Ocean gridding inspection method, device and equipment based on GIS information and medium

Abstract

The invention discloses an ocean gridding inspection method and device based on GIS information, equipment and a medium. The ocean gridding inspection method comprises the steps that an inspection area is divided into a plurality of initial inspection grids based on obtained target pattern spot data; acquiring image data of the inspection area, and optimizing each initial inspection grid based on the image data to obtain a plurality of target inspection grids; monitoring the target routing inspection grid, if abnormal grids exist in the target routing inspection grid, determining an abnormal type corresponding to each abnormal grid, automatically generating a plurality of candidate routing inspection paths based on the abnormal types and the abnormal grids, determining a target routing inspection path based on routing inspection data acquired in real time, and sending the target routing inspection path to a server; and performing routing inspection on each abnormal grid according to the target routing inspection path. The inspection efficiency can be improved.

Description

Technical Field

[0001] This application relates to the field of intelligent inspection, and particularly to a marine grid inspection method, device, equipment and medium based on GIS information. Background Art

[0002] With the rapid development of the marine economy, the development and utilization of sea areas and islands are becoming increasingly frequent. Through the supervision of sea areas and islands, the development and utilization behaviors of sea areas and islands can be standardized, overdevelopment and abuse of resources can be prevented, thus ensuring the sustainable development of the marine economy. At the same time, marine disasters can be detected and warned in a timely manner, and timely response and prevention measures can be provided for relevant departments and the public, thereby reducing the losses caused by disasters. Therefore, how to efficiently and intelligently detect sea areas has become increasingly important.

[0003] Currently, satellite remote sensing, unmanned aerial vehicle inspection, manual inspection, marine monitoring buoys and other technologies are mainly relied on to inspect the ocean. However, the frequency and quality of data obtained by these technologies are limited, the cost is high, and there are also problems such as small inspection range and low inspection efficiency. Moreover, when the marine environment changes, traditional inspection technologies are difficult to capture these changes in a timely manner, and it is thus difficult to adaptively adjust the inspection plan, that is, dynamic supervision cannot be carried out. Therefore, there is an urgent need for an intelligent marine inspection method to improve the inspection efficiency. Summary of the Invention

[0004] This application provides a marine grid inspection method, device, equipment and medium based on GIS information to improve the inspection efficiency.

[0005] In the first aspect, this application provides a marine grid inspection method based on GIS information, including: Dividing the inspection area into a number of initial inspection grids based on the obtained target patch data; Obtaining the image data of the inspection area, and optimizing each of the initial inspection grids based on the image data to obtain a number of target inspection grids; Monitoring the target inspection grids. If there are abnormal grids among the target inspection grids, determining the abnormal types corresponding to each of the abnormal grids, automatically generating a number of candidate inspection paths based on the abnormal types and the abnormal grids, determining the target inspection path based on the real-time obtained inspection data, and inspecting each of the abnormal grids according to the target inspection path.

[0006] In the embodiments of the present application, by dividing the inspection area into several initial inspection grids, the inspection area can be decomposed into initial inspection grids that are easier to manage; by obtaining the image data of the inspection area, the area information of the inspection area can be understood in more detail. By optimizing the initial inspection grids, target inspection grids that more accurately reflect the actual situation of the inspection area can be obtained, facilitating the subsequent rapid discovery of abnormal information in each target inspection grid; by monitoring the target inspection grids, it can be accurately determined whether there are abnormal grids in the target inspection grids, and then corresponding candidate inspection paths can be quickly generated; based on the inspection data obtained in real time to determine the target inspection path, the inspection path can be continuously adjusted in real time based on the inspection data obtained in real time to obtain the target inspection path and perform inspections according to the target inspection path, and the abnormal grids can be inspected quickly and accurately. Compared with the prior art, the present application can improve the inspection efficiency.

