CN118247072A

CN118247072A - Fishing condition prediction method based on fishery application digital twin system

Info

Publication number: CN118247072A
Application number: CN202410468177.8A
Authority: CN
Inventors: 李寒; 谢宏
Original assignee: Xi'an Kunlan Electronic Technology Co ltd
Current assignee: Xi'an Kunlan Electronic Technology Co ltd
Priority date: 2024-04-18
Filing date: 2024-04-18
Publication date: 2024-06-25

Abstract

The embodiment of the application relates to the technical field of digital twinning, in particular to a fishing condition prediction method based on a fishery application digital twinning system, which comprises the following steps: performing grid division on the sea chart of the target sea area, and performing unique grid coding on each divided grid unit; establishing a static attribute table and a dynamic attribute table for each grid unit based on geographic information of a target sea area and fishery application demand information; generating a digital base map of the target sea area based on the static attribute table, and superposing the content in the latest dynamic attribute table on the digital base map to obtain a fishery application digital twin system; based on the fishery application digital twin system, the predicted fishing zone is calculated intelligently by utilizing information related to the fish condition prediction, and grid codes of all grid units in the range of the predicted fishing zone are packed and sent to the user terminal, so that the precision of the fish condition prediction is improved, the fish condition prediction is intuitively displayed on a chart of the user terminal, and reasonable development and sustainable utilization of marine fishery resources are facilitated.

Description

Fishing condition prediction method based on fishery application digital twin system

Technical Field

The embodiment of the application relates to the technical field of digital twinning, in particular to a fishing condition prediction method based on a fishery application digital twinning system.

Background

The fish condition prediction, also called fish condition prediction and fish condition prediction, is the main content of the research of the marine fishery, is also the comprehensive application of the basic principle and method in the fishery, and is one of the main tasks for the production service of the fishery. The prediction of fish conditions specifically refers to predicting each element of aquatic resources at a certain period and in a certain water area in the future, for example, the number of fish shoal, the type of fish shoal, the position of fish farm, the duration of fish flood and fish flood, and the possible fish gain. The accurate fish condition prediction not only provides necessary scientific basis for how fish flood production management is carried out by fishery authorities and production units, but also greatly improves the production efficiency of fishery and reduces the production cost. The prediction of the fishing condition can also provide possibility for scientific management of marine fishery resources, not only can the fishery management department use the prediction result as reference information for making the fishery policy, but also the fishery production enterprises can reasonably arrange the fishing force according to the prediction information, so as to adapt to the requirements of responsible fishing and sustainable development of the fishery.

However, the traditional fish condition prediction relies on the experience of fishermen to judge the position of the fish shoal, so that the accuracy of the position of the fish shoal is difficult to ensure, and the fishing efficiency is seriously affected. In recent years, a fish-condition prediction analysis method based on frequency analysis and habitat index has been proposed, but the prediction accuracy is also relatively low, and fish-condition prediction based on LSTM (Long Short Term Memory, long and short term memory) recurrent neural network is also a front, but the running cost of the model is high, and the fish-condition prediction cannot be performed in a large range. In addition, many factors such as oceanographic, sea state, sea geography and sea traffic may affect the position of the shoal of fish and the safety of the sailing operation of the ship, and the current fish condition prediction method cannot well utilize the information.

Disclosure of Invention

The embodiment of the application aims to provide a fish condition prediction method based on a fishery application digital twin system, aims to improve the precision of fish condition prediction and intuitively display on a chart of a user terminal, provides technical decision support for establishing fishery resource scientific management, and is beneficial to realizing reasonable development and sustainable utilization of marine fishery resources.

In order to achieve the above purpose, the embodiment of the application provides a fishing condition prediction method based on a digital twin system for fishery application, which is applied to a cloud server and comprises the following steps: performing grid division on the sea chart of the target sea area, and performing unique grid coding on each divided grid unit; establishing static attribute and dynamic attribute for each grid unit based on the geographic information of the target sea area and the fishery application demand information, and generating a static attribute table and a dynamic attribute table of each grid unit; the fishery application demand information comprises historical fishing condition information, historical weather information, historical marine traffic accident information, remote sensing information, real-time weather information, ship operation information, real-time marine traffic information and time administration information, wherein static attributes represent static things and time-invariant information of the static things in the grid cells, and dynamic attributes represent moving things and time-variant information of the static things in the grid cells; generating a digital base map of the target sea area based on a static attribute table of each grid unit, and overlapping the content in the latest dynamic attribute table of each grid unit on the digital base map in the forms of characters, numbers, animation and icons to obtain a fishery application digital twin system capable of predicting the fishing condition and reflecting real-time weather, traffic, sea conditions, ship distribution and time administration information; based on the fishery application digital twin system, the predicted fishing zone is calculated intelligently by utilizing information related to the prediction of the fishing condition, and grid codes of all grid cells in the range of the predicted fishing zone are packed and sent to a user terminal for the user terminal to display the predicted fishing zone on a chart display interface.

In order to achieve the above object, an embodiment of the present application further provides a fishing condition prediction system based on a digital twin system for fishery application, including: the sea chart dividing module is used for dividing sea charts of the target sea areas into grids and carrying out unique grid coding on each divided grid unit; the attribute establishing module is used for establishing static attribute and dynamic attribute for each grid unit based on the geographic information of the target sea area and fishery application demand information, and generating a static attribute list and a dynamic attribute list of each grid unit, wherein the fishery application demand information comprises historical fish information, historical weather information, historical marine traffic accident information, remote sensing information, real-time weather information, ship operation information, real-time marine traffic information and time administration information, the static attribute represents static things and time-invariant information of the static things in the grid unit, and the dynamic attribute represents the moving things and time-variant information of the static things in the grid unit; the digital twin system construction module is used for generating a digital base map of the target sea area based on the static attribute table of each grid unit, and overlapping the content in the latest dynamic attribute table of each grid unit on the digital base map in the forms of characters, numbers, animation and icons to obtain the fishery application digital twin system capable of carrying out fish condition prediction and reflecting real-time weather, traffic, sea conditions, ship distribution and time administrative information; and the prediction execution module is used for intelligently calculating a predicted fishing zone by utilizing information related to fishing condition prediction based on the fishery application digital twin system, and transmitting grid codes of all grid units in the range of the predicted fishing zone to a user terminal for the user terminal to display the predicted fishing zone on a chart display interface.

