An over-the-ocean fishery safety fishing method and system based on the Internet of Things and a medium

Abstract

The application discloses a kind of over-ocean fishery safety fishing method, system and medium based on Internet of Things.The present application obtains seabed image data and sonar collection data, analyzes the fish school information such as fish school species, quantity, activity track in seabed, according to fish school information, combined with environmental factors such as weather, can accurately predict the appropriate fishing depth layer and fishing path, according to fishing depth layer and fishing path, sea area fishing can effectively improve fishing yield, realize the purpose of increasing marine production economic benefits.In addition, the present application can reduce the abnormal situation encountered by fishing net in seabed by analyzing the seabed topographic complexity in fishing path, reasonably excluding dangerous fishing path, improve the safety factor of fishing boat operation.

Description

Technical Field

[0001] This invention relates to the field of marine fishing, and more specifically, to a method, system, and medium for safe transoceanic fishing based on the Internet of Things. Background Technology

[0002] Distant-water fishing, which involves fishing within another country's 200-nautical-mile exclusive economic zone, is characterized by high investment and high risk, and has a profound impact on international fisheries cooperation and diplomatic strategy. However, instability in fishing operations and economic losses suffered by enterprises occur frequently. These issues are caused by factors such as low catch yields, safety problems affecting fishing progress, and external factors like severe weather often impacting catches. Therefore, there is an urgent need for a method to increase catch yields. Summary of the Invention

[0003] To address at least one of the aforementioned technical problems, this invention proposes a method for safe fishing in transoceanic fisheries based on the Internet of Things.

[0004] The first aspect of this invention provides a method for safe fishing in transoceanic fisheries based on the Internet of Things, comprising:

[0005] Obtain information on fish species, fish numbers, and fish activity at different depths in the ocean;

[0006] Fish monitoring data is obtained by organizing information on fish species, fish numbers, and fish activity.

[0007] Obtain historical marine weather data and derive marine weather forecast data based on the historical marine weather data;

[0008] Fish school monitoring data and marine weather forecast data are imported into the fish school prediction model for analysis to obtain fish school prediction data and fishing prediction data.

[0009] Fish swarm prediction data and fishing prediction data are sent to preset terminal devices for display.

[0010] In this solution, obtaining information on fish species, fish numbers, and fish activity at different depths in the ocean specifically includes:

[0011] Within the monitored sea area, the seabed is divided into layers based on the maximum fishing depth, and seabed image data and sonar data are acquired at different depths.

[0012] Image feature extraction is performed on the seabed image data to obtain image feature value data;

[0013] By comparing and statistically analyzing the features of the image feature values ​​with those of the fish images, and combining this with sonar data, information on the species and number of fish in the school can be obtained.

[0014] In this solution, obtaining information on fish species, fish numbers, and fish activity at different depths in the ocean also includes:

[0015] Construct a three-dimensional seabed map model for a specific sea area;

[0016] Collect sonar feedback data of schools of fish on the seabed, and perform data fusion analysis based on the feedback data and the three-dimensional seabed map model to obtain the movement location information of the schools of fish;

[0017] Based on the location information of the fish school, the movement trajectory of the fish school is analyzed and the fish school movement trajectory information is obtained. The fish school movement location information and fish school movement trajectory information are merged and sorted to obtain the fish school activity information.

[0018] In this solution, the acquisition of historical marine weather data and the generation of marine weather forecast data based on that data specifically involve:

[0019] Obtain three-dimensional regional information of the fishing area, and divide the area into N initial marine sub-regions based on the three-dimensional regional information of the fishing area;

[0020] Acquire historical marine weather data for each marine sub-region and analyze the similarity of historical marine weather data in adjacent sub-regions;

[0021] If the similarity of historical marine weather data in adjacent sub-regions is higher than the preset weather similarity, then the sub-regions are merged to obtain M merged marine sub-regions;

[0022] Historical marine weather data from merged marine sub-regions are acquired and analyzed to obtain marine weather forecast data.