[0007] Further, the dividing the inspection area into several initial inspection grids based on the obtained target patch data is specifically as follows: Input the shoreline data and the first patch data into a geographic information system to determine the corresponding target patch data; Eliminate the second patch data that does not meet the conditions in the target patch data according to a preset elimination rule to obtain the third patch data, and determine the inspection area based on the third patch data, and sequentially perform grid division on the inspection area according to a preset division rule to obtain the initial inspection grids; wherein, the second patch data is an area where personnel cannot reach or cannot perform effective inspections, and the preset division rule includes a division direction and a grid size.

[0008] In this way, by dividing the inspection area into several initial inspection grids, the inspection area can be decomposed into initial inspection grids that are easier to manage.

[0009] Further, the optimizing each of the initial inspection grids based on the image data to obtain several target inspection grids is specifically as follows: Compare the image data with the initial inspection grids to obtain a comparison result, and determine the reachable area and the obstacle area based on the comparison result; Judge whether each of the target inspection grids exists in the reachable area or the obstacle area. If each of the target inspection grids does not exist in the reachable area or each of the target inspection grids exists in the obstacle area, then update each of the target inspection grids based on the reachable area or the obstacle area.

[0010] In this way, by obtaining the image data of the inspection area, the area information of the inspection area can be understood in more detail. By optimizing the initial inspection grid, a target inspection grid that can more accurately reflect the actual situation of the inspection area can be obtained, which is convenient for quickly discovering the abnormal information of each target inspection grid subsequently.

[0011] Further, when monitoring the target inspection grid, if there are abnormal grids in the target inspection grid, determine the abnormal types corresponding to each of the abnormal grids, specifically: Obtain the sensor data and historical inspection records in each of the target inspection grids, and input the sensor data and the historical inspection records into a pre-trained anomaly detection model to determine the abnormal grids and the abnormal types corresponding to each of the abnormal grids.

[0012] In this way, by monitoring the target inspection grid, it can be accurately judged whether there are abnormal grids and the abnormal types in the target inspection grid, which is convenient for the subsequent generation of candidate inspection paths.

[0013] Further, automatically generating a number of candidate inspection paths based on the abnormal types and the abnormal grids, specifically: Determine the inspection importance levels corresponding to each of the abnormal grids based on each of the abnormal types; Automatically generate a number of candidate inspection paths to reach each of the abnormal grids in the order of the inspection importance levels.

[0014] In this way, by determining the inspection importance levels corresponding to each of the abnormal grids, the corresponding candidate inspection paths can be quickly generated according to the inspection importance levels.

[0015] Further, determining the target inspection path based on the inspection data obtained in real time, specifically: Obtain the inspection data of the abnormal grids in real time, and determine the inspection difficulty levels of each of the abnormal grids based on the inspection data; Sort each of the abnormal grids according to the inspection difficulty levels to obtain a sorting result, and determine the target inspection path from the candidate inspection paths based on the sorting result.

[0016] In this way, determining the target inspection path based on the inspection data obtained in real time can continuously adjust the inspection path based on the inspection data obtained in real time to obtain the target inspection path, which is convenient for quickly and accurately inspecting the abnormal grids subsequently.

[0017] Further, the marine grid-based inspection method based on GIS information further includes: updating each target inspection grid based on the sensor data and the inspection data.

[0018] In this way, by updating each target inspection grid, the target inspection grid can be continuously corrected and adjusted, ensuring that a target inspection grid that more accurately reflects the actual situation of the inspection area can be obtained.

[0019] In a second aspect, the present application provides an ocean grid-based inspection device based on GIS information, including: an acquisition module, an optimization module, and an inspection module; The acquisition module is used to divide the inspection area into a number of initial inspection grids based on the acquired target patch data; The optimization module is used to acquire the image data of the inspection area and optimize each of the initial inspection grids based on the image data to obtain a number of target inspection grids; The inspection module is used to monitor the target inspection grids. If there are abnormal grids among the target inspection grids, determine the abnormal types corresponding to each of the abnormal grids, automatically generate a number of candidate inspection paths based on the abnormal types and the abnormal grids, determine the target inspection path based on the real-time acquired inspection data, and inspect each of the abnormal grids according to the target inspection path.

