Enterprise geographical range identification method and device, equipment and storage medium

Abstract

The invention discloses an enterprise geographical range identification method and device, equipment and a storage medium. The method comprises the following steps: acquiring the latitude and longitude of a to-be-identified enterprise, a remote sensing image, and the picture boundary latitude and longitude and picture boundary pixel coordinates of the remote sensing image; inputting the remote sensing image into a trained image segmentation network model to obtain enterprise boundary pixel coordinates; according to the picture boundary latitude and longitude and the picture boundary pixel coordinates of the remote sensing image, converting the enterprise boundary pixel coordinates into enterprise boundary latitude and longitude; obtaining a to-be-optimized enterprise boundary fence according to the enterprise boundary longitude and latitude and the longitude and latitude of the to-be-identified enterprise; and segmenting the to-be-optimized enterprise boundary fence based on the route information to obtain an enterprise geographical range. According to the application, a satellite remote sensing image map is used, and a deep neural network is adopted to accurately identify geographical ranges of factories and enterprises, so that vehicle behaviors and factory operation conditions are judged and analyzed.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for identifying the geographical scope of an enterprise. Background Art

[0002] With the rapid development of the logistics industry, there are more and more factories, logistics parks and other enterprises. Accurately obtaining enterprise boundary information and effectively identifying vehicles entering and leaving the factory are crucial to judging vehicle behavior and factory operations.

[0003] In the related technologies, most of the existing technologies for generating enterprise geographic spatial scope are generated by aggregation based on geographic grids. This method easily divides different enterprises into one range, resulting in large errors, thereby reducing the accuracy of enterprise geographic spatial scope. Summary of the invention

[0004] The embodiments of the present application provide a method, apparatus, device and storage medium for identifying the geographic scope of an enterprise, so as to at least solve the technical problem of low accuracy in the division of the geographic scope of an enterprise in the related art.

[0005] According to one aspect of an embodiment of the present application, a method for identifying a geographical scope of an enterprise is provided, comprising:

[0006] Obtaining the longitude and latitude of the enterprise to be identified, the remote sensing image, and the longitude and latitude of the image boundary and the pixel coordinates of the image boundary of the remote sensing image;

[0007] Inputting the remote sensing image into a trained image segmentation network model to obtain the pixel coordinates of the enterprise boundary;

[0008] According to the picture boundary longitude and latitude of the remote sensing image and the picture boundary pixel coordinates, converting the enterprise boundary pixel coordinates into the enterprise boundary longitude and latitude;

[0009] Obtaining the enterprise boundary fence to be optimized according to the enterprise boundary longitude and latitude and longitude and the enterprise to be identified;

[0010] The boundary fence of the enterprise to be optimized is segmented based on the route information to obtain the geographical scope of the enterprise.

[0011] In an optional embodiment, converting the enterprise boundary pixel coordinates into the enterprise boundary longitude and latitude according to the picture boundary longitude and latitude of the remote sensing image and the picture boundary pixel coordinates includes:

[0012] According to the longitude and latitude of the image boundary and the pixel coordinates of the image boundary of the remote sensing image, the pixel coordinates of the enterprise boundary are converted into the longitude and latitude of the enterprise boundary by using the Mercator coordinate mapping formula.

[0013] In an optional embodiment, obtaining the enterprise boundary fence to be optimized according to the enterprise boundary longitude and latitude and longitude and latitude and longitude of the enterprise to be identified includes:

[0014] According to the longitude and latitude of the enterprise boundary and the longitude and latitude of the enterprise to be identified, determining whether the polygon corresponding to the output longitude and latitude of the enterprise boundary contains the enterprise to be identified;

[0015] If included, the polygon corresponding to the longitude and latitude of the enterprise boundary is used as a candidate enterprise geo-fence;

[0016] From the candidate enterprise geo-fences, select the fence with the highest model confidence as the enterprise boundary fence to be optimized.