[0023] In this scheme, the process of importing fish school monitoring data and marine weather forecast data into a fish school prediction model for analysis to obtain fish school prediction data and fishing prediction data specifically involves:

[0024] Fish monitoring data is imported into a fish prediction model to predict and analyze the trajectory and number of fish, resulting in predicted fish movement trajectory data and fish number distribution data.

[0025] Fish movement trajectory prediction data and fish population distribution data are processed to obtain fish population prediction data.

[0026] This plan also includes:

[0027] The marine weather forecast data corresponding to the merged marine sub-regions are analyzed for weather anomalies to obtain weather anomaly values.

[0028] Multiple ocean sub-regions with weather anomalies lower than preset anomaly values ​​are selected, and the average weather anomaly value of multiple ocean sub-regions is calculated.

[0029] The multiple marine sub-regions are merged to obtain the first fishing area;

[0030] Fish swarm prediction data, the first fishing area, and average weather anomalies are imported into the fish swarm prediction model to perform fishing path prediction analysis, and fishing path prediction data are obtained.

[0031] This plan also includes:

[0032] Obtain fish movement trajectory prediction data and fish population distribution data from the fish school prediction data;

[0033] Based on the predicted data of fish movement trajectories and the data on fish population distribution, the data of the first fishing depth layer was analyzed.

[0034] The average weather anomaly value is imported into the fish school prediction model, and the fish school depth correction coefficient is calculated and analyzed.

[0035] Based on the fish school depth correction coefficient, the first fishing depth layer data is corrected to obtain the fishing prediction depth layer data.

[0036] The fishing prediction depth layer data and the fishing prediction path data are merged to obtain the fishing prediction data.

[0037] A second aspect of the present invention also provides an Internet of Things (IoT)-based safe fishing system for transoceanic fisheries. The system includes a memory and a processor. The memory includes an IoT-based safe fishing method program for transoceanic fisheries. When executed by the processor, the IoT-based safe fishing method program for transoceanic fisheries performs the following steps:

[0038] Obtain information on fish species, fish numbers, and fish activity at different depths in the ocean;

[0039] Fish monitoring data is obtained by organizing information on fish species, fish numbers, and fish activity.

[0040] Obtain historical marine weather data and derive marine weather forecast data based on the historical marine weather data;

[0041] Fish school monitoring data and marine weather forecast data are imported into the fish school prediction model for analysis to obtain fish school prediction data and fishing prediction data.

[0042] Fish swarm prediction data and fishing prediction data are sent to preset terminal devices for display.

[0043] A third aspect of the present invention also provides a computer-readable storage medium comprising an Internet of Things (IoT)-based method program for safe fishing in transoceanic fisheries, wherein when the IoT-based method program is executed by a processor, it implements the steps of the IoT-based method for safe fishing in transoceanic fisheries as described in any of the preceding claims.

[0044] This invention discloses a method, system, and medium for safe transoceanic fishing based on the Internet of Things (IoT). By acquiring seabed image data and sonar data, this invention analyzes information about fish schools, including their species, quantity, and activity patterns. Based on this information, combined with environmental factors such as weather, it can accurately predict suitable fishing depths and routes. Fishing according to these depths and routes can effectively increase catch yields and improve the economic benefits of marine production. Furthermore, by analyzing the complexity of the seabed topography along the fishing route, this invention can rationally eliminate dangerous fishing paths, reducing the number of abnormal situations encountered by fishing nets on the seabed and improving the safety of fishing operations. Attached Figure Description

[0045] Figure 1 A flowchart of a method for safe fishing in transoceanic fisheries based on the Internet of Things (IoT) of the present invention is shown.

[0046] Figure 2 This invention illustrates a flowchart of the process for obtaining fish activity information.

[0047] Figure 3 This invention illustrates a flowchart of the process for acquiring marine weather forecast data.

[0048] Figure 4 A block diagram of an Internet of Things-based safe fishing system for transoceanic fisheries is shown. Detailed Implementation

[0049] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0050] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0051] Figure 1A flowchart of a method for safe fishing in transoceanic fisheries based on the Internet of Things (IoT) of the present invention is shown.