To achieve the above object, an embodiment of the present application further provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the fishery application digital twin system based fishing condition prediction method described above.

To achieve the above object, an embodiment of the present application further provides a computer readable storage medium storing a computer program, where the computer program is executed by a processor to implement the above-mentioned fishing condition prediction method based on a digital twin system for fishery application.

According to the fishing condition prediction method based on the digital twin system for the fishery application, firstly, the sea chart of a target sea area is subjected to grid division, unique grid coding is carried out on grid units, then, a static attribute table and a dynamic attribute table are built for each grid unit based on geographic information, historical fishing condition information, historical weather information, historical marine traffic accident information, remote sensing information, real-time weather information, ship operation information, real-time marine traffic information and time administration information of the target sea area, then, a digital base map of the target sea area is generated based on the static attribute table of each grid unit, the content in the latest dynamic attribute table of each grid unit is superimposed on the digital base map in the form of characters, numbers, animations and icons, the digital twin system for the fishery application is obtained, finally, the predicted fishing region is calculated intelligently based on the digital twin system for the fishery application, and the grid codes of all grid units in the predicted fishing region are packaged and sent to a user terminal for the user terminal to display the predicted fishing region on a sea chart display interface. Based on autonomous digital twin design thought, the technology of fishery scientific research results, grid division, cloud computing, big data, artificial intelligence, communication satellites, navigation satellites, remote sensing satellites and the like is combined, and a fishery application digital twin system capable of carrying out fishery condition prediction and reflecting real-time weather, traffic, sea conditions, ship distribution and time administrative information is constructed. The digital twin system for fishery application can efficiently, quickly and accurately calculate the predicted fishing zone, intuitively display the predicted fishing zone on a chart of a user terminal, provide technical decision support for establishing fishery resource scientific management, and be beneficial to realizing reasonable development and sustainable utilization of marine fishery resources.

In some optional embodiments, the establishing static attribute and dynamic attribute for each grid cell based on the geographic information of the target sea area and fishery application requirement information includes: establishing static attributes for each grid unit based on the geographic information of the target sea area, the historical fishing condition information, the historical weather information and the historical offshore traffic accident information; establishing dynamic attributes for each grid cell based on the remote sensing information, the real-time weather information, the ship operation information, the real-time offshore traffic information and the time administration information; the geographic information of the target sea area is acquired from ocean geographic departments and hydrologic departments, and comprises water depth information, whether underwater submerged reefs exist, whether underwater shoals exist, submerged reef depths and shoal depths; the historical fish information is obtained by collecting and counting fish information in preset years and comprises fish group distribution information, fish group quantity information and fish group type information of each year and each time period of the target sea area; the historical weather information is acquired from a marine weather bureau and comprises weather information of each year and each time period of the target sea area; the historical marine traffic accident information is acquired from traffic information parts and maritime bureaus and comprises accident sites of the target sea area, once-occurring marine traffic accidents and accident types which are easy to occur; the remote sensing information is obtained by shooting and desensitizing analysis of a target sea area by calling a remote sensing satellite, and comprises chlorophyll concentration, sea temperature information, salinity information, vortex information, flow interval information and ocean current intersection information of the target sea area; the real-time weather information is acquired from a marine weather bureau and comprises real-time weather, real-time wind speed, real-time wave height and real-time weather disasters of a target sea area; the ship operation information is acquired from a shipborne user terminal and comprises position information, navigational speed information, heading information and tonnage information of each ship; the real-time maritime traffic information is acquired from a traffic information part and a maritime bureau and comprises a real-time state that each route in the target sea area is busy, whether a maritime traffic accident exists or not and a current processing stage of the accident; the time administrative information is obtained from fishery departments and maritime offices, and comprises whether the target sea area is in a non-fishing period, belongs to a special fishing zone, discovers pirates and is a situation tension zone.

In some alternative embodiments, after receiving the grid codes of all grid cells within the range of the predicted fishing zone and displaying the predicted fishing zone on a chart display interface, the method further comprises: determining a target grid cell based on the predicted fishing zone, wherein the target grid cell is a grid cell to which a ship of the user terminal is going; based on the position relation between the grid unit where the ship belongs to and the target grid unit, combining the real-time weather, the real-time wind speed, the real-time wave height, the position information of each ship, the tonnage information of the ship, the real-time marine traffic information, the time administration information and the geographic information of the target sea area, determining the safety passing property of the grid unit where the ship belongs to each middle grid unit among the target grid units; an optimal route for the belonging ship to the target grid cell is planned according to the safety passing performance of each intermediate grid cell. The prediction fishing zone provides an optional place for the fisher to fish, the fisher selects a target grid unit according to the prediction fishing zone, a digital twin system is applied based on the fishery, and the information of the ship is combined to rapidly plan the optimal route which is close in distance, passable and safe, so that the fuel for sailing of the fishing vessel is saved, the efficiency of the fishing operation of the fisher is improved, and the income of the fisher is improved.

