weather information, ocean information, wind speed information, tidal current information, lunar phase information, tide information, fishing catch information, fishing location information, marine life information, salinity concentration information, and climate change information. For example, an air temperature sensor measures 25°C and a seawater temperature sensor measures 20°C. The input is data from various sensors, and the output is the collected data.

[0591] Step 2: Send data

[0592] The terminal (data collection device on the fishing boat) transmits the collected data to the central data processing device using wireless communication (e.g. Wi-Fi or satellite communication). For example, a Wi-Fi module is used to transmit the data. The input is the collected data and the output is the data transmitted to the central data processing device.

[0593] Step 3: Receiving data

[0594] The server receives data sent from the terminal. It opens a receiving port to wait for data and temporarily stores the received data. The input is the data sent from the terminal, and the output is the data stored in the server.

[0595] Step 4: Data Preprocessing

[0596] The server preprocesses the received data. Specifically, it uses the pandas library of Python (registered trademark) to create a data frame, impute missing values, and detect and correct outliers. For example, if there are missing values, they are imputed with the mean value, and if there are outliers, they are corrected with the median value. The input is the received data, and the output is the preprocessed data.

[0597] Step 5: Data analysis

[0598] The server inputs the preprocessed data into a machine learning algorithm (e.g., TensorFlow (registered trademark) or PyTorch (registered trademark)) and performs analysis. For example, a random forest model is used to predict the behavioral patterns of fish species. The input is the preprocessed data, and the output is the analysis result.

[0599] Step 6: Generate behavior predictions

[0600] The server generates a behavioral prediction for the fish species based on the analysis results. For example, it generates a prediction that mackerel will move to 35 degrees north latitude and 140 degrees east longitude during a specific time period. The input is the analysis results, and the output is the behavioral prediction results.

[0601] Step 7: Sending results

[0602] The server transmits the generated behavior prediction result to the terminal. For example, the prediction result is transmitted in JSON format using the HTTP protocol. The input is the behavior prediction result, and the output is the prediction result transmitted to the terminal.

[0603] Step 8: View the results

[0604] The terminal (fish finder) displays the received prediction results in real time. For example, a marine chart and GPS information are overlaid on the fish finder display, and the predicted locations of the schools of fish are indicated with markers. The input is the prediction results sent from the server, and the output is the prediction results displayed on the display.

[0605] (Application example 1)

[0606] Next, a description will be given of Application Example 1 of Form 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".

[0607] In traditional fishing, fishermen often relied on experience and intuition to select fishing spots, making it difficult to catch fish efficiently. In addition, fishing boats also required manual operation, which was labor-intensive and time-consuming. Furthermore, there was a lack of real-time data analysis to respond to changes in weather conditions and the marine environment, making it difficult to increase catches.

[0608] 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. In this invention, the server includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for creating a behavior prediction of the target fish species, etc., a means for predicting where the target fish species are moving in a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, a means for improving the catch in the fishing industry, a means for updating the navigation system of the autonomous fishing boat, a means for predicting the behavior of fish using data collected in real time, and a means for moving the autonomous fishing boat to the optimal fishing spot based on the prediction result. This allows not only fishers to efficiently select fishing spots, but also allows the autonomous fishing boat to automatically move to the optimal fishing spot.

[0609] "Various data" refers to information such as nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and the rate of temperature change due to global warming.

[0610] "Means for analyzing" refers to methods and devices for analyzing various collected data and extracting meaningful information.

[0611] "Means for creating a behavioral prediction" refers to a method or device that constructs a predictive model based on collected data and generates the results in order to predict the behavior of a target fish species.

[0612] "Means for displaying in real time" refers to a method or device for instantly displaying the prediction results on a chart or GPS on a fish finder.

[0613] "Measures to improve fishing yield" refers to methods or devices that increase fishing yield by assisting in the selection of efficient fishing sites and the operation of fishing vessels.

[0614] "Means for updating the navigation system of an autonomous fishing vessel" refers to a method or device for correcting and updating the route and operation plan of an autonomous fishing vessel in real time based on the prediction results.

[0615] "Means for predicting fish behavior using data collected in real time" refers to a method or device for instantly predicting fish behavior based on the latest data obtained from sensors and data collection devices.

[0616] "Means for moving an autonomous fishing vessel to an optimal fishing location based on prediction results" refers to a method or device for automatically moving an autonomous fishing vessel to the most efficient fishing location based on the results of behavioral prediction.

[0617] The system for carrying out this invention collects data obtained from various sensors and data collection devices mounted on fishing boats in real time, and analyzes the data in a central data processing device to predict the behavior of specific fish species. A specific embodiment of this system will be described below.

[0618] Hardware and Software Used

[0619] Hardware

[0620] Various sensors: GPS, temperature sensor, sea water temperature sensor, anemometer, tide gauge, salinity meter, etc.

[0621] Data collection equipment: A device that collects data from sensors and transmits it to a central data processing device.

[0622] Central Data Processing Unit: A computer equipped with a high-performance CPU / GPU.

[0623] software

[0624] Python(registered trademark): A programming language.

[0625] scikit-learn(registered trademark): Machine learning library.

[0626] pandas: A data processing library.

[0627] matplotlib(registered trademark): A data visualization library.

[0628] Data processing and calculation

[0629] Data collection

[0630] The sensors collect data in real time, including GPS location, air temperature, seawater temperature, wind speed, tides, moon phase, tide graphs, catch volume, fishing location, fish and shellfish ecology, salinity, and the rate of temperature change due to global warming.

[0631] Data Preprocessing

[0632] Convert the collected data into a data frame and impute missing values, thereby ensuring data consistency and accuracy.

[0633] Training the model

[0634] A random forest regression model is trained using historical data, which allows us to build a fish behavior prediction model.

[0635] Behavioral Prediction

[0636] The data collected in real time is used to predict fish behavior, and the prediction results are displayed in real time on the fish finder's nautical chart and GPS.

[0637] Navigation system updates

[0638] The prediction results are used to update the navigation system of autonomous fishing boats, allowing them to automatically navigate to the optimal fishing spots.

[0639] Examples

[0640] For example, if it is predicted that a fishing vessel needs to move 10km northeast from its current position, the navigation system will automatically move the vessel in that direction.

[0641] Examples of prompt statements

[0642] "Enter the current GPS location, air temperature, seawater temperature, wind speed, tides, moon phase, tide graph, catch volume, fishing location, fish and shellfish ecology, salinity, and rate of temperature change due to global warming, and predict the location with the best chance of catching fish within the next hour."

[0643] In this way, by applying the invention to the navigation system of an autonomous fishing boat, more efficient fishing becomes possible.

[0644] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0645] Step 1:

[0646] Collecting data from sensors

[0647] The server collects data in real time from various sensors (GPS, temperature sensor, seawater temperature sensor, anemometer, tide gauge, salinity meter, etc.). As input, it receives measurements from each sensor and sends them to the data collector. As output, the collected data is stored in data frame format.

[0648] Step 2:

[0649] Data Preprocessing

[0650] The server converts the collected data into a data frame and imputes missing values. As input, it takes the data collected in step 1 and converts it into a data frame. If there are missing values, it imputes them with the previous value. As output, it obtains a preprocessed data frame.

[0651] Step 3:

[0652] Training a machine learning model

[0653] The server trains a random forest regression model using historical data. As input, it receives a preprocessed data frame and separates it into features and target variables. The features include air temperature, seawater temperature, wind speed, and currents, while the target variables include fish location information. As output, it obtains a trained machine learning model.

[0654] Step 4:

[0655] Real-time data collection

[0656] The server collects new data from the sensors in real time. As input, it takes the latest measurements from each sensor and adds them to a data frame. As output, it gets a data frame with the latest data.

[0657] Step 5:

[0658] Predicting fish behavior

[0659] The server uses the collected data in real time to predict the fish behavior. As input, it receives the latest data frame obtained in step 4 and feeds it into the trained machine learning model. As output, it obtains the predicted fish behavior result.

[0660] Step 6:

[0661] Navigation system updates

[0662] The server updates the navigation system of the autonomous fishing vessel based on the prediction results. As input, it receives the fish behavior prediction results obtained in step 5 and calculates the optimal fishing spot. As output, it obtains the updated navigation system instructions.

[0663] Step 7:

[0664] Autonomous Driving of Fishing Boats

[0665] The terminal moves the autonomous fishing vessel to the optimal fishing spot according to the updated navigation system instructions. As input, it receives the navigation system instructions obtained in step 6 and reflects them in the fishing vessel's operation system. As output, the fishing vessel automatically moves to the optimal fishing spot.

[0666] In this way, efficient fishing can be achieved through each step.

[0667] Example 2

[0668] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0669] In conventional fishing, data collection and analysis to predict the location and behavior of fish schools was insufficient, making it difficult to increase catches. In addition, there was a problem that efficient fishing could not be carried out because predictions of fish species' behavior were inaccurate. This reduced the efficiency of fishing and often resulted in economic losses.

[0670] 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.

[0671] In this invention, the server includes a means for collecting various data (nautical charts, location information, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for transmitting the collected data to the server via a communication module, a means for storing the received data in a database, a means for analyzing the stored data, a means for predicting the behavior of fish species from the analyzed data using a generative AI model, a means for displaying the prediction results on a terminal, and a means for improving the catch in the fishing industry. This makes it possible to accurately predict the location and behavior of schools of fish and to conduct efficient fishing.

[0672] "Various data" refers to information such as nautical charts, location information, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of seafood, salinity concentration, and the rate of temperature change due to global warming.

[0673] "Means of collection" refers to the method of obtaining various data using sensors and data collection devices installed on fishing vessels.

[0674] "Communication module" refers to a communication device for transmitting collected data to a server.

[0675] "Database" refers to an information system for storing and managing received Data.

[0676] "Analysis means" refers to the methods and techniques used to process the stored data and convert it into meaningful information.

[0677] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to make predictions and classifications from data.

[0678] "Behavioral prediction" refers to predicting the movement and activity patterns of fish species based on analyzed data.

[0679] "Terminal" refers to a device for displaying prediction results.

[0680] "Measures to improve catches" refers to methods and technologies for fishing efficiently based on prediction results and increasing catches.

[0681] The present invention relates to a system for collecting and analyzing various data and predicting the behavior of fish species in order to improve catches in the fishing industry. A specific embodiment of this system will be described below.

[0682] Hardware and Software Used

[0683] Hardware: Sensors installed on fishing boats (seawater temperature sensor, salinity sensor, tide gauge, etc.), GPS, communication module

[0684] Software: Data collection software, data analysis software, generative AI models (e.g., using TensorFlow® or PyTorch®)

[0685] Data collection and transmission

[0686] The terminal uses various sensors installed on the fishing boat to collect data on seawater temperature, salinity, currents, etc. in real time. For example, the seawater temperature sensor measures the current seawater temperature, and the salinity sensor measures the salinity. The collected data is sent to a server via a communication module.

[0687] Data storage and analysis

[0688] The server saves the received data in a database. For example, it stores the data in a MySQL database. The saved data is preprocessed using a Python script. Specifically, it complements missing values ​​in the data and normalizes it.

[0689] Behavioral Prediction

[0690] The server uses a generative AI model to predict the behavior of fish species from the analyzed data. For example, the prediction is made using a TensorFlow (registered trademark) model. The behavior of fish species is predicted by inputting the following prompt sentence into the generative AI model.

[0691] Example prompt:

[0692] The current seawater temperature is 25 degrees, the salinity is 3.5%, the tide is 1.2 knots in the northeast direction, the air temperature is 20 degrees, the moon is a full moon, and the tide chart shows a rising tide. Under these conditions, please predict the preferred waters of the fish species and the time of day when they will be active.

[0693] Displaying the results and executing the fishery

[0694] The terminal displays the prediction results sent from the server on the fishing boat's terminal. For example, the display may show, "The preferred sea area for this fish species is 35 degrees north latitude and 140 degrees east longitude. The time period when they are active is from 2:00 pm to 4:00 pm." Based on this prediction result, the user (fisherman) moves the fishing boat to the preferred sea area for the fish species and fishes according to the time period when they are active.

[0695] In this way, by performing specific actions at each step, the system achieves efficient fishing based on predictions of fish species' behavior.

[0696] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0697] Step 1:

[0698] Data collection

[0699] The terminal uses various sensors installed on the fishing boat to collect data on seawater temperature, salinity, currents, etc. in real time. For example, the seawater temperature sensor measures the current seawater temperature, and the salinity sensor measures the salinity.

[0700] Input: Data from ocean temperature sensor, salinity sensor, and tide gauge

[0701] Output: Collected ocean temperature, salinity, and current data

[0702] Step 2:

[0703] Data transmission

[0704] The terminal transmits the collected data to a server via a communication module. For example, collected data on seawater temperature, salinity, and currents is sent as packets.

[0705] Input: Collected ocean temperature, salinity, and current data

[0706] Output: Data packet sent to the server

[0707] Step 3:

[0708] Data Storage

[0709] The server stores the received data in a database, for example a MySQL database.

[0710] Input: Data packet sent to the server

[0711] Output: Data stored in the database

[0712] Step 4:

[0713] 4. Data Analysis

[0714] The server analyzes the stored data, for example by preprocessing the data using Python scripts, such as by filling in missing values ​​and normalizing the data.

[0715] Input: Data stored in the database

[0716] Output: Preprocessed data

[0717] Step 5:

[0718] Behavioral Prediction

[0719] The server uses a generative AI model to predict the behavior of fish species from the analyzed data. For example, the prediction is made using a TensorFlow (registered trademark) model. The behavior of fish species is predicted by inputting the following prompt sentence into the generative AI model.

[0720] Input: Preprocessed data, prompt statement

[0721] Output: Fish species behavior prediction results

[0722] Example prompt:

[0723] The current seawater temperature is 25 degrees, the salinity is 3.5%, the tide is 1.2 knots in the northeast direction, the air temperature is 20 degrees, the moon is a full moon, and the tide chart shows a rising tide. Under these conditions, please predict the preferred waters of the fish species and the time of day when they will be active.