[0017] In an optional embodiment, the enterprise boundary fence to be optimized is segmented based on route information to obtain the enterprise geographic scope, including:

[0018] Acquire a route database and select a route that intersects with the boundary fence of the enterprise to be optimized;

[0019] Traversing the intersecting routes, and using the routes to segment the boundary fence of the enterprise to be optimized;

[0020] The enterprise boundary fence to be optimized after the route is divided is used as the enterprise geographical scope; wherein, if the route divides the enterprise boundary fence to be optimized into two parts, the part containing the longitude and latitude of the enterprise to be identified is used as the enterprise boundary fence to be optimized.

[0021] In an optional embodiment, before inputting the remote sensing image into the trained image segmentation network model, the method further includes:

[0022] Acquire a plurality of remote sensing images, and draw polygonal boundaries of the enterprise in the remote sensing images;

[0023] Obtaining the longitude and latitude of the image boundary, the pixel coordinates of the image boundary, and the longitude and latitude of the enterprise boundary of the remote sensing image;

[0024] Calculate the pixel coordinates of the enterprise boundary using the Mercator coordinate mapping formula according to the longitude and latitude of the image boundary, the pixel coordinates of the image boundary and the longitude and latitude of the enterprise boundary;

[0025] A sample data set is constructed based on the remote sensing image and the pixel coordinates of the enterprise boundaries in the image.

[0026] In an optional embodiment, after constructing the sample data set, the method further includes:

[0027] Dividing the sample data set into a training set and a test set according to a preset ratio;

[0028] Using the training set to train the Detectron2 deep neural network model to obtain a pre-trained neural network model;

[0029] Inputting the test set into the pre-trained neural network model to obtain predicted enterprise polygon boundaries;

[0030] The average intersection-and-union ratio between the predicted enterprise polygon boundary and the enterprise actual polygon boundary is used as an evaluation index;

[0031] Based on the evaluation index, a neural network model with the best performance is selected as the image segmentation network model.

[0032] In an optional embodiment, the intersection-to-union ratio is obtained according to the ratio of the intersection and the union of the predicted enterprise polygon boundary and the actual enterprise polygon boundary;

[0033] The average of the intersection-and-union ratios of all data in the test set is taken to obtain the average intersection-and-union ratio.

[0034] According to another aspect of an embodiment of the present application, a device for identifying a geographical range of an enterprise is provided, comprising:

[0035] An acquisition module, used to acquire the longitude and latitude of the enterprise to be identified, a remote sensing image, and the longitude and latitude of the image boundary and the pixel coordinates of the image boundary of the remote sensing image;

[0036] A prediction module, used for inputting the remote sensing image into a trained image segmentation network model to obtain the pixel coordinates of the enterprise boundary;

[0037] A conversion module, used for converting the enterprise boundary pixel coordinates into enterprise boundary longitude and latitude according to the picture boundary longitude and latitude of the remote sensing image and the picture boundary pixel coordinates;

[0038] An identification module, used to obtain the enterprise boundary fence to be optimized according to the longitude and latitude of the enterprise boundary and the longitude and latitude of the enterprise to be identified;

[0039] The optimization module is used to segment the boundary fence of the enterprise to be optimized based on the route information to obtain the geographical scope of the enterprise.

[0040] According to another aspect of an embodiment of the present application, there is also provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the above-mentioned method for identifying the geographic scope of an enterprise through the computer program.

[0041] According to another aspect of the embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned enterprise geographic scope identification method when running.