[0020] In the embodiment of the present application, by dividing the inspection area into a number of initial inspection grids, the inspection area can be decomposed into more manageable initial inspection grids; by acquiring the image data of the inspection area, the regional information of the inspection area can be understood in more detail. By optimizing the initial inspection grids, target inspection grids that more accurately reflect the actual situation of the inspection area can be obtained, facilitating the subsequent rapid discovery of abnormal information in each target inspection grid; by monitoring the target inspection grids, it can be accurately determined whether there are abnormal grids in the target inspection grids, and then corresponding candidate inspection paths can be quickly generated; determining the target inspection path based on the real-time acquired inspection data can continuously adjust the inspection path based on the real-time acquired inspection data in real time to obtain the target inspection path and perform inspections according to the target inspection path, enabling rapid and accurate inspection of the abnormal grids. Compared with the prior art, the present application can improve the inspection efficiency.

[0021] In a third aspect, the present application further provides a terminal device, including: one or more processors; a memory coupled to the processor for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the ocean grid-based inspection method based on GIS information as described in the present application.

[0022] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the ocean grid-based inspection method based on GIS information as described in the present application. Description of the Drawings

[0023] Figure 1 It is a schematic flowchart of an embodiment of the method for ocean grid inspection based on GIS information provided by this application; Figure 2 It is a schematic structural diagram of an embodiment of the ocean grid inspection device based on GIS information provided by this application; Figure 3 It is a schematic structural diagram of an embodiment of the terminal device provided by this application. Detailed implementation manners

[0024] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of this application.

[0025] It should be understood that the step numbers used in the text are only for convenient description and do not limit the execution order of the steps.

[0026] It should be understood that the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0027] The terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0028] The term " / and / " refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0029] With the rapid development of the marine economy, the development of sea areas and islands is frequent. The supervision of sea areas and islands can standardize the development and utilization behaviors of sea areas and islands and promptly discover and warn of marine disasters, thereby reducing the losses caused by disasters. Currently, technologies such as satellite remote sensing, unmanned aerial vehicles, manual inspections, and buoys are relied on to inspect the ocean, but these technologies have disadvantages such as low frequency of data acquisition, limited quality, high cost, low efficiency, and difficulty in adapting to changes in the marine environment in a timely manner, and cannot achieve dynamic supervision of sea areas and islands. Therefore, there is an urgent need for an intelligent inspection method to improve efficiency.

[0030] Next, the nouns involved in this application will be analyzed: GIS is short for Geographic Information System, and its Chinese name is Geographic Information System. It is a technical system that collects, stores, manages, calculates, analyzes, displays, and describes geographical distribution data in the space of the entire or part of the earth's surface (including the atmosphere) with the support of computer software and hardware systems. It combines geography, cartography, remote sensing, and computer science and has been widely applied in different fields. It is a computer system used to input, store, query, analyze, and display geographical data.

[0031] Based on this, the embodiments of the present application provide a marine grid inspection method, device, equipment, and medium based on GIS information, which can improve the inspection efficiency.

[0032] The marine grid inspection method, device, equipment, and medium based on GIS information provided by the embodiments of the present application will be specifically described through the following embodiments. First, the marine grid inspection method based on GIS information in the embodiments of the present application will be described.

[0033] The marine grid inspection method based on GIS information provided by the embodiments of the present application relates to the field of intelligent inspection. The marine grid inspection method based on GIS information provided by the embodiments of the present application can be applied to a terminal, a server, or software running on a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements a marine grid inspection method based on GIS information, etc., but is not limited to the above forms.