[0724] Step 6:

[0725] Results display

[0726] The terminal displays the prediction results sent from the server on the fishing boat's terminal. For example, the display might say, "The fish species' preferred sea area is 35 degrees north latitude and 140 degrees east longitude. They are most active between 2:00 and 4:00 p.m."

[0727] Input: Fish species behavior prediction results

[0728] Output: Prediction results displayed on the terminal

[0729] Step 7:

[0730] Fishing

[0731] Based on the prediction results, users (fishermen) can move their fishing boats to areas favored by fish species and fish during times when the fish species are most active.

[0732] Input: Prediction result displayed on the device

[0733] Output: Movement of fishing vessels and execution of fishing

[0734] (Application example 2)

[0735] Next, a description will be given of Application Example 2 of Form 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".

[0736] Conventional fishing systems had problems with low fishing efficiency due to insufficient data analysis and behavioral prediction to improve catches. In addition, optimization of fishing boat routes and notifications of fishing timing were done manually, which placed a heavy burden on fishermen and made it difficult to fish efficiently.

[0737] 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.

[0738] In this invention, the server includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, moon age, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, rate of temperature change due to global warming, etc.), a means for creating a behavior prediction for the target fish species, etc., a means for predicting where the target fish species are moving during a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, a means for improving the catch volume in the fishing industry, a means for optimizing the navigation route of the autonomous vehicle, a means for notifying the timing of fishing, a means for predicting behavior using a generative AI model, and a means for generating prompt sentences. This makes it possible to significantly improve the efficiency of the fishing industry.

[0739] "Various data" refers to information such as nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and the rate of temperature change due to global warming.

[0740] "Means for analysis" refers to methods and devices for analyzing various collected data and extracting meaningful information.

[0741] "Means for generating a behavioral prediction" refers to a method or device that uses the calculations and models necessary to predict the behavior of a target fish species.

[0742] "Means for displaying in real time" refers to a method or device for instantly reflecting the prediction results on a display device.

[0743] "Fishing yield enhancing measures" means any method or device used to increase the yield in a fishery.

[0744] "Means for optimizing the navigation route of an autonomous vehicle" refers to a method or device for an autonomous vehicle to select and navigate an optimal route.

[0745] "Fishing timing communication means" means a method or device that informs fishermen of the optimal time to fish.

[0746] A "generative AI model" refers to a model that uses artificial intelligence to make predictions and generate information from data.

[0747] "Means for generating prompt sentences" refers to a method or device for creating instruction sentences to be input into a generative AI model.

[0748] The system for carrying out the present invention collects and analyzes various data, predicts behavior, optimizes the navigation route of an autonomous vehicle based on the results, and notifies the timing of fishing. A specific embodiment of this system will be described below.

[0749] System Configuration

[0750] The system consists of the following main components:

[0751] 1. Data collection module:

[0752] Various data are collected, such as nautical charts, GPS, air temperature, sea water temperature, wind speed, currents, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and the rate of temperature change due to global warming.

[0753] Sensors and satellite communications are used to collect data.

[0754] 2. Data Analysis Module:

[0755] Analyze the collected data and extract meaningful information.

[0756] Analyze the data using machine learning algorithms.

[0757] 3. Behavioral Prediction Module:

[0758] Generative AI models are used to predict the behavior of target fish species.

[0759] Based on the prediction results, the results are displayed in real time on the fish finder's nautical chart and GPS.

[0760] 4. Route Optimization Module:

[0761] Based on the prediction results, the optimal route for the autonomous vehicle is calculated.

[0762] It issues instructions to the autonomous driving system to move fishing boats to the optimal sea area.

[0763] 5. Catch Timing Notification Module:

[0764] It notifies you of the times when tuna are active.

[0765] Optimize fishing timing and improve catches.

[0766] 6. Prompt generation module:

[0767] Create a prompt to input to the generative AI model.

[0768] Processing flow

[0769] The server first collects various data using a data collection module. Next, the data analysis module analyzes the collected data, and the behavior prediction module predicts the behavior of fish species using a generative AI model. The prediction results are displayed in real time, and the navigation route optimization module calculates the optimal navigation route and issues instructions to the autonomous driving system. In addition, the fishing timing notification module notifies the optimal fishing timing. The prompt generation module creates prompt sentences to input into the generative AI model.

[0770] Hardware and Software Used

[0771] Hardware: Sensors, satellite communication devices, autonomous driving systems, fish finders, GPS devices

[0772] Software: Machine learning algorithms, generative AI models, data analysis tools

[0773] Examples

[0774] For example, the following prompt sentence could be input to a generative AI model:

[0775] Predict the behavior of tuna when the sea water temperature is 25 degrees, the salinity is 35, the current is 1.5 m / s, the air temperature is 28 degrees, the moon phase is 0.5, and the tide graph is 1.2.

[0776] By inputting this prompt into the generative AI model, it is possible to predict the tuna's behavior and calculate the optimal navigation route.

[0777] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0778] Step 1:

[0779] The server uses a data collection module to collect various data, such as nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, and the rate of temperature change due to global warming, through sensors and satellite communications. The input is data from various sensors and satellite communications, and the output is the collected data set.

[0780] Step 2:

[0781] The server analyzes the collected data using a data analysis module, which uses machine learning algorithms to pre-process the data and extract meaningful information. The input is the dataset collected in step 1, and the output is the analyzed data.

[0782] Step 3:

[0783] The server inputs a prompt sentence into the generative AI model using the behavior prediction module to predict the behavior of the target fish species. Specifically, the server inputs the prompt sentence created by the prompt generation module into the generative AI model to obtain the prediction result. The input is the analyzed data and the prompt sentence, and the output is the predicted behavior result of the fish species.

[0784] Step 4:

[0785] The server displays the prediction results on the fish finder's chart and GPS in real time. Specifically, the prediction results are visualized and reflected on the display device so that the user can check them. The input is the predicted behavior of the fish species, and the output is the predicted results displayed in real time.

[0786] Step 5:

[0787] The server uses the navigation route optimization module to calculate the optimal navigation route for the autonomous vehicle. Specifically, it calculates the optimal route based on the prediction results and issues instructions to the autonomous driving system. The input is the behavior prediction results of the fish species, and the output is the optimal navigation route.

[0788] Step 6:

[0789] The server uses a fishing timing notification module to notify the user of the optimal fishing timing. Specifically, it calculates the time periods when tuna are active and notifies the user. The input is the predicted behavior of the fish species, and the output is a notification of the fishing timing.

[0790] Step 7:

[0791] The server uses the prompt generation module to create a prompt sentence to be input to the generative AI model. Specifically, the server generates a prompt sentence based on the collected data and passes it to the behavior prediction module. The input is the collected data, and the output is the prompt sentence.

[0792] In addition, an emotion engine that estimates the emotion of the user may be further combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0793] "Example 1"

[0794] As one embodiment of the present invention, there is a system that combines an emotion engine. This system includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for creating a behavior prediction of target fish species, etc., a means for predicting where the target fish species are moving at a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, and a means for improving the catch volume in the fishing industry. In addition, an emotion engine that recognizes the user's emotions is combined. This emotion engine recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. It is possible to adjust the behavior prediction of the target fish species using the output of the emotion engine. Specifically, when the user is feeling stressed, the emotion engine captures that information and adjusts the behavior prediction. This makes it possible to propose a more appropriate fishing method according to the user's emotional state.

[0795] "Example 2"

[0796] As one embodiment of the present invention, there is a system that combines an emotion engine. This system includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for creating a behavior prediction of target fish species, etc., a means for predicting where the target fish species are moving at a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, and a means for improving the catch volume in the fishing industry. In addition, an emotion engine that recognizes the user's emotions is combined. This emotion engine recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. It is possible to adjust the behavior prediction of the target fish species using the output of the emotion engine. Specifically, when the user is feeling stressed, the emotion engine captures that information and adjusts the behavior prediction. This makes it possible to propose a more appropriate fishing method according to the user's emotional state.

[0797] The process flow of each embodiment will be described below.

[0798] "Example 1"

[0799] Step 1: The system collects various data (nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, rate of temperature change due to global warming, etc.).

[0800] Step 2: Analyze the collected data and create predictions for the behavior of target fish species, etc.

[0801] Step 3: Predict where the target fish species will be moving at a specific time and display it in real time on the fish finder's chart and GPS.

[0802] Step 4: Recognize the user's emotions with the emotion engine. The emotion engine recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc.

[0803] Step 5: Use the emotion engine's output to adjust the behavioral predictions of the target fish species. Specifically, when the user is stressed, the emotion engine captures that information and adjusts its behavioral predictions.

[0804] Step 6: Based on the adjusted behavioral predictions, propose optimal fishing strategies to improve catches in the fishery.

[0805] Example 1

[0806] Next, a description will be given of Example 1 of Form 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".

[0807] In conventional fishing systems, data analysis and behavior prediction to improve catches were not sufficiently performed, making it difficult for fishermen to efficiently select fishing spots. In addition, there was a problem of increased stress and fatigue for fishermen because fishing methods were not proposed taking into account the user's emotional state. To solve these issues, a system that collects and analyzes various data and predicts behavior in real time is required. In addition, a function to recognize the user's emotional state and adjust behavior predictions based on that is also required.

[0808] 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.

[0809] In this invention, the server includes a means for collecting various data (such as a nautical chart, location information, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graph, catch volume, fishing location, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for transmitting the collected data to a central data processing device, a means for analyzing the data using a machine learning algorithm, a means for creating a behavior prediction for the target fish species, a means for predicting where the target fish species are moving during a specific time period and displaying the prediction in real time on the nautical chart and location information on the fish finder, a means for recognizing the user's emotions and adjusting the behavior prediction based on the emotion data, and a means for improving the catch in the fishing industry. This allows fishermen to efficiently select fishing spots and also makes it possible to suggest more appropriate fishing methods according to the user's emotional state.

[0810] "Various data" refers to information such as nautical charts, location information, air temperature, sea water temperature, wind speed, currents, lunar age, tide graphs, catch volume, fishing locations, ecology of seafood, salinity, and the rate of temperature change due to global warming.

[0811] "Means of collection" refers to the method of obtaining various data using sensors and data collection devices installed on fishing vessels.

[0812] "Central Data Processing Unit" refers to a computer system that receives, analyzes, and processes collected data.

[0813] A "machine learning algorithm" is a mathematical model that learns patterns and rules from data to make predictions and classifications.

[0814] "Means for generating behavioral predictions" refers to methods that use machine learning algorithms to predict the migration patterns and behavior of targeted fish species.

[0815] "Means of displaying in real time" refers to a method of instantly reflecting the prediction results on the nautical chart and location information on the fish finder.

[0816] "Means of recognizing emotions" refers to methods for analyzing a user's emotional state from facial expressions, tone of voice, choice of words, etc.

[0817] "Means for adjusting behavioral prediction based on emotional data" refers to a method for modifying the results of behavioral prediction by taking into account the emotional state of the user.

[0818] "Measures to improve fishing yield" refers to methods to improve fishing performance through the selection of efficient fishing sites and the proposal of appropriate fishing methods.

[0819] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0820] This invention is a system for achieving efficient fishing in the fishing industry. It collects and analyzes various data, predicts the behavior of fish species, and has the ability to adjust the prediction results taking into account the emotional state of the user.

[0821] Data collection

[0822] Fishing boats are equipped with sensors and data collection devices to collect various data such as nautical charts, location information, air temperature, seawater temperature, wind speed, tides, moon phase, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, rate of temperature change due to global warming, etc. This data is transmitted in real time to a central data processing device (server) using wireless communication technology (e.g. Wi-Fi, LTE).

[0823] Data analysis

[0824] The server preprocesses the received data, complementing missing values, removing outliers, normalizing data, etc. Specifically, it uses the Pandas library of Python (registered trademark). It extracts features from the preprocessed data, and uses the Scikit-learn (registered trademark) library to extract features such as fluctuation patterns of air and seawater temperature, and the direction and speed of tidal currents. Next, it trains a model to predict the behavior of fish species using a machine learning algorithm (e.g., TensorFlow (registered trademark), PyTorch (registered trademark)).

[0825] Generate behavioral predictions

[0826] The server uses the trained model to predict the behavior of target fish species, for example, where they will move at a certain time of day, and displays the prediction results in real time on the fish finder's chart and location information.

[0827] Combining emotion engines

[0828] To recognize the user's emotions, the fishing boat is equipped with cameras and microphones. The terminal uses these devices to collect emotion data from the user's facial expressions, tone of voice, choice of words, etc. The server analyzes the emotion data using OpenCV and Google Cloud Speech-to-Text (registered trademark) APIs to recognize the user's emotional state. Based on the analyzed emotion data, it adjusts behavior predictions and suggests more appropriate fishing methods according to the user's emotional state.

[0829] Examples

[0830] For example, when a fisherman goes fishing, he can input the following prompt sentence into the generative AI model to check how the system works:

[0831] "The current air temperature is 25 degrees, the sea temperature is 20 degrees, the wind speed is 5 m / s, and the tide is flowing northeast. The moon is full, and according to the tide graph, the tide is rising. The catch has been declining recently, and fishing is mainly taking place along the coast. According to the ecology data of fish and shellfish, the migration patterns of the target fish species are changing due to global warming. The user seems to be stressed. Please predict and suggest the best fishing spot under these conditions."

[0832] By inputting this prompt, the system can predict the best fishing spots in real time based on the collected data and the user's emotional state and display it on the fish finder.

[0833] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0834] Step 1:

[0835] The terminal uses sensors and data collection devices installed on the fishing boat to collect various data such as nautical charts, location information, air temperature, seawater temperature, wind speed, tides, moon phase, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, and the rate of change in air temperature due to global warming. The input is data from the various sensors, and the output is the collected data. In concrete terms, the sensors acquire data in real time and send it to the terminal.

[0836] Step 2:

[0837] The terminal transmits the collected data to the server in real time using wireless communication technology (e.g., Wi-Fi, LTE). The input is the collected data, and the output is the data transmitted to the server. In concrete terms, the terminal divides the data into packets and transmits them to the server via wireless communication.