[0042] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0043] The enterprise geographic scope recognition method provided in the embodiment of the present application is based on satellite remote sensing images and uses a deep neural network model to recognize the enterprise geographic scope boundary in the image, and uses routes to segment and optimize the identified fences, thereby obtaining a division result that is more in line with the actual situation and has a higher accuracy rate. The division accuracy and efficiency of the enterprise boundary are greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0045] Figure 1 is a flow chart of an optional method for identifying the geographic scope of an enterprise according to an embodiment of the present application;

[0046] Figure 2 is a schematic diagram of a model training method according to an embodiment of the present application;

[0047] Figure 3 is a schematic diagram of a method for identifying the geographic scope of an enterprise according to an embodiment of the present application;

[0048] Figure 4 is a schematic diagram of a remote sensing image after marking according to an embodiment of the present application;

[0049] Figure 5 is a schematic diagram of an enterprise geographical scope identified according to an embodiment of the present application;

[0050] Figure 6 is another schematic diagram of the geographical scope of an enterprise identified according to an embodiment of the present application;

[0051] Figure 7 is a schematic diagram of a device for identifying the geographical scope of an enterprise according to an embodiment of the present application;

[0052] Figure 8 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0054] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0055] The following is combined with Figure 1 The method for identifying the geographical scope of an enterprise in the embodiment of the present application is described in detail. Figure 1 As shown, the method mainly includes the following steps:

[0056] S101 obtains the longitude and latitude of the enterprise to be identified, the remote sensing image, and the longitude and latitude of the image boundary of the remote sensing image, and the pixel coordinates of the image boundary.

[0057] Remote sensing images are images of the earth's surface or other celestial bodies' surfaces acquired through remote sensing technology, which usually uses sensors carried by aircraft, satellites or other aircraft to capture images.

[0058] Specifically, when identifying the boundaries of enterprises in unknown areas, obtain the map remote sensing image, obtain the longitude and latitude of the enterprise to be identified, and use the marking tool to call the map service interface to save the remote sensing image and the longitude and latitude of the image boundary and the pixel coordinates of the image boundary.

[0059] Figure 4 is a schematic diagram of a marked remote sensing image according to an embodiment of the present application, such as Figure 4 As shown, the enterprise boundaries are marked in the picture using a marking tool.

[0060] S102 inputs the remote sensing image into the trained image segmentation network model to obtain the pixel coordinates of the enterprise boundary.

[0061] In one embodiment, the method further includes training an image segmentation network model.

[0062] Specifically, firstly, a training data set is constructed, multiple remote sensing images are obtained, and polygonal boundaries of enterprises are drawn in the remote sensing images.

[0063] Among them, an enterprise boundary marking system based on a third-party map service platform is built. Using this system, the polygonal boundary of the enterprise at the specified location can be manually drawn against the background of satellite remote sensing images. The interface provided by the map service is used to save the map image screenshot, as well as the longitude and latitude of the image boundary, the pixel coordinates of the image boundary, and the longitude and latitude of the manually drawn enterprise polygonal boundary.

[0064] Furthermore, the longitude and latitude of the image boundary, the pixel coordinates of the image boundary and the longitude and latitude of the enterprise boundary of the remote sensing image are obtained; based on the longitude and latitude of the image boundary, the pixel coordinates of the image boundary and the longitude and latitude of the enterprise boundary, the Mercator coordinate mapping formula is used to calculate the pixel coordinates of the enterprise boundary.

[0065] Furthermore, a certain batch of satellite remote sensing images is generated by manual labeling. According to the remote sensing images and the pixel coordinates of enterprise boundaries in the images, the pixel coordinates of enterprise boundaries are used as label data to construct a sample data set.

[0066] In an optional embodiment, after constructing the sample data set, the method further includes: dividing the sample data set into a training set and a test set according to a preset ratio.

[0067] In an exemplary scenario, the sample data set is divided into multiple training sets and test sets in a ratio of 4:1. The specific division method is not specifically limited in this application and can be set according to actual conditions.

[0068] Furthermore, the training set is used to train the Detectron2 deep neural network model to obtain a pre-trained neural network model.

[0069] The solution of this application adopts the Detectron2 deep neural network model, which is a deep learning framework for computer vision tasks, supporting bounding box detection, instance segmentation, semantic segmentation, and human key point detection, etc. It has higher accuracy than traditional CV recognition algorithms or deep learning recognition algorithms using UNET networks.

[0070] In an optional embodiment, an attention mechanism may be added to the Detectron2 deep neural network model to improve the performance of the model.