[0034] This application can also be used in numerous general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0035] Embodiment 1 Please refer to Figure 1 , Figure 1 , which is a schematic flowchart of an embodiment of the ocean grid inspection method based on GIS information provided by this application, including steps S101 to S103; Step S101: Divide the inspection area into several initial inspection grids based on the obtained target patch data; In some embodiments, dividing the inspection area into several initial inspection grids based on the obtained target patch data includes: inputting shoreline data and first patch data into a geographic information system to determine the corresponding target patch data; eliminating second patch data that does not meet the conditions in the target patch data according to a preset elimination rule to obtain third patch data, determining the inspection area based on the third patch data, and sequentially performing grid division on the inspection area according to a preset division rule to obtain initial inspection grids; where the second patch data is an area where personnel cannot reach or cannot effectively conduct inspections, and the preset division rule includes a division direction and a grid size. Specifically, first, obtain shoreline data and the land use map patch data of the third national land survey, that is, the first patch data, from websites or materials, and then input the shoreline data and the first patch data into a geographic information system, and use the spatial selection function of GIS to select the target patch data located on the seaward side of the shoreline according to the shoreline data; secondly, according to the preset elimination rule, eliminate the second patch data that does not meet the conditions from the target patch data, leaving the third patch data that meets the conditions, and summarize and merge the spatial ranges of the third patch data to form an inspection area. Finally, according to the preset division rule (including the division direction, grid size, etc.), perform grid division on the inspection area to obtain initial inspection grids.

[0036] It should be noted that the second patch data refers to areas where personnel cannot reach or effectively conduct inspections due to terrain, environmental, or policy restrictions, such as shrub swamps, river water surfaces, mangrove forests, etc.

[0037] It should be noted that the preset elimination rules are formulated based on on-site inspections and historical inspection data to ensure the accessibility and practicality of the inspection area. The preset elimination rules include the division direction and grid size. Among them, the division direction is determined based on geographical features (such as the coastline trend) or administrative boundaries, and the grid size is determined according to inspection requirements (such as personnel allocation, equipment coverage, etc.).

[0038] In some embodiments, the spatial ranges of the third patch data are summarized and merged to form an inspection area. Specifically: starting from the shoreline data, a buffer zone with a preset distance is generated towards the land side; at the same time, starting from the land-sea boundary line after eliminating inaccessible areas, a buffer zone with a preset distance is also generated towards the sea side. Then, the above two buffer zones are merged with the area between the shoreline and the land-sea boundary line to form the inspection area.

[0039] It should be noted that the inspection area includes a marine inspection area and a land inspection area. Among them, the marine inspection area is an area formed by extending a certain distance towards the sea and towards the land with the shoreline data as the midline. Then, the marine inspection area can be removed from the inspection area to obtain the land inspection area.

[0040] It should be noted that if there are patches in the marine inspection area that are small and discontinuous, or patches that are distributed in a long and narrow strip along the shoreline, then these patches are merged with the land inspection area and no separate grids are set. If the area of the marine inspection area is large and continuous, separate grids need to be set.

[0041] It should be noted that the division direction is determined based on geographical features (such as the coastline trend) or administrative boundaries. Generally, grid division is carried out along the shoreline data based on administrative boundaries, and the grid size is determined according to inspection requirements (such as personnel allocation, equipment coverage, etc.). For land inspection grids, it is necessary to ensure that the shoreline length corresponding to each grid is about 4 - 6 kilometers. For marine grids, according to the size and continuity of the marine inspection area, ensure that the area of each grid is about 40 - 60 hectares. For patches in the marine inspection area that are small and discontinuous or distributed in a long and narrow strip, they can be considered to be merged with land grids.

[0042] It should be noted that when dividing the initial inspection grids, singularities and frayed edges need to be eliminated.

[0043] In this way, by dividing the inspection area into several initial inspection grids, the inspection area can be decomposed into more manageable initial inspection grids.