In some optional embodiments, after planning an optimal route of the ship to the target grid unit, the user terminal further needs to transmit the optimal route back to the cloud server; after receiving the optimal route, the cloud server marks the ship to which the user terminal belongs as a target ship; tracking the target ship, and generating a track of the target ship according to ship operation information of the target ship; and packaging and transmitting the track and the optimal route to a user terminal with the monitoring requirement only for the target ship. Based on the fishery application digital twin system, the monitoring of the target ship can be realized, the position and the track of the target ship can be known in real time, the safety coefficient of fishing operation is further improved, and the fishing device can timely react and be connected with the target ship after an emergency occurs.

In some optional embodiments, the cloud server sends the predicted fishing condition information of the predicted fishing zone to the user terminal while sending the grid code package of all grid cells within the range of the predicted fishing zone to the user terminal; after the ship reaches the target grid unit, the user terminal calls a shipborne fish detection radar and/or an underwater sonar detection system of the ship to detect the real fish condition of the target grid unit, and fuses the predicted fish condition information and the detected real fish condition information of the target grid unit to make a fishing plan; the user terminal returns the real fishing information to the cloud server after detecting the real fishing information of the target grid unit; and after receiving the real fish information, the cloud server corrects the predicted fish information of the target grid unit based on the real fish information. The prediction fishing zone is a prediction made according to the historical big data and the real-time big data, the prediction fishing condition information is not necessarily completely accurate, the real fishing condition information is detected and returned to the cloud server after the fishing boat reaches the target grid unit, the cloud server corrects the prediction fishing condition information according to the real fishing condition information and issues correction information, thereby better helping fishermen to formulate a fishing plan, helping fishery departments to make fishery policies, and better adapting to requirements of responsible fishing and sustainable development of fishery.

In some optional embodiments, the user terminal continuously collects information related to fishery production during the process of the ship going out of the sea, and returns the information related to fishery production to the cloud server during a production operation intermittence period. And the cloud server performs data classification, image recognition and intelligent semantic recognition conversion processing on the relevant information of the fishery production and then writes the relevant information into a dynamic attribute table of the corresponding grid unit. The iterative updating of the dynamic attribute table is essentially the accumulation process of the marine big data related to fishery, the marine civil carriers (ships) are numerous, the moving range and the route are wide, the marine data collected by the civil ships are incomparable with the traditional data collection mode in depth and breadth, and the method has wider application value.

In some optional embodiments, the predicted fishing zone is divided into a plurality of grades, the grade of the predicted fishing zone with higher fish probability is higher, and the grid codes of all grid cells in the range of the predicted fishing zone are packaged and sent to a user terminal for the user terminal to display the predicted fishing zone on a chart display interface, which comprises: according to the grades of the predicted fishing zone, the grid codes of all grid units in the range of the predicted fishing zone of each grade are packed and sent to a user terminal, so that the user terminal can display the predicted fishing zone on a chart display interface, and different colors are adopted to represent different grades. The method has the advantages that the different-grade prediction fishing areas are marked by different colors, more fishing destination selections can be provided for fishermen, and further, the fishermen can be better helped to select better fishing destinations and fishing strategies which are more in line with actual conditions.

Drawings

FIG. 1 is a flow chart of a method for predicting a fishing condition based on a digital twinning system for fishery applications, provided in one embodiment of the application;

FIG. 2 is a chart of a meshing target sea area provided in one embodiment of the application;

FIG. 3 is a flow chart for establishing static and dynamic properties for each grid cell based on geographic information of a target sea area and fishery application demand information, provided in one embodiment of the application;

Fig. 4 is a schematic diagram of a connection relationship between a cloud server and a remote sensing satellite, and between the cloud server and a user terminal according to an embodiment of the present application;

FIG. 5 is a flow chart providing, in one embodiment of the present application, a user terminal selecting a target grid cell and performing optimal routing;

FIG. 6 is a schematic diagram of a fish condition prediction system based on a digital twinning system for fishery applications according to another embodiment of the present application;

fig. 7 is a schematic structural diagram of an electronic device according to another embodiment of the present application.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the embodiments of the present application will be described in detail below with reference to the accompanying drawings. However, it will be understood by those of ordinary skill in the art that in various embodiments of the present application, numerous specific details are set forth in order to provide a thorough understanding of the present application. The claimed application may be practiced without these specific details and with various changes and modifications based on the following embodiments. The following embodiments are divided for convenience of description, and should not be construed as limiting the specific implementation of the present application, and the embodiments can be mutually combined and referred to without contradiction.

An embodiment of the present application provides a fishing condition prediction method based on a digital twin system for fishery application, which is applied to a cloud server, and implementation details of the fishing condition prediction method based on the digital twin system for fishery application provided in this embodiment are specifically described below, and the following details are provided only for easy understanding, but are not necessary for implementing the present embodiment.

The specific flow of the fishing condition prediction method based on the digital twin system for fishery application provided in this embodiment may be as shown in fig. 1, and includes:

step 101, performing grid division on the sea chart of the target sea area, and performing unique grid coding on each divided grid unit.

In the specific implementation, the cloud server firstly determines the target sea area, after determining the target sea area, can carry out grid division on the sea chart of the target sea area, and carries out unique grid coding on each divided grid unit to form a grid position index table, and the conversion between the grid coding of the grid unit and longitude and latitude can be realized.

In one example, the sea chart of the meshing target sea area may be as shown in fig. 2.

In one example, the cloud server performs unique grid coding on each divided grid unit based on a preset coding rule, the coded grid coding is in an integer form or a character string form, the used coding rule can select national standard coding modes such as Beidou grid position codes, and compared with the mode of directly using floating-point longitude and latitude to perform space multidimensional information query and calculation, the efficiency is greatly improved, and the calculation force requirement of a digital twin system applied to the fishery which is constructed later in use is reduced.

Step 102, based on the geographic information of the target sea area and the fishery application demand information, establishing static attributes and dynamic attributes for each grid unit, and generating a static attribute table and a dynamic attribute table of each grid unit.