[0838] Step 3:

[0839] The server preprocesses the received data. The input is the data sent from the terminal, and the output is the preprocessed data. Specifically, it uses the Pandas library of Python (registered trademark) to complement missing values, remove outliers, and normalize the data.

[0840] Step 4:

[0841] The server extracts features from the preprocessed data. The input is the preprocessed data, and the output is the extracted features. Specifically, the server uses the Scikit-learn library to extract features such as fluctuation patterns of air and sea temperature, and the direction and speed of tidal currents.

[0842] Step 5:

[0843] The server trains a machine learning model using the extracted features. The input is the extracted features, and the output is the trained model. Specifically, the server uses TensorFlow (registered trademark) and PyTorch (registered trademark) to build a fish species behavior prediction model.

[0844] Step 6:

[0845] The server uses the trained model to predict the behavior of the fish species that are the target of fishing. The input is the trained model and real-time data, and the output is the behavior prediction result. Specifically, the server inputs data into the model and generates a prediction result.

[0846] Step 7:

[0847] The server transmits the prediction result to the terminal. The input is the behavior prediction result, and the output is the prediction result transmitted to the terminal. In particular, the server formats the prediction result and transmits it to the terminal via wireless communication.

[0848] Step 8:

[0849] The terminal displays the prediction results in real time on the marine chart and location information on the fish finder. The input is the prediction results sent from the server, and the output is the displayed prediction results. The specific operation is to display the prediction results on the fish finder display.

[0850] Step 9:

[0851] The device collects emotion data from the user's facial expressions, tone of voice, choice of words, etc. The input is data from the camera and microphone, and the output is the collected emotion data. Specifically, the device uses the camera and microphone to capture the user's emotional state in real time.

[0852] Step 10:

[0853] The server analyzes the collected emotion data. The input is the emotion data sent from the terminal, and the output is the analyzed emotion state. Specifically, it uses OpenCV and Google Cloud Speech-to-Text (registered trademark) API to recognize the user's emotion state.

[0854] Step 11:

[0855] The server adjusts the behavior prediction based on the analyzed emotion data. The input is the analyzed emotion state and the behavior prediction result, and the output is the adjusted behavior prediction result. As a specific operation, the prediction result is modified according to the emotion state, and a more appropriate fishing method is proposed.

[0856] Step 12:

[0857] The server sends the adjusted behavior prediction result to the terminal, where the input is the adjusted behavior prediction result and the output is the adjustment result sent to the terminal. In particular, the server formats the adjustment result and sends it to the terminal through wireless communication.

[0858] Step 13:

[0859] The terminal displays the adjusted behavior prediction results on the marine chart and position information on the fish finder in real time. The input is the adjustment result sent from the server, and the output is the displayed adjustment result. The specific operation is to display the adjustment result on the fish finder display.

[0860] (Application example 1)

[0861] Next, a description will be given of Application Example 1 of Form 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".

[0862] In conventional fishing, fishermen have to spend a lot of time and effort to identify the location of fish schools, which reduces fishing efficiency. In addition, the emotional state of fishermen can affect fishing results, and the efficiency of fishing activities can further decrease due to accumulated stress and fatigue. In addition, there is a problem that it is difficult to improve the catch because the navigation of fishing boats and suggestions on fishing methods are not performed in real time.

[0863] 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.

[0864] In this invention, the server includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for creating a behavior prediction of the target fish species, etc., a means for predicting where the target fish species are moving during a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, a means for suggesting a fishing method according to the user's emotional state using an emotion engine that recognizes the user's emotions, a means for improving the navigation and fishing efficiency of the fishing boat that is installed on the autonomous fishing boat, and a means for receiving the location of the school of fish and the proposed fishing method in real time through the smart device. This enables fishermen to efficiently identify the location of the school of fish and increase the amount of catch. In addition, the proposed fishing method according to the user's emotional state can reduce the fishermen's stress and fatigue and improve the efficiency of fishing activities.

[0865] "Various data" refers to information such as nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and the rate of temperature change due to global warming.

[0866] "Means of analysis" refers to devices and algorithms used to analyze various collected data and predict the behavior of schools of fish.

[0867] "Means for creating behavioral predictions" refers to devices and algorithms that use the analyzed data to predict the behavior of targeted fish species.

[0868] "Means for displaying in real time" refers to devices or software for instantly displaying the predicted location information of schools of fish on a fish finder or GPS.

[0869] "Means to improve catches" refers to devices and algorithms that propose efficient fishing methods based on information on the location and behavioral predictions of fish schools, thereby increasing catches.

[0870] An "emotion engine" refers to a device or software that recognizes emotions from a user's facial expressions, tone of voice, choice of words, etc., and adjusts fishing methods based on that information.

[0871] An "autonomous fishing vessel" refers to a fishing vessel that is designed to navigate and conduct fishing activities automatically.

[0872] "Measures to improve navigation and fishing efficiency" refers to devices and algorithms that enable autonomous fishing vessels to navigate and fish efficiently.

[0873] "Smart devices" refers to portable information terminals such as smartphones, tablets, smart glasses, and head-mounted displays.

[0874] "Means of receiving real-time information on the location of schools of fish and suggestions on efficient fishing methods" refers to equipment or software that allows a smart device to instantly receive information on the location of schools of fish and suggestions on efficient fishing methods.

[0875] The following system configuration will be described as an embodiment of the present invention.

[0876] System Configuration

[0877] Hardware Configuration

[0878] 1. Sensors installed on fishing boats: Various sensors to collect data such as nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and rate of temperature change due to global warming.

[0879] 2. Central Data Processing Unit: A computer capable of high-speed data processing, such as a server equipped with an NVIDIA (registered trademark) GPU.

[0880] 3. Smart devices: Portable information terminals such as smartphones, tablets, smart glasses, and head-mounted displays.

[0881] Software Configuration

[0882] 1. Data collection software: Software for collecting data from various sensors and transmitting it to a central data processing device.

[0883] 2. Data analysis software: Software that analyzes collected data using machine learning algorithms such as TensorFlow (registered trademark) and PyTorch (registered trademark).

[0884] 3. Behavioral prediction software: Software that predicts the behavior of fish species being targeted for fishing based on analyzed data.

[0885] 4. Real-time display software: Software that displays the predicted locations of fish schools in real time on a fish finder or GPS.

[0886] 5. Emotion engine software: Software that recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. and adjusts fishing methods based on that information.

[0887] 6. Navigation software: Software that enables autonomous fishing vessels to navigate and fish efficiently.

[0888] 7. Application for smart devices: An application to receive real-time information on fish locations and fishing method suggestions via smart devices.

[0889] Processing flow

[0890] 1. Data collection: Various sensors installed on fishing boats collect data such as nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, moon phase, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, rate of temperature change due to global warming, etc. This data is sent to a central data processing unit through data collection software.

[0891] 2. Data Analysis: The central data processing unit analyses the collected data using data analysis software, which uses machine learning algorithms such as TensorFlow® and PyTorch®.

[0892] 3. Behavioral prediction: Based on the analyzed data, behavioral prediction software predicts the behavior of the targeted fish species, thereby predicting where schools of fish will be moving at a particular time.

[0893] 4. Real-time display: The prediction results are displayed on fish finders and GPS through real-time display software, which helps fishermen to efficiently select fishing spots.

[0894] 5. Emotion Recognition and Adjustment: The emotion engine software recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. and adjusts its fishing strategy based on that information. For example, if the user is stressed, the emotion engine will pick up on that information and adjust its behavior predictions.

[0895] 6. Improved navigation and fishing efficiency: Navigation software will help autonomous fishing vessels navigate and fish more efficiently, which will improve fishing efficiency.

[0896] 7. Notifications on smart devices: Through a smart device application, fishermen can receive real-time information on the location of fish schools and suggestions on how to catch them.

[0897] Examples

[0898] For example, if a fisherman is wearing smart glasses, he can input prompt sentences like the following into the generative AI model and receive real-time information about the location of fish schools and suggestions on how to catch them.

[0899] Examples of prompt statements

[0900] "The current seawater temperature is 25 degrees, the wind speed is 5 m / s, and the current is flowing northeast. Please tell me where we can expect to catch the most fish in the next hour."

[0901] By feeding this prompt into a generative AI model, the AI ​​will suggest optimal fishing locations based on the collected data.

[0902] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0903] Step 1:

[0904] Various sensors installed on fishing boats collect data such as nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, and the rate of temperature change due to global warming. This data is sent to a central data processing device through data collection software. The input is real-time data from the various sensors, and the output is the data sent to the central data processing device.

[0905] Step 2:

[0906] The central data processing unit analyzes the collected data using data analysis software. Machine learning algorithms such as TensorFlow and PyTorch are used for the analysis. The input is the data collected in step 1, and the output is the analysis result. Specific operations include data preprocessing, feature extraction, and application of machine learning models.

[0907] Step 3:

[0908] Based on the analyzed data, the behavioral prediction software predicts the behavior of the target fish species. This allows it to predict where fish schools will be moving at a specific time. The input is the analysis result from step 2, and the output is the predicted behavioral data of the fish schools. Specific operations include applying a predictive model and generating a prediction result.

[0909] Step 4:

[0910] The prediction results are displayed on the fish finder or GPS through real-time display software. This allows fishermen to efficiently select fishing locations. The input is the behavior prediction data from step 3, and the output is the display data on the fish finder or GPS. Specific operations include data visualization and real-time display.

[0911] Step 5:

[0912] The emotion engine software recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc., and adjusts its fishing methods based on that information. For example, if the user is feeling stressed, the emotion engine captures that information and adjusts its behavior predictions. The input is the user's emotion data, and the output is adjusted behavior prediction data. Specific operations include applying emotion recognition algorithms and recalibrating the prediction model.

[0913] Step 6:

[0914] The navigation software efficiently navigates the autonomous fishing vessel and performs fishing activities, thereby improving fishing efficiency. The input is adjusted behavior prediction data, and the output is navigation data for the autonomous fishing vessel. Specific operations include calculation of navigation routes and autonomous driving control.

[0915] Step 7:

[0916] Through the smart device application, fishermen can receive real-time fish location and fishing method suggestions. The input is the navigation data and coordinated behavior prediction data of the autonomous fishing boat, and the output is notification data on the smart device. Specific operations include transmitting data and generating notifications.

[0917] Example 2

[0918] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0919] In conventional fishing systems, data analysis and behavioral prediction to improve catches were not sufficiently performed, making efficient fishing difficult. In addition, there were no proposals for fishing methods that took into account the emotional state of fishermen, which led to problems with increased stress and fatigue among fishermen. This has led to a demand for simultaneously improving the efficiency of fishing and the satisfaction of fishermen.

[0920] 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.

[0921] In this invention, the server includes a means for analyzing various data (map information, location information, weather information, ocean information, tide information, lunar age information, tide information, fishing information, fishing location information, fish ecology information, salinity information, climate change information, etc.), a means for creating a behavior prediction for the target fish to be caught, a means for predicting where the target fish will move during a specific time period and displaying this in real time on the map information and location information on the fish finder, a means for improving the catch in the fishing industry, and a means including an emotion engine that recognizes the user's emotions and adjusting the behavior prediction using the output of the emotion engine. This makes it possible to make highly accurate behavior predictions based on collected data and to suggest appropriate fishing methods according to the user's emotional state.

[0922] "Map information" is data that shows the topography and location relationships of oceans and land.

[0923] "Location information" is data that indicates the latitude and longitude of a specific point using technology such as GPS.

[0924] "Weather information" is data that indicates atmospheric conditions such as temperature, wind speed, and precipitation.

[0925] "Ocean information" refers to data that indicates ocean conditions, such as seawater temperature, salinity, and tidal currents.

[0926] "Tidal current information" is data that indicates the direction and speed of ocean water flow.

[0927] "Moon age information" is data that indicates the phases of the moon.

[0928] "Tidal information" is data that indicates the up and down movement of the sea surface.

[0929] "Catch information" is data that indicates the type and quantity of fish caught.

[0930] "Fishing location information" is data that indicates the specific location where the fishing took place.

[0931] "Fish ecological information" is data that indicates fish behavior patterns and habitats.

[0932] "Salinity concentration information" is data that indicates the percentage of salinity in seawater.

[0933] "Climate change information" is data showing long-term changes in temperature and precipitation.

[0934] An "emotion engine" is a system that recognizes emotions from a user's facial expressions, tone of voice, choice of words, etc.

[0935] A "machine learning algorithm" is a computational method for making predictions and classifications based on data.

[0936] This invention is a system for improving catches in the fishing industry, which collects and analyzes various data, predicts fish behavior, and suggests appropriate fishing methods according to the user's emotional state.

[0937] The server collects various data such as map information, location information, weather information, ocean information, tide information, lunar phase information, tide information, fishing information, fishing location information, fish ecology information, salinity information, and climate change information. These data are obtained from dedicated sensors and databases. For example, the latest seawater temperature, salinity, and tide data is obtained from the ocean database, and temperature, wind speed, lunar phase, and tide information is obtained from the weather database. In addition, real-time location information and catch volume data are collected from the GPS and fish finder installed on the fishing boat.

[0938] The server analyzes the collected data and creates predictions for the behavior of tuna and other fish. Using machine learning algorithms, it analyzes data such as seawater temperature, salinity, and currents to predict the areas that fish prefer. It also predicts the times when fish will be active based on data such as temperature, moon phase, and tide information. This allows fishing boats to fish more efficiently.

[0939] The server displays the prediction results on the map information on the fish finder and on the GPS in real time. This allows fishing boats to move to areas where fish are predicted to be present and fish more efficiently. The prediction results are converted into a data format for display on the fish finder display and sent to the GPS device.

[0940] It is combined with an emotion engine that recognizes the user's emotions. The emotion engine recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. For example, the emotion engine captures the user's facial expressions with a camera and performs image analysis. It also collects the user's tone of voice with a microphone and performs audio analysis. The server receives the output data from the emotion engine and adjusts the parameters of the behavior prediction model if the user is feeling stressed.