[0052] like Figure 1 As shown, the first aspect of the present invention provides a method for safe fishing in transoceanic fisheries based on the Internet of Things, comprising:

[0053] S102, Obtain information on fish species, fish numbers, and fish activity at different depths in the ocean;

[0054] S104, Fish school monitoring data is obtained by organizing information on fish species, fish quantity, and fish activity.

[0055] S106, Obtain historical marine weather data and obtain marine weather forecast data based on historical marine weather data;

[0056] S108, Fish school monitoring data and marine weather forecast data are imported into the fish school prediction model for analysis to obtain fish school prediction data and fishing prediction data;

[0057] S110 sends fish school prediction data and fishing prediction data to a preset terminal device for display.

[0058] It should be noted that the preset terminal devices include mobile terminal devices and computer terminal devices.

[0059] According to an embodiment of the present invention, obtaining information on fish species, fish numbers, and fish activity at different depths in the ocean specifically includes:

[0060] Within the monitored sea area, the seabed is divided into layers based on the maximum fishing depth, and seabed image data and sonar data are acquired at different depths.

[0061] Image feature extraction is performed on the seabed image data to obtain image feature value data;

[0062] By comparing and statistically analyzing the features of the image feature values ​​with those of the fish images, and combining this with sonar data, information on the species and number of fish in the school can be obtained.

[0063] It should be noted that the layering based on the maximum seabed fishing depth generally involves three layers: the first layer, the second layer, and the third layer. The information on fish species and numbers varies significantly between these layers. The sonar data is collected using a sonar data acquisition device, while the seabed image data is collected using a seabed optical acquisition device. The sonar data acquisition device and the seabed optical acquisition device can communicate and transmit data via an Internet of Things (IoT) connection.

[0064] Figure 2 The flowchart illustrating the present invention for obtaining information on fish activity is shown.

[0065] According to an embodiment of the present invention, the step of obtaining information on fish species, fish numbers, and fish activity at different depths in the ocean further includes:

[0066] S202, Construct a three-dimensional seabed map model within a specific sea area;

[0067] S204: Collect sonar feedback data of schools of fish on the seabed, and perform data fusion analysis based on the feedback data and the three-dimensional seabed map model to obtain the movement location information of the schools of fish.

[0068] S206. Based on the location information of the fish school, analyze the movement trajectory of the fish school and obtain the movement trajectory information of the fish school. Merge and organize the movement location information and movement trajectory information of the fish school to obtain the activity information of the fish school.

[0069] It should be noted that the collected seabed sonar feedback data is acquired using a sonar data acquisition device. The fish movement location information and fish movement trajectory information are data information based on a three-dimensional seabed map model.

[0070] Figure 3 The flowchart illustrating the process of acquiring marine weather forecast data according to the present invention is shown.

[0071] According to an embodiment of the present invention, the step of acquiring historical marine weather data and obtaining marine weather forecast data based on the historical marine weather data specifically includes:

[0072] S302, Obtain three-dimensional regional information of the fishing area, divide the area according to the three-dimensional regional information of the fishing area, and obtain N initial marine sub-regions;

[0073] S304, acquire historical marine weather data in each marine sub-region and analyze the similarity of historical marine weather data in adjacent sub-regions;

[0074] S306, If the similarity of historical marine weather data in adjacent sub-regions is higher than the preset weather similarity, then the sub-regions are merged to obtain M merged marine sub-regions;

[0075] S308: Acquire and analyze historical marine weather data from merged marine sub-regions to obtain marine weather forecast data.

[0076] It should be noted that the three-dimensional regional information of the fishing area is based on a three-dimensional seabed map model. The historical marine weather data is the weather data for the most recent 30 days, and the marine weather forecast data is the forecast data for the next 20 days. The merged marine sub-region is at least one region. Furthermore, if the similarity of the historical marine weather data in adjacent sub-regions is higher than a preset weather similarity, it indicates that the historical marine weather data in the adjacent sub-regions are consistent. The value of N is determined based on the three-dimensional regional information of the fishing area; the larger the area corresponding to the three-dimensional region of the fishing area, the larger N is. Additionally, M is less than or equal to N.