In a specific implementation, after completing grid division and grid coding of the sea chart of the target sea area, the cloud server can establish static attribute and dynamic attribute for each grid unit based on geographic information and fishery application demand information of the target sea area, and generate a static attribute table and a dynamic attribute table of each grid unit. The fishery application demand information comprises historical fishery information, historical weather information, historical marine traffic accident information, remote sensing information, real-time weather information, ship operation information, real-time marine traffic information, timely administration information and the like, static attributes of the grid cells represent static things and time-invariant information of the static things in the grid cells, and dynamic attributes of the grid cells represent moving things and time-variant information of the static things in the grid cells.

In one example, the cloud server establishes static attribute and dynamic attribute for each grid cell based on the geographic information of the target sea area and the fishery application requirement information, which may be implemented by the steps shown in fig. 3, and specifically includes:

Step 1021, establishing static attributes for each grid cell based on the geographic information, the historical fish information, the historical weather information and the historical marine traffic accident information of the target sea area.

In a specific implementation, after grid division and grid coding of the sea chart of the target sea area are completed, the cloud server can respectively establish static properties for each grid unit based on geographic information of the target sea area, historical fishing condition information, historical weather information and historical marine traffic accident information in fishery application demand information.

In one example, the geographic information of the target sea area is obtained from the ocean geographic department and the hydrologic department, including water depth information, whether there is a submerged reef under water, whether there is a shoal under water, a submerged reef depth, a shoal depth and the like, and the cloud server adds the water depth information, whether there is a submerged reef under water, whether there is a shoal under water, a submerged reef depth, a shoal depth and the like as static attributes to the static attribute table of each grid unit.

In one example, the historical fish information is obtained by counting fish information distribution data and corresponding time accumulated from fish enterprises and fishery departments for years, namely, the probability of fish in each time period of a target sea area in one year is counted, specifically, the fish information comprises fish distribution information, fish quantity information, fish class information and the like of each year and each time period of the target sea area, and the cloud server takes fish distribution information, fish quantity information, fish class information and the like of each year and each time period of the target sea area as static attributes and adds the static attributes to a static attribute table of each grid unit.

In one example, the historical weather information is obtained from a marine weather bureau, that is, the historical weather information of the target sea area is statistically analyzed to obtain weather information in each time period in one year of the target sea area, that is, weather information of each year, each time period, and the like of the target sea area, such as seasonal storm high-altitude area information and the like, and the cloud server adds the weather information of each year, each time period, and the like of the target sea area as static attributes to the static attribute table of each grid unit.

In one example, the historical marine traffic accident information is obtained from a traffic information unit and a maritime office, and includes accident sites, accident types and accident types of the target sea area, and the like, and the cloud server adds the accident sites, the accident types and the accident types of the target sea area, the accident types and the like as static attributes to the static attribute table of each grid unit.

Step 1022, based on the remote sensing information, the real-time weather information, the ship operation information, the real-time marine traffic information, and the real-time administration information, respectively, establishing dynamic properties for each grid cell.

In a specific implementation, the cloud server needs to establish dynamic attributes for each grid unit based on remote sensing information, real-time weather information, ship operation information, real-time marine traffic information and real-time administrative information while establishing static attributes for each grid unit.

In one example, the remote sensing information is obtained after the cloud server shoots and desensitizes the target sea area by calling the remote sensing satellite, specifically, the cloud server can cooperate with a remote sensing information processing unit to obtain the remote sensing information from the remote sensing information processing unit, and the cloud server can analyze the remote sensing image after the desensitization processing based on various analysis algorithms to obtain the remote sensing information. The remote sensing information comprises chlorophyll concentration, sea temperature information, salinity information, vortex information, flow interval information, ocean current intersection information and the like of the target sea area, and the cloud server takes the chlorophyll concentration, sea temperature information, salinity information, vortex information, flow interval information, ocean current intersection information and the like of the target sea area as dynamic attributes and adds the dynamic attributes to a dynamic attribute table of each grid unit.

It is noted that the fishing zone prediction is performed based on the marine remote sensing related scientific research results by using the remote sensing information, and the remote sensing information can be content with dynamic properties, but more importantly, the fish in the sea area formed by the grids can be predicted based on the content, and then the fish information is filled in the corresponding grid properties, so that the area where the fish is likely to be in the target sea area is determined.

The key points of the partial processing of the remote sensing information include: the water temperature and the sea water temperature are closely related to the survival and migration of fishes, and various fishes have the optimum survival temperature range and also perform the temperature-adaptive migration along with seasons. The remote sensing satellite provides large-area sea surface temperature information, and the fish shoal position can be predicted by combining historical and short-term season data, so that the fish production service is provided for fishery; the flow gap exists in the ocean, and a large temperature gradient exists among different flow systems to form the flow gap, so that the distribution of different flow systems can be clearly reflected after the infrared image is subjected to density segmentation treatment, and indexes are provided for determining a central fishing ground; chlorophyll and marine fishing resources are based on annual yield of plankton, potential of the fishing resources is estimated through measurement of annual yield of plankton, the marine chlorophyll is an important parameter reflecting photosynthesis of the marine plankton, and remote sensing satellites can provide relative concentration distribution of chlorophyll in the ocean and provide basis for richness of fishery resources in each area of the sea; when the satellite is used for monitoring that the fishing zone has medium-small scale cold water vortex with the diameter of tens to hundreds of kilometers, a central fishing ground can be formed near the center of the vortex.

In one example, the real-time weather information is periodically obtained from a marine weather bureau, including real-time weather, real-time wind speed, real-time wave height, real-time weather disasters, etc. of the target sea area, and the cloud server adds the real-time weather, the real-time wind speed, the real-time wave height, the real-time weather disasters, etc. of the target sea area as dynamic attributes to the dynamic attribute table of each grid cell.