[0941] The server generates the optimal fishing method based on the adjusted behavior prediction results. The generated proposal is displayed on the terminal display and notified to the user. This makes it possible to propose a more appropriate fishing method according to the user's emotional state.

[0942] As a concrete example, if the seawater temperature on a certain day is 25 degrees, the salinity is 3.5%, and the tidal current is flowing northeast, the server will use this data to predict the areas where tuna prefer and move fishing boats to those areas.Also, if the air temperature is 20 degrees, the moon is a full moon, and the tidal information shows a rising tide, the server will predict the times when tuna will be active and give instructions to fish during those times.

[0943] An example of a prompt sentence is as follows:

[0944] "Predict the areas where tuna prefer to fish if the seawater temperature is 25 degrees, the salinity is 3.5%, and the current is flowing northeast. Also, if the air temperature is 20 degrees, the moon is a full moon, and the tidal information shows a rising tide, predict the time of day when tuna will be active."

[0945] In this way, the system can predict fish behavior based on collected data and improve catches. In addition, by using an emotion engine, the system can suggest more appropriate fishing methods according to the user's emotional state.

[0946] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0947] Step 1:

[0948] The server collects various data such as map information, location information, weather information, ocean information, tidal current information, lunar phase information, tide information, fishing information, fishing location information, fish ecology information, salinity concentration information, and climate change information.

[0949] Input: Various data from dedicated sensors and databases

[0950] Output: Various data collected

[0951] Specific behavior:

[0952] The server accesses an oceanographic database to obtain the latest ocean temperature, salinity, and current data.

[0953] The server retrieves temperature, wind speed, lunar age, and tide information from a weather database.

[0954] The server collects real-time location and catch data from the GPS and fish finders installed on the fishing boats.

[0955] Step 2:

[0956] The server analyzes the collected data and creates predictions of fish behavior.

[0957] Input: Various data collected

[0958] Output: Fish behavior prediction results

[0959] Specific behavior:

[0960] The server inputs the collected seawater temperature, salinity, and current data and applies it to a model to predict which marine areas fish prefer.

[0961] The server uses data on temperature, lunar phase, and tide information to run models to predict when fish will be active.

[0962] Step 3:

[0963] The server displays the prediction results in real time on the fish finder's map information and GPS.

[0964] Input: Fish behavior prediction results

[0965] Output: Display data to fishfinder and GPS devices

[0966] Specific behavior:

[0967] The server converts the prediction results into a data format for display on the fish finder display.

[0968] The server sends the prediction results to the GPS device and displays them in real time.

[0969] Step 4:

[0970] It is combined with an emotion engine that recognizes the user's emotions from facial expressions, tone of voice, choice of words, etc.

[0971] Input: User facial expressions, tone of voice, and word choice

[0972] Output: The user's emotional state.

[0973] Specific behavior:

[0974] The emotion engine captures the user's facial expressions with a camera and performs image analysis.

[0975] The emotion engine collects the user's voice tone through a microphone and performs voice analysis.

[0976] Step 5:

[0977] The server uses the output of the emotion engine to refine the behavior predictions of the fish.

[0978] Input: User's emotional state, fish behavior prediction results

[0979] Output: Adjusted fish behavior prediction results

[0980] Specific behavior:

[0981] The server receives the output data from the emotion engine and adjusts the parameters of the behavior prediction model if the user is feeling stressed.

[0982] Step 6:

[0983] The server generates the optimal fishing method based on the adjusted behavior prediction results, and the generated proposal is displayed on the terminal display and notified to the user.

[0984] Input: Adjusted fish behavior prediction results

[0985] Output: Recommendations for optimal fishing methods

[0986] Specific behavior:

[0987] The server generates an optimal fishing method based on the adjusted behavior prediction results.

[0988] The server displays the generated proposal on the display of the terminal and notifies the user.

[0989] (Application example 2)

[0990] Next, a description will be given of Application Example 2 of Form 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".

[0991] Conventional fishing systems generally catch fish based on ocean conditions and fish school behavior predictions, but there was no system that took the user's emotional state into account. As a result, it was not possible to suggest the optimal fishing method depending on whether the user was stressed or relaxed, which could lead to reduced fishing efficiency. In addition, these systems were rarely applied to autonomous vehicles, and the automation and efficiency of fishing had not progressed sufficiently.

[0992] 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.

[0993] In this invention, the server includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, rate of temperature change due to global warming, etc.), a means for creating a behavior prediction for target fish species, etc., a means for predicting where the target fish species are moving during a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, a means for improving the catch volume in fishing, a means for recognizing the user's emotional state, a means for adjusting the behavior prediction based on the user's emotional state, and a means for being installed in the autonomous vehicle. This makes it possible to propose an optimal fishing method according to the user's emotional state and improve fishing efficiency.

[0994] "Various data" refers to information such as nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and the rate of temperature change due to global warming.

[0995] "Means of analysis" refers to methods and equipment for analyzing various types of data and understanding fish behavior and oceanographic conditions.

[0996] "Means for generating behavioral predictions" refers to methods or devices for predicting the behavior of target fish species based on collected data.

[0997] "Means for displaying in real time" refers to a method or device for instantly displaying predicted fish school location information on a marine chart or GPS on a fish finder.

[0998] "Means for improving catches" refers to methods and devices for fishing efficiently and increasing catches based on predicted fish school location information.

[0999] "Means for recognizing a user's emotional state" refers to a method or device for identifying emotions from a user's facial expressions, tone of voice, choice of words, etc.

[1000] "Means for adjusting behavior prediction" refers to a method or device for modifying the behavior prediction of the school of fish based on the emotional state of the user.

[1001] "Means installed in an autonomous vehicle" refers to a method or apparatus for mounting and operating each of the means described above on an autonomous vehicle.

[1002] A system for implementing this invention is configured as follows: First, the server collects various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.) and analyzes this data. Software such as Python (registered trademark), Pandas, and Scikit-learn (registered trademark) are used for the analysis.

[1003] The server then uses machine learning algorithms to generate predictions of the behavior of the target fish species, based on ecological knowledge of the target species, and displays the predicted fish locations in real time on the chart and GPS on the fish finder.

[1004] In addition, the server uses emotion recognition software such as EmotionEngine® to recognize the user's emotional state. It identifies emotions from the user's facial expressions, tone of voice, choice of words, etc., and adjusts behavior predictions based on the user's emotional state. For example, if the user is stressed, it predicts the location of schools of fish by emphasizing the influence of tides. Conversely, if the user is relaxed, it predicts the location of schools of fish by reducing the influence of tides.

[1005] This system will be installed in autonomous vehicles, which will be able to move automatically based on the predicted location information of fish schools and fish more efficiently, thereby improving catches.

[1006] As a concrete example, the operation of the system can be confirmed by inputting the following prompt sentence into the generative AI model.

[1007] Example prompt:

[1008] Create a Python (registered trademark) program that predicts the location of schools of fish based on oceanographic condition data and fish behavior data. Add a function to adjust the parameters of the prediction model according to the user's emotional state. There are two types of emotional state: "stressed" and "relaxed," and the influence of the tides should be adjusted according to each state.

[1009] In this way, the server, terminals, and users can work together to operate the system, making it possible to streamline and automate fishing.

[1010] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1011] Step 1:

[1012] The server collects various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, rate of temperature change due to global warming, etc.). This data is obtained from sensors and external databases. The input is data from various sensors and databases, and the output is a set of collected data.

[1013] Step 2:

[1014] The server analyzes the collected data. Specifically, it preprocesses the data using Python (registered trademark) and Pandas, and performs missing value completion and outlier removal. The input is the collected data set, and the output is the preprocessed data.

[1015] Step 3:

[1016] The server uses machine learning algorithms (e.g., Scikit-learn® random forest regression models) to generate behavioral predictions for the fish species being fished. The input is the pre-processed data, and the output is the predicted location of the fish schools.

[1017] Step 4:

[1018] The server displays the predicted fish school location information on the fish finder's nautical chart or GPS in real time. The input is the fish school location prediction, and the output is the displayed location information. The specific operation is to plot the location information on the fish finder's display.

[1019] Step 5:

[1020] The server uses the EmotionEngine to recognize the user's emotional state. The input is data such as the user's facial expression, tone of voice, and choice of words, and the output is the user's emotional state (e.g., stressed, relaxed).

[1021] Step 6:

[1022] The server adjusts the action prediction based on the user's emotional state. For example, if the user is stressed, it re-predicts the fish school's location by emphasizing the influence of tides. The input is the user's emotional state and the fish school's location prediction, and the output is the adjusted fish school location prediction.

[1023] Step 7:

[1024] The autonomous vehicle moves automatically based on the adjusted fish school position information. The input is the adjusted fish school position prediction, and the output is the autonomous vehicle's movement path. Specifically, the vehicle's navigation system calculates a new path and moves the vehicle according to the new path.

[1025] Step 8:

[1026] The user fishes based on the information provided by the system. The input is the location information and fishing method suggestions from the system, and the output is the actual fishing results. In concrete terms, the user fishes at the specified location and checks the amount of catch.

[1027] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[1028] 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> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[1029] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1030] 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 smart glasses 214.

[1031] [Third embodiment]

[1032] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1033] 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.

[1034] 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 wide area network (WAN) and / or a local area network (LAN).

[1035] 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.

[1036] 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 the voice according to instructions from the processor 46.

[1037] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1038] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1039] Fig. 6 shows an example of 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.

[1040] 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.

[1041] 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.

[1042] In the headset type terminal 314, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The processor 46 executes the reception output process on the RAM 48.

[1043] This is realized by operating as the control unit 46A in accordance with the reception output program 60.

[1044] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1045] "Example 1"

[1046] In one embodiment of the present invention, a fishing boat is equipped with sensors and data collection devices for collecting various data (such as nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, and rate of temperature change due to global warming). These data are sent to a central data processing device and analyzed using machine learning algorithms. The analysis results are generated as a behavior prediction of the target fish species, and predict where the target fish species will be moving at a specific time period. The prediction results are displayed in real time on the nautical charts and GPS on the fish finder, allowing fishermen to efficiently select fishing locations.

[1047] "Example 2"

[1048] As a specific example, consider a fishing boat that fishes for tuna. Various data on the ecology of tuna and ocean conditions are collected, and predictions of tuna behavior are made based on this data. For example, based on data such as seawater temperature, salinity, and tides, the areas that tuna prefer can be predicted, and the fishing boat can be moved to those areas. Also, based on data such as temperature, moon phase, and tide graphs, the times when tuna will be active can be predicted, and fishing can be carried out at those times. This makes it possible to significantly increase the catch.

[1049] The process flow of each embodiment will be described below.

[1050] "Example 1"

[1051] Step 1: Sensors and data collection devices are installed on the fishing boat to collect various data (nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar phase, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of temperature change due to global warming, etc.).

[1052] Step 2: The collected data is transmitted to a central data processing device.

[1053] Step 3: The data processor uses machine learning algorithms to analyze the data and generate behavioral predictions for the fish species being fished.

[1054] Step 4: Predict where the target fish species will be moving at a specific time and display this prediction in real time on the chart and GPS on the fish finder.

[1055] "Example 2"

[1056] Step 1: Sensors and data collection devices will be installed on tuna fishing boats to collect various data on tuna ecology and ocean conditions.

[1057] Step 2: The collected data is transmitted to a central data processing device.

[1058] Step 3: The data processor uses machine learning algorithms to analyze the data and generate predictions of tuna behavior.

[1059] Step 4: Using data on seawater temperature, salinity, tidal currents, etc., predict the areas preferred by tuna and move fishing boats to those areas.

[1060] Step 5: Using data such as temperature, moon phase, and tide graphs, predict the times when the tuna will be active and fish during those times.

[1061] Example 1

[1062] Next, a description will be given of Example 1 of the embodiment 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".

[1063] In conventional fishing, it was difficult for fishermen to accurately determine the location of schools of fish, making it difficult to increase catches. In addition, there was a lack of systems that could efficiently collect and analyze a wide variety of data, such as meteorological and oceanographic information, and provide it to fishermen in real time. This reduced the efficiency of fishing and made it difficult to predict catches.

[1064] 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.

[1065] In this invention, the server includes a means for collecting various data (map information, location information, weather information, ocean information, wind speed information, tidal current information, lunar age information, tide information, fishing information, fishing location information, marine life information, salinity concentration information, climate change information, etc.), a means for transmitting the collected data to a central data processing device, a means for receiving the transmitted data and performing preprocessing, a means for analyzing the preprocessed data using a machine learning algorithm, a means for generating a behavior prediction of fish species based on the analysis result, a means for transmitting the generated behavior prediction result to a terminal, and a means for displaying the prediction result on the terminal in real time. This enables fishermen to grasp the location of schools of fish in real time and efficiently select fishing spots.

[1066] "Various data" refers to map information, location information, weather information, ocean information, wind speed information, current information, lunar age information, tidal information, fishing information, fishing location information, marine life information, salinity concentration information, climate change information, etc.

[1067] "Means of collection" refers to the equipment and methods used to obtain various data using sensors and data collection devices installed on fishing vessels.

[1068] "Central Data Processing Unit" refers to a computer system for receiving, pre-processing and analyzing collected data.

[1069] "Transmitting means" refers to a device or method for transmitting collected data to a central data processing device using wireless or wired communication.

[1070] "Preprocessing means" refers to software or algorithms for filling in missing values ​​or correcting outliers in the received data.

[1071] "Machine learning algorithms" refers to artificial intelligence techniques for analyzing data and creating patterns and predictions.

[1072] "Means for generating a behavioral prediction" refers to software or algorithms for predicting behavioral patterns of fish species using machine learning algorithms.

[1073] "Terminal" refers to fish finders and other display devices installed on fishing vessels.

[1074] "Means for displaying in real time" refers to software or hardware for instantly displaying the generated behavior prediction results on a terminal.

[1075] "Means for improving catch" refers to methods and devices for increasing catch by accurately determining the location of fish schools and efficiently selecting fishing spots.