[0077] According to an embodiment of the present invention, the step of importing fish school monitoring data and marine weather forecast data into a fish school prediction model for analysis to obtain fish school prediction data and fishing prediction data specifically includes:

[0078] Fish monitoring data is imported into a fish prediction model to predict and analyze the trajectory and number of fish, resulting in predicted fish movement trajectory data and fish number distribution data.

[0079] Fish movement trajectory prediction data and fish population distribution data are processed to obtain fish population prediction data.

[0080] According to an embodiment of the present invention, the fishing prediction data further includes:

[0081] The marine weather forecast data corresponding to the merged marine sub-regions are analyzed for weather anomalies to obtain weather anomaly values.

[0082] Multiple ocean sub-regions with weather anomalies lower than preset anomaly values ​​are selected, and the average weather anomaly value of multiple ocean sub-regions is calculated.

[0083] The multiple marine sub-regions are merged to obtain the first fishing area;

[0084] Fish swarm prediction data, the first fishing area, and average weather anomalies are imported into the fish swarm prediction model to perform fishing path prediction analysis, and fishing path prediction data are obtained.

[0085] It should be noted that the weather anomaly value is a specific numerical parameter reflecting abnormal weather conditions. When the weather forecast data indicates severe weather such as heavy rain, blizzards, or typhoons, the larger the weather anomaly value, the better. When the weather anomaly value is less than a preset anomaly value, it indicates that the corresponding marine sub-region is suitable for fishing. The average weather anomaly value is the weather anomaly value corresponding to the entire region represented by the first fishing area. The fishing prediction depth layer data specifically refers to the number of seabed depths suitable for fishing. Furthermore, the fishing seabed area is generally divided into three layers: the first layer, the second layer, and the third layer; the number of seabed depths refers to the specific layer number.

[0086] According to an embodiment of the present invention, the fishing prediction data further includes:

[0087] Obtain fish movement trajectory prediction data and fish population distribution data from the fish school prediction data;

[0088] Based on the predicted data of fish movement trajectories and the data on fish population distribution, the data of the first fishing depth layer was analyzed.

[0089] The average weather anomaly value is imported into the fish school prediction model, and the fish school depth correction coefficient is calculated and analyzed.

[0090] Based on the fish school depth correction coefficient, the first fishing depth layer data is corrected to obtain the fishing prediction depth layer data.

[0091] The fishing prediction depth layer data and the fishing prediction path data are merged to obtain the fishing prediction data.

[0092] It should be noted that the fish school depth correction coefficient is generally negative, and the larger the average weather anomaly value, the larger the absolute value of the fish school depth correction coefficient. Furthermore, by analyzing the average weather anomaly value, the depth layer at which fish schools move can be predicted. When encountering severe weather, fish schools generally swim to the lower seabed layers. The fish school depth correction coefficient can be used to correct the predicted fishing depth layer data, resulting in a more reasonable fishing depth layer. Fishing operations based on the fishing prediction data can effectively increase marine catch yields, thereby increasing the economic benefits of fisheries production.

[0093] According to an embodiment of the present invention, obtaining the fishing prediction data further includes:

[0094] The fishing prediction path data is split into multiple prediction sub-path data segments;

[0095] Obtain path region data corresponding to multiple predicted sub-path data segments;

[0096] Based on the path area data, obtain the seabed topography sonar data collected in the path area;

[0097] Based on the seabed topography sonar data, seabed topography analysis is performed to obtain the topography complexity corresponding to each predicted sub-path data.

[0098] Obtain predicted sub-path data with terrain complexity less than a preset terrain complexity, and fuse the predicted sub-path data to obtain new fishing predicted path data.

[0099] It should be noted that the path area data is regional data based on a three-dimensional seabed map model, and the seabed topographic sonar data is acquired through a sonar data acquisition device. In the process of acquiring predicted sub-path data with terrain complexity less than a preset terrain complexity, and fusing this predicted sub-path data to obtain new fishing predicted path data, by analyzing the complexity of the seabed terrain corresponding to the predicted path, paths with complex terrain can be reasonably excluded, reducing abnormal situations encountered by fishing nets on the seabed and improving the safety factor of fishing vessel operations.

