Deployment method and device of resource equipment, computer program product and electronic equipment

Abstract

The invention relates to the technical field of communication network planning, and relates to a resource equipment deployment method and device, a computer program product and electronic equipment. The method comprises the steps that multi-source equipment data is acquired, the multi-source equipment data comprises space remote sensing position data and position recording data of resource equipment, the space remote sensing position data refers to geographic information data acquired through a remote sensing technology, and the position recording data is acquired based on service data spatialization processing; spatial analysis is carried out based on the spatial remote sensing position data, the position recording data and the data source features, multiple reference ground feature deviations are obtained, and each reference ground feature deviation has a respective corresponding analysis detection mode; performing consistency weighted fusion according to the reference ground feature deviation to obtain a fusion result, and correcting the position record data according to the fusion result to obtain corrected position data; and performing layout deployment optimization on the resource equipment according to the corrected position data. According to the invention, the accuracy and efficiency of resource equipment deployment optimization can be improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication network planning, and more particularly to a resource device deployment method, a resource device deployment apparatus, a computer program product and an electronic device. BACKGROUND

[0002] With the acceleration of urbanization and the continuous improvement of various infrastructures, it is crucial to efficiently and accurately manage and maintain a large number of resource devices, especially in the field of telecommunications.

[0003] However, traditional resource device management methods, such as manual inspection and single-satellite positioning-based account records, have been difficult to adapt to the current needs of large-scale and high-density device deployment.

[0004] Therefore, there is an urgent need for a method that can accurately detect the spatial position of resource devices, correct errors, and provide spatial layout deployment based on this.

[0005] It should be noted that the information disclosed in the above BACKGROUND section is only used to strengthen the understanding of the background of the present disclosure, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] The purpose of the present disclosure is to provide a resource device deployment method, a resource device deployment apparatus, a computer program product and an electronic device, thereby improving the accuracy and operation and maintenance efficiency of resource device deployment.

[0007] Other characteristics and advantages of the present disclosure will become apparent from the following detailed description, or will be learned by practice of the present disclosure.

[0008] According to one aspect of the present disclosure, a resource device deployment method is provided, comprising: obtaining multi-source device data, the multi-source device data including spatial remote sensing position data and position record data of resource devices unified to a target spatial coordinate system, the spatial remote sensing position data being geographic information data obtained by remote sensing technology, and the position record data being obtained based on business data spatialization processing; performing spatial analysis based on the spatial remote sensing position data, the position record data and data source characteristics of the multi-source device data to obtain a plurality of reference ground object deviations, different reference ground object deviations having respective corresponding analysis detection methods; performing consistent weighted fusion according to the plurality of reference ground object deviations to obtain a fusion result, and correcting the position record data according to the fusion result to obtain corrected position data; and deploying the resource devices according to the corrected position data.

[0009] In an example embodiment of the present disclosure, the multi-source device data is acquired, including: performing address matching and / or coordinate standardization processing on the business data to associate the business data to a geographic spatial position to obtain reference position record data; acquiring spatial remote sensing image data and city vector map data and performing registration processing to obtain reference spatial remote sensing position data; and converting the reference spatial remote sensing position data and the reference position record data to a target spatial coordinate system to obtain spatial remote sensing position data and position record data.

[0010] In an example embodiment of the present disclosure, the spatial remote sensing position data includes remote sensing feature classification grids and city vector layers; and spatial analysis is performed based on the spatial remote sensing position data, the position record data, and data source features of the multi-source device data to obtain a plurality of reference feature deviations, including: performing denoising processing on the remote sensing feature classification grids using morphological opening and closing operations to obtain first remote sensing feature data; pre-processing feature objects in the city vector layers to obtain second spatial vector data; performing overlay analysis on the position record data and the first remote sensing feature data based on the data source features to obtain first reference feature deviations; performing distance detection on the position record data and the second spatial vector data to obtain second reference feature deviations; performing spatial interpolation processing using historical signal information to construct a signal field, and calculating signal strengths of the position record data according to the signal field to determine third reference feature deviations according to the signal strengths.

[0011] In an example embodiment of the present disclosure, the feature objects in the city vector layers are pre-processed to obtain the second spatial vector data, including: constructing a building buffer zone according to building object data in the city vector layers, and extracting an outer contour of the building buffer zone to obtain building contour information; constructing a corridor buffer zone according to road center object data in the city vector layers; and determining the second spatial vector data based on the building contour information and the corridor buffer zone.

[0012] In an example embodiment of the present disclosure, the overlay analysis is performed on the position record data and the first remote sensing feature data based on the data source features to obtain the first reference feature deviations, including: performing overlay analysis on the position record data and the first remote sensing feature data to determine a category relationship between the position record data and the first remote sensing feature data; calculating an intersection and union ratio of the position record data and the first remote sensing feature data, and determining the first reference feature deviations according to the intersection and union ratio and the category relationship.

[0013] In an example embodiment of the present disclosure, the second reference object deviation is obtained based on distance detection between the location record data and the second spatial vector data, comprising: calculating a first distance between the resource device and the road based on the location record data and the corridor buffer; calculating a second distance between the resource device and the building contour based on the location record data and the building contour information; comparing the first distance and the second distance with corresponding distance thresholds respectively to obtain the second reference object deviation.

[0014] In an example embodiment of the present disclosure, the consistency weighted fusion is performed according to the plurality of reference object deviations to obtain a fusion result, and the location record data is corrected according to the fusion result to obtain corrected location data, comprising: performing consistency processing on the plurality of reference object deviations to obtain a plurality of target object deviations corresponding to the plurality of reference object deviations respectively; performing weighted fusion on the target object deviations based on a preset weight to obtain the fusion result; if the fusion result is less than a preset fusion threshold, it is determined that the location record data has an object deviation, and the location record data is corrected respectively by using different correction methods corresponding to different object deviations to obtain the corrected location data.

[0015] In an example embodiment of the present disclosure, the resource device is deployed according to the corrected location data, comprising: constructing a target optimization function based on user demand information, geographic environment obstacle information, network topology and load information, business operation constraint information and the corrected location data; determining a corresponding optimization solver according to the task type, and solving the target optimization function based on the optimization solver to obtain target layout information, so as to deploy and optimize the resource device according to the target layout information.