In one example, the ship operation information is periodically acquired from a user terminal on board the ship, including position information (longitude and latitude), speed information, heading information, tonnage information, and the like of each ship, and the cloud server needs to add the position information, speed information, heading information, tonnage information, and the like of each ship as dynamic attributes to the dynamic attribute table of each grid cell based on the position information of each ship.

In one example, the real-time maritime traffic information is obtained from a traffic information department, maritime bureau, including a real-time status of each route busy within the target sea area, whether there is a maritime traffic accident, and the current stage of the accident.

In one example, the time administrative information is periodically acquired from the fishery department and the maritime bureau, including whether the target sea area is in a restricted fishing period, belongs to a dedicated fishing zone, finds pirates, is a situation tension zone, and the like, and the cloud server adds the target sea area, whether the target sea area is in the restricted fishing period, belongs to the dedicated fishing zone, finds the pirates, is the situation tension zone, and the like as dynamic attributes to the dynamic attribute table of each grid unit.

In one example, for a remote sensing image, the cloud server scales the remote sensing image to a scale used by the system chart based on a preset scale, and then maps the remote sensing information to a corresponding grid cell through an image recognition technology.

Step 103, generating a digital base map of the target sea area based on the static attribute table of each grid unit, and superposing the content in the latest dynamic attribute table of each grid unit on the digital base map in the forms of characters, numbers, animations and icons to obtain the fishery application digital twin system capable of carrying out fish condition prediction and reflecting real-time weather, traffic, sea conditions, marine carrier distribution and time administrative information.

In a specific implementation, after the static attribute table and the dynamic attribute table are established for each grid unit, the cloud server can generate a digital base map of the target sea area based on the static attribute table of each grid unit, and superimpose the content in the latest dynamic attribute table of each grid unit on the digital base map in the form of characters, numbers, animation and icons to obtain the fishery application digital twin system capable of carrying out fish condition prediction and reflecting real-time weather, traffic, sea conditions, marine carrier distribution and time administration information.

In one example, the cloud server is connected with a cloud service platform, a chart of a target sea area can be displayed on a display large screen of the cloud service platform, and various information (including a static attribute table and a dynamic attribute table) of the fishery application digital twin system is superimposed on the chart in different text, figures, animation and icon forms, so that the fishery application digital twin system can interact visually.

In one example, after the cloud server is constructed to obtain the fishery application digital twin system, a database can be formed based on the grid position index table and the static attribute table and the dynamic attribute table of each grid unit, and the database and the sea chart of the target sea area are preloaded to the user terminal to serve as a basic sea chart information base of the user terminal and serve as basic elements of end cloud fusion processing and service content display.

Step 104, based on the fishery application digital twin system, the predicted fishing zone is calculated intelligently by utilizing information related to the prediction of the fishing condition, and grid codes of all grid units in the range of the predicted fishing zone are packed and sent to a user terminal for the user terminal to display the predicted fishing zone on a chart display interface.

In a specific implementation, after the digital twin system for fishery application is established, the cloud server can intelligently calculate the predicted fishing zone (including the predicted fishing condition information of the predicted fishing zone, such as the predicted fish population number, the predicted fish population type, and the like) by using the information related to the fish condition prediction based on the digital twin system for fishery application, and the cloud server packages and transmits the grid codes of all grid units within the range of the predicted fishing zone to the user terminal for the user terminal to display the predicted fishing zone on a chart display interface.

In one example, the predicted fishing zone intelligently calculated by the cloud server is divided into a plurality of grades, the grade of the predicted fishing zone with higher fish probability is higher, the cloud server packages and sends grid codes of all grid units in the range of the predicted fishing zone of each grade to the user terminal according to the grade of the predicted fishing zone, the user terminal displays the predicted fishing zone on a chart display interface after receiving the information, and different grades are expressed by adopting different colors for the fishermen to identify the positions of the fish shoals.

In an example, the connection relationship between the cloud server and the remote sensing satellite or the user terminal may be as shown in fig. 4, and in fig. 4, the user terminal may be divided into a shipborne user terminal and an industry alliance user terminal, where the shipborne user terminal is further connected to the communication satellite or the navigation satellite.

According to the embodiment, firstly, a sea chart of a target sea area is subjected to grid division, unique grid coding is carried out on grid cells, then, a static attribute table and a dynamic attribute table are built for each grid cell based on geographic information, historical fish information, historical weather information, historical marine traffic accident information, remote sensing information, real-time weather information, ship operation information and time administration information of the target sea area, then, a digital base chart of the target sea area is generated based on the static attribute tables of the grid cells, the latest dynamic attribute tables of the grid cells are superimposed on the digital base chart, a fishery application digital twin system is obtained, finally, a prediction fishing zone is calculated intelligently based on the fishery application digital twin system, grid coding packages of all grid cells in the range of the prediction fishing zone are sent to a user terminal, and the user terminal displays the prediction fishing zone on a sea chart display interface. Based on autonomous digital twin design thought, the technology of fishery scientific research results, grid division, cloud computing, big data, artificial intelligence, communication satellites, navigation satellites, remote sensing satellites and the like is combined, and a fishery application digital twin system capable of carrying out fishery condition prediction and reflecting real-time weather, traffic, sea conditions, ship distribution and time administrative information is constructed. The digital twin system for fishery application can efficiently, quickly and accurately calculate the predicted fishing zone, intuitively display the predicted fishing zone on a chart of a user terminal, provide technical decision support for establishing fishery resource scientific management, and be beneficial to realizing reasonable development and sustainable utilization of marine fishery resources.

In one embodiment, after receiving the grid codes of all grid cells within the range of the predicted fishing zone and displaying the predicted fishing zone on the chart display interface, the user terminal may select a target grid cell and perform an optimal route planning according to the steps shown in fig. 5, which specifically includes:

step 201, determining a target grid cell, i.e. a grid cell to which the ship of the user terminal belongs is going, based on the predicted fishing zone.