[0100] Figure 4 A block diagram of an Internet of Things-based safe fishing system for transoceanic fisheries is shown.

[0101] S102, Obtain information on fish species, fish numbers, and fish activity at different depths in the ocean;

[0102] S104, Fish school monitoring data is obtained by organizing information on fish species, fish quantity, and fish activity.

[0103] S106, Obtain historical marine weather data and obtain marine weather forecast data based on historical marine weather data;

[0104] S108, Fish school monitoring data and marine weather forecast data are imported into the fish school prediction model for analysis to obtain fish school prediction data and fishing prediction data;

[0105] S110 sends fish school prediction data and fishing prediction data to a preset terminal device for display.

[0106] It should be noted that the preset terminal devices include mobile terminal devices and computer terminal devices.

[0107] According to an embodiment of the present invention, obtaining information on fish species, fish numbers, and fish activity at different depths in the ocean specifically includes:

[0108] Within the monitored sea area, the seabed is divided into layers based on the maximum fishing depth, and seabed image data and sonar data are acquired at different depths.

[0109] Image feature extraction is performed on the seabed image data to obtain image feature value data;

[0110] By comparing and statistically analyzing the features of the image feature values ​​with those of the fish images, and combining this with sonar data, information on the species and number of fish in the school can be obtained.

[0111] It should be noted that the layering based on the maximum seabed fishing depth generally involves three layers: the first layer, the second layer, and the third layer. The information on fish species and numbers varies significantly between these layers. The sonar data is collected using a sonar data acquisition device, while the seabed image data is collected using a seabed optical acquisition device. The sonar data acquisition device and the seabed optical acquisition device can communicate and transmit data via an Internet of Things (IoT) connection.

[0112] Figure 2 The flowchart illustrating the present invention for obtaining information on fish activity is shown.

[0113] According to an embodiment of the present invention, the step of obtaining information on fish species, fish numbers, and fish activity at different depths in the ocean further includes:

[0114] S202, Construct a three-dimensional seabed map model within a specific sea area;

[0115] S204: Collect sonar feedback data of schools of fish on the seabed, and perform data fusion analysis based on the feedback data and the three-dimensional seabed map model to obtain the movement location information of the schools of fish.

[0116] S206. Based on the location information of the fish school, analyze the movement trajectory of the fish school and obtain the movement trajectory information of the fish school. Merge and organize the movement location information and movement trajectory information of the fish school to obtain the activity information of the fish school.

[0117] It should be noted that the collected seabed sonar feedback data is acquired using a sonar data acquisition device. The fish movement location information and fish movement trajectory information are data information based on a three-dimensional seabed map model.

[0118] Figure 3 The flowchart illustrating the process of acquiring marine weather forecast data according to the present invention is shown.

[0119] According to an embodiment of the present invention, the step of acquiring historical marine weather data and obtaining marine weather forecast data based on the historical marine weather data specifically includes:

[0120] S302, Obtain three-dimensional regional information of the fishing area, divide the area according to the three-dimensional regional information of the fishing area, and obtain N initial marine sub-regions;

[0121] S304, acquire historical marine weather data in each marine sub-region and analyze the similarity of historical marine weather data in adjacent sub-regions;

[0122] S306, If the similarity of historical marine weather data in adjacent sub-regions is higher than the preset weather similarity, then the sub-regions are merged to obtain M merged marine sub-regions;

[0123] S308: Acquire and analyze historical marine weather data from merged marine sub-regions to obtain marine weather forecast data.

[0124] It should be noted that the three-dimensional regional information of the fishing area is based on a three-dimensional seabed map model. The historical marine weather data is the weather data for the most recent 30 days, and the marine weather forecast data is the forecast data for the next 20 days. The merged marine sub-region is at least one region. Furthermore, if the similarity of the historical marine weather data in adjacent sub-regions is higher than a preset weather similarity, it indicates that the historical marine weather data in the adjacent sub-regions are consistent. The value of N is determined based on the three-dimensional regional information of the fishing area; the larger the area corresponding to the three-dimensional region of the fishing area, the larger N is. Additionally, M is less than or equal to N.

