CN111818557B - Network coverage problem identification method, device and system - Google Patents

Network coverage problem identification method, device and system Download PDF

Info

Publication number
CN111818557B
CN111818557B CN202010770729.2A CN202010770729A CN111818557B CN 111818557 B CN111818557 B CN 111818557B CN 202010770729 A CN202010770729 A CN 202010770729A CN 111818557 B CN111818557 B CN 111818557B
Authority
CN
China
Prior art keywords
image
boundary information
map
network
neural network
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010770729.2A
Other languages
Chinese (zh)
Other versions
CN111818557A (en
Inventor
赵伟
曾伟
许绍松
王科
陈乐�
何国华
刘宏嘉
杨汉源
李巍
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China United Network Communications Group Co Ltd
Original Assignee
China United Network Communications Group Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China United Network Communications Group Co Ltd filed Critical China United Network Communications Group Co Ltd
Priority to CN202010770729.2A priority Critical patent/CN111818557B/en
Publication of CN111818557A publication Critical patent/CN111818557A/en
Application granted granted Critical
Publication of CN111818557B publication Critical patent/CN111818557B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W24/00Supervisory, monitoring or testing arrangements
    • H04W24/02Arrangements for optimising operational condition
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The embodiment of the invention provides a method, a device and a system for identifying network coverage problems, wherein the method comprises the following steps: acquiring internet map data, wherein the internet map data comprises an image to be processed; preprocessing the image to be processed; acquiring map interest Point (POI) boundary information in the preprocessed image and boundary information of mountains and water areas such as mountains, rivers and lakes on the basis of a neural network; and fitting and displaying the boundary information of the POI, the boundary information of the mountain and the water area and the network quality index information of each MDT sampling point on a rasterized electronic map, thereby obtaining a network coverage problem identification result and further improving the effectiveness and the accuracy of network coverage problem identification.

Description

网络覆盖问题识别方法、装置及系统Network coverage problem identification method, device and system

技术领域technical field

本发明实施例涉及通信技术领域,尤其涉及一种网络覆盖问题识别方法、装置及系统。Embodiments of the present invention relate to the field of communication technologies, and in particular, to a method, device and system for identifying network coverage problems.

背景技术Background technique

随着通讯技术的发展以及大数据的应用,当前针对网络的覆盖评估,已从小区级KPI、MR指标评估扩展至地理化、栅格化评估,结合场景的电子边框可准确评估场景的网络覆盖情况以及覆盖问题所在的具体位置,对网络建设及优化具有重要的指导作用。但在实际的无线环境中存在着大量山体与水域。这些区域中,大部分人迹罕至或为无人区,并不需要移动网络覆盖。With the development of communication technology and the application of big data, the current network coverage assessment has expanded from community-level KPI and MR index assessment to geographic and grid assessment. Combined with the electronic border of the scene, the network coverage of the scene can be accurately evaluated The situation and the specific location of the coverage problem play an important guiding role in network construction and optimization. But there are a lot of mountains and waters in the actual wireless environment. Most of these areas are inaccessible or uninhabited and do not require mobile network coverage.

相关技术中,常用的网络覆盖评估指标为有效栅格占比和良好栅格占比。其中,有效栅格占比指有MR采样点的栅格面积与场景面积之比;良好栅格是指良好栅格覆盖面积与场景面积之比。比如,根据某地区统计数据,该地区山地和丘陵占74.63%,平坦地占20.32%,河流和湖泊占5.05%。相较平原地区,如果不剔除该地区的山体与水域的面积,将无法体现该地区内各场景的真实网络覆盖情况。In related technologies, commonly used evaluation indicators for network coverage are the proportion of effective grids and the proportion of good grids. Among them, the effective grid ratio refers to the ratio of the grid area with MR sampling points to the scene area; the good grid refers to the ratio of the good grid coverage area to the scene area. For example, according to the statistics of a certain area, mountains and hills account for 74.63%, flat land accounts for 20.32%, and rivers and lakes account for 5.05%. Compared with plain areas, if the area of mountains and waters in this area is not excluded, it will not be able to reflect the real network coverage of each scene in this area.

目前对网络覆盖问题的测试方式不够完善,存在对网络覆盖问题的测试的有效性和准确性较低的技术问题。At present, the test method for the network coverage problem is not perfect, and there is a technical problem that the validity and accuracy of the test for the network coverage problem are low.

发明内容Contents of the invention

本发明实施例提供一种网络覆盖问题识别方法、装置及系统,以克服对网络覆盖问题的测试的有效性和准确性较低的技术问题。Embodiments of the present invention provide a method, device and system for identifying network coverage problems, so as to overcome the technical problem of low effectiveness and accuracy in testing network coverage problems.

第一方面,本发明实施例提供一种网络覆盖问题识别方法,包括:In a first aspect, an embodiment of the present invention provides a method for identifying a network coverage problem, including:

获取互联网地图数据,所述互联网地图数据包括待处理图像;Obtain Internet map data, the Internet map data includes images to be processed;

对所述待处理图像进行预处理;Preprocessing the image to be processed;

将预处理后的图像输入预先建立的神经网络,得到所述待处理图像中的地图兴趣点POI边界信息、山体和水域的边界信息;Input the preprocessed image into a pre-established neural network to obtain the POI boundary information of the map point of interest in the image to be processed, the boundary information of mountains and waters;

将所述地图兴趣点POI边界信息、山体和水域的边界信息和每个最小化路测MDT采样点的网络质量指标信息在栅格化的电子地图上拟合显示,以呈现网络覆盖问题识别结果。Fitting and displaying the POI boundary information of the map interest point, the boundary information of mountains and waters, and the network quality index information of each minimum drive test MDT sampling point on the gridded electronic map to present the network coverage problem identification result .

可选的,所述待处理图像包括卫星地图图像;所述对所述待处理图像进行预处理,包括:Optionally, the image to be processed includes a satellite map image; the preprocessing of the image to be processed includes:

在所述卫星地图图像中确定预设数量个目标区域;determining a preset number of target areas in the satellite map image;

对所述目标区域中的山体和水域进行标注;Mark the mountains and waters in the target area;

将标注完成的卫星地图图像切分成预设尺寸的图片;Cut the marked satellite map image into pictures of preset size;

对切分之后的卫星地图图像进行基于灰度的均衡化处理。Perform grayscale-based equalization processing on the segmented satellite map image.

可选的,所述对切分之后的卫星地图图像进行基于灰度的均衡化处理,包括:Optionally, the grayscale-based equalization processing of the segmented satellite map image includes:

对所述切分之后的卫星地图图像中除了标注位置之外的区域进行基于灰度的均衡化处理。A grayscale-based equalization process is performed on the regions in the segmented satellite map image except for the marked position.