[1076] The present invention is a system for improving catches in the fishing industry, which collects various data, analyzes them using machine learning algorithms, and generates predictions of fish species behavior. A specific embodiment of the system will be described below.

[1077] Data collection

[1078] The user (fisherman) uses sensors and data collection devices installed on the fishing boat to collect various data such as map information, location information, weather information, ocean information, wind speed information, tidal current information, lunar age information, tide information, fishing catch information, fishing location information, marine life information, salinity concentration information, climate change information, etc. For example, an air temperature sensor measures 25°C and a seawater temperature sensor measures 20°C.

[1079] Data transmission

[1080] The terminal (data collection device on the fishing boat) transmits the collected data to the central data processing device using wireless communication (e.g., Wi-Fi (registered trademark) or satellite communication). For example, the data is transmitted using a Wi-Fi module.

[1081] Data reception and preprocessing

[1082] The server receives data sent from the terminal. For the received data, a data frame is created using the Python (registered trademark) pandas library, missing values ​​are complemented, and outliers are detected and corrected. For example, missing values ​​are complemented with the average value, and outliers are corrected with the median value.

[1083] Data analysis

[1084] The server inputs the preprocessed data into a machine learning algorithm (e.g., TensorFlow® or PyTorch®) for analysis. For example, it uses a random forest model to predict the behavioral patterns of fish species.

[1085] Generate behavioral predictions

[1086] Based on the analysis results, the server generates a prediction of the behavior of fish species, for example, a prediction that mackerel will move to 35 degrees north latitude and 140 degrees east longitude during a specific time period.

[1087] Sending and viewing results

[1088] The server sends the generated behavior prediction results to the terminal. For example, it sends the prediction results in JSON format using the HTTP protocol. The terminal (fish finder) displays the received prediction results in real time. For example, it displays a nautical chart and GPS information on the fish finder display, overlaying them, and indicates the predicted location of the school of fish with a marker.

[1089] Examples

[1090] For example, a fisherman might collect the following data using sensors on his boat:

[1091] Nautical Chart Data GPS data Temperature: 25°C Sea water temperature: 20°C Wind speed: 5m / s Current: 1m / s Moon age: 15 days Tide Graph: High Tide Catch: 100kg Fishing location: 35 degrees north latitude, 139 degrees east longitude Ecology of fish and shellfish: Mackerel Salinity: 3.5% Rate of temperature change due to global warming: 0.02°C / year

[1092] This data is sent to a central data processor where it is analysed using machine learning algorithms, which generate predictions of when mackerel will move to 35 degrees north and 140 degrees east at a specific time, and which are then displayed in real time on the charts and GPS on the fish finder.

[1093] Examples of prompt statements

[1094] Examples of prompts to be input to a generative AI model include:

[1095] "Please predict the behavior of mackerel based on the following data:

[1096] Nautical Chart Data GPS data Temperature: 25°C Sea water temperature: 20°C Wind speed: 5m / s Current: 1m / s Moon age: 15 days Tide Graph: High Tide Catch: 100kg Fishing location: 35 degrees north latitude, 139 degrees east longitude Ecology of fish and shellfish: Mackerel Salinity: 3.5% Rate of temperature change due to global warming: 0.02°C / year

[1097] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1098] Step 1: Data collection

[1099] Users (fishermen) use sensors and data collection devices installed on their fishing boats to collect various data such as map information, location information, weather information, ocean information, wind speed information, tidal current information, lunar phase information, tide information, fishing catch information, fishing location information, marine life information, salinity concentration information, and climate change information. For example, an air temperature sensor measures 25°C and a seawater temperature sensor measures 20°C. The input is data from various sensors, and the output is the collected data.

[1100] Step 2: Send data

[1101] The terminal (data collection device on the fishing boat) transmits the collected data to the central data processing device using wireless communication (e.g. Wi-Fi or satellite communication). For example, a Wi-Fi module is used to transmit the data. The input is the collected data and the output is the data transmitted to the central data processing device.

[1102] Step 3: Receiving data

[1103] The server receives data sent from the terminal. It opens a receiving port to wait for data and temporarily stores the received data. The input is the data sent from the terminal, and the output is the data stored in the server.

[1104] Step 4: Data Preprocessing

[1105] The server preprocesses the received data. Specifically, it uses the pandas library of Python (registered trademark) to create a data frame, impute missing values, and detect and correct outliers. For example, if there are missing values, they are imputed with the mean value, and if there are outliers, they are corrected with the median value. The input is the received data, and the output is the preprocessed data.

[1106] Step 5: Data analysis

[1107] The server inputs the preprocessed data into a machine learning algorithm (e.g., TensorFlow (registered trademark) or PyTorch (registered trademark)) and performs analysis. For example, a random forest model is used to predict the behavioral patterns of fish species. The input is the preprocessed data, and the output is the analysis result.

[1108] Step 6: Generate behavior predictions

[1109] The server generates a behavioral prediction for the fish species based on the analysis results. For example, it generates a prediction that mackerel will move to 35 degrees north latitude and 140 degrees east longitude during a specific time period. The input is the analysis results, and the output is the behavioral prediction results.

[1110] Step 7: Sending results

[1111] The server transmits the generated behavior prediction result to the terminal. For example, the prediction result is transmitted in JSON format using the HTTP protocol. The input is the behavior prediction result, and the output is the prediction result transmitted to the terminal.

[1112] Step 8: View the results

[1113] The terminal (fish finder) displays the received prediction results in real time. For example, a marine chart and GPS information are overlaid on the fish finder display, and the predicted locations of the schools of fish are indicated with markers. The input is the prediction results sent from the server, and the output is the prediction results displayed on the display.

[1114] (Application example 1)

[1115] Next, a description will be given of Application Example 1 of Form 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".

[1116] In traditional fishing, fishermen often relied on experience and intuition to select fishing spots, making it difficult to catch fish efficiently. In addition, fishing boats also required manual operation, which was labor-intensive and time-consuming. Furthermore, there was a lack of real-time data analysis to respond to changes in weather conditions and the marine environment, making it difficult to increase catches.

[1117] 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. In this invention, the server includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for creating a behavior prediction of the target fish species, etc., a means for predicting where the target fish species are moving in a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, a means for improving the catch in the fishing industry, a means for updating the navigation system of the autonomous fishing boat, a means for predicting the behavior of fish using data collected in real time, and a means for moving the autonomous fishing boat to the optimal fishing spot based on the prediction result. This allows not only fishers to efficiently select fishing spots, but also allows the autonomous fishing boat to automatically move to the optimal fishing spot.

[1118] "Various data" refers to information such as nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and the rate of temperature change due to global warming.

[1119] "Means for analyzing" refers to methods and devices for analyzing various collected data and extracting meaningful information.

[1120] "Means for creating a behavioral prediction" refers to a method or device that constructs a predictive model based on collected data and generates the results in order to predict the behavior of a target fish species.

[1121] "Means for displaying in real time" refers to a method or device for instantly displaying the prediction results on a chart or GPS on a fish finder.

[1122] "Measures to improve fishing yield" refers to methods or devices that increase fishing yield by assisting in the selection of efficient fishing sites and the operation of fishing vessels.

[1123] "Means for updating the navigation system of an autonomous fishing vessel" refers to a method or device for correcting and updating the route and operation plan of an autonomous fishing vessel in real time based on the prediction results.

[1124] "Means for predicting fish behavior using data collected in real time" refers to a method or device for instantly predicting fish behavior based on the latest data obtained from sensors and data collection devices.

[1125] "Means for moving an autonomous fishing vessel to an optimal fishing location based on prediction results" refers to a method or device for automatically moving an autonomous fishing vessel to the most efficient fishing location based on the results of behavioral prediction.

[1126] The system for carrying out the present invention collects data obtained from various sensors and data collection devices mounted on fishing boats in real time, and analyzes the data in a central data processing device to predict the behavior of specific fish species. A specific embodiment of this system will be described below.

[1127] Hardware and Software Used

[1128] Hardware

[1129] Various sensors: GPS, temperature sensor, sea water temperature sensor, anemometer, tide gauge, salinity meter, etc.

[1130] Data collection equipment: A device that collects data from sensors and transmits it to a central data processing device.

[1131] Central Data Processing Unit: A computer equipped with a high-performance CPU / GPU.

[1132] software

[1133] Python(registered trademark): A programming language.

[1134] scikit-learn(registered trademark): Machine learning library.

[1135] pandas(registered trademark): A data processing library.

[1136] matplotlib(registered trademark): A data visualization library.

[1137] Data processing and calculation

[1138] Data collection

[1139] The sensors collect data in real time, including GPS location, air temperature, seawater temperature, wind speed, tides, moon phase, tide graphs, catch volume, fishing location, fish and shellfish ecology, salinity, and the rate of temperature change due to global warming.

[1140] Data Preprocessing

[1141] Convert the collected data into a data frame and impute missing values, thereby ensuring data consistency and accuracy.

[1142] Training the model

[1143] A random forest regression model is trained using historical data, which allows us to build a fish behavior prediction model.

[1144] Behavioral Prediction

[1145] The data collected in real time is used to predict fish behavior, and the prediction results are displayed in real time on the fish finder's nautical chart and GPS.

[1146] Navigation system updates

[1147] The prediction results are used to update the navigation system of autonomous fishing boats, allowing them to automatically navigate to the optimal fishing spots.

[1148] Examples

[1149] For example, if it is predicted that a fishing vessel needs to move 10km northeast from its current position, the navigation system will automatically move the vessel in that direction.

[1150] Examples of prompt statements

[1151] "Enter the current GPS location, air temperature, seawater temperature, wind speed, tides, moon phase, tide graph, catch volume, fishing location, fish and shellfish ecology, salinity, and rate of temperature change due to global warming, and predict the location with the best chance of catching fish within the next hour."

[1152] In this way, by applying the invention to the navigation system of an autonomous fishing boat, more efficient fishing becomes possible.

[1153] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1154] Step 1:

[1155] Collecting data from sensors

[1156] The server collects data in real time from various sensors (GPS, temperature sensor, seawater temperature sensor, anemometer, tide gauge, salinity meter, etc.). As input, it receives measurements from each sensor and sends them to the data collector. As output, the collected data is stored in data frame format.

[1157] Step 2:

[1158] Data Preprocessing

[1159] The server converts the collected data into a data frame and imputes missing values. As input, it takes the data collected in step 1 and converts it into a data frame. If there are missing values, it imputes them with the previous value. As output, it obtains a preprocessed data frame.

[1160] Step 3:

[1161] Training a machine learning model

[1162] The server trains a random forest regression model using historical data. As input, it receives a preprocessed data frame and separates it into features and target variables. The features include air temperature, seawater temperature, wind speed, and currents, while the target variables include fish location information. As output, it obtains a trained machine learning model.

[1163] Step 4:

[1164] Real-time data collection

[1165] The server collects new data from the sensors in real time. As input, it takes the latest measurements from each sensor and adds them to a dataframe. As output, it gets a dataframe with the latest data.

[1166] Step 5:

[1167] Predicting fish behavior

[1168] The server uses the collected data in real time to predict the fish behavior. As input, it receives the latest data frame obtained in step 4 and feeds it into the trained machine learning model. As output, it obtains the predicted fish behavior result.

[1169] Step 6:

[1170] Navigation system updates

[1171] The server updates the navigation system of the autonomous fishing vessel based on the prediction results. As input, it receives the fish behavior prediction results obtained in step 5 and calculates the optimal fishing spot. As output, it obtains the updated navigation system instructions.

[1172] Step 7:

[1173] Autonomous Driving of Fishing Boats

[1174] The terminal moves the autonomous fishing vessel to the optimal fishing spot according to the updated navigation system instructions. As input, it receives the navigation system instructions obtained in step 6 and reflects them in the fishing vessel's operation system. As output, the fishing vessel automatically moves to the optimal fishing spot.

[1175] In this way, efficient fishing can be achieved through each step.

[1176] Example 2

[1177] Next, a second embodiment of the second form will be described. 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".

[1178] In conventional fishing, data collection and analysis to predict the location and behavior of fish schools was insufficient, making it difficult to increase catches. In addition, there was a problem that efficient fishing could not be carried out because predictions of fish species' behavior were inaccurate. This reduced the efficiency of fishing and often resulted in economic losses.

[1179] 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.

[1180] In this invention, the server includes a means for collecting various data (nautical charts, location information, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for transmitting the collected data to the server via a communication module, a means for storing the received data in a database, a means for analyzing the stored data, a means for predicting the behavior of fish species from the analyzed data using a generative AI model, a means for displaying the prediction results on a terminal, and a means for improving the catch in the fishing industry. This makes it possible to accurately predict the location and behavior of schools of fish and to conduct efficient fishing.

[1181] "Various data" refers to information such as nautical charts, location information, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of seafood, salinity concentration, and the rate of temperature change due to global warming.

[1182] "Means of collection" refers to the method of obtaining various data using sensors and data collection devices installed on fishing vessels.

[1183] "Communication module" refers to a communication device for transmitting collected data to a server.

[1184] "Database" refers to an information system for storing and managing received Data.

[1185] "Analysis means" refers to the methods and techniques used to process the stored data and convert it into meaningful information.

[1186] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to make predictions and classifications from data.

[1187] "Behavioral prediction" refers to predicting the movement and activity patterns of fish species based on analyzed data.

[1188] "Terminal" refers to a device for displaying prediction results.

[1189] "Measures to improve catches" refers to methods and technologies for fishing efficiently based on prediction results and increasing catches.

[1190] The present invention relates to a system for collecting and analyzing various data and predicting the behavior of fish species in order to improve catches in the fishing industry. A specific embodiment of this system will be described below.

[1191] Hardware and Software Used

[1192] Hardware: Sensors installed on fishing boats (seawater temperature sensor, salinity sensor, tide gauge, etc.), GPS, communication module

[1193] Software: Data collection software, data analysis software, generative AI models (e.g., using TensorFlow® or PyTorch®)

[1194] Data collection and transmission

[1195] The terminal uses various sensors installed on the fishing boat to collect data on seawater temperature, salinity, currents, etc. in real time. For example, the seawater temperature sensor measures the current seawater temperature, and the salinity sensor measures the salinity. The collected data is sent to a server via a communication module.