[0125] According to an embodiment of the present invention, the step of importing fish school monitoring data and marine weather forecast data into a fish school prediction model for analysis to obtain fish school prediction data and fishing prediction data specifically includes:

[0126] Fish monitoring data is imported into a fish prediction model to predict and analyze the trajectory and number of fish, resulting in predicted fish movement trajectories and fish number distribution data.

[0127] Fish movement trajectory prediction data and fish population distribution data are processed to obtain fish population prediction data.

[0128] According to an embodiment of the present invention, the fishing prediction data further includes:

[0129] The marine weather forecast data corresponding to the merged marine sub-regions are analyzed for weather anomalies to obtain weather anomaly values.

[0130] Multiple ocean sub-regions with weather anomalies lower than preset anomaly values ​​are selected, and the average weather anomaly value of multiple ocean sub-regions is calculated.

[0131] The multiple marine sub-regions are merged to obtain the first fishing area;

[0132] Fish swarm prediction data, the first fishing area, and average weather anomalies are imported into the fish swarm prediction model to perform fishing path prediction analysis, and fishing path prediction data are obtained.

[0133] It should be noted that the weather anomaly value is a specific numerical parameter reflecting abnormal weather conditions. When the weather forecast data indicates severe weather such as heavy rain, blizzards, or typhoons, the larger the weather anomaly value, the better. When the weather anomaly value is less than a preset anomaly value, it indicates that the corresponding marine sub-region is suitable for fishing. The average weather anomaly value is the weather anomaly value corresponding to the entire region represented by the first fishing area. The fishing prediction depth layer data specifically refers to the number of seabed depths suitable for fishing. Furthermore, the fishing seabed area is generally divided into three layers: the first layer, the second layer, and the third layer; the number of seabed depths refers to the specific layer number.

[0134] According to an embodiment of the present invention, the fishing prediction data further includes:

[0135] Obtain fish movement trajectory prediction data and fish population distribution data from the fish school prediction data;

[0136] Based on the predicted data of fish movement trajectories and the data on fish population distribution, the data of the first fishing depth layer was analyzed.

[0137] The average weather anomaly value is imported into the fish school prediction model, and the fish school depth correction coefficient is calculated and analyzed.

[0138] Based on the fish school depth correction coefficient, the first fishing depth layer data is corrected to obtain the fishing prediction depth layer data.

[0139] The fishing prediction depth layer data and the fishing prediction path data are merged to obtain the fishing prediction data.

[0140] It should be noted that the fish school depth correction coefficient is generally negative, and the larger the average weather anomaly value, the larger the absolute value of the fish school depth correction coefficient. Furthermore, by analyzing the average weather anomaly value, the depth layer at which fish schools move can be predicted. When encountering severe weather, fish schools generally swim to the lower seabed layers. The fish school depth correction coefficient can be used to correct the predicted fishing depth layer data, resulting in a more reasonable fishing depth layer. Fishing operations based on the fishing prediction data can effectively increase marine catch yields, thereby increasing the economic benefits of fisheries production.

[0141] According to an embodiment of the present invention, obtaining the fishing prediction data further includes:

[0142] The fishing prediction path data is split into multiple prediction sub-path data segments;

[0143] Obtain path region data corresponding to multiple predicted sub-path data segments;

[0144] Based on the path area data, obtain the seabed topography sonar data collected in the path area;

[0145] Based on the seabed topography sonar data, seabed topography analysis is performed to obtain the topography complexity corresponding to each predicted sub-path data.

[0146] Obtain predicted sub-path data with terrain complexity less than a preset terrain complexity, and fuse the predicted sub-path data to obtain new fishing predicted path data.

[0147] It should be noted that the path area data is regional data based on a three-dimensional seabed map model, and the seabed topographic sonar data is acquired through a sonar data acquisition device. In the process of acquiring predicted sub-path data with terrain complexity less than a preset terrain complexity, and fusing this predicted sub-path data to obtain new fishing predicted path data, by analyzing the complexity of the seabed terrain corresponding to the predicted path, paths with complex terrain can be reasonably excluded, reducing abnormal situations encountered by fishing nets on the seabed and improving the safety factor of fishing vessel operations.