In a specific implementation, after receiving and displaying the predicted fishing zone, the user terminal may determine a target grid cell based on the predicted fishing zone, where the target grid cell is a grid cell to which the ship to which the user terminal belongs is about to go, that is, a destination to which the user terminal is to go to catch fish.

Step 202, based on the position relationship between the grid cell where the ship belongs to and the target grid cell, combining the real-time weather, the real-time wind speed, the real-time wave height, the position information of each ship, the tonnage information of the ship, the real-time offshore traffic information, the time administration information and the geographic information of the target sea area, the security passing ability of the grid cell where the ship belongs to each middle grid cell between the target grid cells is determined.

In a specific implementation, after determining the target grid cell, the user terminal may determine the safety trafficability of the grid cell, where the ship belongs, to each intermediate grid cell between the target grid cells based on the position relationship between the grid cell where the ship belongs and the target grid cell, in combination with real-time weather, real-time wind speed, real-time wave height, position information of each ship, tonnage information of the ship, real-time marine traffic information, and geographic information of the target sea area. The information is actually derived from a static attribute table and a dynamic attribute table of each grid unit in the fishery application digital twin system, and the user terminal can acquire the information from the cloud server.

Step 203, according to the safety passing performance of each middle grid unit, planning the optimal route of the ship to the target grid unit.

In a specific implementation, after determining the security passing capability of each intermediate grid cell between the grid cell where the ship belongs to and the target grid cell, the server may plan the optimal route of the ship to the target grid cell according to the security passing capability of each intermediate grid cell.

It can be understood that the prediction fishing zone provides an optional place for the fisher to fish, the fisher selects the target grid unit according to the prediction fishing zone, a digital twin system is applied based on fishery, and the information of the ship is combined, so that the optimal route which is close in distance, passable and safe is quickly planned, the fuel for sailing of the fishing vessel is saved, the efficiency of the fishing operation of the fisher is improved, and the income of the fisher is improved.

In one example, the user terminal, after planning the best route of the vessel to the target grid cell, also needs to transmit the best route back to the cloud server. After receiving the optimal route, the cloud server can mark the ship to which the user terminal belongs as a target ship, then track the target ship, generate a route of the target ship according to the ship operation information of the target ship, and package and send the route of the target ship and the optimal route corresponding to the target ship to the user terminal with only monitoring requirements on the target ship. Based on the fishery application digital twin system, the monitoring of the target ship can be realized, the position and the track of the target ship can be known in real time, the safety coefficient of fishing operation is further improved, and the fishing device can timely react and be connected with the target ship after an emergency occurs.

In one example, when a target ship enters a certain grid or a certain grid cell group, the cloud server marks the ship state in the dynamic attribute of the corresponding grid cell, for example, the target ship enters the grid cell and marks 1, and the target ship leaves the grid cell and marks 0, so that the running position of the carrier in the target sea area can be tracked, and the track of the target ship is dynamically formed in real time according to the information of the speed, the heading and the like, so that corresponding service is provided for a user with monitoring requirements.

In one example, the cloud server may also need to send predicted fishing information of the predicted fishing zone to the user terminal while sending the grid code package of all grid cells within the range of the predicted fishing zone to the user terminal. After the ship reaches the target grid unit, the user terminal can call a ship-borne fish detection radar and/or an underwater sonar detection system of the ship to detect the real fishing condition of the target grid unit, and the predicted fishing condition information and the detected real fishing condition information of the target grid unit are fused to make a fishing plan. The user terminal can also transmit the real fish information back to the cloud server after detecting the real fish information of the target grid unit, and the cloud server corrects the predicted fish information of the target grid unit based on the real fish information after receiving the real fish information.

It can be understood that the prediction fishing zone is a prediction made according to the historical big data and the real-time big data, the prediction fishing condition information is not necessarily completely accurate, the real fishing condition information is detected and returned to the cloud server after the fishing vessel arrives at the target grid unit, the cloud server corrects the prediction fishing condition information according to the real fishing condition information and issues correction information, thereby better helping fishermen to make a fishing plan, helping fishery departments to make a fishery policy, and better adapting to requirements of responsible fishing and sustainable development of the fishery.

In one example, the user terminal may continuously collect information related to fishery production during the process of the ship going out of the sea, and transmit the collected information related to fishery production back to the cloud server during the production operation intermittence period. And the cloud server performs data classification, image recognition and intelligent semantic recognition conversion processing on the fishery production related information and writes the data into a dynamic attribute table of the corresponding grid unit. The iterative updating of the dynamic attribute table is essentially the accumulation process of the marine big data related to fishery, the marine civil carriers (ships) are numerous, the moving range and the route are wide, the marine data collected by the civil ships are incomparable with the traditional data collection mode in depth and breadth, and the method has wider application value.

In one example, after the data is accumulated to a certain extent, the cloud server can intelligently select a time period according to the network use condition of each user terminal in an OTA push mode, and remotely update the grid position code feature library (namely the dynamic attribute table) of the user terminal, so that the grid feature library of the user terminal is kept up to date, and the user obtains the optimal service experience.

Another embodiment of the present application provides a fishing condition prediction system based on a digital twin system for fishery application, the details of the fishing condition prediction system based on the digital twin system for fishery application provided in this embodiment are specifically described below, and the following is only implementation details provided for easy understanding, but not essential to the embodiment, and fig. 6 is a schematic diagram of the fishing condition prediction system based on the digital twin system for fishery application provided in this embodiment, including: a chart partitioning module 301, an attribute establishing module 302, a digital twin system constructing module 303 and a prediction executing module 304.