可选的,所述对切分之后的卫星地图图像进行基于灰度的均衡化处理,包括:Optionally, the grayscale-based equalization processing of the segmented satellite map image includes:

采用直方图均衡化处理的方式来对切分之后的卫星地图图像进行基于灰度的均衡化处理,或者,通过直接调节对比度和亮度指标的方式来对待处理图像进行基于灰度的均衡化处理。Use histogram equalization processing to perform grayscale-based equalization processing on the segmented satellite map image, or directly adjust the contrast and brightness indicators to perform grayscale-based equalization processing on the image to be processed.

可选的,所述神经网络包括第一神经网络和第二神经网络;所述将预处理后的图像输入预先建立的神经网络,得到所述待处理图像中的地图兴趣点POI边界信息、山体和水域的边界信息,包括:Optionally, the neural network includes a first neural network and a second neural network; the pre-processed image is input into the pre-established neural network to obtain the map interest point POI boundary information, the mountain body in the image to be processed and water boundary information, including:

将所述预处理后的图像输入所述第一神经网络,所述第一神经网络用于提取所述预处理后的图像中的图像边界信息;inputting the preprocessed image into the first neural network, and the first neural network is used to extract image boundary information in the preprocessed image;

将所述第一神经网络输出的图像边界信息输入所述第二神经网络,所述第二神经网络用于在所述图像边界信息中识别地图兴趣点POI边界信息、山体和水域的边界信息。The image boundary information output by the first neural network is input into the second neural network, and the second neural network is used to identify POI boundary information on the map, boundary information of mountains and waters in the image boundary information.

可选的,所述将所述地图兴趣点POI边界信息、山体和水域的边界信息和每个最小化路测MDT采样点的网络质量指标信息在栅格化的电子地图上拟合显示,以呈现网络覆盖问题识别结果,包括:Optionally, the POI boundary information of the map interest point, the boundary information of mountains and waters, and the network quality index information of each minimum drive test MDT sampling point are fitted and displayed on the gridded electronic map, so as to Presentation of network coverage problem identification results, including:

将所述地图兴趣点POI边界信息、山体和水域的边界信息结合每个采样点对应的用于表征网络质量的参数信息进行拟合,并在电子地图上进行全局呈现;Fitting the POI boundary information of the map interest point, the boundary information of mountains and waters in combination with the parameter information used to characterize the quality of the network corresponding to each sampling point, and performing global presentation on the electronic map;

所述全局呈现的结果包括各个区域的网络覆盖信息;The result presented globally includes network coverage information of each area;

剔除山体和水域所占的区域,根据所述网络覆盖信息确定有效栅格比和良好栅格占比;Eliminate the area occupied by mountains and waters, and determine the effective grid ratio and good grid ratio according to the network coverage information;

根据所述有效栅格比和良好栅格占比,识别网络覆盖的问题位置。According to the effective grid ratio and the proportion of good grids, the location of the network coverage problem is identified.

第二方面,本发明实施例提供一种网络覆盖问题识别装置,包括:In a second aspect, an embodiment of the present invention provides a network coverage problem identification device, including:

数据获取模块,用于获取互联网地图数据,所述互联网地图数据包括待处理图像;A data acquisition module, configured to acquire Internet map data, the Internet map data including images to be processed;

数据处理模块,用于对所述待处理图像进行预处理;A data processing module, configured to preprocess the image to be processed;

场景识别模块,用于将预处理后的图像输入预先建立的神经网络,得到所述待处理图像中的地图兴趣点POI边界信息、山体和水域的边界信息;The scene recognition module is used to input the pre-processed image into the pre-established neural network to obtain the POI boundary information of the map point of interest in the image to be processed, the boundary information of mountains and waters;

问题识别模块,用于将所述地图兴趣点POI边界信息、山体和水域的边界信息和每个最小化路测MDT采样点的网络质量指标信息在栅格化的电子地图上拟合显示,以呈现网络覆盖问题识别结果。The problem identification module is used to fit and display the POI boundary information of the map point of interest, the boundary information of mountains and waters, and the network quality index information of each minimum drive test MDT sampling point on the gridded electronic map, to Presents the network coverage problem identification results.

第三方面,本发明实施例提供一种网络覆盖问题识别系统,包括:In a third aspect, an embodiment of the present invention provides a network coverage problem identification system, including:

互联网地图数据收集子系统,用于获取互联网地图数据,所述互联网地图数据包括待处理图像;Internet map data collection subsystem, used to obtain Internet map data, the Internet map data includes images to be processed;

图像预处理子系统,用于对所述待处理图像进行预处理;An image preprocessing subsystem, configured to preprocess the image to be processed;

基于神经网络图像分割子系统,用于将预处理后的图像输入预先建立的神经网络,得到所述待处理图像中的地图兴趣点POI边界信息、山体和水域的边界信息;Based on the neural network image segmentation subsystem, it is used to input the preprocessed image into the pre-established neural network to obtain the POI boundary information of the map interest point in the image to be processed, the boundary information of mountains and waters;

网络覆盖呈现及评估子系统,用于将所述地图兴趣点POI边界信息、山体和水域的边界信息和每个最小化路测MDT采样点的网络质量指标信息在栅格化的电子地图上拟合显示,以呈现网络覆盖问题识别结果。The network coverage presentation and evaluation subsystem is used to simulate the POI boundary information of the map point of interest, the boundary information of mountains and waters, and the network quality index information of each minimum drive test MDT sampling point on the gridded electronic map. combined display to present the identification results of network coverage problems.

第四方面,本发明实施例提供一种电子设备,包括:至少一个处理器和存储器;In a fourth aspect, an embodiment of the present invention provides an electronic device, including: at least one processor and a memory;

所述存储器存储计算机执行指令;the memory stores computer-executable instructions;

所述至少一个处理器执行所述存储器存储的计算机执行指令,使得所述至少一个处理器执行如上第一方面以及第一方面各种可能的设计所述的网络覆盖问题识别方法。The at least one processor executes the computer-executed instructions stored in the memory, so that the at least one processor executes the network coverage problem identification method described in the above first aspect and various possible designs of the first aspect.

第四方面,本发明实施例提供一种计算机可读存储介质,所述计算机可读存储介质中存储有计算机执行指令,当处理器执行所述计算机执行指令时,实现如上第一方面以及第一方面各种可能的设计所述的网络覆盖问题识别方法。In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when the processor executes the computer-executable instructions, the above first aspect and the first Aspects of various possible designs of the described network coverage problem identification method.

本发明实施例提供的网络覆盖问题识别方法、装置及系统,该方法通过获取互联网地图数据,所述互联网地图数据包括待处理图像;然后对所述待处理图像进行预处理;然后基于神经网络获取预处理图像中的地图兴趣点POI边界信息,山川、河流、湖泊等山体和水域的边界信息;最后将所述地图兴趣点POI边界信息、山体和水域的边界信息和每个最小化路测MDT采样点的网络质量指标信息在栅格化的电子地图上拟合显示,从而得到网络覆盖问题识别结果,进而提高了网络覆盖问题识别的有效性和准确性。The network coverage problem identification method, device and system provided by the embodiments of the present invention, the method acquires Internet map data, the Internet map data includes images to be processed; then preprocesses the images to be processed; then obtains based on the neural network The POI boundary information of the map POI in the preprocessing image, the boundary information of mountains and waters such as mountains, rivers, and lakes; finally, the POI boundary information of the map, the boundary information of mountains and waters and each minimized drive test MDT The network quality index information of the sampling points is fitted and displayed on the gridded electronic map, so as to obtain the identification result of the network coverage problem, thereby improving the validity and accuracy of the identification of the network coverage problem.