[0016] According to one aspect of the present disclosure, a resource device deployment apparatus is provided, comprising: a data acquisition module configured to acquire multi-source device data, the multi-source device data comprising spatial remote sensing location data and location record data of resource devices unified to a target spatial coordinate system, the spatial remote sensing location data being geographic information data obtained by remote sensing technology, and the location record data being obtained based on spatialization processing of business data; a spatial analysis module configured to perform spatial analysis based on the spatial remote sensing location data, the location record data and data source characteristics of the multi-source device data to obtain a plurality of reference object deviations, different reference object deviations having respective corresponding analysis detection methods; a correction processing module configured to perform consistency weighted fusion according to the plurality of reference object deviations to obtain a fusion result, and correct the location record data according to the fusion result to obtain corrected location data; and a deployment module configured to deploy and optimize the resource device according to the corrected location data.

[0017] According to one aspect of the present disclosure, a computer program product is provided, comprising a computer program, the computer program being executed by a processor to implement the method of any one of the above.

[0018] According to an aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the method of any one of the above via executing the executable instructions.

[0019] The method for deploying resource equipment in the example embodiment of the present disclosure comprises the following steps: first, acquiring multi-source equipment data, the multi-source equipment data comprising spatial remote sensing position data and position record data of resource equipment unified to a target spatial coordinate system, the spatial remote sensing position data being geographic information data acquired through remote sensing technology, and the position record data being obtained based on spatialization processing of business data; then, performing spatial analysis based on the spatial remote sensing position data, the position record data, and data source characteristics of the multi-source equipment data to obtain a plurality of reference ground object deviations, different reference ground object deviations having respective corresponding analysis detection modes; next, performing consistent weighted fusion according to the plurality of reference ground object deviations to obtain a fusion result, and correcting the position record data according to the fusion result to obtain corrected position data; and finally, deploying the resource equipment according to the corrected position data.

[0020] On the one hand, by coupling multi-source spatial data (i.e., multi-source equipment data), the spatial position error of resource equipment is detected and corrected, greatly improving the accuracy and reliability of the position data of resource equipment. Based on the corrected accurate position data and multi-dimensional spatial analysis, targeted device spatial layout optimization suggestions are provided, significantly improving the scientificity and intelligent level of network planning and optimization, avoiding resource waste and planning errors caused by position errors, and the optimized spatial layout directly helps to improve network coverage, improve capacity, and balance load, thereby comprehensively improving the overall performance of the telecommunication network and user experience. On the other hand, by automatic detection and intelligent optimization, a large amount of manual checking and field survey work is reduced, significantly improving the operation and maintenance efficiency and reducing the operation cost.

[0021] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and are not limiting to the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0022] The above and other objects, features and advantages of the present disclosure exemplary embodiments will be readily understood through reading the detailed description below, with reference to the accompanying drawings. In the drawings, several embodiments of the present disclosure are illustrated by way of example and not limitation.

[0023] Figure 1 An application environment diagram related to a method for deploying resource equipment according to an example embodiment of the present disclosure is shown.

[0024] Figure 2A flow chart of a method for deploying a resource device is shown according to an example embodiment of the present disclosure.

[0025] Figure 3 A flow chart of acquiring multi-source device data is shown according to an example embodiment of the present disclosure.

[0026] Figure 4 A flow chart of determining a plurality of reference object biases is shown according to an example embodiment of the present disclosure.

[0027] Figure 5 A flow chart of acquiring a first reference object bias is shown according to an example embodiment of the present disclosure.

[0028] Figure 6 A composition diagram of a deployment apparatus of a resource device is shown according to an example embodiment of the present disclosure.

[0029] Figure 7 A block diagram of an electronic device is shown according to an example embodiment of the present disclosure.

[0030] In the drawings, the same or similar reference numerals refer to the same or similar parts. DETAILED DESCRIPTION

[0031] Example embodiments now will be described more fully hereinafter with reference to the accompanying drawings. Example embodiments, may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the example embodiments to those skilled in the art. Like reference numerals refer to like elements throughout the figures.

[0032] Moreover, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the embodiments of the disclosure can be practiced without one or more of the specific details, or

[0033] The block diagrams in the drawings show functions and functionality as they can be implemented in software. They do not imply a specific order in the exercises or the order of execution, nor that individual functions or blocks must be implemented in a computer program. They are shown as blocks and functional descriptions that can be implemented in software or other functional means, as is conventional for hardware realization. They can also be implemented as software modules or code segments.

[0034] Firstly, the concepts involved in the disclosure are explained.

[0035] Multi-source data, also known as multi-source device data, refers to a collection of multiple heterogeneous data used to detect and optimize the spatial position of resource devices. Among them, the multi-source device data can include remote sensing classification data (reflecting ground cover, land use type), spatial vector data (including administrative division, road, water system, building, planning area, etc.), field street view data (providing high-precision, perspective local environment information), and internal spatialization data of telecommunications (such as device account, work order, fault, performance data, etc.).

[0036] Spatial analysis refers to a series of techniques for analyzing and processing data with spatial position and shape characteristics using GIS (Geographic Information System) technology to reveal spatial patterns, relationships and trends. In the disclosure, spatial analysis methods such as overlay analysis, proximity analysis, network analysis, and spatial interpolation can be used for spatial analysis.

[0037] The spatial position detection of resource devices, that is, the acquisition of reference ground deviation, refers to the use of multi-source data and spatial analysis methods to identify and correct the inaccuracy of location data in the resource device account of telecommunications, including the position error caused by manual input errors, on-site collection device errors, and device reported coordinate offset, and intelligent correction.

[0038] Layout deployment optimization, also known as spatial layout optimization, refers to the use of spatial analysis and optimization algorithms to recommend more reasonable and efficient deployment solutions for telecommunications resource devices based on the corrected accurate device location data, combined with network performance targets, user needs, geographical environment constraints, etc.

[0039] Currently, in the management of resource device deployment, there are the following problems: Firstly, the device spatial position data is generally inaccurate. Its main sources include, but are not limited to, errors in manual input and mapping process, accuracy limitations or signal interference of on-site collection devices (such as GPS), and possible offset of device reported coordinates. These errors cause a deviation between the device account location in the system and its actual geographical position, which seriously affects the accuracy of assets, operation and maintenance efficiency, and fault positioning accuracy.