[0044] Step S102: Obtain the image data of the inspection area, and optimize each of the initial inspection grids based on the image data to obtain a number of target inspection grids; In some embodiments, obtaining the image data of the inspection area specifically includes: obtaining the image data of the inspection area through technologies such as satellite remote sensing images or unmanned aerial vehicle (UAV) aerial images, so as to understand in more detail information such as terrain, landform, and building distribution, and ensure that the grids accurately reflect the actual situation on the ground.

[0045] In some embodiments, optimizing each of the initial inspection grids based on the image data to obtain a number of target inspection grids includes: comparing the image data with the initial inspection grids to obtain a comparison result, and determining an accessible area and an obstacle area based on the comparison result; judging whether each of the target inspection grids exists in the accessible area or the obstacle area. If the accessible area does not exist in each of the target inspection grids or the obstacle area exists in each of the target inspection grids, then update each of the target inspection grids based on the accessible area or the obstacle area. Specifically: First, perform a spatial comparison between the image data obtained in real time and the initial inspection grids to obtain a comparison result, and clearly divide the actual accessible area and the obstacle area based on the comparison result; Second, compare the determined accessible area and obstacle area with the target inspection grids to judge whether these areas are correctly included in the grids or excluded from the grids. If the accessible area is not correctly included in the target inspection grids, or the obstacle area is wrongly included, then it is necessary to adjust and optimize the initial inspection grids based on the actual distribution of the accessible area and the obstacle area to obtain the target inspection grids, so as to ensure that the target inspection grids can accurately reflect the actual situation on the ground.

[0046] It should be noted that the actual accessible area is an area without obstacles and easy to pass through, and the obstacle area is an area with obstacles such as vegetation cover, water bodies, and buildings.

[0047] It should be noted that the comparison methods include but are not limited to pixel-level analysis, texture feature extraction, and semantic segmentation techniques to identify obstacle areas (such as vegetation-covered areas, water bodies, etc.) and accessible areas in the images.

[0048] In this way, by obtaining the image data of the inspection area, the area information of the inspection area can be understood in more detail. By optimizing the initial inspection grids, target inspection grids that can more accurately reflect the actual situation of the inspection area can be obtained, which is convenient for quickly discovering abnormal information in each of the target inspection grids subsequently.

[0049] Step S103: Monitor the target inspection grid. If there are abnormal grids in the target inspection grid, determine the abnormal types corresponding to each abnormal grid, automatically generate several candidate inspection paths based on the abnormal types and the abnormal grids, determine the target inspection path based on the real-time obtained inspection data, and inspect each abnormal grid according to the target inspection path.

[0050] In some embodiments, when monitoring the target inspection grid, if there are abnormal grids in the target inspection grid, determining the abnormal types corresponding to each abnormal grid includes: obtaining the sensor data and historical inspection records in each target inspection grid, and inputting the sensor data and the historical inspection records into a pre-trained anomaly detection model to determine the abnormal grids and the abnormal types corresponding to each abnormal grid. Specifically, first, collect real-time inspection data from each target inspection grid through sensors, monitoring devices, inspection personnel's handheld terminals, etc., and at the same time obtain past historical inspection records, and input the sensor data and the historical inspection records into a pre-trained anomaly detection model. Through the anomaly detection model, abnormal networks can be identified, and the abnormal type corresponding to each abnormal network can be determined.

[0051] It should be noted that the anomaly detection model uses a convolutional neural network (CNN) in deep learning and is trained with historical inspection data and sensor data to be able to automatically identify abnormal types, such as pollution, equipment failure, etc.

[0052] In this way, by monitoring the target inspection grid, it can be accurately judged whether there are abnormal grids and their abnormal types in the target inspection grid, which is convenient for the subsequent generation of candidate inspection paths.