附图说明Description of drawings

为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍,显而易见地,下面描述中的附图是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained according to these drawings without any creative effort.

图1为本发明一实施例提供的网络覆盖问题识别方法的流程示意图;FIG. 1 is a schematic flowchart of a network coverage problem identification method provided by an embodiment of the present invention;

图2为本发明另一实施例提供的网络覆盖问题识别方法的流程示意图;FIG. 2 is a schematic flowchart of a method for identifying network coverage problems provided by another embodiment of the present invention;

图3为本发明一实施例提供的区域边界提取示意图;FIG. 3 is a schematic diagram of region boundary extraction provided by an embodiment of the present invention;

图4为本发明另一实施例提供的区域边界提取示意图;FIG. 4 is a schematic diagram of region boundary extraction provided by another embodiment of the present invention;

图5为本发明一实施例提供的网络覆盖问题识别装置的结构示意图;FIG. 5 is a schematic structural diagram of a network coverage problem identification device provided by an embodiment of the present invention;

图6为本发明一实施例提供的网络覆盖问题识别系统的结构示意图;FIG. 6 is a schematic structural diagram of a network coverage problem identification system provided by an embodiment of the present invention;

图7为本发明实施例提供的电子设备的硬件结构示意图。FIG. 7 is a schematic diagram of a hardware structure of an electronic device provided by an embodiment of the present invention.

具体实施方式Detailed ways

为使本发明实施例的目的、技术方案和优点更加清楚,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

目前,随着通讯技术的发展以及大数据的应用,当前针对网络的覆盖评估,已从小区级KPI、MR指标评估扩展至地理化、栅格化评估,结合场景的电子边框可准确评估场景的网络覆盖情况以及覆盖问题所在的具体位置,对网络建设及优化具有重要的指导作用。但在实际的无线环境中存在着大量山体与水域。这些区域中,大部分人迹罕至或为无人区,并不需要移动网络覆盖。相关技术中,常用的网络覆盖评估指标为有效栅格占比和良好栅格占比。其中,有效栅格占比指有MR采样点的栅格面积与场景面积之比;良好栅格是指良好栅格覆盖面积与场景面积之比。比如,根据某地区统计数据,该地区山地和丘陵占74.63%,平坦地占20.32%,河流和湖泊占5.05%。相较平原地区,如果不剔除该地区的山体与水域的面积,将无法体现该地区内各场景的真实网络覆盖情况。目前对网络覆盖问题的测试方式不够完善,存在对网络覆盖问题的测试的有效性和准确性较低的技术问题。At present, with the development of communication technology and the application of big data, the current coverage evaluation for the network has been expanded from the evaluation of community-level KPI and MR indicators to the evaluation of geographic and grid evaluation. Combined with the electronic border of the scene, it can accurately evaluate the coverage of the scene. The network coverage and the specific location of the coverage problem play an important guiding role in network construction and optimization. But there are a lot of mountains and waters in the actual wireless environment. Most of these areas are inaccessible or uninhabited and do not require mobile network coverage. In related technologies, commonly used evaluation indicators for network coverage are the proportion of effective grids and the proportion of good grids. Among them, the effective grid ratio refers to the ratio of the grid area with MR sampling points to the scene area; the good grid refers to the ratio of the good grid coverage area to the scene area. For example, according to the statistics of a certain area, mountains and hills account for 74.63%, flat land accounts for 20.32%, and rivers and lakes account for 5.05%. Compared with plain areas, if the area of mountains and waters in this area is not excluded, it will not be able to reflect the real network coverage of each scene in this area. At present, the test method for the network coverage problem is not perfect, and there is a technical problem that the validity and accuracy of the test for the network coverage problem are low.

针对此缺陷,本申请提供的技术构思为:对指定区域进行网络覆盖评估时,获取互联网地图数据,对电子地图数据进行预处理,将预处理的待处理图像提供给神经网络,并经所述神经网络输出所述待处理图像的处理结果。进一步结合MDT栅格化数据完成地市级、场景级的有效栅格覆盖率、良好栅格覆盖率准确统计,用于指导规划建设与网络优化。In response to this defect, the technical idea provided by this application is: when evaluating the network coverage of a designated area, obtain Internet map data, preprocess the electronic map data, provide the preprocessed images to the neural network, and pass the The neural network outputs the processing result of the image to be processed. Further combine the MDT rasterized data to complete the accurate statistics of effective grid coverage and good grid coverage at the city level and scene level, which are used to guide planning and construction and network optimization.

图1为本发明一实施例提供的网络覆盖问题识别方法的流程示意图。FIG. 1 is a schematic flowchart of a method for identifying a network coverage problem provided by an embodiment of the present invention.

如图1所示,本实施例提供的方法可以包括以下步骤。As shown in FIG. 1 , the method provided in this embodiment may include the following steps.

S101,获取互联网地图数据,所述互联网地图数据包括待处理图像。S101. Acquire Internet map data, where the Internet map data includes images to be processed.

具体的,互联网地图数据包括地图的2D平面图、卫星图、3D俯视图和全景地图。还包括省市区边界数据、地图兴趣点(Point of Interest,POI)数据、POI电子边框数据以及地理分类数据。Specifically, the Internet map data includes a 2D plan view, a satellite image, a 3D top view and a panoramic map of the map. It also includes provincial and urban boundary data, map point of interest (Point of Interest, POI) data, POI electronic frame data, and geographic classification data.

S102,对所述待处理图像进行预处理。S102. Perform preprocessing on the image to be processed.

其中,待处理图像可以是互联网上分地市下载的卫星地图TIF格式的图像文件。Wherein, the image to be processed may be an image file in TIF format of a satellite map downloaded by cities on the Internet.

具体的,在图像中随机算去部分区域,使用标注软件LabelMe软件对区域内的山体和水域进行标注,然后将标注好的图像随机切分成256*256像素小尺寸图片。然后在对图像进行基于灰度的均衡化处理,最终得到预处理后的图像。Specifically, part of the area is randomly calculated in the image, and the labeling software LabelMe software is used to label the mountains and waters in the area, and then the marked image is randomly divided into small-sized pictures of 256*256 pixels. Then the image is equalized based on the gray level, and finally the preprocessed image is obtained.

需要说明的是,本步骤的具体实施过程将在后面实施例中进行详细描述。It should be noted that the specific implementation process of this step will be described in detail in the following embodiments.