[0071] Specifically, the Detectron2 deep neural network model includes a backbone network, a feature pyramid network (FPN), a region proposal network (RPN), and a region of interest (ROI) head. Backbone network: Detectron2 supports a variety of backbone networks, such as ResNet, ResNeXt, etc., for feature extraction. Feature pyramid network (FPN): FPN is used to build multi-scale feature representations, which is very useful for detecting objects of different sizes. Region proposal network (RPN): RPN is used to generate candidate regions, which may contain target objects. ROI head: For each candidate region, the ROI head is responsible for further classification and bounding box regression. Add an attention module at the end of the backbone network or at each stage of the feature pyramid network to enhance feature representation. Modify the build_model function according to the added attention module to ensure that the new attention mechanism is included when the model is built.

[0072] Furthermore, the test set is input into the pre-trained neural network model to obtain the predicted enterprise polygonal boundary; the average intersection ratio of the predicted enterprise polygonal boundary and the actual enterprise polygonal boundary is used as an evaluation indicator.

[0073] In an optional embodiment, the intersection-and-union ratio is obtained based on the ratio of the intersection and union of the predicted enterprise polygon boundary and the actual enterprise polygon boundary; the intersection-and-union ratio can be obtained based on the ratio of the intersection and union of the two polygon areas, and then the intersection-and-union ratios of all data on the test set are averaged to obtain an average intersection-and-union ratio. The higher the average intersection-and-union ratio, the more similar the predicted enterprise polygon boundary is to the actual enterprise polygon boundary, and the better the prediction effect of the model.

[0074] Furthermore, based on the evaluation indicators, the neural network model with the best performance is selected as the image segmentation network model.

[0075] Figure 2 Schematic diagram of a model training method according to an embodiment of the present application. Figure 2 As shown, the training method of the image segmentation network model includes:

[0076] Build a marking tool that can save satellite images, satellite image boundary longitude and latitude, satellite image boundary pixel coordinates, and marked enterprise boundary longitude and latitude. Generate a certain batch of data through manual marking.

[0077] Through the longitude and latitude of the satellite image boundary, the pixel coordinates of the satellite image boundary and the longitude and latitude of the marked enterprise boundary, the enterprise longitude and latitude boundary polygon is converted into the enterprise polygon pixels in the image through the Mercator coordinate system mapping formula.

[0078] Furthermore, the satellite image is used as feature data, and the enterprise boundary pixel data in the image is used as label data to establish a sample data set. The sample data set is divided into multiple training sets and test sets in a ratio of 4:1.

[0079] Traverse the training set, use the Detectron2 deep neural network model to model and train the training set, and use the average intersection-over-union ratio of the predicted boundary and the actual boundary output by the model in the test set as the prediction indicator. Adjust the model parameters, train multiple times, and use the model with the best evaluation index as the application model to obtain a trained image segmentation model.

[0080] Input the image to be identified into the trained image segmentation network model to obtain the pixel coordinates of the enterprise boundary in the image.

[0081] S103 converts the enterprise boundary pixel coordinates into the enterprise boundary longitude and latitude according to the image boundary longitude and latitude of the remote sensing image and the image boundary pixel coordinates.

[0082] In an optional embodiment, the enterprise boundary pixel coordinates are converted into the enterprise boundary longitude and latitude according to the picture boundary longitude and latitude of the remote sensing image and the picture boundary pixel coordinates, including: according to the picture boundary longitude and latitude of the remote sensing image and the picture boundary pixel coordinates, the enterprise boundary pixel coordinates are converted into the enterprise boundary longitude and latitude using the Mercator coordinate mapping formula.

[0083] S104 obtains the enterprise boundary fence to be optimized according to the longitude and latitude of the enterprise boundary and the longitude and latitude of the enterprise to be identified.