[0053] In some embodiments, automatically generating several candidate inspection paths based on the abnormal types and the abnormal grids includes: determining the inspection importance level corresponding to each abnormal grid based on each abnormal type; automatically generating several candidate inspection paths to reach each abnormal grid in the order of the inspection importance level. Specifically, first, after determining the abnormal types corresponding to each abnormal grid, it is necessary to analyze the abnormal types, understand in detail the impact of each abnormal type on the abnormal grid, and assign an inspection importance level to each abnormal grid according to the degree of impact; secondly, according to the inspection importance level, sort all abnormal grids to obtain a sorting result to ensure that high-priority abnormal grids are accessed first in the inspection path, and through a path planning algorithm (such as Dijkstra algorithm, A* algorithm, etc.) or heuristic method, generate multiple candidate inspection paths that can cover all abnormal grids according to the sorted grid order.

[0054] It should be noted that the inspection importance level may be a numerical value (such as levels 1 - 5, where level 1 represents the highest importance) or a descriptive label (such as urgent, high, medium, low).

[0055] It should be noted that path planning also needs to consider factors such as the spatial relationship, connectivity, and obstacles between abnormal grids.

[0056] In this way, by determining the inspection importance level corresponding to each abnormal grid, a corresponding candidate inspection path can be quickly generated according to the inspection importance level.

[0057] It should be noted that for the inspection importance level, each abnormal grid will be graded according to different colors.

[0058] In some embodiments, determining the target inspection path based on the real - time obtained inspection data includes: obtaining the inspection data of the abnormal grid in real - time, and determining the inspection difficulty level of each abnormal grid based on the inspection data; sorting each abnormal grid according to the inspection difficulty level to obtain a sorting result, and determining the target inspection path from the candidate inspection paths based on the sorting result. Specifically, after determining the candidate inspection path, it is necessary to collect the inspection data of the abnormal grid in real - time, determine an inspection difficulty level for each abnormal grid according to these inspection data, sort the candidate inspection paths according to the inspection difficulty level to obtain a sorting result, and select the optimal or a path that meets specific criteria in the sorting result as the target inspection path.

[0059] It should be noted that the inspection difficulty level may be affected by various factors such as weather, traffic, personnel availability, and inspection speed. When these factors change, it is necessary to make a real - time judgment to determine whether the target inspection path needs to be adjusted.

[0060] It should be noted that the inspection difficulty level is to obtain the inspection data of the abnormal grid in real - time during the inspection process, that is, to judge the road conditions in the current inspection grid, whether there are areas that are difficult to reach due to non - human factors, etc., to further determine the inspection difficulty level.

[0061] In this way, determining the target inspection path based on the real - time obtained inspection data can continuously adjust the inspection path in real - time based on the real - time obtained inspection data to obtain the target inspection path, which is convenient for subsequent quick and accurate inspection of the abnormal grid.

[0062] In some embodiments, the abnormal grids are inspected according to the target inspection path. Specifically, the target inspection path is packaged into a task and sent to the inspection personnel, inspection system or inspection machine to execute the inspection task according to the target inspection path. During the inspection process, the inspection data is continuously recorded and uploaded. At the same time, the unreachable areas and difficult inspection areas in the abnormal grids are analyzed according to the target inspection path, and the target inspection path is adaptively adjusted based on these factors. Among them, the task includes a detailed description of the abnormality, location coordinates, and specific inspections and measures to be carried out.

[0063] In some embodiments, each target inspection grid is updated based on the sensor data and the inspection data. Specifically, each target inspection grid is verified one by one according to the latest remotely sensed image obtained in real time, the existing shoreline condition data, the sensor data, and the inspection data. When the target inspection grid does not match the actual situation, targeted adjustments need to be made to the inspection scope and the target inspection grid. The specific adjustments include deleting unreachable areas and supplementing the un-covered areas in the inspection area.