S103,将预处理后的图像输入预先建立的神经网络,得到所述待处理图像中的地图兴趣点POI边界信息、山体和水域的边界信息。S103. Input the preprocessed image into the pre-established neural network to obtain boundary information of POIs on the map, boundary information of mountains and waters in the image to be processed.

其中,神经网络的网络结构可以但不限于采用全卷积网络FCN,U-Net、SegNet、DeepLab、RefineNet、Mask Rcnn等神经网络所采用的图像语义分割模型。Among them, the network structure of the neural network can be but not limited to the image semantic segmentation model adopted by the fully convolutional network FCN, U-Net, SegNet, DeepLab, RefineNet, Mask Rcnn and other neural networks.

具体的,神经网络可以包括第一神经网络和第二神经网络,第一神经网络用于提取所述预处理后的图像中的图像边界信息;第二神经网络用于在所述图像边界信息中识别地图兴趣点POI边界信息、山体和水域的边界信息。将所述预处理后的图像输入所述第一神经网络,所述第一神经网络输出预处理后的图像中的图像边界信息;将所述第一神经网络输出的图像边界信息输入所述第二神经网络,所述第二神经网络输出在图像边界信息中识别的地图兴趣点POI边界信息、山体和水域的边界信息。Specifically, the neural network may include a first neural network and a second neural network, the first neural network is used to extract the image boundary information in the preprocessed image; the second neural network is used to extract the image boundary information in the image boundary information Identify POI boundary information of map points of interest, boundary information of mountains and waters. Input the preprocessed image into the first neural network, and the first neural network outputs image boundary information in the preprocessed image; input the image boundary information output by the first neural network into the first neural network Two neural networks, the second neural network outputs the POI boundary information of the map identified in the image boundary information, the boundary information of mountains and waters.

本步骤中,经过神经网络处理后的图像如图3和图4所示。In this step, the image processed by the neural network is shown in Fig. 3 and Fig. 4 .

S104,将所述地图兴趣点POI边界信息、山体和水域的边界信息和每个最小化路测MDT采样点的网络质量指标信息在栅格化的电子地图上拟合显示,以呈现网络覆盖问题识别结果。S104, fitting and displaying the POI boundary information of the map interest point, the boundary information of mountains and waters, and the network quality index information of each minimum drive test MDT sampling point on the gridded electronic map, so as to present the network coverage problem Recognition results.

具体的,将所述地图兴趣点POI边界信息、山体和水域的边界信息结合每个采样点对应的用于表征网络质量的参数信息进行拟合,并在电子地图上进行全局呈现;所述全局呈现的结果包括各个区域的网络覆盖信息,比如,某条道路或者某个小区或者某个区县的网络覆盖情况;然后剔除山体和水域所占的区域,比如,山川、河流、湖泊等山体与水域所占的区域;根据所述网络覆盖信息确定有效栅格比(即,有MR采样点的栅格面积和场景面积之比)和良好栅格占比(即,良好栅格覆盖面积和场景面积之比);根据所述有效栅格比和良好栅格占比,识别网络覆盖的问题位置,以供后续进行网络优化或其它处理。Specifically, the POI boundary information of the map interest point, the boundary information of mountains and waters are combined with the parameter information corresponding to each sampling point for representing the quality of the network, and are globally presented on the electronic map; the global The presented results include the network coverage information of each area, for example, the network coverage of a certain road or a certain community or a certain district; then remove the area occupied by mountains and waters, such as mountains, rivers, lakes and other The area occupied by the water area; determine the effective grid ratio (that is, the ratio of the grid area with MR sampling points to the scene area) and the good grid ratio (that is, the good grid coverage area and the scene area) according to the network coverage information area ratio); according to the effective grid ratio and good grid ratio, identify the location of the network coverage problem for subsequent network optimization or other processing.

本实施例中,通过获取互联网地图数据,所述互联网地图数据包括待处理图像;然后对所述待处理图像进行预处理;然后基于神经网络获取预处理图像中的地图兴趣点POI边界信息,山川、河流、湖泊等山体和水域的边界信息;最后将所述地图兴趣点POI边界信息、山体和水域的边界信息和每个最小化路测MDT采样点的网络质量指标信息在栅格化的电子地图上拟合显示,从而得到网络覆盖问题识别结果,进而提高了网络覆盖问题识别的有效性和准确性。In this embodiment, by obtaining the Internet map data, the Internet map data includes the image to be processed; then the image to be processed is preprocessed; then the map POI boundary information in the preprocessed image is obtained based on the neural network, mountains and rivers , rivers, lakes and other mountain and water boundary information; finally, the POI boundary information of the map point of interest, the boundary information of mountains and waters, and the network quality index information of each minimum drive test MDT sampling point in the gridded electronic Fitting and displaying on the map, thereby obtaining the identification result of the network coverage problem, thereby improving the validity and accuracy of the identification of the network coverage problem.

图2为本发明另一实施例提供的网络覆盖问题识别方法的流程示意图,本实施例在图1所示实施例的基础上,对图像的预处理过程进一步详细描述。FIG. 2 is a schematic flowchart of a network coverage problem identification method provided by another embodiment of the present invention. This embodiment further describes the image preprocessing process in detail on the basis of the embodiment shown in FIG. 1 .

如图2所示,本实施例提供的方法可以包括以下步骤。As shown in FIG. 2, the method provided in this embodiment may include the following steps.

S201,在所述卫星地图图像中确定预设数量个目标区域。S201. Determine a preset number of target areas in the satellite map image.

具体的,互联网地图数据中包含省市区县边界数据、地图POI数据、POI电子边框数据,地理分类数据。根据这些数据,从互联网上分地市下载卫星地图TIF格式图像文件,在地图图像中随机选取一个区域,作为目标区域标注软件LabelMe软件对区域内的山体和水域进行标注,其中,目标区域的数量可随机设定。Specifically, the Internet map data includes provincial, city, county boundary data, map POI data, POI electronic frame data, and geographic classification data. According to these data, the satellite map TIF format image file is downloaded from the Internet by prefecture and city, and an area is randomly selected in the map image as the target area labeling software. Can be set randomly.

S202,对所述目标区域中的山体和水域进行标注。S202. Mark mountains and waters in the target area.

具体的,确定了目标区域后,使用标注软件LabelMe软件对区域内的山体和水域进行标注。Specifically, after determining the target area, use the labeling software LabelMe software to mark the mountains and waters in the area.

示例性的,可以通过边框将目标区域中的山脉、河流等山体和水域框选出来。Exemplarily, mountains and waters such as mountains and rivers in the target area may be selected by a frame.

S203,将标注完成的卫星地图图像切分成预设尺寸的图片。S203. Segment the marked satellite map image into pictures of a preset size.

其中,预设尺寸可以根据实际需求进行设定,比如,设置成256*256像素。Wherein, the preset size can be set according to actual needs, for example, set to 256*256 pixels.