[0148] A second aspect of the present invention also provides an Internet of Things (IoT)-based safe fishing system 4 for transoceanic fisheries. The system includes a memory 41 and a processor 42. The memory includes an IoT-based safe fishing method program for transoceanic fisheries. When executed by the processor, the IoT-based safe fishing method program for transoceanic fisheries performs the following steps:

[0149] Obtain information on fish species, fish numbers, and fish activity at different depths in the ocean;

[0150] Fish monitoring data is obtained by organizing information on fish species, fish numbers, and fish activity.

[0151] Obtain historical marine weather data and derive marine weather forecast data based on the historical marine weather data;

[0152] Fish school monitoring data and marine weather forecast data are imported into the fish school prediction model for analysis to obtain fish school prediction data and fishing prediction data.

[0153] Fish swarm prediction data and fishing prediction data are sent to preset terminal devices for display.

[0154] A third aspect of the present invention also provides a computer-readable storage medium comprising an Internet of Things (IoT)-based method program for safe fishing in transoceanic fisheries, wherein when the IoT-based method program is executed by a processor, it implements the steps of the IoT-based method for safe fishing in transoceanic fisheries as described in any of the preceding claims.

[0155] This invention discloses a method, system, and medium for safe transoceanic fishing based on the Internet of Things (IoT). By acquiring seabed image data and sonar data, this invention analyzes information about fish schools, including their species, quantity, and activity patterns. Based on this information, combined with environmental factors such as weather, it can accurately predict suitable fishing depths and routes. Fishing according to these depths and routes can effectively increase catch yields and improve the economic benefits of marine production. Furthermore, by analyzing the complexity of the seabed topography along the fishing route, this invention can rationally eliminate dangerous fishing paths, reducing the number of abnormal situations encountered by fishing nets on the seabed and improving the safety of fishing operations.

[0156] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0157] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0158] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0159] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0160] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0161] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for safe fishing in transoceanic fisheries based on the Internet of Things, characterized in that, include: Obtain information on fish species, fish numbers, and fish activity at different depths in the ocean; Fish monitoring data is obtained by organizing information on fish species, fish numbers, and fish activity. Obtain historical marine weather data and derive marine weather forecast data based on the historical marine weather data; Fish school monitoring data and marine weather forecast data are imported into the fish school prediction model for analysis to obtain fish school prediction data and fishing prediction data. The fish school prediction data and the fishing prediction data are sent to the preset terminal device for display. Specifically, the acquisition of historical marine weather data and the generation of marine weather forecast data based on that data include: Obtain three-dimensional regional information of the fishing area, and divide the area into N initial marine sub-regions based on the three-dimensional regional information of the fishing area; Acquire historical marine weather data for each marine sub-region and analyze the similarity of historical marine weather data in adjacent sub-regions; If the similarity of historical marine weather data in adjacent sub-regions is higher than the preset weather similarity, then the sub-regions are merged to obtain M merged marine sub-regions; Historical marine weather data from merged marine sub-regions are acquired and analyzed to obtain marine weather forecast data. Specifically, the process of importing fish school monitoring data and marine weather forecast data into a fish school prediction model for analysis to obtain fish school prediction data and fishing prediction data involves: Fish monitoring data is imported into a fish prediction model to predict and analyze the trajectory and number of fish, resulting in predicted fish movement trajectory data and fish number distribution data. Fish movement trajectory prediction data and fish population distribution data are processed to obtain fish population prediction data; The marine weather forecast data corresponding to the merged marine sub-regions are analyzed for weather anomalies to obtain weather anomaly values. Multiple ocean sub-regions with weather anomalies lower than preset anomaly values ​​are selected, and the average weather anomaly value of multiple ocean sub-regions is calculated. The multiple marine sub-regions are merged to obtain the first fishing area; Fish school prediction data, first fishing area, and average weather anomaly values ​​are imported into the fish school prediction model to conduct fishing path prediction analysis and obtain fishing path prediction data. Obtain fish movement trajectory prediction data and fish population distribution data from the fish school prediction data; Based on the predicted data of fish movement trajectories and the data on fish population distribution, the data of the first fishing depth layer was analyzed. The average weather anomaly value is imported into the fish school prediction model, and the fish school depth correction coefficient is calculated and analyzed. Based on the fish school depth correction coefficient, the first fishing depth layer data is corrected to obtain the fishing prediction depth layer data. The fishing prediction depth layer data and the fishing prediction path data are merged to obtain the fishing prediction data. The fishing prediction data also includes: Obtain fish movement trajectory prediction data and fish population distribution data from the fish school prediction data; Based on the predicted fish movement trajectory data and fish population distribution data, the data of the first fishing depth layer was analyzed. The average weather anomaly value is imported into the fish school prediction model, and the fish school depth correction coefficient is calculated and analyzed. Based on the fish school depth correction coefficient, the first fishing depth layer data is corrected to obtain the fishing prediction depth layer data. The fishing prediction depth layer data and the fishing prediction path data are merged to obtain the fishing prediction data. The method of obtaining fishing prediction data also includes: The fishing prediction path data is split into multiple prediction sub-path data segments; Obtain path region data corresponding to multiple predicted sub-path data segments; Based on the path area data, obtain the seabed topography sonar data collected in the path area; Based on the seabed topography sonar data, seabed topography analysis is performed to obtain the topography complexity corresponding to each predicted sub-path data. Obtain predicted sub-path data with terrain complexity less than a preset terrain complexity, and fuse the predicted sub-path data to obtain new fishing predicted path data.