The chart dividing module 301 is configured to grid-divide a chart of a target sea area, and perform unique grid coding on each divided grid unit.

The attribute establishing module 302 is configured to establish a static attribute and a dynamic attribute for each grid cell based on geographic information of a target sea area and fishery application requirement information, and generate a static attribute table and a dynamic attribute table of each grid cell, where the fishery application requirement information includes historical fishery information, historical weather information, historical marine traffic accident information, remote sensing information, real-time weather information, ship operation information and time administration information, the static attribute characterizes static things and time-invariant information thereof in the grid cell, and the dynamic attribute characterizes moving things and time-variant information thereof in the grid cell.

The digital twin system construction module 303 is configured to generate a digital base map of the target sea area based on the static attribute table of each grid unit, and superimpose the contents in the latest dynamic attribute table of each grid unit on the digital base map in the form of characters, numbers, animation and icons, so as to obtain the fishery application digital twin system capable of predicting the fishing condition and reflecting real-time weather, traffic, sea conditions, ship distribution and time administrative information.

The prediction execution module 304 is configured to intelligently calculate a predicted fishing zone based on a fishery application digital twin system by using information related to fish condition prediction, and package and send grid codes of all grid cells within a range of the predicted fishing zone to a user terminal for the user terminal to display the predicted fishing zone on a chart display interface.

It is to be noted that this embodiment is a system embodiment corresponding to the above-described method embodiment, and this embodiment may be implemented in cooperation with the above-described method embodiment. The related technical details and technical effects mentioned in the above embodiments are still valid in this embodiment, and in order to reduce repetition, they are not repeated here. Accordingly, the related technical details mentioned in the present embodiment can also be applied to the above-described embodiments.

It should be noted that, each module involved in this embodiment is a logic module, and in practical application, one logic unit may be one physical unit, or may be a part of one physical unit, or may be implemented by a combination of multiple physical units. In addition, in order to highlight the innovative part of the present application, units less closely related to solving the technical problem presented by the present application are not introduced in the present embodiment, but it does not indicate that other units are not present in the present embodiment.

Another embodiment of the present application relates to an electronic device, as shown in fig. 7, comprising: at least one processor 401; and a memory 402 communicatively coupled to the at least one processor 401; the memory 402 stores instructions executable by the at least one processor 401, where the instructions are executed by the at least one processor 401, so that the at least one processor 401 can execute the fishing condition prediction method based on the digital twin system for fishery application described in the above embodiments.

Where the memory and the processor are connected by a bus, the bus may comprise any number of interconnected buses and bridges, the buses connecting the various circuits of the one or more processors and the memory together. The bus may also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver may be one element or may be a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. The data processed by the processor is transmitted over the wireless medium via the antenna, which further receives the data and transmits the data to the processor.

The processor is responsible for managing the bus and general processing and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. And memory may be used to store data used by the processor in performing operations.

Another embodiment of the application relates to a computer-readable storage medium storing a computer program. The computer program implements the above-described method embodiments when executed by a processor.

That is, it will be understood by those skilled in the art that all or part of the steps in implementing the methods of the embodiments described above may be implemented by a program stored in a storage medium, where the program includes several instructions for causing a device (which may be a single-chip microcomputer, a chip or the like) or a processor (processor) to perform all or part of the steps in the methods of the embodiments of the application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a ROM (Read-Only Memory), a RAM (Random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples of carrying out the application and that various changes in form and details may be made therein without departing from the spirit and scope of the application.

Claims

1. The fish condition prediction method based on the fishery application digital twin system is characterized by being applied to a cloud server, and comprises the following steps:

performing grid division on the sea chart of the target sea area, and performing unique grid coding on each divided grid unit;

Establishing static attribute and dynamic attribute for each grid unit based on the geographic information of the target sea area and the fishery application demand information, and generating a static attribute table and a dynamic attribute table of each grid unit; the fishery application demand information comprises historical fishing condition information, historical weather information, historical marine traffic accident information, remote sensing information, real-time weather information, ship operation information, real-time marine traffic information and time administration information, wherein static attributes represent static things and time-invariant information of the static things in the grid cells, and dynamic attributes represent moving things and time-variant information of the static things in the grid cells;

Generating a digital base map of the target sea area based on a static attribute table of each grid unit, and overlapping the content in the latest dynamic attribute table of each grid unit on the digital base map in the forms of characters, numbers, animation and icons to obtain a fishery application digital twin system capable of predicting the fishing condition and reflecting real-time weather, traffic, sea conditions, ship distribution and time administration information;

based on the fishery application digital twin system, the predicted fishing zone is calculated intelligently by utilizing information related to the prediction of the fishing condition, and grid codes of all grid cells in the range of the predicted fishing zone are packed and sent to a user terminal for the user terminal to display the predicted fishing zone on a chart display interface.

2. The fishing condition prediction method based on a digital twin system for fishery application according to claim 1, wherein the establishing static and dynamic properties for each grid cell based on the geographical information of the target sea area and the fishery application demand information comprises:

establishing static attributes for each grid unit based on the geographic information of the target sea area, the historical fishing condition information, the historical weather information and the historical offshore traffic accident information;

establishing dynamic attributes for each grid cell based on the remote sensing information, the real-time weather information, the ship operation information, the real-time offshore traffic information and the time administration information;

The geographic information of the target sea area is acquired from ocean geographic departments and hydrologic departments, and comprises water depth information, whether underwater submerged reefs exist, whether underwater shoals exist, submerged reef depths and shoal depths;

The historical fish information is obtained by collecting and counting fish information in preset years and comprises fish group distribution information, fish group quantity information and fish group type information of each year and each time period of the target sea area;

the historical weather information is acquired from a marine weather bureau and comprises weather information of each year and each time period of the target sea area;