具体的,将标注后的卫星地图图像,随机切分成256*256像素小尺寸图片。Specifically, the marked satellite map image is randomly divided into small-sized pictures of 256*256 pixels.

S204,对切分之后的卫星地图图像进行基于灰度的均衡化处理。S204. Perform grayscale-based equalization processing on the segmented satellite map image.

在一种可能的实施例中,所述对切分之后的卫星地图图像进行基于灰度的均衡化处理,包括:对所述切分之后的卫星地图图像中除了标注位置之外的区域进行基于灰度的均衡化处理。In a possible embodiment, the grayscale-based equalization processing of the segmented satellite map image includes: performing grayscale-based equalization processing on regions other than marked positions in the segmented satellite map image. Grayscale equalization.

具体的,针对标注好的图像随机切分成256*256像素小尺寸图片,进行基于灰度的均衡化处理,也可以对待处理图像的部分区域进行基于灰度的均衡化处理,例如,针对待处理图像中的除外标注边框之外的其他区域进行基于灰度的均衡化处理。Specifically, the marked image is randomly divided into small-sized images of 256*256 pixels, and equalization processing based on grayscale is performed, and partial areas of the image to be processed can also be equalized based on grayscale. For example, for the image to be processed Grayscale-based equalization is performed on other areas of the image except for the marked frame.

在一种可能的实施例中,所述对切分之后的卫星地图图像进行基于灰度的均衡化处理,包括:采用直方图均衡化处理的方式来对切分之后的卫星地图图像进行基于灰度的均衡化处理,或者,通过直接调节对比度和亮度指标的方式来对待处理图像进行基于灰度的均衡化处理。In a possible embodiment, the grayscale-based equalization processing on the segmented satellite map image includes: using histogram equalization processing to perform grayscale-based equalization processing on the segmented satellite map image. The equalization processing of brightness, or, by directly adjusting the contrast and brightness indicators, the image to be processed is equalized based on grayscale.

具体的,针对标注好的图像随机切分成256*256像素小尺寸图片,可以采用直方图均衡化处理的方式来对待处理图像进行基于灰度的均衡化处理,也可以采用其他方式来对待处理图像进行基于灰度的均衡化处理,例如,通过直接调节对比度和/亮度等指标的方式来对待处理图像进行基于灰度的均衡化处理。Specifically, the marked image is randomly divided into 256*256 pixel small-size pictures, and the histogram equalization processing method can be used to perform grayscale-based equalization processing on the image to be processed, or other methods can be used to process the image to be processed Perform grayscale-based equalization processing, for example, perform grayscale-based equalization processing on the image to be processed by directly adjusting indicators such as contrast and/or brightness.

进一步的,针对标注好的图像随机切分成256*256像素小尺寸图片,可以通过旋转、镜像、模糊、增加白噪声等处理来增加样本有效性。Further, the labeled image is randomly divided into small-sized images of 256*256 pixels, and the validity of the sample can be increased by processing such as rotation, mirroring, blurring, and adding white noise.

图5为本发明一实施例提供的网络覆盖问题识别装置的结构示意图。Fig. 5 is a schematic structural diagram of an apparatus for identifying a network coverage problem according to an embodiment of the present invention.

如图5所示,本实施例提供的装置包括:数据获取模块501,数据处理模块502,场景识别模块503和问题识别模块504;其中,数据获取模块,用于获取互联网地图数据,所述互联网地图数据包括待处理图像;数据处理模块,用于对所述待处理图像进行预处理;场景识别模块,用于将预处理后的图像输入预先建立的神经网络,得到所述待处理图像中的地图兴趣点POI边界信息、山体和水域的边界信息;问题识别模块,用于将所述地图兴趣点POI边界信息、山体和水域的边界信息和每个最小化路测MDT采样点的网络质量指标信息在栅格化的电子地图上拟合显示,以呈现网络覆盖问题识别结果。As shown in Figure 5, the device provided by this embodiment includes: a data acquisition module 501, a data processing module 502, a scene identification module 503 and a problem identification module 504; wherein, the data acquisition module is used to acquire Internet map data, and the Internet The map data includes an image to be processed; the data processing module is used to preprocess the image to be processed; the scene recognition module is used to input the preprocessed image into a pre-established neural network to obtain the Map interest point POI boundary information, boundary information of mountains and waters; problem identification module, for the network quality index of the map POI boundary information, mountains and waters boundary information and each minimum drive test MDT sampling point The information is fitted and displayed on a rasterized electronic map to present the identification results of network coverage problems.

进一步的,所述待处理图像包括卫星地图图像;所述数据处理模块具体用于:在所述卫星地图图像中确定预设数量个目标区域;对所述目标区域中的山体和水域进行标注;将标注完成的卫星地图图像切分成预设尺寸的图片;对切分之后的卫星地图图像进行基于灰度的均衡化处理。Further, the image to be processed includes a satellite map image; the data processing module is specifically used to: determine a preset number of target areas in the satellite map image; mark mountains and waters in the target area; Segment the marked satellite map image into images of a preset size; perform grayscale-based equalization processing on the segmented satellite map image.

进一步的,所述数据处理模块具体用于:对所述切分之后的卫星地图图像中除了标注位置之外的区域进行基于灰度的均衡化处理。Further, the data processing module is specifically configured to: perform grayscale-based equalization processing on regions in the segmented satellite map image except for marked positions.

进一步的,所述数据处理模块具体用于:采用直方图均衡化处理的方式来对切分之后的卫星地图图像进行基于灰度的均衡化处理,或者,通过直接调节对比度和亮度指标的方式来对待处理图像进行基于灰度的均衡化处理。Further, the data processing module is specifically used to: use histogram equalization processing to perform grayscale-based equalization processing on the segmented satellite map image, or directly adjust the contrast and brightness indicators. The image to be processed is equalized based on the gray level.

进一步的,所述神经网络包括第一神经网络和第二神经网络;所述场景识别模块具体用于:将所述预处理后的图像输入所述第一神经网络,所述第一神经网络用于提取所述预处理后的图像中的图像边界信息;将所述第一神经网络输出的图像边界信息输入所述第二神经网络,所述第二神经网络用于在所述图像边界信息中识别地图兴趣点POI边界信息、山体和水域的边界信息。Further, the neural network includes a first neural network and a second neural network; the scene recognition module is specifically configured to: input the preprocessed image into the first neural network, and the first neural network uses Extracting the image boundary information in the preprocessed image; inputting the image boundary information output by the first neural network into the second neural network, and the second neural network is used in the image boundary information Identify POI boundary information of map points of interest, boundary information of mountains and waters.