[0040] Secondly, the network planning and optimization based on inaccurate location information is poor in effect. The planning and optimization of a telecommunication network, such as base station site selection, antenna parameter adjustment and optical cable route design, highly depend on the accurate spatial information of the equipment and its surrounding environment. However, when the basic location data has errors, no matter how advanced the theoretical model or optimization algorithm is, the output result may not be consistent with the actual situation, resulting in blind areas in network coverage, uneven capacity allocation, and even resource waste, making it difficult to achieve the expected network performance improvement.

[0041] Therefore, there is an urgent need for a technology that can couple multi-source spatial data with advanced spatial analysis methods to achieve accurate detection of the spatial location of resource equipment, error correction, and on this basis, provide an intelligent spatial layout optimization scheme, so as to comprehensively improve the intelligent level and operation efficiency of telecommunication network asset management.

[0042] The deployment method of resource equipment provided by the exemplary embodiments of the present disclosure can be applied to the application environment as shown in Figure 1 The terminal 101 communicates with the server 102 through a network. The data storage system can store the data required to be processed by the server 102. The data storage system can be integrated on the server 102, or placed on the cloud or other network servers.

[0043] In an exemplary embodiment, the deployment method of resource equipment provided by the exemplary embodiments of the present disclosure can be executed by the server 102, and the corresponding deployment device of resource equipment is arranged in the server 102. Correspondingly, in this mode executed by the server 102, the server 102 can start to execute the steps in the technical solutions of the exemplary embodiments of the present disclosure in response to a trigger order, wherein the trigger order can be sent by a terminal used by a user, or triggered locally by the server in response to some automatic events.

[0044] The server 102 can be a stand-alone physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, and basic cloud computing services such as big data and artificial intelligence platforms. The server 102 can execute background tasks.

[0045] Furthermore, in another exemplary embodiment, the terminal 101 can also have similar functions as the server 102, so as to execute the deployment method of resource equipment provided by the exemplary embodiments of the present disclosure.

[0046] The terminal 101 can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, an Internet of Things device, and a portable wearable device. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The terminal 101 can also be referred to as a mobile terminal, a terminal device, a mobile device, etc. The exemplary embodiments of the present disclosure do not limit the type of the terminal 101.

[0047] In addition, the technical solutions of the exemplary embodiments of the present disclosure can also be executed by the terminal 101 and the server 102 in cooperation. In this way of cooperation, some steps in the technical solutions provided by the exemplary embodiments of the present disclosure are executed by the terminal 101, and the other steps are executed by the server 102. It should be noted that in this way of cooperation, the steps executed by the terminal 101 and the server 102 can be dynamically adjusted according to actual conditions, and no special limitation is made. The terminal 101 and the server 102 can be directly or indirectly connected through wireless communication, and the exemplary embodiments of the present disclosure do not make special limitation.

[0048] As shown in FIG. 1, the terminal 101 and the server 102 are connected through a wireless communication network. Figure 2 FIG. 2 shows a flowchart of a method for deploying a resource device according to an exemplary embodiment of the present disclosure. The method includes the following steps. In step S210, multi-source device data is acquired. The multi-source device data includes spatial remote sensing position data and position record data of the resource device unified to a target spatial coordinate system. The spatial remote sensing position data is geographic information data acquired through remote sensing technology, and the position record data is obtained based on spatialization processing of business data.

[0049] In step S220, spatial analysis is performed based on the spatial remote sensing position data, the position record data, and the data source characteristics of the multi-source device data, to obtain a plurality of reference ground object deviations. Different reference ground object deviations have respective corresponding analysis detection methods.

[0050] In step S230, consistency weighted fusion is performed according to the plurality of reference ground object deviations to obtain a fusion result. The position record data is corrected according to the fusion result to obtain corrected position data.

[0051] In step S240, the resource device is deployed and optimized according to the corrected position data.

[0052] According to the resource device deployment method of the example embodiment of the present disclosure, on the one hand, the detection and correction of the spatial position error of the resource device are realized by coupling multi-source spatial data (i.e., multi-source device data), which greatly improves the accuracy and reliability of the position data of the resource device. Based on the corrected accurate position data and multi-dimensional spatial analysis, targeted device spatial layout optimization suggestions are provided, which significantly improves the scientificity and intelligent level of network planning and optimization, avoids resource waste and planning errors caused by position errors, and the optimized spatial layout directly helps to improve network coverage, improve capacity, and balance load, thereby comprehensively improving the overall performance of the telecommunication network and user experience. On the other hand, through automatic detection and intelligent optimization, the workload of a large amount of manual checking and field survey is reduced, the operation and maintenance efficiency is significantly improved, and the operation cost is reduced.

[0053] The steps S210 to S240 will be described in more detail below.

[0054] In step S210, multi-source device data is obtained, which includes spatial remote position data of resource devices unified to a target spatial coordinate system and position record data. The spatial remote position data refers to geographic information data obtained by remote sensing technology, and the position record data is obtained based on spatialization processing of business data.

[0055] In the example embodiment of the present disclosure, the multi-source device data is obtained by integrating multi-source telecommunication spatial data. In order to uniformly process the data of resource devices from different channels, the data of resource devices of each channel needs to be unified to a target spatial coordinate system. The resource devices are devices such as base stations, poles, optical cross boxes, and fiber distribution boxes required for telecommunication network layout. The spatial remote position data of the resource devices refers to geographic information data obtained by remote sensing technology, including vector data (point, line, and surface) and raster data (pixel matrix) representing the spatial range of the resource devices, such as satellite remote sensing images, aerial images, and urban vector maps. The position record data is obtained by spatialization of telecommunication business data, which includes but is not limited to recorded device data (containing recorded position information), work order data, fault data, network performance data, and user density distribution data. The position record data is obtained by spatialization of these data. In the example embodiment of the present disclosure, the position record data can include device account record data or position data reported by the device itself.

[0056] In an example embodiment, as shown in FIG. 2, obtaining multi-source device data can include: Figure 3 Step S310: performing address matching and / or coordinate standardization processing on the business data to associate the business data to a geographic spatial position, to obtain reference position record data.

[0057] ​Business data can be understood as non-spatialized data from enterprise or department business systems. For example, a signal record can be device ID: installation location; signal strength. The record is a text description without latitude and longitude coordinates. Address matching is the conversion of textually described address information into geographic coordinates (latitude and longitude), which can be converted through a geocoding service; coordinate standardization processing can convert various non-standard format geographic location information contained in business data into a unified coordinate format that conforms to international standards or industry specifications through format conversion, unit unification, symbol specification, and other technical means. For example, the coordinates in the business data can use Chinese description (such as north latitude 30 degrees, east longitude 120 degrees), mixed symbol representation (such as N30°, E120°), or non-standard numerical format, which needs to be identified, parsed, and converted into a unified numerical representation (such as decimal system format). Reference location record data is business data that has been spatialized after the above-mentioned spatialization processing. The business data has been converted from pure text records to spatial point data with geographic coordinates.

[0058] Step S320: Obtain remote sensing raster image data and urban vector map data and perform registration processing to obtain reference spatial remote sensing location data.

[0059] The remote sensing raster image data can be obtained through the location of an AI image recognition device. The computer vision technology can be used to classify the remote sensing image into building, green land, and water body layers, and no special restrictions are made. The urban vector map data is geographic data stored in the form of point, line, and surface geometric objects, such as the accurate boundaries and locations of roads, buildings, green lands, and points of interest. The registration processing is the process of geometric correction and alignment of the remote sensing image to the vector map reference, and then the reference spatial remote sensing location data is obtained.

[0060] Step S330: Convert the reference spatial remote sensing location data and the reference location record data to a target spatial coordinate system to obtain spatial remote sensing location data and location record data.

[0061] The target spatial coordinate system refers to a unified spatial reference datum, such as WGS-84. All data must be unified to the same coordinate system, and the calculation of spatial distance and relationship is accurate and reliable.

[0062] The exemplary embodiments of the present disclosure solve the problem that multi-source spatial data cannot be directly analyzed due to different reference, format, and semantics by spatializing, registering, and unifying the coordinate system of heterogeneous multi-source data, and provide a high-quality, consistent, and comparable data basis for subsequent multi-dimensional spatial analysis and data fusion.

[0063] In step S220, spatial analysis is performed based on the spatial remote sensing position data, the position record data, and the data source features of the multi-source device data, to obtain a plurality of reference object deviations, and different reference object deviations have respective analysis detection modes.

[0064] In the example embodiments of the present disclosure, different analysis detection modes can be used to achieve multi-source position comparison and detection results, thereby providing advantageous support for determining whether the position record data has a deviation.

[0065] In an example embodiment, the spatial remote sensing position data includes a remote sensing object classification grid and a city vector layer.

[0066] As shown in Figure 4 Based on the spatial remote sensing position data, the position record data, and the data source features of the multi-source device data, the spatial analysis to obtain a plurality of reference object deviations can include: Step S410: performing denoising processing on the remote sensing object classification grid by using morphological opening and closing operation to obtain first remote sensing object data.

[0067] The morphological opening and closing operation is a digital image processing operation for purifying an image. The remote sensing object classification grid can be processed by erosion first and then dilation to obtain the first remote sensing object data.

[0068] Step S420: preprocessing the object in the city vector layer to obtain second spatial vector data.

[0069] The preprocessing of the object in the city vector layer (such as a building object B, a road center object D, a water body object W, etc.) means processing the object into a layout mode that conforms to the actual scene. For example, the contour is extended outward to cover the eave error, and the road center line is extended by X meters on both sides to generate a corridor of the fall rod belt, etc. The example embodiments of the present disclosure can flexibly adjust the preprocessing mode according to the actual situation.

[0070] In an example embodiment, the preprocessing of the object in the city vector layer to obtain the second spatial vector data can include: First, a building buffer zone is constructed according to the building object data in the city vector layer, and an outer contour of the building buffer zone is extracted to obtain building contour information. Second, a corridor buffer zone is constructed according to the road center object data in the city vector layer. Finally, the second spatial vector data is determined based on the building contour information and the corridor buffer zone.

[0071] Specifically, the position record data includes a device account position or a self-reported position P0, the remote sensing object classification grid is R, and the city vector layer is Wherein, morphological opening and closing operation can be performed on R, a buffer zone is established for B to cover eave error (such as extending the contour outward by x meters), and the outer contour information aB of the building buffer zone is extracted, that is, a buffer zone is generated for D (such as being expandable by m meters on both sides of the center line), and a "rod-falling zone" corridor D+ is obtained. Further, the second spatial vector data can be determined according to the corridor D+ and the outer contour information aB.

[0072] Step S430: based on the data source feature, superimposed analysis is performed on the position record data and the first remote sensing ground object data to obtain a first reference ground object deviation.

[0073] The first reference ground object deviation includes a category deviation and a position deviation, and the data source feature refers to the actual position of the ground object category, for example, the position of the resource equipment is at the edge of the road or the sidewalk.

[0074] In an exemplary embodiment, as shown in Figure 5 based on the data source feature, superimposed analysis is performed on the position record data and the first remote sensing ground object data to obtain a first reference ground object deviation, including: Step S510: superimposed analysis is performed on the position record data and the first remote sensing ground object data to determine the category relationship of the position record data and the first remote sensing ground object data.

[0075] The position record data and the first remote sensing ground object data can be superimposed and analyzed (that is, P0 and R are superimposed and analyzed) to determine the category relationship of the position record data and the first remote sensing ground object data, that is, the ground object position where P0 is located is judged through superimposed analysis, for example, P0 is in a water body or inside a building, but according to the data source feature, P0 should be at the edge of the road or the sidewalk, so the ground object categories are inconsistent. It can be represented as follows: P0 belongs to {road edge, sidewalk, green hardening belt, building facade neighborhood} ^ P0 does not belong to {water body, building interior} → inconsistent. The content before "^" is the data source feature.

[0076] Step S520: the intersection-over-union of the position record data and the first remote sensing ground object data is calculated, and the first reference ground object deviation is determined according to the intersection-over-union and the category relationship.

[0077] The intersection-over-union calculation can be used to reflect the object overlap degree, and based on the position record data and the first remote sensing ground object data, the intersection-over-union can be calculated. For example, IoU (device semantic mask, multi-source data mask) can be calculated through the superimposed analysis of P0 and R. Wherein, the IoU can also be compared with a preset intersection-over-union threshold, and whether the object overlap degree meets the requirements is determined according to the comparison result. As shown in formula 1: IoU (device semantic mask, multi-source data mask) < τ IoU Formula 1 wherein, τ IoU is a preset intersection over union threshold, a preset threshold (e.g., 0.5, 0.7, etc.), the device semantic mask can be a regular or irregular area generated according to prior semantic knowledge of the resource device, and the multi-source data mask can be a binary image of an area where the resource device pit exists, which can be understood as an actual observation result.

[0078] Further, the first reference feature deviation can be determined according to the intersection over union and the category relationship.

[0079] Step S440: Distance detection is performed based on the location record data and the second spatial vector data to obtain a second reference feature deviation.

[0080] The distance detection is to detect whether the distance between the resource device and the adjacent feature object is reasonable. The distance detection based on the location record data and the second spatial vector data to obtain the second reference feature deviation includes: First, based on the location record data and the corridor buffer, a first distance between the resource device and the road is calculated. The first distance can be represented by the following formula 2: Formula 2 It can be understood from formula 2 that the distance between the location of the resource device and the road is calculated.

[0081] Second, based on the location record data and the building contour information, a second distance between the resource device and the building contour is calculated. The second distance can be represented by the following formula 3: Formula 3 It can be understood from formula 3 that the distance between the location of the resource device and the building contour is calculated.

[0082] Finally, the first distance and the second distance are compared with the corresponding distance threshold, respectively, to obtain the second reference feature deviation.

[0083] The first distance can be compared with the first threshold, and the second distance can be compared with the second threshold, to determine whether the resource device and the adjacent feature are within a reasonable distance range. The first threshold and the second threshold are set according to the actual detection scene, such as a few meters, a few tens of meters, etc., and are not limited in this regard.

[0084] Step S450: Spatial interpolation processing is performed using historical signal information to construct a signal field, and the signal strength of the location record data is calculated according to the signal field, to determine a third reference feature deviation according to the signal strength.

[0085] The historical signal information can include historical RSSI (Received Signal Strength Indicator) / RSRP (Reference Signal Received Power) of the inspection and / or reported track, and the signal field F(x, y) can be obtained by spatio-temporal Kriging interpolation or IDW (Inverse Distance Weighted) interpolation based on the historical signal information, and the F(P0) distribution centered at P0 can be obtained, and the distribution is compared with the signal distribution template corresponding to the resource device, and if there is a mismatch, it is determined that the resource device has a deviation.

[0086] As described above, the first reference ground object deviation, the second reference ground object deviation, and the third reference ground object deviation, i.e., multiple reference ground object deviations, are obtained.

[0087] The multiple types of reference ground object deviations are obtained by different analysis and detection methods, which ensures the comprehensiveness and robustness of the analysis, provides rich, accurate, and complementary deviation data sources for subsequent weighted fusion, and thus significantly improves the accuracy and reliability of the final positioning result of the resource device.

[0088] In step S230, the multiple reference ground object deviations are subjected to consistent weighted fusion to obtain a fusion result, and the position record data is corrected according to the fusion result to obtain corrected position data.

[0089] In the exemplary embodiments of the present disclosure, the multiple reference ground object deviations are subjected to consistent weighted fusion, which takes into account the problem that only using a certain detection method for deviation detection may be inaccurate. By fusing the multiple reference ground object deviations, it is accurately determined whether the position record data has a ground object deviation, i.e., the position data of the recorded or reported resource device may be inaccurate.

[0090] In an exemplary embodiment, the multiple reference ground object deviations are subjected to consistent weighted fusion to obtain a fusion result, and the position record data is corrected according to the fusion result to obtain corrected position data, including: First, the multiple reference ground object deviations are subjected to consistent processing to obtain target ground object deviations corresponding to the multiple reference ground object deviations, respectively.

[0091] Second, the target ground object deviations are subjected to weighted fusion based on a preset weight to obtain a fusion result. If the fusion result is less than a preset fusion threshold, it is determined that the position record data has a ground object deviation, and the position record data is corrected by using different correction methods corresponding to the ground object deviations to obtain corrected position data.

[0092] Specifically, the weighting and fusion of each target ground object deviation based on the preset weight can be represented by formula 4: Formula 4 wherein, is the fusion result, w1, w2, w3, and w4 are preset weights, which can be set according to actual scene requirements, for example, w1=0.2, w2=0.2, w3=0.2, and w4=0.4, and the exemplary embodiments of the present disclosure do not limit this. h(), f(), and u() respectively represent different consistency processing modes, which are used to process each reference ground object deviation to obtain multiple target ground object deviations with a unified processing standard, and the specific consistency processing mode is also set according to the conversion requirement.

[0093] After obtaining the fusion result, the fusion result can be compared with the preset fusion threshold, and if the fusion result is less than the preset fusion threshold, it is determined that the position record data has a ground object deviation. The preset fusion threshold can also be flexibly set according to actual requirements, for example, 75 points, 85 points, etc.

[0094] In an exemplary embodiment, different correction modes corresponding to different ground object deviations can be set in advance. For example, for the first reference ground object deviation (i.e., consistency correction), a nearest neighbor reasonable ground object edge coordinate point search method can be used for consistency correction; for the second reference ground object deviation (distance correction), a projection method can be used for distance correction; and for the third reference ground object deviation (signal offset correction), a signal field peak point search method can be used for offset correction.

[0095] Specifically, the nearest neighbor reasonable ground object edge coordinate point search method can determine what the reasonable ground object is according to the device type (such as the reasonable ground object of a street lamp being a road), then find the nearest reasonable natural ground object edge point in the corresponding vector layer, and take the point as the corrected position, so that major errors that do not conform to geographical common sense and business rules can be fundamentally corrected.

[0096] The projection method for distance correction can be a classical geometric algorithm for calculating the nearest distance from a point to a line or a point to a plane and finding the foot point (projection point). For linear ground objects (such as road centerlines), the projection point is the foot point; for planar ground objects (such as building surfaces), the projection point is the nearest point on its boundary. Further, the spatial relationship between the device and its associated ground object (such as close to or along the road) can be established, which meets the business requirements.

[0097] The search for the offset correction in the vicinity of the signal field peak value point can be performed on the continuous signal strength grid map generated by the historical signal data interpolation, in a reasonable neighborhood radius centered on the service record point, to find the pixel point with the maximum signal strength value, and the point is taken as the corrected position, so that the device deployment can truly meet the demand of its service function (such as communication coverage).

[0098] In step S240, the resource device is deployed and optimized according to the corrected position data.

[0099] In the exemplary embodiments of the present disclosure, the optimal site of the resource device (such as a base station), the optimal height and direction of the antenna, and the economic route of the transmission network such as optical cable can be intelligently recommended by integrating the signal propagation model, user demand heat map, geographical environment obstacles, existing network load and other key spatial and service data, and using multi-objective optimization technology.

[0100] Among them, the target optimization function can be constructed based on user demand information, geographical environment obstacle information, network topology and load information, service operation constraint information and corrected position data. Then the corresponding optimization solver is determined according to the task type, and the target optimization function is solved based on the optimization solver to obtain the target layout information, so as to optimize the layout and deployment of the resource device according to the target layout information.

[0101] Specifically, the high-precision device position data P (i.e. corrected position data), user demand heat map U (such as spatial density distribution), geographical environment obstacles N (such as buildings, elevation, rivers, etc.), existing network topology and load information G, service operation constraints B (construction cost, construction restrictions, regulations, etc.) are obtained to obtain input .

[0102] Then, the multi-objective optimization function can be defined as: Formula 5 Where x is the spatial decision variable to be optimized (such as base station site selection, antenna height and direction, optical cable routing), is the feasible solution space (all scheme sets that meet the geographical and business constraints), represents that the optimization can be maximized or minimized according to the nature of the task, and F() is a comprehensive benefit or comprehensive cost function. When it is defined as a comprehensive benefit function (such as positive indicators such as coverage rate, capacity, user experience weighted minus cost indicators), take When it is defined as a comprehensive cost function (such as negative indicators such as construction cost, coverage gap, path loss weighted sum), take For example, formula 6 is a comprehensive benefit function: Formula 6 Wherein, is network coverage, is network capacity, is user experience score, is construction and operation cost, is a weight parameter, which can be dynamically adjusted according to the operation strategy.

[0103] Further, in the optimization solving, a corresponding optimization solver can be constructed according to different task types (such as site optimization, path optimization) and the like.

[0104] Specifically, through the target optimization function, multiple factors such as user demand, geographical obstacles, network state, and operation cost, which compete with each other and even contradict each other, are integrated into a unified mathematical model through weight coefficients. The optimization solver is used to automatically find the value of the decision variable that can make the target optimization function reach the optimal value (maximum value or minimum value). In the present disclosure, the decision variable is the deployment location, quantity, and configuration parameter of the resource device. The optimization solver can be a linear programming solver, a genetic algorithm, a particle swarm algorithm, a simulated annealing algorithm, and the like, and no special limitation is made thereto.

[0105] The target layout information includes, for example, base station position, antenna hanging height, and direction. Further, the target layout information can be fed back to the user end to perform efficient layout deployment, so as to improve the operation efficiency.

[0106] The target layout information obtained by constructing the target optimization function and the optimization solver through comprehensive multi-source information can improve network coverage, capacity, user experience, and overall operation efficiency, and realize fine configuration and value maximization of telecommunication resources.

[0107] The deployment method of the resource device of the exemplary embodiment of the present disclosure will be described below with specific examples.

[0108] First, the coordinates of a certain urban pole (or optical distribution box) account record are (E116.3°, N39.9°) (i.e. position record data), and it is found through superposition analysis that the position belongs to the "water body" layer (remote sensing image shows a river), which is the first reference ground object deviation. Through adjacent analysis calculation, the distance between the coordinates and the nearest road network is 80 meters (far beyond the "vehicle accessibility" threshold of 30 meters), which is the second reference ground object deviation. Combined with street view image recognition, it is found that the base station is actually located on the roof of a communication machine room on the opposite side of the river (E116.302°, N39.901°).

[0109] Second, the target ground object deviations are weighted and fused based on the preset weight. The position record data is determined to have a ground object deviation through multi-source data weighting, and the position record data is corrected respectively by using different correction methods corresponding to different ground object deviations to obtain corrected position data.

[0110] Wherein, the corrected coordinates can be generated and the prompt "Original coordinates deviate due to the error of manually entering decimal point" can be given to the management personnel for correction. Of course, the position record data can be corrected according to different correction methods corresponding to the deviation of the ground object, so as to realize automatic or semi-automatic correction of the position record data, that is, the coordinates of the pole (or optical box) account record.

[0111] Again, the obtained position record data is taken as an optimization input, and user demand information, geographical environment obstacle information, network topology and load information, and business operation constraint information are obtained to construct a target optimization function and an optimization solver. Among them, the candidate position with no obstruction, high network accessibility and effective elimination of blind area can be selected in the feasible solution space of Ω, that is, the target layout information is obtained and layout optimization is performed accordingly.

[0112] After layout optimization, combined with the park user density heat map (such as the user density of 80 people per 100 square meters in the core office area) and the terrain data (three 15-story high-rise buildings in the middle), it is found that the original planning of the No. 4 base station (preliminarily selected at the edge of the park) can only cover 20% of the high-density area, and is obstructed by high-rise buildings to form three coverage blind areas. Based on the corrected base station coordinates, it is recommended to adjust the location of the No. 4 base station to the top of the high-rise building in the middle of the park (confirmed by adjacent analysis that the position has no obstruction and network accessibility), and determine the antenna hanging height of 35 meters and the azimuth angle of 120 degrees through multi-objective optimization technology. After optimization, the coverage rate of the high-density area can be improved from 65% to 98%, and the coverage blind area is eliminated.

[0113] It should be noted that the detailed content of the example has been described in the above exemplary embodiments, and will not be repeated here.

[0114] The deployment method of the resource device in the exemplary embodiments of the present disclosure first obtains multi-source device data, which includes spatial remote sensing position data and position record data of the resource device unified to a target spatial coordinate system, and the position record data is obtained based on spatialization processing of business data. Then, spatial analysis is performed based on the spatial remote sensing position data, the position record data, and the data source characteristics of the multi-source device data to obtain a plurality of reference ground object deviations, different reference ground object deviations having respective corresponding analysis detection methods. Then, the plurality of reference ground object deviations are consistently weighted and fused to obtain a fusion result, and the position record data is corrected according to the fusion result to obtain corrected position data. Finally, the resource device is deployed according to the corrected position data.

[0115] On the one hand, by coupling multi-source spatial data (i.e., multi-source device data), the spatial location error of resource devices can be detected and corrected, significantly improving the accuracy and reliability of the location data of resource devices. Based on the corrected precise location data and multi-dimensional spatial analysis, targeted suggestions for optimizing device spatial layout are provided, significantly improving the scientific and intelligent level of network planning and optimization, avoiding resource waste and planning errors caused by location errors, and the optimized spatial layout directly helps to improve network coverage, increase capacity, and balance load, thereby comprehensively improving the overall performance of telecommunications networks and user experience. On the other hand, through automated detection and intelligent optimization, a large amount of manual verification and on-site surveying work is reduced, significantly improving operation and maintenance efficiency and reducing operating costs. In addition, the exemplary embodiments of this disclosure have good adaptability and can be widely applied to multiple fields such as network planning and construction, IoT device management, and smart city infrastructure operation and maintenance.

[0116] In exemplary embodiments of this disclosure, a deployment apparatus for resource devices is also provided, such as... Figure 6 As shown, the deployment device 600 for the resource equipment includes: The data acquisition module 610 is used to acquire multi-source device data, which includes spatial remote sensing location data and location record data of resource devices unified to the target spatial coordinate system. The spatial remote sensing location data is geographic information data acquired through remote sensing technology, and the location record data is obtained based on the spatialization processing of business data. The spatial analysis module 620 is used to perform spatial analysis based on the data source characteristics of the spatial remote sensing location data, location record data, and multi-source device data to obtain multiple reference ground feature deviations. Different reference ground feature deviations have their own corresponding analysis and detection methods. The correction processing module 630 is used to perform consistency weighted fusion based on multiple reference ground feature deviations to obtain the fusion result, and to correct the location record data based on the fusion result to obtain corrected location data. The deployment module 640 is used to deploy the resource devices according to the corrected location data.

[0117] Since the details of each functional module of the resource device deployment apparatus of the exemplary embodiments of this disclosure have been described in the exemplary embodiments of the resource device deployment method described above, they will not be repeated here.

[0118] It should be noted that although several modules or units of the resource equipment deployment apparatus have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0119] The exemplary embodiments of the present disclosure also provide a computer program product. The computer program product includes a computer program, which, when executed by a processor, implements the above-mentioned deployment method of resource device.

[0120] In an embodiment, the computer program product can be a tangible product containing the computer program, such as a computer-readable storage medium storing the computer program. The readable storage medium can be a storage medium based on electric, magnetic, optical, electromagnetic, infrared, etc. signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory (Flash), mechanical hard disk (HDD), solid state disk (SSD), etc. For example, the computer program product can be implemented as a non-volatile storage medium storing the computer program, such as read-only memory, Nand flash, etc.

[0121] In an embodiment, the computer program product can be an intangible product containing the computer program. For example, the computer program product can be implemented as a virtual digital product, such as an executable file, installation package, etc. digital file storing the computer program.

[0122] The code of the computer program can be written in one or more programming languages. The program code can be executed entirely on the user computing device, or partially on the user computing device, or as a separate software package, or partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case involving a remote computing device, the remote computing device can be connected to the user computing device through any kind of network, such as a local area network (LAN), a wide area network (WAN), etc., or can be connected to an external computing device (for example, through an Internet connection provided by an operator).

[0123] The computer program can be carried or transmitted by electric, magnetic, optical, electromagnetic, infrared, etc. signals. The electronic device can convert the signal carrying the computer program into a digital signal, and then run the computer program. When the computer program is running on the electronic device, its code is used to make the electronic device execute (more specifically, can make the processor of the electronic device execute) the method steps of various exemplary embodiments of the present disclosure, such as can execute the steps of the above-mentioned deployment method of resource device.

[0124] Furthermore, in exemplary embodiments of the present disclosure, an electronic device capable of implementing the above-described method is also provided. Those skilled in the art can understand that various aspects of the present disclosure can be implemented as a system, a method or a program product. Therefore, various aspects of the present disclosure can be embodied as a complete hardware embodiment, a complete software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, which can be collectively referred to as "circuitry", "module" or "system" herein.

[0125] The electronic device 700 according to such an embodiment of the present disclosure will be described below with reference to Figure 7 Figure 7 The electronic device 700 shown is merely an example and should not limit the function and usage range of the embodiments of the present disclosure.

[0126] As shown in Figure 7 The electronic device 700 is in the form of a general computing device. The components of the electronic device 700 can include, but are not limited to, the at least one processing unit 710 described above, the at least one storage unit 720 described above, a bus 730 connecting different system components (including the storage unit 720 and the processing unit 710), and a display unit 740.

[0127] The storage unit stores program code that can be executed by the processing unit 710, so that the processing unit 710 performs the steps described in the "Exemplary Method" section of the present specification according to various exemplary embodiments of the present disclosure.

[0128] The storage unit 720 can include a readable medium in the form of a volatile storage unit, such as a random access memory (RAM) 721 and / or a cache memory unit 722, and can further include a read-only memory (ROM) 723.

[0129] The storage unit 720 can further include program / utility 724 having a set of (at least one) program modules 725, including but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or a combination thereof can include implementation of a network environment.

[0130] The bus 730 can represent one or more of several types of bus structures, including a storage unit bus or storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of a variety of bus structures.

[0131] ​The electronic device 700 can also communicate with one or more external devices 800 such as a keyboard or pointing device, a Bluetooth device, or a database, and can communicate with one or more devices enabling user interaction with the electronic device 700 (for example, a display, speakers, a haptic output device, or the like) and / or one or more devices (for example, a router, a modem, or the like) enabling communication with one or more other computing devices. Such communication can occur via Input / Output (I / O) interface 750. Still yet, the electronic device 700 can communicate with one or more networks (for example, a local area network (LAN), a wide area network (WAN), or the like, or a public network, for example, the Internet) via network adapter 760. As depicted, network adapter 760 communicates with the other components of the electronic device 700 via bus 730. It should be appreciated that although not shown, other hardware and / or software modules could be used in connection with the electronic device 700. Such modules include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0132] From the above description of the embodiments, those skilled in the art will readily appreciate that the example embodiments described herein can be implemented by software and / or by hardware coupled with software. Accordingly, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (for example, a CD-ROM, a USB flash drive, a mobile hard disk, or the like) or a network, and includes a number of instructions for causing a computing device (for example, a personal computer, a server, a terminal device, or a network device, etc.) to perform the methods according to the embodiments of the present disclosure.

[0133] In addition, the above-described figures are only schematic illustrations of the processes included in the methods according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above-described figures do not indicate or limit the time sequence of the processes. In addition, it will be readily understood that the processes can be executed synchronously or asynchronously, for example, in a plurality of modules.

[0134] Other embodiments of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features disclosed herein. It is intended that the present disclosure cover any and all variations of the present disclosure that come within the scope of the claims and their equivalents. It is intended that the specification and examples be considered exemplary only, with the true scope and spirit of the disclosure indicated by the following claims.

Claims

1. A method for deploying resource equipment, characterized in that, The method comprises the following steps: acquiring multi-source device data, the multi-source device data comprising spatial remote sensing position data and position record data of resource devices unified to a target spatial coordinate system, the spatial remote sensing position data being geographic information data acquired through remote sensing technology, and the position record data being obtained based on business data spatialization processing; performing spatial analysis based on the spatial remote sensing position data, the position record data, and data source characteristics of the multi-source device data to obtain multiple reference ground object deviations, different reference ground object deviations having respective corresponding analysis detection modes; performing consistent weighted fusion according to the multiple reference ground object deviations to obtain a fusion result, and modifying the position record data according to the fusion result to obtain modified position data; optimizing layout and deployment of the resource devices according to the modified position data.

2. The method of claim 1, wherein, The acquiring of the multi-source device data comprises the following steps: performing address matching and / or coordinate standardization on business data to associate the business data to a geographic spatial position to obtain reference position record data; acquiring remote sensing grid image data and city vector map data and performing registration processing to obtain reference spatial remote sensing position data; converting the reference spatial remote sensing position data and the reference position record data to the target spatial coordinate system to obtain the spatial remote sensing position data and the position record data.

3. The method of claim 1, wherein, The spatial remote sensing position data comprises remote sensing ground object classification grids and city vector layers. The spatial analysis based on the spatial remote sensing position data, the position record data, and data source characteristics of the multi-source device data to obtain multiple reference ground object deviations comprises the following steps: performing denoising processing on the remote sensing ground object classification grids by using morphological opening and closing operation to obtain first remote sensing ground object data; preprocessing ground object objects in the city vector layers to obtain second spatial vector data; performing overlay analysis on the position record data and the first remote sensing ground object data based on the data source characteristics to obtain first reference ground object deviations; performing distance detection on the position record data and the second spatial vector data to obtain second reference ground object deviations; performing spatial interpolation processing on historical signal information to construct a signal field, and calculating signal strength of the position record data according to the signal field to determine third reference ground object deviations according to the signal strength.

4. The method of claim 3, wherein, The preprocessing of the ground object objects in the city vector layers to obtain the second spatial vector data comprises the following steps: constructing a building buffer zone according to building object data in the city vector layers, and extracting an outer contour of the building buffer zone to obtain building contour information; constructing a corridor buffer zone according to road center object data in the city vector layers; determining the second spatial vector data based on the building contour information and the corridor buffer zone.

5. The method of claim 3, wherein, The overlay analysis of the position record data and the first remote sensing ground object data based on the data source characteristics to obtain the first reference ground object deviations comprises the following steps: performing overlay analysis on the position record data and the first remote sensing ground object data to determine a category relationship between the position record data and the first remote sensing ground object data; Calculate the intersection and union ratio of the position record data and the first remote sensing feature data, and determine the first reference feature deviation according to the intersection and union ratio and the category relationship.

6. The method of claim 4, wherein, The distance detection based on the position record data and the second spatial vector data obtains a second reference feature deviation, including: Based on the position record data and the corridor buffer, calculate the first distance between the resource device and the road; Based on the position record data and the building contour information, calculate the second distance between the resource device and the building contour; Compare the first distance and the second distance with the corresponding distance threshold respectively to obtain the second reference feature deviation.

7. The method of claim 3, wherein, The consistency weighted fusion according to the plurality of reference feature deviations obtains a fusion result, and the position record data is corrected according to the fusion result to obtain corrected position data, including: Consistency processing is performed on the plurality of reference feature deviations to obtain target feature deviations corresponding to the plurality of reference feature deviations respectively; Based on the preset weight, the target feature deviations are weighted and fused to obtain a fusion result; If the fusion result is less than a preset fusion threshold, it is determined that the position record data has a feature deviation, and the position record data is corrected by using different correction methods corresponding to different feature deviations to obtain corrected position data.

8. The method of claim 1, wherein, The layout and deployment optimization of the resource device according to the corrected position data, including: Based on user demand information, geographic environmental barrier information, network topology and load information, business operation constraint information and the corrected position data, a target optimization function is constructed; According to the task type, a corresponding optimization solver is determined, and the target optimization function is solved based on the optimization solver to obtain target layout information, so that the resource device is deployed and optimized according to the target layout information.

9. A deployment apparatus of a resource device, characterized by, Including: The data acquisition module is used for acquiring multi-source device data, and the multi-source device data includes spatial remote sensing position data and position record data of resource devices unified to a target spatial coordinate system, the spatial remote sensing position data is geographic information data obtained by remote sensing technology, and the position record data is obtained based on business data spatialization processing; The spatial analysis module is used for spatial analysis based on the spatial remote sensing position data, the position record data and the data source characteristics of the multi-source device data to obtain a plurality of reference feature deviations, and different reference feature deviations have respective corresponding analysis detection methods; The correction processing module is used for consistency weighted fusion according to the plurality of reference feature deviations to obtain a fusion result, and the position record data is corrected according to the fusion result to obtain corrected position data; The deployment module is used for layout and deployment optimization of the resource device according to the corrected position data.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to realize the method in any one of claims 1-8.

11. An electronic device, comprising: Including: A processor; And A memory for storing executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 8 via execution of the executable instructions. The processor is configured to perform the method of any one of claims 1 to 8 via execution of the executable instructions.

Images