[0064] It should be noted that the target inspection grid can be updated within a preset cycle range. The shorelines with significant changes within a certain time range are regularly screened, and the inspection scope of the grid is corrected and adjusted according to the shoreline change situation. Generally speaking, the update iteration frequency of this item is relatively high in the early stage of grid distribution (updated once a quarter or half a quarter in the early stage), and the update frequency gradually decreases as the inspection scope of the grid tends to be stable.

[0065] In this way, by updating each target inspection grid, the target inspection grid can be continuously corrected and adjusted, and a target inspection grid that can more accurately reflect the actual situation of the inspection area can be obtained.

[0066] In the embodiment of the present application, by dividing the inspection area into several initial inspection grids, the inspection area can be decomposed into more manageable initial inspection grids; by obtaining the image data of the inspection area, the area information of the inspection area can be understood in more detail. By optimizing the initial inspection grid, a target inspection grid that can more accurately reflect the actual situation of the inspection area can be obtained, which is convenient for quickly discovering the abnormal information of each target inspection grid in the future; by monitoring the target inspection grid, it can be accurately judged whether there are abnormal grids in the target inspection grid, and then a corresponding candidate inspection path can be quickly generated; based on the inspection data obtained in real time to determine the target inspection path, the inspection path can be continuously adjusted in real time based on the inspection data obtained in real time to obtain the target inspection path and perform inspections according to the target inspection path, and the abnormal grids can be inspected quickly and accurately. Compared with the prior art, the present application can improve the inspection efficiency.

[0067] Embodiment 2 Please refer toFigure 2 , Figure 2 is a schematic structural diagram of an embodiment of the marine grid inspection device based on GIS information provided by this application, including: an acquisition module 100, an optimization module 200, and an inspection module 300; The acquisition module 100 is configured to divide the inspection area into a plurality of initial inspection grids based on the acquired target patch data; The optimization module 200 is configured to acquire the image data of the inspection area and optimize each of the initial inspection grids based on the image data to obtain a plurality of target inspection grids; The inspection module 300 is configured to monitor the target inspection grids. If there are abnormal grids among the target inspection grids, determine the abnormal types corresponding to each of the abnormal grids, automatically generate a plurality of candidate inspection paths based on the abnormal types and the abnormal grids, determine the target inspection path based on the real-time acquired inspection data, and inspect each of the abnormal grids according to the target inspection path.

[0068] Regarding the information interaction, execution process, etc. among the modules in the above-mentioned marine grid inspection device based on GIS information, since it is based on the same concept as the embodiment of the marine grid inspection method based on GIS information in the first aspect of the present invention, the achieved technical effects are basically the same. For specific content, reference can be made to the description in Embodiment 1 of the method of the present invention, and details will not be repeated here.

[0069] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separated, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the method of this embodiment.

[0070] Please refer to Figure 3 , Figure 3 which shows the hardware structure of a terminal device in an embodiment. The terminal device includes: A processor 301, which can be implemented in a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided by the embodiments of this application; The memory 302 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 302 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 302, and the processor 301 is used to call and execute the large model-based conversation risk assessment method of the embodiments of this application; The input / output interface 303 is used to implement information input and output; The communication interface 304 is used to implement communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or through wireless means (such as mobile network, WIFI, Bluetooth, etc.); The bus 305 transmits information between various components of the device (such as the processor 301, the memory 302, the input / output interface 303, and the communication interface 304); Among them, the processor 301, the memory 302, the input / output interface 303, and the communication interface 304 achieve communication connections with each other inside the device through the bus 305.

[0071] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the GIS information-based ocean grid inspection method as described in the first embodiment above.

[0072] Those of ordinary skill in the art can understand that all or part of the processes in implementing the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0073] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of this application. It should be understood that the above are only specific embodiments of this application and are not used to limit the protection scope of this application.

[0074] It is particularly pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this application shall be included in the protection scope of this application.