进一步的,所述问题识别模块具体用于:将所述地图兴趣点POI边界信息、山体和水域的边界信息结合每个采样点对应的用于表征网络质量的参数信息进行拟合,并在电子地图上进行全局呈现;所述全局呈现的结果包括各个区域的网络覆盖信息;剔除山体和水域所占的区域,根据所述网络覆盖信息确定有效栅格比和良好栅格占比;根据所述有效栅格比和良好栅格占比,识别网络覆盖的问题位置。Further, the problem identification module is specifically configured to: combine the POI boundary information of the map interest point, the boundary information of mountains and waters with the parameter information corresponding to each sampling point for characterizing the network quality, and perform the fitting in the electronic A global presentation is performed on the map; the results of the global presentation include network coverage information in each area; the area occupied by mountains and waters is eliminated, and the effective grid ratio and good grid ratio are determined according to the network coverage information; according to the Effective grid ratio and good grid ratio to identify problematic locations of network coverage.

本实施例提供的装置,可用于执行上述方法实施例的技术方案,其实现原理和技术效果类似,本实施例此处不再赘述。The device provided in this embodiment can be used to implement the technical solutions of the above method embodiments, and its implementation principle and technical effect are similar, so this embodiment will not repeat them here.

图6为本发明一实施例提供的网络覆盖问题识别系统的结构示意图,Fig. 6 is a schematic structural diagram of a network coverage problem identification system provided by an embodiment of the present invention,

如图6所示,本实施例提供的系统包括:互联网地图数据收集子系统601,图像预处理子系统602,基于神经网络图像分割子系统603和网络覆盖呈现及评估子系统604,其中,互联网地图数据收集子系统,用于获取互联网地图数据,所述互联网地图数据包括待处理图像;图像预处理子系统,用于对所述待处理图像进行预处理;基于神经网络图像分割子系统,用于将预处理后的图像输入预先建立的神经网络,得到所述待处理图像中的地图兴趣点POI边界信息、山体和水域的边界信息;网络覆盖呈现及评估子系统,用于将所述地图兴趣点POI边界信息、山体和水域的边界信息和每个最小化路测MDT采样点的网络质量指标信息在栅格化的电子地图上拟合显示,以呈现网络覆盖问题识别结果。As shown in Figure 6, the system provided by this embodiment includes: Internet map data collection subsystem 601, image preprocessing subsystem 602, neural network-based image segmentation subsystem 603 and network coverage presentation and evaluation subsystem 604, wherein the Internet The map data collection subsystem is used to obtain Internet map data, and the Internet map data includes images to be processed; the image preprocessing subsystem is used to preprocess the images to be processed; the neural network image segmentation subsystem is used to Input the preprocessed image into the pre-established neural network to obtain the POI boundary information of the map interest point in the image to be processed, the boundary information of mountains and waters; the network coverage presentation and evaluation subsystem is used to use the map Point of interest POI boundary information, mountain and water boundary information, and network quality index information of each minimum drive test MDT sampling point are fitted and displayed on the rasterized electronic map to present the identification results of network coverage problems.

进一步的,所述待处理图像包括卫星地图图像;所述图像预处理子系统具体用于:在所述卫星地图图像中确定预设数量个目标区域;对所述目标区域中的山体和水域进行标注;将标注完成的卫星地图图像切分成预设尺寸的图片;对切分之后的卫星地图图像进行基于灰度的均衡化处理。Further, the image to be processed includes a satellite map image; the image preprocessing subsystem is specifically used to: determine a preset number of target areas in the satellite map image; Labeling; segmenting the marked satellite map image into pictures of preset sizes; performing grayscale-based equalization processing on the segmented satellite map image.

进一步的,所述图像预处理子系统具体用于:对所述切分之后的卫星地图图像中除了标注位置之外的区域进行基于灰度的均衡化处理。Further, the image preprocessing subsystem is specifically configured to: perform grayscale-based equalization processing on regions other than marked positions in the segmented satellite map image.

进一步的,所述图像预处理子系统具体用于:采用直方图均衡化处理的方式来对切分之后的卫星地图图像进行基于灰度的均衡化处理,或者,通过直接调节对比度和亮度指标的方式来对待处理图像进行基于灰度的均衡化处理。Further, the image preprocessing subsystem is specifically used to: use histogram equalization processing to perform grayscale-based equalization processing on the segmented satellite map image, or directly adjust the contrast and brightness indicators The method is used to perform grayscale-based equalization processing on the image to be processed.

进一步的,所述神经网络包括第一神经网络和第二神经网络;所述基于神经网络图像分割子系统具体用于:将所述预处理后的图像输入所述第一神经网络,所述第一神经网络用于提取所述预处理后的图像中的图像边界信息;将所述第一神经网络输出的图像边界信息输入所述第二神经网络,所述第二神经网络用于在所述图像边界信息中识别地图兴趣点POI边界信息、山体和水域的边界信息。Further, the neural network includes a first neural network and a second neural network; the neural network-based image segmentation subsystem is specifically configured to: input the preprocessed image into the first neural network, and the second neural network A neural network is used to extract the image boundary information in the preprocessed image; the image boundary information output by the first neural network is input into the second neural network, and the second neural network is used in the In the image boundary information, identify the POI boundary information of the map interest point, the boundary information of mountains and waters.

进一步的,所述网络覆盖呈现及评估子系统具体用于:将所述地图兴趣点POI边界信息、山体和水域的边界信息结合每个采样点对应的用于表征网络质量的参数信息进行拟合,并在电子地图上进行全局呈现;所述全局呈现的结果包括各个区域的网络覆盖信息;剔除山体和水域所占的区域,根据所述网络覆盖信息确定有效栅格比和良好栅格占比;根据所述有效栅格比和良好栅格占比,识别网络覆盖的问题位置。Further, the network coverage presentation and evaluation subsystem is specifically used to: combine the POI boundary information of the map interest point, the boundary information of mountains and waters with the parameter information used to characterize the network quality corresponding to each sampling point for fitting , and perform a global presentation on the electronic map; the result of the global presentation includes network coverage information in each area; remove the area occupied by mountains and waters, and determine the effective grid ratio and good grid ratio according to the network coverage information ; According to the effective grid ratio and the proportion of good grids, identify the location of the network coverage problem.

本实施例提供的系统,可用于执行上述方法实施例的技术方案,其实现原理和技术效果类似,本实施例此处不再赘述。The system provided in this embodiment can be used to implement the technical solution of the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not repeat them here.

图7为本发明实施例提供的电子设备的硬件结构示意图。如图7所示,本实施例的电子设备70包括:处理器701以及存储器702;其中FIG. 7 is a schematic diagram of a hardware structure of an electronic device provided by an embodiment of the present invention. As shown in FIG. 7, the electronic device 70 of this embodiment includes: a processor 701 and a memory 702;

存储器702,用于存储计算机执行指令;memory 702, for storing computer-executable instructions;

处理器701,用于执行存储器存储的计算机执行指令,以实现上述实施例中网络覆盖问题识别方法所执行的各个步骤。具体可以参见前述方法实施例中的相关描述。The processor 701 is configured to execute the computer-executable instructions stored in the memory, so as to implement each step performed by the method for identifying a network coverage problem in the foregoing embodiments. For details, refer to the related descriptions in the foregoing method embodiments.