[0084] In an optional embodiment, the enterprise boundary fence to be optimized is obtained according to the longitude and latitude of the enterprise boundary and the longitude and latitude of the enterprise to be identified, including: judging whether the polygon corresponding to the longitude and latitude of the enterprise boundary output contains the enterprise to be identified according to the longitude and latitude of the enterprise boundary and the longitude and latitude of the enterprise to be identified. That is, judging whether the converted longitude and latitude polygon contains the longitude and latitude of the enterprise to be predicted. If it does, the polygon corresponding to the longitude and latitude of the enterprise boundary is used as a candidate enterprise geo-fence. From the candidate enterprise geo-fences, the fence with the highest model confidence is selected as the enterprise boundary fence to be optimized.

[0085] S105 divides the boundary fence of the enterprise to be optimized based on the route information to obtain the geographical scope of the enterprise.

[0086] In an optional embodiment, the enterprise boundary fence to be optimized is segmented based on the route information to obtain the enterprise geographic scope, including: obtaining a route database, selecting a route that intersects with the enterprise boundary fence to be optimized; traversing the intersecting routes, and using the routes to segment the enterprise boundary fence to be optimized; using the enterprise boundary fence to be optimized after the route segmentation as the enterprise geographic scope; wherein, if the route segments the enterprise boundary fence to be optimized into two parts, the part containing the longitude and latitude of the enterprise to be identified is used as the enterprise boundary fence to be optimized. By performing route segmentation, the identified boundary can be made more consistent with the actual situation.

[0087] Figure 5 is a schematic diagram of an enterprise geographical scope identified according to an embodiment of the present application; Figure 6 is another schematic diagram of the enterprise geographical scope identified according to an embodiment of the present application; Figure 5 and 6 As shown, by adopting this technical solution, the scope boundaries of a large number of enterprises can be identified.

[0088] In order to facilitate understanding of the solution of the embodiment of the present application, Figure 3 Further description, Figure 3 is a schematic diagram of a method for identifying the geographic scope of an enterprise according to an embodiment of the present application, such as Figure 3 As shown, including:

[0089] Record the longitude and latitude of the POI to be predicted, that is, record the longitude and latitude of the enterprise to be predicted, and save the map image and the longitude and latitude data of the image boundary through the marking tool. Use the model to predict the pixel coordinates of the enterprise boundary in the image.

[0090] Furthermore, the pixel coordinates are converted to longitude and latitude coordinates by using the latitude and longitude and Mercator coordinate mapping formula, and it is determined whether the converted longitude and latitude polygon contains the longitude and latitude of the POI (enterprise) to be predicted. If it does, the boundary polygon is used as a candidate enterprise geo-fence. From the candidate enterprise geo-fences, the fence with the highest model confidence is selected as the enterprise boundary fence to be optimized.

[0091] Further, a route intersecting with the enterprise boundary fence to be optimized is selected from the route database; the intersecting route is traversed to determine whether the route can divide the enterprise boundary fence to be optimized into two parts, and if it can be divided into two parts, the part containing the longitude and latitude of the enterprise to be identified is used as the enterprise boundary fence to be optimized. The route is continued to be traversed, and the enterprise boundary fence to be optimized after the route is divided is used as the enterprise geographical scope.

[0092] According to the method of the present application, a neural network model can be used to automatically divide the geographical boundaries of an enterprise, which is not only highly accurate but also efficient, and is convenient for subsequent analysis of vehicle entry and exit conditions.

[0093] According to another aspect of the embodiment of the present application, there is also provided a device for identifying the geographic scope of an enterprise for implementing the above-mentioned method for identifying the geographic scope of an enterprise. Figure 7 As shown, the device comprises:

[0094] The acquisition module 701 is used to acquire the longitude and latitude of the enterprise to be identified, the remote sensing image, and the longitude and latitude of the image boundary of the remote sensing image, and the pixel coordinates of the image boundary;

[0095] Prediction module 702, used to input the remote sensing image into the trained image segmentation network model to obtain the pixel coordinates of the enterprise boundary;

[0096] The conversion module 703 is used to convert the enterprise boundary pixel coordinates into the enterprise boundary longitude and latitude according to the image boundary longitude and latitude of the remote sensing image and the image boundary pixel coordinates;

[0097] An identification module 704 is used to obtain the enterprise boundary fence to be optimized according to the longitude and latitude of the enterprise boundary and the longitude and latitude of the enterprise to be identified;

[0098] The optimization module 705 is used to segment the boundary fence of the enterprise to be optimized based on the route information to obtain the geographical scope of the enterprise.