Claims

1. A marine grid inspection method based on GIS information, characterized in that: include: The inspection area is divided into a number of initial inspection grids based on the acquired target pattern data; Acquire image data of the inspection area, and optimize each of the initial inspection grids based on the image data to obtain a plurality of target inspection grids; The target inspection grid is monitored. If there are abnormal grids in the target inspection grid, the abnormal type corresponding to each abnormal grid is determined, and a number of candidate inspection paths are automatically generated based on the abnormal type and the abnormal grid. The target inspection path is determined based on the inspection data obtained in real time, and each abnormal grid is inspected according to the target inspection path.

2. The marine grid inspection method based on GIS information according to claim 1 is characterized in that: The inspection area is divided into a number of initial inspection grids based on the acquired target spot data, specifically: Inputting the shoreline data and the first spot data into a geographic information system to determine corresponding target spot data; According to the preset elimination rules, the second spot data that does not meet the conditions in the target spot data are eliminated to obtain the third spot data, and the inspection area is determined based on the third spot data, and the inspection area is grid-divided in turn according to the preset division rules to obtain the initial inspection grid; wherein, the second spot data is an area that personnel cannot reach or cannot conduct effective inspections, and the preset division rules include division direction and grid size.

3. The marine grid inspection method based on GIS information according to claim 1 is characterized in that: The initial inspection grids are optimized based on the image data to obtain a plurality of target inspection grids, specifically: Comparing the image data with the initial inspection grid to obtain a comparison result, and determining a reachable area and an obstacle area based on the comparison result; Determine whether the reachable area or the obstacle area exists in each of the target inspection grids; if the reachable area does not exist in each of the target inspection grids or the obstacle area exists in each of the target inspection grids, update each of the target inspection grids based on the reachable area or the obstacle area.

4. The marine grid inspection method based on GIS information according to claim 1 is characterized in that: The target inspection grid is monitored, and if there are abnormal grids in the target inspection grid, the abnormal type corresponding to each abnormal grid is determined, specifically: The sensor data and historical inspection records in each of the target inspection grids are acquired, and the sensor data and the historical inspection records are input into a pre-trained anomaly detection model to determine the abnormal grids and the anomaly types corresponding to each of the abnormal grids.

5. The marine grid inspection method based on GIS information according to claim 4 is characterized in that: The automatic generation of a plurality of candidate inspection paths based on the abnormal type and the abnormal grid is specifically as follows: Determine the inspection importance level corresponding to each abnormal grid based on each abnormal type; A plurality of candidate inspection paths to each of the abnormal grids are automatically generated in the order of the inspection importance levels.

6. The marine grid inspection method based on GIS information according to claim 5 is characterized in that: The target inspection path is determined based on the inspection data obtained in real time, specifically: Acquire inspection data of abnormal grids in real time, and determine the inspection difficulty level of each abnormal grid based on the inspection data; The abnormal grids are sorted according to the inspection difficulty level to obtain a sorting result, and a target inspection path is determined from the candidate inspection paths based on the sorting result.

7. The marine grid inspection method based on GIS information according to claim 6 is characterized in that: Also includes: Each target inspection grid is updated based on the sensor data and the inspection data.

8. A marine grid inspection device based on GIS information, characterized in that: include: Acquisition module, optimization module and inspection module; The acquisition module is used to divide the inspection area into a plurality of initial inspection grids based on the acquired target spot data; The optimization module is used to obtain image data of the inspection area, and optimize each of the initial inspection grids based on the image data to obtain a plurality of target inspection grids; The inspection module is used to monitor the target inspection grid. If there are abnormal grids in the target inspection grid, the abnormal type corresponding to each abnormal grid is determined, and a number of candidate inspection paths are automatically generated based on the abnormal type and the abnormal grid. The target inspection path is determined based on the inspection data obtained in real time, and each abnormal grid is inspected according to the target inspection path.

9. A terminal device, characterized in that: include: one or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the marine grid inspection method based on GIS information as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the marine grid inspection method based on GIS information as described in any one of claims 1 to 7 is implemented.

Images