[1196] Data storage and analysis

[1197] The server saves the received data in a database. For example, the data is stored in a MySQL database. The saved data is preprocessed using a Python script. Specifically, missing values ​​of the data are complemented and normalization is performed.

[1198] Behavioral Prediction

[1199] The server uses a generative AI model to predict the behavior of fish species from the analyzed data. For example, the prediction is made using a TensorFlow (registered trademark) model. The behavior of fish species is predicted by inputting the following prompt sentence into the generative AI model.

[1200] Example prompt:

[1201] The current seawater temperature is 25 degrees, the salinity is 3.5%, the tide is 1.2 knots in the northeast direction, the air temperature is 20 degrees, the moon is a full moon, and the tide chart shows a rising tide. Under these conditions, please predict the preferred waters of the fish species and the time of day when they will be active.

[1202] Displaying the results and executing the fishery

[1203] The terminal displays the prediction results sent from the server on the fishing boat's terminal. For example, the display may show, "The preferred sea area for this fish species is 35 degrees north latitude and 140 degrees east longitude. The time period when they are active is from 2:00 pm to 4:00 pm." Based on this prediction result, the user (fisherman) moves the fishing boat to the preferred sea area for the fish species and fishes according to the time period when they are active.

[1204] In this way, by performing specific actions at each step, the system achieves efficient fishing based on predictions of fish species' behavior.

[1205] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1206] Step 1:

[1207] Data collection

[1208] The terminal uses various sensors installed on the fishing boat to collect data on seawater temperature, salinity, currents, etc. in real time. For example, the seawater temperature sensor measures the current seawater temperature, and the salinity sensor measures the salinity.

[1209] Input: Data from ocean temperature sensor, salinity sensor, and tide gauge

[1210] Output: Collected ocean temperature, salinity, and current data

[1211] Step 2:

[1212] Data transmission

[1213] The terminal transmits the collected data to a server via a communication module. For example, collected data on seawater temperature, salinity, and currents is sent as packets.

[1214] Input: Collected ocean temperature, salinity, and current data

[1215] Output: Data packet sent to the server

[1216] Step 3:

[1217] Data Storage

[1218] The server stores the received data in a database, for example a MySQL database.

[1219] Input: Data packet sent to the server

[1220] Output: Data stored in the database

[1221] Step 4:

[1222] 4. Data Analysis

[1223] The server analyzes the stored data, for example by preprocessing the data using Python scripts, such as by filling in missing values ​​and normalizing the data.

[1224] Input: Data stored in the database

[1225] Output: Preprocessed data

[1226] Step 5:

[1227] Behavioral Prediction

[1228] The server uses a generative AI model to predict the behavior of fish species from the analyzed data. For example, the prediction is made using a TensorFlow (registered trademark) model. The behavior of fish species is predicted by inputting the following prompt sentence into the generative AI model.

[1229] Input: Preprocessed data, prompt statement

[1230] Output: Fish species behavior prediction results

[1231] Example prompt:

[1232] The current seawater temperature is 25 degrees, the salinity is 3.5%, the tide is 1.2 knots in the northeast direction, the air temperature is 20 degrees, the moon is a full moon, and the tide chart shows a rising tide. Under these conditions, please predict the preferred waters of the fish species and the time of day when they will be active.

[1233] Step 6:

[1234] Results display

[1235] The terminal displays the prediction results sent from the server on the fishing boat's terminal. For example, the display might say, "The fish species' preferred sea area is 35 degrees north latitude and 140 degrees east longitude. They are most active between 2:00 and 4:00 p.m."

[1236] Input: Fish species behavior prediction results

[1237] Output: Prediction results displayed on the terminal

[1238] Step 7:

[1239] Fishing

[1240] Based on the prediction results, users (fishermen) can move their fishing boats to areas favored by fish species and fish during times when the fish species are most active.

[1241] Input: Prediction result displayed on the device

[1242] Output: Movement of fishing vessels and execution of fishing

[1243] (Application example 2)

[1244] Next, a description will be given of Application Example 2 of Form 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".

[1245] Conventional fishing systems had problems with low fishing efficiency due to insufficient data analysis and behavioral prediction to improve catches. In addition, optimization of fishing boat routes and notifications of fishing timing were done manually, which placed a heavy burden on fishermen and made it difficult to fish efficiently.

[1246] 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.

[1247] In this invention, the server includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, moon age, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, rate of temperature change due to global warming, etc.), a means for creating a behavior prediction for the target fish species, etc., a means for predicting where the target fish species are moving during a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, a means for improving the catch volume in the fishing industry, a means for optimizing the navigation route of the autonomous vehicle, a means for notifying the timing of fishing, a means for predicting behavior using a generative AI model, and a means for generating prompt sentences. This makes it possible to significantly improve the efficiency of the fishing industry.

[1248] "Various data" refers to information such as nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and the rate of temperature change due to global warming.

[1249] "Means for analysis" refers to methods and devices for analyzing various collected data and extracting meaningful information.

[1250] "Means for generating a behavioral prediction" refers to a method or device that uses the calculations and models necessary to predict the behavior of a target fish species.

[1251] "Means for displaying in real time" refers to a method or device for instantly reflecting the prediction results on a display device.

[1252] "Fishing yield enhancing measures" means any method or device used to increase the yield in a fishery.

[1253] "Means for optimizing the navigation route of an autonomous vehicle" refers to a method or device for an autonomous vehicle to select and navigate an optimal route.

[1254] "Fishing timing communication means" means a method or device that informs fishermen of the optimal time to fish.

[1255] A "generative AI model" refers to a model that uses artificial intelligence to make predictions and generate information from data.

[1256] "Means for generating prompt sentences" refers to a method or device for creating instruction sentences to be input into a generative AI model.

[1257] The system for carrying out the present invention collects and analyzes various data, predicts behavior, and optimizes the navigation route of an autonomous vehicle based on the results, and notifies the timing of fishing. A specific embodiment of this system will be described below.

[1258] System Configuration

[1259] The system consists of the following main components:

[1260] 1. Data collection module:

[1261] Various data are collected, such as nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and the rate of temperature change due to global warming.

[1262] Sensors and satellite communications are used to collect data.

[1263] 2. Data Analysis Module:

[1264] Analyze the collected data and extract meaningful information.

[1265] Analyze the data using machine learning algorithms.

[1266] 3. Behavioral Prediction Module:

[1267] Generative AI models are used to predict the behavior of target fish species.

[1268] Based on the prediction results, the results are displayed in real time on the fish finder's nautical chart and GPS.

[1269] 4. Route Optimization Module:

[1270] Based on the prediction results, the optimal route for the autonomous vehicle is calculated.

[1271] It issues instructions to the autonomous driving system to move fishing boats to the optimal sea area.

[1272] 5. Catch Timing Notification Module:

[1273] It notifies you of the times when tuna are active.

[1274] Optimize fishing timing and improve catches.

[1275] 6. Prompt generation module:

[1276] Create a prompt to input to the generative AI model.

[1277] Processing flow

[1278] The server first collects various data using a data collection module. Next, the data analysis module analyzes the collected data, and the behavior prediction module predicts the behavior of fish species using a generative AI model. The prediction results are displayed in real time, and the navigation route optimization module calculates the optimal navigation route and issues instructions to the autonomous driving system. In addition, the fishing timing notification module notifies the optimal fishing timing. The prompt generation module creates prompt sentences to input into the generative AI model.

[1279] Hardware and Software Used

[1280] Hardware: Sensors, satellite communication devices, autonomous driving systems, fish finders, GPS devices

[1281] Software: Machine learning algorithms, generative AI models, data analysis tools

[1282] Examples

[1283] For example, the following prompt sentence could be input to a generative AI model:

[1284] Predict the behavior of tuna when the sea water temperature is 25 degrees, the salinity is 35, the current is 1.5 m / s, the air temperature is 28 degrees, the moon phase is 0.5, and the tide graph is 1.2.

[1285] By inputting this prompt into the generative AI model, it is possible to predict the tuna's behavior and calculate the optimal navigation route.

[1286] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1287] Step 1:

[1288] The server uses a data collection module to collect various data, such as nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, and the rate of temperature change due to global warming, through sensors and satellite communications. The input is data from various sensors and satellite communications, and the output is the collected data set.

[1289] Step 2:

[1290] The server analyzes the collected data using a data analysis module, which uses machine learning algorithms to pre-process the data and extract meaningful information. The input is the dataset collected in step 1, and the output is the analyzed data.

[1291] Step 3:

[1292] The server inputs a prompt sentence into the generative AI model using the behavior prediction module to predict the behavior of the target fish species. Specifically, the server inputs the prompt sentence created by the prompt generation module into the generative AI model to obtain the prediction result. The input is the analyzed data and the prompt sentence, and the output is the predicted behavior result of the fish species.

[1293] Step 4:

[1294] The server displays the prediction results on the fish finder's chart and GPS in real time. Specifically, the prediction results are visualized and reflected on the display device so that the user can check them. The input is the predicted behavior of the fish species, and the output is the predicted results displayed in real time.

[1295] Step 5:

[1296] The server uses the navigation route optimization module to calculate the optimal navigation route for the autonomous vehicle. Specifically, it calculates the optimal route based on the prediction results and issues instructions to the autonomous driving system. The input is the behavior prediction results of the fish species, and the output is the optimal navigation route.

[1297] Step 6:

[1298] The server uses a fishing timing notification module to notify the user of the optimal fishing timing. Specifically, it calculates the time periods when tuna are active and notifies the user. The input is the predicted behavior of the fish species, and the output is a notification of the fishing timing.

[1299] Step 7:

[1300] The server uses a prompt generation module to create a prompt sentence to be input to the generative AI model. Specifically, the server generates a prompt sentence based on the collected data and passes it to the behavior prediction module. The input is the collected data, and the output is the prompt sentence.

[1301] In addition, 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.

[1302] "Example 1"

[1303] As one embodiment of the present invention, there is a system that combines an emotion engine. This system includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for creating a behavior prediction of target fish species, etc., a means for predicting where the target fish species are moving at a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, and a means for improving the catch volume in the fishing industry. In addition, an emotion engine that recognizes the user's emotions is combined. This emotion engine recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. It is possible to adjust the behavior prediction of the target fish species using the output of the emotion engine. Specifically, when the user is feeling stressed, the emotion engine captures that information and adjusts the behavior prediction. This makes it possible to propose a more appropriate fishing method according to the user's emotional state.

[1304] "Example 2"

[1305] As one embodiment of the present invention, there is a system that combines an emotion engine. This system includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for creating a behavior prediction of target fish species, etc., a means for predicting where the target fish species are moving at a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, and a means for improving the catch volume in the fishing industry. In addition, an emotion engine that recognizes the user's emotions is combined. This emotion engine recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. It is possible to adjust the behavior prediction of the target fish species using the output of the emotion engine. Specifically, when the user is feeling stressed, the emotion engine captures that information and adjusts the behavior prediction. This makes it possible to propose a more appropriate fishing method according to the user's emotional state.

[1306] The process flow of each embodiment will be described below.

[1307] "Example 1"

[1308] Step 1: The system collects various data (nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, rate of temperature change due to global warming, etc.).

[1309] Step 2: Analyze the collected data and create predictions for the behavior of target fish species, etc.

[1310] Step 3: Predict where the target fish species will be moving at a specific time and display it in real time on the fish finder's chart and GPS.

[1311] Step 4: Recognize the user's emotions with the emotion engine. The emotion engine recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc.

[1312] Step 5: Use the emotion engine's output to adjust the behavioral predictions of the target fish species. Specifically, when the user is stressed, the emotion engine captures that information and adjusts its behavioral predictions.

[1313] Step 6: Based on the adjusted behavioral predictions, propose optimal fishing strategies to improve catches in the fishery.

[1314] Example 1

[1315] Next, a description will be given of Example 1 of the embodiment 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".

[1316] In conventional fishing systems, data analysis and behavior prediction to improve catches were not sufficiently performed, making it difficult for fishermen to efficiently select fishing spots. In addition, there was a problem of increased stress and fatigue for fishermen because fishing methods were not proposed taking into account the user's emotional state. To solve these issues, a system that collects and analyzes various data and predicts behavior in real time is required. In addition, a function to recognize the user's emotional state and adjust behavior predictions based on that is also required.

[1317] 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.

[1318] In this invention, the server includes a means for collecting various data (such as a nautical chart, location information, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graph, catch volume, fishing location, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for transmitting the collected data to a central data processing device, a means for analyzing the data using a machine learning algorithm, a means for creating a behavior prediction for the target fish species, a means for predicting where the target fish species are moving during a specific time period and displaying the prediction in real time on the nautical chart and location information on the fish finder, a means for recognizing the user's emotions and adjusting the behavior prediction based on the emotion data, and a means for improving the catch in the fishing industry. This allows fishermen to efficiently select fishing spots and also makes it possible to suggest more appropriate fishing methods according to the user's emotional state.

[1319] "Various data" refers to information such as nautical charts, location information, air temperature, sea water temperature, wind speed, currents, lunar age, tide graphs, catch volume, fishing locations, ecology of seafood, salinity, and the rate of temperature change due to global warming.

[1320] "Means of collection" refers to the method of obtaining various data using sensors and data collection devices installed on fishing vessels.

[1321] "Central Data Processing Unit" refers to a computer system that receives, analyzes, and processes collected data.

[1322] A "machine learning algorithm" is a mathematical model that learns patterns and rules from data to make predictions and classifications.

[1323] "Means for generating behavioral predictions" refers to methods that use machine learning algorithms to predict the migration patterns and behavior of targeted fish species.

[1324] "Means of displaying in real time" refers to a method of instantly reflecting the prediction results on the nautical chart and location information on the fish finder.

[1325] "Means of recognizing emotions" refers to methods for analyzing a user's emotional state from facial expressions, tone of voice, choice of words, etc.