[0099] It should be noted that the enterprise geographic scope identification device provided in the above embodiment only uses the division of the above functional modules as an example when executing the enterprise geographic scope identification method. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the enterprise geographic scope identification device provided in the above embodiment and the enterprise geographic scope identification method embodiment belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

[0100] According to another aspect of the embodiments of the present application, an electronic device corresponding to the enterprise geographic scope identification method provided in the above embodiments is also provided to execute the above enterprise geographic scope identification method.

[0101] Please refer to Figure 8 , which shows a schematic diagram of an electronic device provided by some embodiments of the present application. Figure 8 As shown, the electronic device includes: a processor 800, a memory 801, a bus 802 and a communication interface 803, and the processor 800, the communication interface 803 and the memory 801 are connected via the bus 802; the memory 801 stores a computer program that can be run on the processor 800, and when the processor 800 runs the computer program, it executes the enterprise geographic scope identification method provided in any of the aforementioned embodiments of the present application.

[0102] The memory 801 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 803 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0103] The bus 802 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 801 is used to store programs, and the processor 800 executes the programs after receiving the execution instructions. The method for identifying the geographic scope of an enterprise disclosed in any implementation of the embodiment of the present application may be applied to the processor 800, or implemented by the processor 800.

[0104] The processor 800 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 800. The above processor 800 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 801, and the processor 800 reads the information in the memory 801 and completes the steps of the above method in combination with its hardware.

[0105] The electronic device provided in the embodiment of the present application and the method for identifying the geographical scope of an enterprise provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0106] According to another aspect of the embodiments of the present application, a computer-readable storage medium corresponding to the method for identifying the geographic scope of an enterprise provided in the aforementioned embodiments is also provided, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it will execute the method for identifying the geographic scope of an enterprise provided in any of the aforementioned embodiments.

[0107] It should be noted that examples of computer-readable storage media may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0108] The computer-readable storage medium provided by the above-mentioned embodiments of the present application and the method for identifying the enterprise geographic scope provided by the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0109] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0110] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the attached claims.

Claims

1. A method for identifying the geographical scope of an enterprise, characterized in that: include: Obtaining the longitude and latitude of the enterprise to be identified, the remote sensing image, and the longitude and latitude of the image boundary and the pixel coordinates of the image boundary of the remote sensing image; Inputting the remote sensing image into a trained image segmentation network model to obtain the pixel coordinates of the enterprise boundary; According to the picture boundary longitude and latitude of the remote sensing image and the picture boundary pixel coordinates, converting the enterprise boundary pixel coordinates into the enterprise boundary longitude and latitude; Obtaining the enterprise boundary fence to be optimized according to the enterprise boundary longitude and latitude and longitude and the enterprise to be identified; The boundary fence of the enterprise to be optimized is segmented based on the route information to obtain the geographical scope of the enterprise.

2. The method according to claim 1, characterized in that: According to the longitude and latitude of the image boundary and the pixel coordinates of the image boundary of the remote sensing image, the pixel coordinates of the enterprise boundary are converted into the longitude and latitude of the enterprise boundary, including: According to the longitude and latitude of the image boundary and the pixel coordinates of the image boundary of the remote sensing image, the pixel coordinates of the enterprise boundary are converted into the longitude and latitude of the enterprise boundary by using the Mercator coordinate mapping formula.