可选地,存储器702既可以是独立的,也可以跟处理器701集成在一起。Optionally, the memory 702 can be independent or integrated with the processor 701 .

当存储器702独立设置时,该电子设备还包括总线703,用于连接所述存储器702和处理器701。When the memory 702 is set independently, the electronic device further includes a bus 703 for connecting the memory 702 and the processor 701 .

本发明实施例还提供一种计算机可读存储介质,所述计算机可读存储介质中存储有计算机执行指令,当处理器执行所述计算机执行指令时,实现如上所述的网络覆盖问题识别方法。An embodiment of the present invention also provides a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when a processor executes the computer-executable instructions, the method for identifying a network coverage problem as described above is implemented.

在本发明所提供的几个实施例中,应该理解到,所揭露的设备和方法,可以通过其它的方式实现。例如,以上所描述的设备实施例仅仅是示意性的,例如,所述模块的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个模块可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或模块的间接耦合或通信连接,可以是电性,机械或其它的形式。In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods, for example, multiple modules can be combined or integrated. to another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or modules may be in electrical, mechanical or other forms.

所述作为分离部件说明的模块可以是或者也可以不是物理上分开的,作为模块显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案。The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the modules can be selected according to actual needs to implement the solution of this embodiment.

另外,在本发明各个实施例中的各功能模块可以集成在一个处理单元中,也可以是各个模块单独物理存在,也可以两个或两个以上模块集成在一个单元中。上述模块成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能单元的形式实现。In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, or each module may physically exist separately, or two or more modules may be integrated into one unit. The units formed by the above modules can be implemented in the form of hardware, or in the form of hardware plus software functional units.

上述以软件功能模块的形式实现的集成的模块,可以存储在一个计算机可读取存储介质中。上述软件功能模块存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)或处理器执行本申请各个实施例所述方法的部分步骤。The above-mentioned integrated modules implemented in the form of software function modules may be stored in a computer-readable storage medium. The above-mentioned software function modules are stored in a storage medium, and include several instructions to make a computer device (which may be a personal computer, server, or network device, etc.) or a processor execute some steps of the methods described in various embodiments of the present application.

应理解,上述处理器可以是中央处理单元(Central Processing Unit,简称CPU),还可以是其他通用处理器、数字信号处理器(Digital Signal Processor,简称DSP)、专用集成电路(Application Specific Integrated Circuit,简称ASIC)等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合发明所公开的方法的步骤可以直接体现为硬件处理器执行完成,或者用处理器中的硬件及软件模块组合执行完成。It should be understood that the above-mentioned processor may be a central processing unit (Central Processing Unit, referred to as CPU), and may also be other general-purpose processors, a digital signal processor (Digital Signal Processor, referred to as DSP), an application specific integrated circuit (Application Specific Integrated Circuit, referred to as ASIC) and so on. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, and the like. The steps of the method disclosed in conjunction with the invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.

存储器可能包含高速RAM存储器,也可能还包括非易失性存储NVM,例如至少一个磁盘存储器,还可以为U盘、移动硬盘、只读存储器、磁盘或光盘等。The storage may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk storage, and may also be a U disk, a mobile hard disk, a read-only memory, a magnetic disk, or an optical disk.

总线可以是工业标准体系结构(Industry Standard Architecture,简称ISA)总线、外部设备互连(Peripheral Component Interconnect,简称PCI)总线或扩展工业标准体系结构(Extended Industry Standard Architecture,简称EISA)总线等。总线可以分为地址总线、数据总线、控制总线等。为便于表示,本申请附图中的总线并不限定仅有一根总线或一种类型的总线。The bus may be an Industry Standard Architecture (Industry Standard Architecture, ISA for short) bus, a Peripheral Component Interconnect (PCI for short) bus, or an Extended Industry Standard Architecture (EISA for short) bus. The bus can be divided into address bus, data bus, control bus and so on. For ease of representation, the buses in the drawings of the present application are not limited to only one bus or one type of bus.

上述存储介质可以是由任何类型的易失性或非易失性存储设备或者它们的组合实现,如静态随机存取存储器(SRAM),电可擦除可编程只读存储器(EEPROM),可擦除可编程只读存储器(EPROM),可编程只读存储器(PROM),只读存储器(ROM),磁存储器,快闪存储器,磁盘或光盘。存储介质可以是通用或专用计算机能够存取的任何可用介质。The above-mentioned storage medium can be realized by any type of volatile or non-volatile storage device or their combination, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable In addition to programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.

一种示例性的存储介质耦合至处理器,从而使处理器能够从该存储介质读取信息,且可向该存储介质写入信息。当然,存储介质也可以是处理器的组成部分。处理器和存储介质可以位于专用集成电路(Application SpecificIntegrated Circuits,简称ASIC)中。当然,处理器和存储介质也可以作为分立组件存在于电子设备或主控设备中。An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may be located in application specific integrated circuits (Application Specific Integrated Circuits, ASIC for short). Of course, the processor and the storage medium can also exist in the electronic device or the main control device as discrete components.

本领域普通技术人员可以理解:实现上述各方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成。前述的程序可以存储于一计算机可读取存储介质中。该程序在执行时,执行包括上述各方法实施例的步骤;而前述的存储介质包括:ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by program instructions and related hardware. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above-mentioned method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other various media that can store program codes.

最后应说明的是:以上各实施例仅用以说明本发明的技术方案,而非对其限制;尽管参照前述各实施例对本发明进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分或者全部技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than limiting them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: It is still possible to modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the various embodiments of the present invention. scope.

Claims (7)