[1326] "Means for adjusting behavioral prediction based on emotional data" refers to a method for modifying the results of behavioral prediction by taking into account the emotional state of the user.

[1327] "Measures to improve fishing yield" refers to methods to improve fishing performance through the selection of efficient fishing sites and the proposal of appropriate fishing methods.

[1328] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1329] This invention is a system for achieving efficient fishing in the fishing industry. It collects and analyzes various data, predicts the behavior of fish species, and has the ability to adjust the prediction results taking into account the emotional state of the user.

[1330] Data collection

[1331] Fishing boats are equipped with sensors and data collection devices to collect various data such as nautical charts, location information, air temperature, seawater temperature, wind speed, tides, moon phase, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, rate of temperature change due to global warming, etc. This data is transmitted in real time to a central data processing device (server) using wireless communication technology (e.g. Wi-Fi (registered trademark), LTE).

[1332] Data analysis

[1333] The server preprocesses the received data, complementing missing values, removing outliers, normalizing data, etc. Specifically, it uses the Pandas library of Python (registered trademark). It extracts features from the preprocessed data, and uses the Scikit-learn (registered trademark) library to extract features such as fluctuation patterns of air and seawater temperature, and the direction and speed of tidal currents. Next, it trains a model to predict the behavior of fish species using a machine learning algorithm (e.g., TensorFlow (registered trademark), PyTorch (registered trademark)).

[1334] Generate behavioral predictions

[1335] The server uses the trained model to predict the behavior of target fish species, for example, where they will move at a certain time of day, and displays the prediction results in real time on the fish finder's chart and location information.

[1336] Combining emotion engines

[1337] To recognize the user's emotions, the fishing boat is equipped with cameras and microphones. The terminal uses these devices to collect emotion data from the user's facial expressions, tone of voice, choice of words, etc. The server analyzes the emotion data using OpenCV and Google Cloud Speech-to-Text (registered trademark) APIs to recognize the user's emotional state. Based on the analyzed emotion data, it adjusts behavior predictions and suggests more appropriate fishing methods according to the user's emotional state.

[1338] Examples

[1339] For example, when a fisherman goes fishing, he can input the following prompt sentence into the generative AI model to check how the system works:

[1340] "The current air temperature is 25 degrees, the sea temperature is 20 degrees, the wind speed is 5 m / s, and the tide is flowing northeast. The moon is full, and according to the tide graph, the tide is rising. The catch has been declining recently, and fishing is mainly taking place along the coast. According to the ecology data of fish and shellfish, the migration patterns of the target fish species are changing due to global warming. The user seems to be stressed. Please predict and suggest the best fishing spot under these conditions."

[1341] By inputting this prompt, the system can predict the best fishing spots in real time based on the collected data and the user's emotional state and display it on the fish finder.

[1342] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1343] Step 1:

[1344] The terminal uses sensors and data collection devices installed on the fishing boat to collect various data such as nautical charts, location information, air temperature, seawater temperature, wind speed, tides, moon phase, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, and the rate of change in air temperature due to global warming. The input is data from the various sensors, and the output is the collected data. In concrete terms, the sensors acquire data in real time and send it to the terminal.

[1345] Step 2:

[1346] The terminal transmits the collected data to the server in real time using wireless communication technology (e.g., Wi-Fi, LTE). The input is the collected data, and the output is the data transmitted to the server. In concrete terms, the terminal divides the data into packets and transmits them to the server via wireless communication.

[1347] Step 3:

[1348] The server preprocesses the received data. The input is the data sent from the terminal, and the output is the preprocessed data. Specifically, it uses the Pandas library of Python (registered trademark) to complement missing values, remove outliers, and normalize the data.

[1349] Step 4:

[1350] The server extracts features from the preprocessed data. The input is the preprocessed data, and the output is the extracted features. Specifically, the server uses the Scikit-learn (registered trademark) library to extract features such as fluctuation patterns of air and seawater temperature, and the direction and speed of tidal currents.

[1351] Step 5:

[1352] The server trains a machine learning model using the extracted features. The input is the extracted features, and the output is the trained model. Specifically, the server uses TensorFlow (registered trademark) and PyTorch (registered trademark) to build a fish species behavior prediction model.

[1353] Step 6:

[1354] The server uses the trained model to predict the behavior of the fish species that are the target of fishing. The input is the trained model and real-time data, and the output is the behavior prediction result. Specifically, the server inputs data into the model and generates a prediction result.

[1355] Step 7:

[1356] The server transmits the prediction result to the terminal. The input is the behavior prediction result, and the output is the prediction result transmitted to the terminal. In particular, the server formats the prediction result and transmits it to the terminal via wireless communication.

[1357] Step 8:

[1358] The terminal displays the prediction results in real time on the marine chart and location information on the fish finder. The input is the prediction results sent from the server, and the output is the displayed prediction results. The specific operation is to display the prediction results on the fish finder display.

[1359] Step 9:

[1360] The device collects emotion data from the user's facial expressions, tone of voice, choice of words, etc. The input is data from the camera and microphone, and the output is the collected emotion data. Specifically, the device uses the camera and microphone to capture the user's emotional state in real time.

[1361] Step 10:

[1362] The server analyzes the collected emotion data. The input is the emotion data sent from the terminal, and the output is the analyzed emotion state. Specifically, it uses OpenCV and Google Cloud Speech-to-Text (registered trademark) API to recognize the user's emotion state.

[1363] Step 11:

[1364] The server adjusts the behavior prediction based on the analyzed emotion data. The input is the analyzed emotion state and the behavior prediction result, and the output is the adjusted behavior prediction result. As a specific operation, the prediction result is modified according to the emotion state, and a more appropriate fishing method is proposed.

[1365] Step 12:

[1366] The server sends the adjusted behavior prediction result to the terminal, where the input is the adjusted behavior prediction result and the output is the adjustment result sent to the terminal. In particular, the server formats the adjustment result and sends it to the terminal through wireless communication.

[1367] Step 13:

[1368] The terminal displays the adjusted behavior prediction results on the marine chart and position information on the fish finder in real time. The input is the adjustment result sent from the server, and the output is the displayed adjustment result. The specific operation is to display the adjustment result on the fish finder display.

[1369] (Application example 1)

[1370] Next, a description will be given of Application Example 1 of Form 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".

[1371] In conventional fishing, fishermen have to spend a lot of time and effort to identify the location of fish schools, which reduces fishing efficiency. In addition, the emotional state of fishermen can affect fishing results, and the efficiency of fishing activities can further decrease due to accumulated stress and fatigue. In addition, there is a problem that it is difficult to improve the catch because the navigation of fishing boats and suggestions on fishing methods are not performed in real time.

[1372] 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.

[1373] In this invention, the server includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.), a means for creating a behavior prediction of the target fish species, etc., a means for predicting where the target fish species are moving during a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, a means for suggesting a fishing method according to the user's emotional state using an emotion engine that recognizes the user's emotions, a means for improving the navigation and fishing efficiency of the fishing boat that is installed on the autonomous fishing boat, and a means for receiving the location of the school of fish and the proposed fishing method in real time through the smart device. This enables fishermen to efficiently identify the location of the school of fish and increase the amount of catch. In addition, the proposed fishing method according to the user's emotional state can reduce the fishermen's stress and fatigue and improve the efficiency of fishing activities.

[1374] "Various data" refers to information such as nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and the rate of temperature change due to global warming.

[1375] "Means of analysis" refers to devices and algorithms used to analyze various collected data and predict the behavior of schools of fish.

[1376] "Means for creating behavioral predictions" refers to devices and algorithms that use the analyzed data to predict the behavior of targeted fish species.

[1377] "Means for displaying in real time" refers to devices or software for instantly displaying the predicted location information of schools of fish on a fish finder or GPS.

[1378] "Means to improve catches" refers to devices and algorithms that propose efficient fishing methods based on information on the location and behavioral predictions of fish schools, thereby increasing catches.

[1379] An "emotion engine" refers to a device or software that recognizes emotions from a user's facial expressions, tone of voice, choice of words, etc., and adjusts fishing methods based on that information.

[1380] An "autonomous fishing vessel" refers to a fishing vessel that is designed to navigate and conduct fishing activities automatically.

[1381] "Measures to improve navigation and fishing efficiency" refers to devices and algorithms that enable autonomous fishing vessels to navigate and fish efficiently.

[1382] "Smart devices" refers to portable information terminals such as smartphones, tablets, smart glasses, and head-mounted displays.

[1383] "Means of receiving real-time information on the location of schools of fish and suggestions on efficient fishing methods" refers to equipment or software that allows a smart device to instantly receive information on the location of schools of fish and suggestions on efficient fishing methods.

[1384] The following system configuration will be described as an embodiment of the present invention.

[1385] System Configuration

[1386] Hardware Configuration

[1387] 1. Sensors installed on fishing boats: Various sensors to collect data such as nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and rate of temperature change due to global warming.

[1388] 2. Central Data Processing Unit: A computer capable of high-speed data processing, such as a server equipped with an NVIDIA (registered trademark) GPU.

[1389] 3. Smart devices: Portable information terminals such as smartphones, tablets, smart glasses, and head-mounted displays.

[1390] Software Configuration

[1391] 1. Data collection software: Software for collecting data from various sensors and transmitting it to a central data processing device.

[1392] 2. Data analysis software: Software that analyzes collected data using machine learning algorithms such as TensorFlow (registered trademark) and PyTorch (registered trademark).

[1393] 3. Behavioral prediction software: Software that predicts the behavior of fish species being targeted for fishing based on analyzed data.

[1394] 4. Real-time display software: Software that displays the predicted locations of fish schools in real time on a fish finder or GPS.

[1395] 5. Emotion engine software: Software that recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. and adjusts fishing methods based on that information.

[1396] 6. Navigation software: Software that enables autonomous fishing vessels to navigate and fish efficiently.

[1397] 7. Application for smart devices: An application to receive real-time information on fish locations and fishing method suggestions via smart devices.

[1398] Processing flow

[1399] 1. Data collection: Various sensors installed on fishing boats collect data such as nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, moon phase, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, rate of temperature change due to global warming, etc. This data is sent to a central data processing unit through data collection software.

[1400] 2. Data Analysis: The central data processing unit analyses the collected data using data analysis software, which uses machine learning algorithms such as TensorFlow and PyTorch.

[1401] 3. Behavioral prediction: Based on the analyzed data, behavioral prediction software predicts the behavior of the targeted fish species, thereby predicting where schools of fish will be moving at a particular time.

[1402] 4. Real-time display: The prediction results are displayed on fish finders and GPS through real-time display software, which helps fishermen to efficiently select fishing spots.

[1403] 5. Emotion Recognition and Adjustment: The emotion engine software recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. and adjusts its fishing strategy based on that information. For example, if the user is stressed, the emotion engine will pick up on that information and adjust its behavior predictions.

[1404] 6. Improved navigation and fishing efficiency: Navigation software will help autonomous fishing vessels navigate and fish more efficiently, which will improve fishing efficiency.

[1405] 7. Notifications on smart devices: Through a smart device application, fishermen can receive real-time information on the location of fish schools and suggestions on how to catch them.

[1406] Examples

[1407] For example, if a fisherman is wearing smart glasses, he can input prompt sentences like the following into the generative AI model and receive real-time information about the location of fish schools and suggestions on how to catch them.

[1408] Examples of prompt statements

[1409] "The current seawater temperature is 25 degrees, the wind speed is 5 m / s, and the current is flowing northeast. Please tell me where we can expect to catch the most fish in the next hour."

[1410] By feeding this prompt into a generative AI model, the AI ​​will suggest optimal fishing locations based on the collected data.

[1411] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1412] Step 1:

[1413] Various sensors installed on fishing boats collect data such as nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, and the rate of temperature change due to global warming. This data is sent to a central data processing device through data collection software. The input is real-time data from the various sensors, and the output is the data sent to the central data processing device.

[1414] Step 2:

[1415] The central data processing unit analyzes the collected data using data analysis software. Machine learning algorithms such as TensorFlow and PyTorch are used for the analysis. The input is the data collected in step 1, and the output is the analysis result. Specific operations include data preprocessing, feature extraction, and application of machine learning models.

[1416] Step 3:

[1417] Based on the analyzed data, the behavioral prediction software predicts the behavior of the target fish species. This allows it to predict where fish schools will be moving at a specific time. The input is the analysis result from step 2, and the output is the predicted behavioral data of the fish schools. Specific operations include applying a predictive model and generating a prediction result.

[1418] Step 4:

[1419] The prediction results are displayed on the fish finder or GPS through real-time display software. This allows fishermen to efficiently select fishing locations. The input is the behavior prediction data from step 3, and the output is the display data on the fish finder or GPS. Specific operations include data visualization and real-time display.

[1420] Step 5:

[1421] The emotion engine software recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc., and adjusts its fishing methods based on that information. For example, if the user is feeling stressed, the emotion engine captures that information and adjusts its behavior predictions. The input is the user's emotion data, and the output is adjusted behavior prediction data. Specific operations include applying emotion recognition algorithms and recalibrating the prediction model.

[1422] Step 6:

[1423] The navigation software efficiently navigates the autonomous fishing vessel and performs fishing activities, thereby improving fishing efficiency. The input is adjusted behavior prediction data, and the output is navigation data for the autonomous fishing vessel. Specific operations include calculation of navigation routes and autonomous driving control.

[1424] Step 7:

[1425] Through the smart device application, fishermen can receive real-time fish location and fishing method suggestions. The input is the navigation data and coordinated behavior prediction data of the autonomous fishing boat, and the output is notification data on the smart device. Specific operations include transmitting data and generating notifications.

[1426] Example 2

[1427] Next, a second embodiment of the second form will be described. 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".

[1428] In conventional fishing systems, data analysis and behavioral prediction to improve catches were not sufficiently performed, making efficient fishing difficult. In addition, there were no proposals for fishing methods that took into account the emotional state of fishermen, which led to problems with increased stress and fatigue among fishermen. This has led to a demand for simultaneously improving the efficiency of fishing and the satisfaction of fishermen.

[1429] 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.