2. The method for safe transoceanic fisheries based on the Internet of Things according to claim 1, characterized in that, The acquisition of information on fish species, fish numbers, and fish activity at different depths in the ocean specifically includes: Within the monitored sea area, the seabed is divided into layers based on the maximum fishing depth, and seabed image data and sonar data are acquired at different depths. Image feature extraction is performed on the seabed image data to obtain image feature value data; By comparing and statistically analyzing the features of the image feature values ​​with those of the fish images, and combining this with sonar data, information on the species and number of fish in the school can be obtained.

3. The method for safe fishing in transoceanic fisheries based on the Internet of Things according to claim 1, characterized in that, The acquisition of information on fish species, fish numbers, and fish activity at different depths in the ocean also includes: Construct a three-dimensional seabed map model for a specific sea area; Collect sonar feedback data of schools of fish on the seabed, and perform data fusion analysis based on the feedback data and the three-dimensional seabed map model to obtain the movement location information of the schools of fish; Based on the location information of the fish school, the movement trajectory of the fish school is analyzed and the fish school movement trajectory information is obtained. The fish school movement location information and fish school movement trajectory information are merged and sorted to obtain the fish school activity information.

4. A transoceanic fishery safety fishing system based on the Internet of Things, characterized in that, The system includes a memory and a processor. The memory includes a program for a method of safe fishing in transoceanic fisheries based on the Internet of Things (IoT). When the program is executed by the processor, it implements the steps of the method of safe fishing in transoceanic fisheries based on the IoT as described in claim 1.

5. A transoceanic fishery safety fishing system based on the Internet of Things according to claim 4, characterized in that, The acquisition of information on fish species, fish numbers, and fish activity at different depths in the ocean specifically includes: Within the monitored sea area, the seabed is divided into layers based on the maximum fishing depth, and seabed image data and sonar data are acquired at different depths. Image feature extraction is performed on the seabed image data to obtain image feature value data; By comparing and statistically analyzing the features of the image feature values ​​with those of the fish images, and combining this with sonar data, information on the species and number of fish in the school can be obtained.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes an Internet of Things (IoT)-based method program for safe fishing in transoceanic fisheries. When the IoT-based method program for safe fishing in transoceanic fisheries is executed by a processor, it implements the steps of the IoT-based method for safe fishing in transoceanic fisheries as described in any one of claims 1 to 3.

Images