3. The method according to claim 1, characterized in that According to the longitude and latitude of the enterprise boundary and the longitude and latitude of the enterprise to be identified, the enterprise boundary fence to be optimized is obtained, including: According to the longitude and latitude of the enterprise boundary and the longitude and latitude of the enterprise to be identified, determining whether the polygon corresponding to the output longitude and latitude of the enterprise boundary contains the enterprise to be identified; If included, the polygon corresponding to the longitude and latitude of the enterprise boundary is used as a candidate enterprise geo-fence; From the candidate enterprise geo-fences, select the fence with the highest model confidence as the enterprise boundary fence to be optimized.

4. The method according to claim 1, characterized in that: The enterprise boundary fence to be optimized is segmented based on the route information to obtain the enterprise geographic scope, including: Acquire a route database and select a route that intersects with the boundary fence of the enterprise to be optimized; Traversing the intersecting routes, and using the routes to segment the boundary fence of the enterprise to be optimized; The enterprise boundary fence to be optimized after the route is divided is used as the enterprise geographical scope; wherein, if the route divides the enterprise boundary fence to be optimized into two parts, the part containing the longitude and latitude of the enterprise to be identified is used as the enterprise boundary fence to be optimized.

5. The method according to claim 1, characterized in that Before inputting the remote sensing image into the trained image segmentation network model, the method further includes: Acquire a plurality of remote sensing images, and draw polygonal boundaries of the enterprise in the remote sensing images; Obtaining the longitude and latitude of the image boundary, the pixel coordinates of the image boundary, and the longitude and latitude of the enterprise boundary of the remote sensing image; Calculate the pixel coordinates of the enterprise boundary using the Mercator coordinate mapping formula according to the longitude and latitude of the image boundary, the pixel coordinates of the image boundary and the longitude and latitude of the enterprise boundary; A sample data set is constructed based on the remote sensing image and the pixel coordinates of the enterprise boundaries in the image.

6. The method according to claim 5, characterized in that After building the sample dataset, it also includes: Dividing the sample data set into a training set and a test set according to a preset ratio; Using the training set to train the Detectron2 deep neural network model to obtain a pre-trained neural network model; Inputting the test set into the pre-trained neural network model to obtain predicted enterprise polygon boundaries; The average intersection-and-union ratio between the predicted enterprise polygon boundary and the enterprise actual polygon boundary is used as an evaluation index; Based on the evaluation index, a neural network model with the best performance is selected as the image segmentation network model.

7. The method according to claim 6, characterized in that Obtaining an intersection-to-union ratio according to a ratio of an intersection and a union between the predicted enterprise polygon boundary and the actual enterprise polygon boundary; The average of the intersection-and-union ratios of all data in the test set is taken to obtain the average intersection-and-union ratio.

8. A device for identifying the geographical scope of an enterprise, characterized in that: include: An acquisition module, used to acquire the longitude and latitude of the enterprise to be identified, a remote sensing image, and the longitude and latitude of the image boundary and the pixel coordinates of the image boundary of the remote sensing image; A prediction module, used for inputting the remote sensing image into a trained image segmentation network model to obtain the pixel coordinates of the enterprise boundary; A conversion module, used for converting the enterprise boundary pixel coordinates into enterprise boundary longitude and latitude according to the picture boundary longitude and latitude of the remote sensing image and the picture boundary pixel coordinates; An identification module, used to obtain the enterprise boundary fence to be optimized according to the longitude and latitude of the enterprise boundary and the longitude and latitude of the enterprise to be identified; The optimization module is used to segment the boundary fence of the enterprise to be optimized based on the route information to obtain the geographical scope of the enterprise.

9. An electronic device, characterized in that: The system comprises a processor and a memory storing program instructions, wherein the processor is configured to execute the method for identifying the geographical scope of an enterprise as claimed in any one of claims 1 to 7 when executing the program instructions.

10. A computer-readable medium, characterized in that Computer-readable instructions are stored thereon, and the computer-readable instructions are executed by a processor to implement a method for identifying the geographical scope of an enterprise as described in any one of claims 1 to 7.

Images