[1430] In this invention, the server includes a means for analyzing various data (map information, location information, weather information, ocean information, tide information, lunar age information, tide information, fishing information, fishing location information, fish ecology information, salinity information, climate change information, etc.), a means for creating a behavior prediction for the target fish to be caught, a means for predicting where the target fish will move during a specific time period and displaying this in real time on the map information and location information on the fish finder, a means for improving the catch in the fishing industry, and a means including an emotion engine that recognizes the user's emotions and adjusting the behavior prediction using the output of the emotion engine. This makes it possible to make highly accurate behavior predictions based on collected data and to suggest appropriate fishing methods according to the user's emotional state.

[1431] "Map information" is data that shows the topography and location relationships of oceans and land.

[1432] "Location information" is data that indicates the latitude and longitude of a specific point using technology such as GPS.

[1433] "Weather information" is data that indicates atmospheric conditions such as temperature, wind speed, and precipitation.

[1434] "Ocean information" refers to data that indicates ocean conditions, such as seawater temperature, salinity, and tidal currents.

[1435] "Tidal current information" is data that indicates the direction and speed of ocean water flow.

[1436] "Moon age information" is data that indicates the phases of the moon.

[1437] "Tidal information" is data that indicates the up and down movement of the sea surface.

[1438] "Catch information" is data that indicates the type and quantity of fish caught.

[1439] "Fishing location information" is data that indicates the specific location where the fishing took place.

[1440] "Fish ecological information" is data that indicates fish behavior patterns and habitats.

[1441] "Salinity concentration information" is data that indicates the percentage of salinity in seawater.

[1442] "Climate change information" is data showing long-term changes in temperature and precipitation.

[1443] An "emotion engine" is a system that recognizes emotions from a user's facial expressions, tone of voice, choice of words, etc.

[1444] A "machine learning algorithm" is a computational method for making predictions and classifications based on data.

[1445] This invention is a system for improving catches in the fishing industry, which collects and analyzes various data, predicts fish behavior, and suggests appropriate fishing methods according to the user's emotional state.

[1446] The server collects various data such as map information, location information, weather information, ocean information, tide information, lunar phase information, tide information, fishing information, fishing location information, fish ecology information, salinity information, and climate change information. These data are obtained from dedicated sensors and databases. For example, the latest seawater temperature, salinity, and tide data is obtained from the ocean database, and temperature, wind speed, lunar phase, and tide information is obtained from the weather database. In addition, real-time location information and catch volume data are collected from the GPS and fish finder installed on the fishing boat.

[1447] The server analyzes the collected data and creates predictions for the behavior of tuna and other fish. Using machine learning algorithms, it analyzes data such as seawater temperature, salinity, and currents to predict the areas that fish prefer. It also predicts the times when fish will be active based on data such as temperature, moon phase, and tide information. This allows fishing boats to fish more efficiently.

[1448] The server displays the prediction results on the map information on the fish finder and on the GPS in real time. This allows fishing boats to move to areas where fish are predicted to be present and fish more efficiently. The prediction results are converted into a data format for display on the fish finder display and sent to the GPS device.

[1449] It is combined with an emotion engine that recognizes the user's emotions. The emotion engine recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. For example, the emotion engine captures the user's facial expressions with a camera and performs image analysis. It also collects the user's tone of voice with a microphone and performs audio analysis. The server receives the output data from the emotion engine and adjusts the parameters of the behavior prediction model if the user is feeling stressed.

[1450] The server generates the optimal fishing method based on the adjusted behavior prediction results. The generated proposal is displayed on the terminal display and notified to the user. This makes it possible to propose a more appropriate fishing method according to the user's emotional state.

[1451] As a concrete example, if the seawater temperature on a certain day is 25 degrees, the salinity is 3.5%, and the tidal current is flowing northeast, the server will use this data to predict the areas where tuna prefer and move fishing boats to those areas.Also, if the air temperature is 20 degrees, the moon is a full moon, and the tidal information shows a rising tide, the server will predict the times when tuna will be active and give instructions to fish during those times.

[1452] An example of a prompt sentence is as follows:

[1453] "Predict the areas where tuna prefer to fish if the seawater temperature is 25 degrees, the salinity is 3.5%, and the current is flowing northeast. Also, if the air temperature is 20 degrees, the moon is a full moon, and the tidal information shows a rising tide, predict the time of day when tuna will be active."

[1454] In this way, the system can predict fish behavior based on collected data and improve catches. In addition, by using an emotion engine, the system can suggest more appropriate fishing methods according to the user's emotional state.

[1455] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1456] Step 1:

[1457] The server collects various data such as map information, location information, weather information, ocean information, tidal current information, lunar phase information, tide information, fishing information, fishing location information, fish ecology information, salinity concentration information, and climate change information.

[1458] Input: Various data from dedicated sensors and databases

[1459] Output: Various data collected

[1460] Specific behavior:

[1461] The server accesses an oceanographic database to obtain the latest ocean temperature, salinity, and current data.

[1462] The server retrieves temperature, wind speed, lunar age, and tide information from a weather database.

[1463] The server collects real-time location and catch data from the GPS and fish finders installed on the fishing boats.

[1464] Step 2:

[1465] The server analyzes the collected data and creates predictions of fish behavior.

[1466] Input: Various data collected

[1467] Output: Fish behavior prediction results

[1468] Specific behavior:

[1469] The server inputs the collected seawater temperature, salinity, and current data and applies it to a model to predict which marine areas fish prefer.

[1470] The server uses data on temperature, lunar phase, and tide information to run models to predict when fish will be active.

[1471] Step 3:

[1472] The server displays the prediction results in real time on the fish finder's map information and GPS.

[1473] Input: Fish behavior prediction results

[1474] Output: Display data to fishfinder and GPS devices

[1475] Specific behavior:

[1476] The server converts the prediction results into a data format for display on the fish finder display.

[1477] The server sends the prediction results to the GPS device and displays them in real time.

[1478] Step 4:

[1479] It is combined with an emotion engine that recognizes the user's emotions from facial expressions, tone of voice, choice of words, etc.

[1480] Input: User facial expressions, tone of voice, and word choice

[1481] Output: The user's emotional state.

[1482] Specific behavior:

[1483] The emotion engine captures the user's facial expressions with a camera and performs image analysis.

[1484] The emotion engine collects the user's voice tone through a microphone and performs voice analysis.

[1485] Step 5:

[1486] The server uses the output of the emotion engine to refine the behavior predictions of the fish.

[1487] Input: User's emotional state, fish behavior prediction results

[1488] Output: Adjusted fish behavior prediction results

[1489] Specific behavior:

[1490] The server receives the output data from the emotion engine and adjusts the parameters of the behavior prediction model if the user is feeling stressed.

[1491] Step 6:

[1492] The server generates the optimal fishing method based on the adjusted behavior prediction results, and the generated proposal is displayed on the terminal display and notified to the user.

[1493] Input: Adjusted fish behavior prediction results

[1494] Output: Recommendations for optimal fishing methods

[1495] Specific behavior:

[1496] The server generates an optimal fishing method based on the adjusted behavior prediction results.

[1497] The server displays the generated proposal on the display of the terminal and notifies the user.

[1498] (Application example 2)

[1499] Next, a description will be given of Application Example 2 of Form 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".

[1500] Conventional fishing systems generally catch fish based on ocean conditions and fish school behavior predictions, but there was no system that took the user's emotional state into account. As a result, it was not possible to suggest the optimal fishing method depending on whether the user was stressed or relaxed, which could lead to reduced fishing efficiency. In addition, these systems were rarely applied to autonomous vehicles, and the automation and efficiency of fishing had not progressed sufficiently.

[1501] 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.

[1502] In this invention, the server includes a means for analyzing various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, rate of temperature change due to global warming, etc.), a means for creating a behavior prediction for target fish species, etc., a means for predicting where the target fish species are moving during a specific time period and displaying the prediction in real time on the nautical chart and GPS on the fish finder, a means for improving the catch volume in fishing, a means for recognizing the user's emotional state, a means for adjusting the behavior prediction based on the user's emotional state, and a means for being installed in the autonomous vehicle. This makes it possible to propose an optimal fishing method according to the user's emotional state and improve fishing efficiency.

[1503] "Various data" refers to information such as nautical charts, GPS, air temperature, sea water temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity concentration, and the rate of temperature change due to global warming.

[1504] "Means of analysis" refers to methods and equipment for analyzing various types of data and understanding fish behavior and oceanographic conditions.

[1505] "Means for generating behavioral predictions" refers to methods or devices for predicting the behavior of target fish species based on collected data.

[1506] "Means for displaying in real time" refers to a method or device for instantly displaying predicted fish school location information on a marine chart or GPS on a fish finder.

[1507] "Means for improving catches" refers to methods and devices for fishing efficiently and increasing catches based on predicted fish school location information.

[1508] "Means for recognizing a user's emotional state" refers to a method or device for identifying emotions from a user's facial expressions, tone of voice, choice of words, etc.

[1509] "Means for adjusting behavior prediction" refers to a method or device for modifying the behavior prediction of the school of fish based on the emotional state of the user.

[1510] "Means installed in an autonomous vehicle" refers to a method or apparatus for mounting and operating each of the means described above on an autonomous vehicle.

[1511] A system for implementing this invention is configured as follows: First, the server collects various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, age of the moon, tide graphs, catch volume, fishing locations, ecology of fish and shellfish, salinity, rate of change in air temperature due to global warming, etc.) and analyzes this data. Software such as Python (registered trademark), Pandas, and Scikit-learn (registered trademark) are used for the analysis.

[1512] The server then uses machine learning algorithms to generate predictions of the behavior of the target fish species, based on ecological knowledge of the target species, and displays the predicted fish locations in real time on the chart and GPS on the fish finder.

[1513] In addition, the server uses emotion recognition software such as EmotionEngine® to recognize the user's emotional state. It identifies emotions from the user's facial expressions, tone of voice, choice of words, etc., and adjusts behavior predictions based on the user's emotional state. For example, if the user is stressed, it predicts the location of schools of fish by emphasizing the influence of tides. Conversely, if the user is relaxed, it predicts the location of schools of fish by reducing the influence of tides.

[1514] This system will be installed in autonomous vehicles, which will be able to move automatically based on the predicted location information of fish schools and fish more efficiently, thereby improving catches.

[1515] As a concrete example, the operation of the system can be confirmed by inputting the following prompt sentence into the generative AI model.

[1516] Example prompt:

[1517] Create a Python program that predicts the location of schools of fish based on oceanographic condition data and fish behavior data. Add a function to adjust the parameters of the prediction model according to the user's emotional state. There are two types of emotional state: "stressed" and "relaxed." Adjust the influence of the tides according to each state.

[1518] In this way, the server, terminals, and users can work together to operate the system, making it possible to streamline and automate fishing.

[1519] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1520] Step 1:

[1521] The server collects various data (nautical charts, GPS, air temperature, seawater temperature, wind speed, tides, lunar age, tide graphs, catch volume, fishing locations, fish and shellfish ecology, salinity, rate of temperature change due to global warming, etc.). This data is obtained from sensors and external databases. The input is data from various sensors and databases, and the output is a set of collected data.

[1522] Step 2:

[1523] The server analyzes the collected data. Specifically, it preprocesses the data using Python (registered trademark) and Pandas, and performs missing value completion and outlier removal. The input is the collected data set, and the output is the preprocessed data.

[1524] Step 3:

[1525] The server uses machine learning algorithms (e.g., Scikit-learn® random forest regression models) to generate behavioral predictions for the fish species being fished. The input is the pre-processed data, and the output is the predicted location of the fish schools.

[1526] Step 4:

[1527] The server displays the predicted fish school location information on the fish finder's nautical chart or GPS in real time. The input is the fish school location prediction, and the output is the displayed location information. The specific operation is to plot the location information on the fish finder's display.

[1528] Step 5:

[1529] The server uses the EmotionEngine to recognize the user's emotional state. The input is data such as the user's facial expression, tone of voice, and choice of words, and the output is the user's emotional state (e.g., stressed, relaxed).

[1530] Step 6:

[1531] The server adjusts the action prediction based on the user's emotional state. For example, if the user is stressed, it re-predicts the fish school's location by emphasizing the influence of tides. The input is the user's emotional state and the fish school's location prediction, and the output is the adjusted fish school location prediction.

[1532] Step 7:

[1533] The autonomous vehicle moves automatically based on the adjusted fish school position information. The input is the adjusted fish school position prediction, and the output is the autonomous vehicle's movement path. Specifically, the vehicle's navigation system calculates a new path and moves the vehicle according to the new path.

[1534] Step 8:

[1535] The user fishes based on the information provided by the system. The input is the location information and fishing method suggestions from the system, and the output is the actual fishing results. In concrete terms, the user fishes at the specified location and checks the amount of catch.

[1536] 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 voice indicating a user input for 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.

[1537] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[1538] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1539] 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.

[1540] [Fourth embodiment]

[1541] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1542] .

[1543] 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.

[1544] 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 wide area network (WAN) and / or a local area network (LAN).

[1545] 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. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1546] 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 the voice according to instructions from the processor 46.

[1547] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1548] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1549] The control target 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, legs, etc. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, legs, etc. 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.

[1550] Fig. 8 shows an example of 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.

[1551] 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.

[1552] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and ...

Claims

1. A means for analyzing various data including data related to ocean, sea, and / or fish; A means for acquiring a behavior prediction result of a fish species to be fished using a prompt sentence for instructing generation of a behavior prediction of the fish species to be fished and a generation AI model; a means for displaying the acquired fish species behavior prediction results on at least one of a nautical chart and position information on a fish finder in real time; A means for optimizing a navigation route of an autonomous vehicle based on the acquired fish species behavior prediction result; A means for acquiring and notifying a timing of fishing based on the acquired behavior prediction result of the fish species; A system including:

2. 2. The system according to claim 1, wherein the analysis of the various data is performed using a machine learning algorithm.

3. 2. The system according to claim 1, wherein the behavior prediction is based on ecological knowledge of the fish species being targeted for fishing.

Images