The historical marine traffic accident information is acquired from traffic information parts and maritime bureaus and comprises accident sites of the target sea area, once-occurring marine traffic accidents and accident types which are easy to occur;

the remote sensing information is obtained by shooting and desensitizing analysis of a target sea area by calling a remote sensing satellite, and comprises chlorophyll concentration, sea temperature information, salinity information, vortex information, flow interval information and ocean current intersection information of the target sea area;

the real-time weather information is acquired from a marine weather bureau and comprises real-time weather, real-time wind speed, real-time wave height and real-time weather disasters of a target sea area;

The ship operation information is acquired from a shipborne user terminal and comprises position information, navigational speed information, heading information and tonnage information of each ship;

the real-time maritime traffic information is acquired from a traffic information part and a maritime bureau and comprises a real-time state that each route in the target sea area is busy, whether a maritime traffic accident exists or not and a current processing stage of the accident;

The time administrative information is obtained from fishery departments and maritime offices, and comprises whether the target sea area is in a non-fishing period, belongs to a special fishing zone, discovers pirates and is a situation tension zone.

3. The fishing condition prediction method based on a digital twin system for fishery application according to claim 2, wherein the user terminal receives grid codes of all grid cells within the range of the predicted fishing zone and displays the predicted fishing zone on a chart display interface, and the method further comprises:

Determining a target grid cell based on the predicted fishing zone, wherein the target grid cell is a grid cell to which a ship of the user terminal is going;

Based on the position relation between the grid unit where the ship belongs to and the target grid unit, combining the real-time weather, the real-time wind speed, the real-time wave height, the position information of each ship, the tonnage information of the ship, the real-time marine traffic information, the time administration information and the geographic information of the target sea area, determining the safety passing property of the grid unit where the ship belongs to each middle grid unit among the target grid units;

An optimal route for the belonging ship to the target grid cell is planned according to the safety passing performance of each intermediate grid cell.

4. A fishing condition prediction method based on a digital twin system for fishery applications according to claim 3, wherein the user terminal further needs to transmit the optimal route back to the cloud server after planning the optimal route of the ship to the target grid unit;

After receiving the optimal route, the cloud server marks the ship to which the user terminal belongs as a target ship;

Tracking the target ship, and generating a track of the target ship according to ship operation information of the target ship;

And packaging and transmitting the track and the optimal route to a user terminal with the monitoring requirement only for the target ship.

5. The fishing condition prediction method based on the digital twin system for fishery application according to claim 3, wherein the cloud server transmits predicted fishing condition information of the predicted fishing zone to the user terminal while packing and transmitting grid codes of all grid cells within the range of the predicted fishing zone to the user terminal;

After the ship reaches the target grid unit, the user terminal calls a shipborne fish detection radar and/or an underwater sonar detection system of the ship to detect the real fish condition of the target grid unit, and fuses the predicted fish condition information and the detected real fish condition information of the target grid unit to make a fishing plan;

The user terminal returns the real fishing information to the cloud server after detecting the real fishing information of the target grid unit;

and after receiving the real fish information, the cloud server corrects the predicted fish information of the target grid unit based on the real fish information and issues correction information.

6. The fish condition prediction method based on the digital twin system for fishery application according to claim 5, wherein the user terminal continuously collects fishery production related information in the process of the sea-going operation of the ship, and returns the fishery production related information to the cloud server in the intermittent period of the production operation;

And the cloud server performs data classification, image recognition and intelligent semantic recognition conversion processing on the relevant information of the fishery production and then writes the relevant information into a dynamic attribute table of the corresponding grid unit.

7. The fish condition prediction method based on a digital twin system for fishery application according to any one of claims 1 to 6, wherein the prediction fish area is divided into a plurality of levels, the higher the fish probability is, the higher the level of the prediction fish area is, the grid codes of all grid cells within the prediction fish area are packed and sent to a user terminal, and the user terminal displays the prediction fish area on a chart display interface, including:

According to the grades of the predicted fishing zone, the grid codes of all grid units in the range of the predicted fishing zone of each grade are packed and sent to a user terminal, so that the user terminal can display the predicted fishing zone on a chart display interface, and different colors are adopted to represent different grades.

8. A fishing condition prediction system based on a digital twin system for fishery applications, comprising:

the sea chart dividing module is used for dividing sea charts of the target sea areas into grids and carrying out unique grid coding on each divided grid unit;

The attribute establishing module is used for establishing static attribute and dynamic attribute for each grid unit based on the geographic information of the target sea area and fishery application demand information, and generating a static attribute list and a dynamic attribute list of each grid unit, wherein the fishery application demand information comprises historical fish information, historical weather information, historical marine traffic accident information, remote sensing information, real-time weather information, ship operation information, real-time marine traffic information and time administration information, the static attribute represents static things and time-invariant information of the static things in the grid unit, and the dynamic attribute represents the moving things and time-variant information of the static things in the grid unit;

the digital twin system construction module is used for generating a digital base map of the target sea area based on the static attribute table of each grid unit, and overlapping the content in the latest dynamic attribute table of each grid unit on the digital base map in the forms of characters, numbers, animation and icons to obtain the fishery application digital twin system capable of carrying out fish condition prediction and reflecting real-time weather, traffic, sea conditions, ship distribution and time administrative information;

and the prediction execution module is used for intelligently calculating a predicted fishing zone by utilizing information related to fishing condition prediction based on the fishery application digital twin system, and transmitting grid codes of all grid units in the range of the predicted fishing zone to a user terminal for the user terminal to display the predicted fishing zone on a chart display interface.

9. An electronic device, comprising:

At least one processor;

And a memory communicatively coupled to the at least one processor;

Wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the fishery application digital twin system-based fish condition prediction method of any one of claims 1 to 7.

10. A computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the fishery application digital twin system-based fish condition prediction method according to any one of claims 1 to 7.