1. A method for identifying network coverage problems, comprising:
acquiring internet map data, wherein the internet map data comprises an image to be processed;
preprocessing the image to be processed;
inputting the preprocessed image into a first neural network, wherein the first neural network is used for extracting image boundary information in the preprocessed image;
inputting the image boundary information output by the first neural network into a second neural network, wherein the second neural network is used for identifying the boundary information of a map interest Point (POI) and boundary information of a mountain and a water area in the image boundary information;
fitting and displaying the boundary information of the POI, the boundary information of the mountain and the water area and the network quality index information of each MDT sampling point on a rasterized electronic map so as to present a network coverage problem identification result;
the image to be processed comprises a satellite map image; the preprocessing the image to be processed comprises the following steps:
determining a preset number of target areas in the satellite map image;
marking the mountain and the water area in the target area;
cutting the marked satellite map image into pictures with preset sizes;
and carrying out gray-level-based equalization processing on the areas except the annotation position in the segmented satellite map image.
2. The method according to claim 1, wherein the performing gray-based equalization processing on the satellite map image after the slicing comprises:
and performing gray-scale-based equalization processing on the divided satellite map image by adopting a histogram equalization processing mode, or performing gray-scale-based equalization processing on the image to be processed by directly adjusting contrast and brightness indexes.
3. The method according to claim 1 or 2, wherein the step of fitting and displaying the map interest point POI boundary information, the boundary information of the mountain and the water area and the network quality index information of each MDT sampling point on a rasterized electronic map to present a network coverage problem identification result comprises the following steps:
fitting the boundary information of the POI (point of interest) of the map, the boundary information of the mountain and the water area by combining the parameter information which corresponds to each sampling point and is used for representing the network quality, and globally presenting the parameter information on the electronic map;
the result of the global presentation comprises network coverage information of each area;
removing areas occupied by mountains and water areas, and determining an effective grid ratio and a good grid ratio according to the network coverage information;
and identifying the problem position of network coverage according to the effective grid ratio and the good grid ratio.
4. An apparatus for identifying network coverage problems, comprising:
the system comprises a data acquisition module, a processing module and a processing module, wherein the data acquisition module is used for acquiring Internet map data which comprises an image to be processed;
the data processing module is used for preprocessing the image to be processed;
a neural network based image segmentation subsystem for: inputting the preprocessed image into a first neural network, wherein the first neural network is used for extracting image boundary information in the preprocessed image; inputting the image boundary information output by the first neural network into a second neural network, wherein the second neural network is used for identifying the boundary information of a map interest Point (POI) and boundary information of a mountain and a water area in the image boundary information;
the problem identification module is used for fitting and displaying the boundary information of the map interest points POI, the boundary information of the mountain and the water area and the network quality index information of each MDT sampling point on a rasterized electronic map so as to present a network coverage problem identification result; the image to be processed includes a satellite map image, and the data processing module is specifically configured to: determining a preset number of target areas in the satellite map image; marking the mountain and the water area in the target area; cutting the marked satellite map image into pictures with preset sizes; and carrying out gray-level-based equalization processing on the areas except the annotation position in the segmented satellite map image.
5. A network coverage problem identification system, comprising:
the system comprises an Internet map data collection subsystem, a processing subsystem and a processing subsystem, wherein the Internet map data collection subsystem is used for acquiring Internet map data which comprises an image to be processed;
the image preprocessing subsystem is used for preprocessing the image to be processed;
the image segmentation subsystem based on the neural network is used for inputting the preprocessed image into a pre-established neural network to obtain the boundary information of a map interest Point (POI) and the boundary information of a mountain and a water area in the image to be processed;
and the network coverage presenting and evaluating subsystem is used for fitting and displaying the boundary information of the POI (point of interest) of the map, the boundary information of the mountain and the water area and the network quality index information of each MDT (minimization drive test) sampling point on the rasterized electronic map so as to present a network coverage problem identification result.
6. An electronic device, comprising: at least one processor and memory;
the memory stores computer execution instructions;
the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the network coverage problem identification method of any one of claims 1 to 3.
7. A computer-readable storage medium having computer-executable instructions stored thereon, which when executed by a processor, implement the network coverage problem identification method of any one of claims 1 to 3.
CN202010770729.2A 2020-08-04 2020-08-04 Network coverage problem identification method, device and system Active CN111818557B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010770729.2A CN111818557B (en) 2020-08-04 2020-08-04 Network coverage problem identification method, device and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010770729.2A CN111818557B (en) 2020-08-04 2020-08-04 Network coverage problem identification method, device and system

Publications (2)

Publication Number Publication Date
CN111818557A CN111818557A (en) 2020-10-23
CN111818557B true CN111818557B (en) 2023-02-28

Family

ID=72863535

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010770729.2A Active CN111818557B (en) 2020-08-04 2020-08-04 Network coverage problem identification method, device and system

Country Status (1)

Country Link
CN (1) CN111818557B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115087023B (en) * 2021-03-16 2024-06-11 中国移动通信集团四川有限公司 Road network analysis method and device

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9589210B1 (en) * 2015-08-26 2017-03-07 Digitalglobe, Inc. Broad area geospatial object detection using autogenerated deep learning models
CN112020723A (en) * 2018-05-23 2020-12-01 富士通株式会社 Training method and device for classification neural network for semantic segmentation, and electronic equipment
CN110633723B (en) * 2018-06-22 2023-10-17 佳能株式会社 Image processing apparatus and method, and storage medium
CN111241881B (en) * 2018-11-29 2022-12-27 中国移动通信集团四川有限公司 Method, apparatus, device and medium for region identification
US10482603B1 (en) * 2019-06-25 2019-11-19 Artificial Intelligence, Ltd. Medical image segmentation using an integrated edge guidance module and object segmentation network
CN110443822B (en) * 2019-07-16 2021-02-02 浙江工业大学 A Semantic Edge Aided Method for Fine Extraction of High-score Remote Sensing Targets
CN110942013A (en) * 2019-11-22 2020-03-31 佛山科学技术学院 Satellite image feature extraction method and system based on deep neural network
CN111107556B (en) * 2019-12-06 2023-03-24 中国联合网络通信集团有限公司 Signal coverage quality evaluation method and device of mobile communication network

Also Published As

Publication number Publication date
CN111818557A (en) 2020-10-23

Similar Documents

Publication Publication Date Title
CN110569878B (en) Photograph background similarity clustering method based on convolutional neural network and computer
CN112232391B (en) Dam crack detection method based on U-net network and SC-SAM attention mechanism
CN109977191B (en) Problem map detection method, device, electronic equipment and medium
CN109886282A (en) Object detection method, apparatus, computer-readable storage medium, and computer device
WO2021217857A1 (en) Slice defect detection method and apparatus, and electronic device and readable storage medium
CN113505781B (en) Target detection method, target detection device, electronic equipment and readable storage medium
CN107067003A (en) Extracting method, device, equipment and the computer-readable storage medium of region of interest border
CN110647886A (en) Interest point marking method and device, computer equipment and storage medium
CN112085022B (en) Method, system and equipment for recognizing characters
CN110969592B (en) Image fusion method, automatic driving control method, device and equipment
US11157735B2 (en) Cloud detection in aerial imagery
CN112669323A (en) Image processing method and related equipment
CN118172291B (en) Image cloud removing method and device for remote sensing image and electronic equipment
CN111950422A (en) Drawing identification method and related device
CN112199268B (en) A software compatibility testing method and electronic equipment
CN117218672A (en) Deep learning-based medical records text recognition method and system
CN117853904A (en) Road disease detection method, device, equipment, medium and system
CN115719447A (en) Building change detection method based on double-time-phase high-resolution remote sensing image
CN111818557B (en) Network coverage problem identification method, device and system
CN110443814B (en) Loss assessment method, device, equipment and storage medium for vehicle
CN114820679B (en) Image labeling method and device electronic device and storage medium
CN113159035B (en) Image processing method, device, equipment and storage medium
CN110781195A (en) System, method and device for updating point of interest information
CN118999600A (en) Road marking information determining method, vehicle, equipment and product
CN114399626B (en) Image processing method, apparatus, computer device, storage medium, and program product

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant