Communication network device positioning method and device

Abstract

The embodiment of the present invention provides a method and device for positioning components in a communication network. The method includes: obtaining two-dimensional position information and basic attribute information of a place to be positioned, and obtaining three-dimensional position information of the place to be positioned based on the two-dimensional position information and basic attribute information; obtaining design drawing images of sites and cells covering the place to be positioned, identifying components in the design drawing images based on a component recognition model, identifying component text information in the design drawing images based on a component text recognition model, and identifying the matching relationship between components and component text information based on a matching relationship model; obtaining three-dimensional position information of each component based on the three-dimensional position information of the place to be positioned, and components and component text information with matching relationships. The embodiment of the present invention realizes the precise positioning of each component in the place to be positioned, and can provide accurate position information for component detection even in a closed scene, thereby improving the efficiency of component fault detection.

Description

Technical Field

[0001] The present invention belongs to the technical field of mobile communication networks, and in particular relates to a method and device for locating a communication network component. Background Art

[0002] By locating the devices in the communication network, the specific location of the devices can be obtained, which facilitates the inspection of device failures. Therefore, device positioning is of great significance.

[0003] The existing technical solutions mainly locate the device position through manual on-site testing, investigation and monitoring of background alarm data, and perform device fault inspection. With the construction and development of communication networks, the business and data traffic in closed scenes such as indoors and trains are growing rapidly. However, due to the obstruction of ground buildings and the closed nature of underground facilities such as subway tracks, underground shopping malls, underground parking lots, etc., it is difficult to obtain the location information provided by the general satellite unit system, such as the location information of GPS (Global Positioning System) positioning, through manual on-site testing and investigation methods in these scenarios. Especially for the network coverage using a distributed system, the granularity of longitude and latitude collection is only at the network element level, and the general satellite system cannot accurately locate the device position. In addition, the manual method has lag, low efficiency and high cost. The method of monitoring background alarm data can only monitor explicit faults, and the alarm location information cannot be directly mapped to the actual location of the device, so the actual location of the device cannot be located.

[0004] In summary, the existing device positioning methods have hysteresis, low efficiency, high cost, and are unable to locate or accurately locate the actual position of the device. Summary of the invention

[0005] In order to overcome the problems of the above-mentioned existing device positioning methods, such as lag, low efficiency, high cost, and inability to locate or accurately locate the actual position of the device, or at least partially solve the above-mentioned problems, an embodiment of the present invention provides a communication network device positioning method and apparatus.

[0006] According to a first aspect of an embodiment of the present invention, a communication network device positioning method is provided, comprising:

[0007] Acquire two-dimensional position information and basic attribute information of the place to be located, and acquire three-dimensional position information of the place to be located according to the two-dimensional position information and basic attribute information;

[0008] Acquire a design drawing image of a site and a cell covering the location to be located, identify a device in the design drawing image based on a device recognition model, identify device text information in the design drawing image based on a device text recognition model, and identify a matching relationship between the device and the device text information based on a matching relationship model;

[0009] According to the three-dimensional position information of the place to be located, and the devices and device text information having a matching relationship, the three-dimensional position information of each device is obtained;

[0010] Among them, the device recognition model, device text recognition model and matching relationship model are trained and acquired based on the design drawing image samples, the marking of devices in the design drawing image samples, the marking of device text information, and the marking of the matching relationship between devices and device text information in the design drawing image samples.

[0011] Specifically, the step of obtaining the two-dimensional location information of the place to be located includes:

[0012] Obtaining the identifier of the place to be located through a web crawler or a public API;

[0013] According to the identifier of the place to be located, the two-dimensional boundary coordinates of the place to be located are parsed; wherein the identifier of the place to be located and the boundary coordinates are pre-associated and stored;

[0014] The two-dimensional boundary coordinates are converted into longitude and latitude formats, and the two-dimensional boundary coordinates in longitude and latitude formats are used as the two-dimensional position information of the place to be located.

[0015] Specifically, when the place to be located is a building, the basic attribute information includes the number of floors of the building and the height of each floor.

[0016] Specifically, the step of acquiring the three-dimensional position information of the place to be located according to the two-dimensional position information and the basic attribute information includes:

[0017] Calculating the reference coordinates of the place to be located according to the two-dimensional position information of the place to be located;

[0018] According to the basic attribute information of the place to be located, the two-dimensional position information and the reference coordinates are expanded into three-dimensional position information of the place to be located.

[0019] Specifically, the reference coordinates of the place to be located are calculated according to the two-dimensional position information of the place to be located by the following formula:

[0020]

[0021]

[0022] Wherein, (Gx, Gy) is the reference coordinates of the location to be located in the latitude and longitude format, (x i ,y i) is the two-dimensional boundary coordinate in the format of longitude and latitude of the i-th two-dimensional location information of the place to be located, (x i+1 ,y i+1 ) is the i+1th two-dimensional boundary coordinate in the longitude and latitude format in the two-dimensional position information of the place to be located.

[0023] Specifically, the device recognition model and the device text recognition model are a combination algorithm of an image feature extraction algorithm and an image recognition algorithm;

[0024] Wherein, the image feature extraction algorithm includes SIFT algorithm and SURF algorithm;

[0025] The image recognition algorithm includes a DPM algorithm, an LDA linear discriminant algorithm and a convolutional neural network algorithm;

[0026] The matching relationship model is a support vector machine or a Fast R-CNN algorithm.

[0027] Specifically, before identifying the device in the design drawing image based on the device identification model, identifying the device text information in the design drawing image based on the device text recognition model, and identifying the matching relationship between the device and the device text information based on the matching relationship model, the method further includes:

[0028] Acquire multiple combinations of device recognition models, device text recognition models, and matching relationship models; wherein at least one model is different between any two combinations;

[0029] Evaluate the output results of each combination to obtain the comprehensive performance of each combination;

[0030] A combination with the best comprehensive performance is selected to use the selected combination to identify the device, device text information, and the matching relationship between the device and the device text information in the design drawing image.

[0031] Specifically, the device text information includes the device number, device name, coordinates of the device in the design drawing, the floor where the device is located, and the cable routing path and length between devices;

[0032] Accordingly, according to the three-dimensional position information of the place to be located, and the devices and device text information having a matching relationship, the step of obtaining the three-dimensional position information of each device includes:

[0033] According to the floor where the device is located and the three-dimensional position information of the place to be located, obtaining the height where the device is located;

[0034] Calculate the distance between the device and the reference axis formed by the three-dimensional position information extended from the reference coordinates according to the coordinates of the device in the design drawing, the cable routing path and length between the devices;

[0035] Acquire the longitude and latitude of the device according to the distance and the longitude and latitude of the reference coordinates;

[0036] The longitude, latitude and altitude of the device are used as the three-dimensional position information of the device.

[0037] According to a second aspect of an embodiment of the present invention, a communication network device positioning device is provided, comprising:

[0038] An acquisition module, used to acquire two-dimensional position information and basic attribute information of the place to be located, and acquire three-dimensional position information of the place to be located according to the two-dimensional position information and basic attribute information;

[0039] an identification module, used to obtain a design drawing image of a site and a cell covering the location to be located, identify a device in the design drawing image based on a device identification model, identify device text information in the design drawing image based on a device text recognition model, and identify a matching relationship between the device and the device text information based on a matching relationship model;

[0040] A positioning module, used for acquiring the three-dimensional position information of each of the devices according to the three-dimensional position information of the place to be positioned, and the devices and device text information having a matching relationship;

[0041] Among them, the device recognition model, device text recognition model and matching relationship model are trained and acquired based on the design drawing image samples, the marking of devices in the design drawing image samples, the marking of device text information, and the marking of the matching relationship between devices and device text information in the design drawing image samples.

[0042] According to a third aspect of an embodiment of the present invention, there is also provided an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor calls the program instructions to execute a communication network device positioning method provided by any possible implementation of the various possible implementations of the first aspect.

[0043] An embodiment of the present invention provides a communication network device positioning method and device. The method collects two-dimensional position information of a place to be positioned, and obtains three-dimensional position information of the place to be positioned in combination with basic attribute information of the place to be positioned; then identifies devices and device description information in design drawing images of coverage sites and cells of the place to be positioned, as well as the matching relationship between the two; finally, based on the three-dimensional position information and device description information of the place to be positioned, accurate position positioning of each device in the place to be positioned is achieved through coordinate mapping, and accurate position information can be provided for device detection even in a closed scene, thereby improving the efficiency of device fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A schematic diagram of the overall flow of a communication network device positioning method provided by an embodiment of the present invention;

[0046] Figure 2 A schematic diagram of the overall structure of a communication network device positioning device provided by an embodiment of the present invention;

[0047] Figure 3 A schematic diagram of the overall structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution 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 are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] In one embodiment of the present invention, a method for locating a communication network device is provided. Figure 1 The overall flow diagram of the communication network device positioning method provided by an embodiment of the present invention comprises: S101, obtaining two-dimensional position information and basic attribute information of a place to be positioned, and obtaining three-dimensional position information of the place to be positioned according to the two-dimensional position information and basic attribute information;

[0050] The place to be located refers to a place where the communication network device needs to be located, such as a building and an underground parking lot. This embodiment is not limited to the type of the place to be located. The two-dimensional location information of the place to be located refers to the longitude and latitude information of the area occupied by the place to be located. The basic attribute information is attribute information related to the height of the place to be located. The basic attribute information of different types of places to be located is different. When the place to be located is a building, the basic attribute information includes the number of floors of the building and the height of each floor.

[0051] After obtaining the two-dimensional location information and basic attribute information of the place to be located, the height information of the place to be located is determined by the basic attribute information, and the two-dimensional location information is expanded in the height direction according to the height information to obtain the three-dimensional location information of the place to be located, that is, the height, longitude and latitude information of each point in the place to be located. The three-dimensional location information is stored in the three-dimensional location information library of the place to be located for subsequent analysis.

[0052] S102, obtaining a design drawing image of a site and a cell covering the location to be located, identifying a device in the design drawing image based on a device recognition model, identifying device text information in the design drawing image based on a device text recognition model, and identifying a matching relationship between the device and the device text information based on a matching relationship model; wherein the device recognition model, the device text recognition model, and the matching relationship model are trained and acquired based on a design drawing image sample, annotating of the device in the design drawing image sample, annotating of the device text information, and annotating of the matching relationship between the device and the device text information in the design drawing image sample;

[0053] The engineering parameter data of the site is collected. The collected engineering parameter data mainly includes the site name, cell name, eNBID, ECGI, and the longitude and latitude of the site and cell. According to the longitude and latitude of the site and cell, and the two-dimensional location information of the place to be located, the site and cell covering the place to be located are obtained. The engineering parameter data information of the site and cell covering the place to be located is associated with the three-dimensional location information of the place to be located and stored, ensuring the timely location of the network quality problem.

[0054] Obtain the design drawings of the sites and communities covering the location to be located, and collect high-definition images of the design drawings through digital cameras, etc. The design drawings include but are not limited to indoor distribution system design drawings, basic information of property points and engineering quantity table drawings, device installation point plane drawings and system topology drawings, etc.

[0055] The device recognition model, device text recognition model and matching relationship model are trained before being used. First, a large number of design drawing image samples are collected, and the devices, device text information, and matching relationships between devices and device text information in the design drawing image samples are annotated. The annotation can be performed manually. The collected design drawing image samples are scaled, rotated, and other operations are performed to achieve image enhancement, and finally a training image data set is formed. The device recognition model, device text recognition model and matching relationship model are trained based on the acquired training image data set.

[0056] Use the trained model to identify components and component text information in the design drawing image, such as component number, component name, and cable length between components, as well as the matching relationship between components and component text information.

[0057] S103, acquiring the three-dimensional position information of each of the devices according to the three-dimensional position information of the place to be located, and the devices and device text information having a matching relationship.

[0058] This embodiment is not limited to the method of obtaining the three-dimensional location information of each device based on the three-dimensional location information of the place to be located, and the devices and device text information with matching relationships. By locating the devices of the sites and cells covering the place to be located, the three-dimensional location information of each device is output, and the three-dimensional location information of the device can be displayed in a three-dimensional GIS (Geographic Information System). Furthermore, the devices that may have faults can be located in real time in combination with the user's complaint location, so as to improve the rectification efficiency and effectively support the daily management and control of the device.

[0059] This embodiment acquires the three-dimensional position information of the place to be located by collecting the two-dimensional position information of the place to be located, and combines it with the basic attribute information of the place to be located; then identifies the components and component description information in the design drawing images of the coverage sites and cells of the place to be located, as well as the matching relationship between the two; finally, based on the three-dimensional position information and component description information of the place to be located, the precise position positioning of each component in the place to be located is achieved through coordinate mapping, which can provide accurate position information for component detection even in a closed scene, thereby improving the efficiency of device fault troubleshooting.

[0060] Based on the above embodiments, the steps for obtaining the two-dimensional location information of the place to be located in this embodiment include: obtaining the identifier UID of the place to be located through a web crawler or a public API (Application Programming Interface); parsing the two-dimensional boundary coordinates of the place to be located according to the identifier of the place to be located; wherein the identifier and boundary coordinates of the place to be located are pre-associated and stored; converting the two-dimensional boundary coordinates into longitude and latitude format, and using the two-dimensional boundary coordinates in the longitude and latitude format as the two-dimensional location information of the place to be located.

[0061] The two-dimensional boundary coordinates of the place to be located refer to the coordinates of each point on the boundary of the area occupied by the place to be located.

[0062] Based on the above embodiment, the step of obtaining the three-dimensional position information of the place to be located based on the two-dimensional position information and the basic attribute information in this embodiment includes: calculating the reference coordinates of the place to be located based on the two-dimensional position information of the place to be located; and expanding the two-dimensional position information and the reference coordinates into the three-dimensional position information of the place to be located based on the basic attribute information of the place to be located.

[0063] Specifically, since the boundary of the place to be located is generally an irregular polygon, and may be a convex polygon or a concave polygon. Therefore, in this embodiment, the centroid coordinates of the boundary polygon of the place to be located are used as the reference coordinates of the place to be located. After the height information of the place to be located is determined by the basic attribute information, the two-dimensional position information is expanded in the height direction according to the height information to obtain the three-dimensional position information of the place to be located in space, and the reference coordinates are expanded in the height direction according to the height information to obtain the three-dimensional position information of the reference axis. The three-dimensional position information of the place to be located in space and the three-dimensional position information of the reference axis are used as the three-dimensional position information of the place to be located. For example, when the place to be located is a certain building, according to the number of floors of the building and the height of each floor, the height of each floor can be set to 5 meters, thereby determining the three-dimensional position information of each floor of the building, and the three-dimensional position information of the reference axis.

[0064] On the basis of the above embodiment, this embodiment calculates the reference coordinates of the place to be located according to the two-dimensional position information of the place to be located by the following formula:

[0065]

[0066]

[0067] Wherein, (Gx, Gy) is the reference coordinates of the location to be located in the latitude and longitude format, (x i ,yi ) is the two-dimensional boundary coordinate in the format of longitude and latitude of the i-th two-dimensional location information of the place to be located, (x i+1 ,y i+1 ) is the i+1th two-dimensional boundary coordinate in the longitude and latitude format in the two-dimensional position information of the place to be located.

[0068] On the basis of the above embodiments, the device recognition model and the device text recognition model described in this embodiment are a combination algorithm of an image feature extraction algorithm and an image recognition algorithm; wherein the image feature extraction algorithm includes a SIFT (Scale-invariant Feature Transform) algorithm and a SURF (Speeded Up Robust Features) algorithm; the image recognition algorithm includes a DPM (Deformable Parts Model) algorithm, an LDA (Linear Discriminant Analysis) algorithm and a convolutional neural network algorithm; the matching relationship model is a support vector machine or a Fast R-CNN algorithm. wherein the Fast R-CNN algorithm is a comprehensive algorithm of selective search, convolutional neural network and ROI extraction algorithm.

[0069] On the basis of the above embodiments, in this embodiment, before identifying the device in the design drawing image based on the device identification model, identifying the device text information in the design drawing image based on the device text identification model, and identifying the matching relationship between the device and the device text information based on the matching relationship model, the method further includes: obtaining multiple combinations of device identification models, device text identification models, and matching relationship models; wherein at least one model is different between any two combinations;

[0070] For example, in one combination, the device recognition model is a hybrid algorithm of the SIFT algorithm and the convolutional neural network algorithm, the device text recognition model is a hybrid algorithm of the SURF algorithm and the convolutional neural network algorithm, and the matching relationship model is a support vector machine; in another combination, the device recognition model is a hybrid algorithm of the SIFT algorithm and the convolutional neural network algorithm, the device text recognition model is a hybrid algorithm of the SIFT algorithm and the convolutional neural network algorithm, and the matching relationship model is a support vector machine. The two combinations only differ in the device text recognition model.

[0071] The output results of each combination are evaluated to obtain the comprehensive performance of each combination; the combination with the best comprehensive performance is selected to use the selected combination to identify the device, device text information, and the matching relationship between the device and the device text information in the design drawing image.

[0072] The output results of each combination are compared from the perspectives of matching efficiency, rotation scale transformation, illumination transformation and viewpoint transformation, and the combination with the best comprehensive performance is selected for device positioning.

[0073] Based on the above embodiments, the device text information described in this embodiment includes the device number, device name, the coordinates of the device in the design drawing, the floor where the device is located, and the cable routing path and length between the devices;

[0074] Accordingly, according to the three-dimensional position information of the place to be located, and the devices and device text information having a matching relationship, the step of obtaining the three-dimensional position information of each device includes: obtaining the height of the device according to the floor where the device is located and the three-dimensional position information of the place to be located;

[0075] According to the three-dimensional position information of each floor in the three-dimensional position information of the location to be located, the height of each floor can be determined. According to the floor where the device is located, the height of the device can be known.

[0076] Calculate the distance between the device and the reference axis formed by the three-dimensional position information extended from the reference coordinates according to the coordinates of the device in the design drawing, the cable routing path and length between the devices;

[0077] Since the starting position of the cable in the communication network to each floor is known, then starting from the starting position, each device is connected in sequence through the cable. The actual distance between the starting position and the reference axis is calculated. According to the path from the starting position to each device, the cable length, the coordinates of each device in the design drawing, and the actual distance between the starting position and the reference axis, the actual distance between each device on the floor and the reference axis is calculated.

[0078] The longitude and latitude of the device are acquired according to the distance and the longitude and latitude of the reference coordinates; and the longitude, latitude and altitude of the device are used as the three-dimensional position information of the device.

[0079] Since the longitude and latitude of the reference axis and the actual distance between the device and the reference axis are known, the longitude and latitude of the device can be calculated. Traverse all devices covering the sites and cells of the location to be located to obtain the three-dimensional location information of each device. Store the three-dimensional location information of all devices in the device location information database.

[0080] In another embodiment of the present invention, a communication network device positioning apparatus is provided, which is used to implement the methods in the above embodiments. Therefore, the description and definition in the above embodiments of the communication network device positioning method can be used to understand the various execution modules in the embodiments of the present invention. Figure 2The overall structure diagram of the communication network device positioning device provided by the embodiment of the present invention includes an acquisition module 201, an identification module 202 and a positioning module 203, wherein:

[0081] The acquisition module 201 is used to acquire the two-dimensional position information and basic attribute information of the place to be located, and acquire the three-dimensional position information of the place to be located according to the two-dimensional position information and basic attribute information;

[0082] The place to be located refers to a place where the communication network device needs to be located, such as a building and an underground parking lot. This embodiment is not limited to the type of the place to be located. The two-dimensional location information of the place to be located refers to the longitude and latitude information of the area occupied by the place to be located. The basic attribute information is attribute information related to the height of the place to be located. The basic attribute information of different types of places to be located is different. When the place to be located is a building, the basic attribute information includes the number of floors of the building and the height of each floor.

[0083] After acquiring the two-dimensional location information and basic attribute information of the place to be located, the acquisition module 201 determines the height information of the place to be located through the basic attribute information, expands the two-dimensional location information in the height direction according to the height information, and obtains the three-dimensional location information of the place to be located, that is, the height, longitude and latitude information of each point in the place to be located. The three-dimensional location information is stored in the three-dimensional location information library of the place to be located for subsequent analysis.

[0084] The identification module 202 is used to obtain a design drawing image of a site and a cell covering the location to be located, identify a device in the design drawing image based on a device identification model, identify device text information in the design drawing image based on a device text recognition model, and identify a matching relationship between the device and the device text information based on a matching relationship model;

[0085] The engineering parameter data of the site is collected. The collected engineering parameter data mainly includes the site name, cell name, eNBID, ECGI, and the longitude and latitude of the site and cell. According to the longitude and latitude of the site and cell, and the two-dimensional location information of the place to be located, the site and cell covering the place to be located are obtained. The engineering parameter data information of the site and cell covering the place to be located is associated with the three-dimensional location information of the place to be located and stored, ensuring the timely location of the network quality problem.

[0086] Obtain the design drawings of the sites and communities covering the location to be located, and collect high-definition images of the design drawings through digital cameras, etc. The design drawings include but are not limited to indoor distribution system design drawings, basic information of property points and engineering quantity table drawings, device installation point plane drawings and system topology drawings, etc.

[0087] The device recognition model, device text recognition model and matching relationship model are trained before being used. First, a large number of design drawing image samples are collected, and the devices, device text information, and matching relationships between devices and device text information in the design drawing image samples are annotated. The annotation can be performed manually. The collected design drawing image samples are scaled, rotated, and other operations are performed to achieve image enhancement, and finally a training image data set is formed. The device recognition model, device text recognition model and matching relationship model are trained based on the acquired training image data set.

[0088] The recognition module 202 uses the trained model to recognize the components and component text information in the design drawing image, such as component numbers, component names, and cable lengths between components, as well as the matching relationship between components and component text information.

[0089] The positioning module 203 is used to obtain the three-dimensional position information of each device according to the three-dimensional position information of the place to be positioned, and the devices and device text information with a matching relationship; wherein the device recognition model, the device text recognition model and the matching relationship model are trained and acquired based on the design drawing image samples, the marking of the devices in the design drawing image samples, the marking of the device text information, and the marking of the matching relationship between the devices and the device text information in the design drawing image samples.

[0090] This embodiment is not limited to the method of obtaining the three-dimensional position information of each device based on the three-dimensional position information of the place to be located, and the devices and device text information having a matching relationship. The positioning module 203 outputs the three-dimensional position information of each device by positioning the devices of the sites and cells covering the place to be located, and can display the three-dimensional position information of the device in three dimensions.

[0091] This embodiment acquires the three-dimensional position information of the place to be located by collecting the two-dimensional position information of the place to be located, and combines it with the basic attribute information of the place to be located; then identifies the components and component description information in the design drawing images of the coverage sites and cells of the place to be located, as well as the matching relationship between the two; finally, based on the three-dimensional position information and component description information of the place to be located, the precise position positioning of each component in the place to be located is achieved through coordinate mapping, which can provide accurate position information for component detection even in a closed scene, thereby improving the efficiency of device fault troubleshooting.

[0092] Based on the above embodiments, the acquisition module in this embodiment is specifically used for: acquiring the identifier of the place to be located through a web crawler or a public API; parsing the two-dimensional boundary coordinates of the place to be located according to the identifier of the place to be located; wherein the identifier and boundary coordinates of the place to be located are pre-associated and stored; converting the two-dimensional boundary coordinates into longitude and latitude format, and using the two-dimensional boundary coordinates in the longitude and latitude format as the two-dimensional position information of the place to be located.

[0093] On the basis of the above embodiment, in this embodiment, when the place to be located is a building, the basic attribute information includes the number of floors of the building and the height of each floor.

[0094] Based on the above embodiments, the acquisition module in this embodiment is specifically used to: calculate the reference coordinates of the place to be located based on the two-dimensional position information of the place to be located; and expand the two-dimensional position information and the reference coordinates into the three-dimensional position information of the place to be located based on the basic attribute information of the place to be located.

[0095] On the basis of the above embodiment, in this embodiment, the acquisition module calculates the reference coordinates of the place to be located according to the two-dimensional position information of the place to be located by the following formula:

[0096]

[0097]

[0098] Wherein, (Gx, Gy) is the reference coordinates of the location to be located in the latitude and longitude format, (x i ,y i ) is the two-dimensional boundary coordinate in the format of longitude and latitude of the i-th two-dimensional location information of the place to be located, (x i+1 ,y i+1 ) is the i+1th two-dimensional boundary coordinate in the longitude and latitude format in the two-dimensional position information of the place to be located.

[0099] Based on the above embodiments, the device recognition model and the device text recognition model in this embodiment are a combination algorithm of an image feature extraction algorithm and an image recognition algorithm; wherein the image feature extraction algorithm includes a SIFT algorithm and a SURF algorithm; the image recognition algorithm includes a DPM algorithm, an LDA linear discriminant algorithm and a convolutional neural network algorithm; and the matching relationship model is a support vector machine or a Fast R-CNN algorithm.

[0100] Based on the above embodiment, this embodiment also includes a selection module for obtaining multiple combinations of device identification models, device text identification models and matching relationship models; wherein at least one model is different between any two combinations; the output results of each combination are evaluated to obtain the comprehensive performance of each combination; the combination with the best comprehensive performance is selected to use the selected combination to identify the device, device text information, and the matching relationship between the device and the device text information in the design drawing image.

[0101] On the basis of the above embodiments, the device text information in this embodiment includes the device number, the device name, the coordinates of the device in the design drawing, the floor where the device is located, and the cable routing path and length between devices; accordingly, the positioning module is specifically used to: obtain the height of the device according to the floor where the device is located and the three-dimensional position information of the place to be positioned; calculate the distance between the device and the reference axis formed by the three-dimensional position information extended by the reference coordinates according to the coordinates of the device in the design drawing, the cable routing path and length between devices; obtain the longitude and latitude of the device according to the distance and the longitude and latitude of the reference coordinates; use the longitude, latitude and height of the device as the three-dimensional position information of the device.

[0102] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3 As shown, the electronic device may include: a processor 301, a communication interface 302, a memory 303 and a communication bus 304, wherein the processor 301, the communication interface 302 and the memory 303 communicate with each other through the communication bus 304. The processor 301 may call the logic instructions in the memory 303 to execute the following method: obtaining the two-dimensional position information and basic attribute information of the place to be located, and obtaining the three-dimensional position information of the place to be located according to the two-dimensional position information and the basic attribute information; obtaining the design drawing images of the sites and cells covering the place to be located, identifying the devices in the design drawing images based on the device recognition model, identifying the device text information in the design drawing images based on the device text recognition model, and identifying the matching relationship between the device and the device text information based on the matching relationship model; obtaining the three-dimensional position information of each device according to the three-dimensional position information of the place to be located, and the devices and device text information having a matching relationship.

[0103] In addition, the logic instructions in the above-mentioned memory 303 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0104] The present embodiment provides a non-transitory computer-readable storage medium, which stores computer instructions. The computer instructions enable a computer to execute the methods provided by the above-mentioned method embodiments, for example, including: obtaining two-dimensional position information and basic attribute information of a place to be located, and obtaining three-dimensional position information of the place to be located based on the two-dimensional position information and the basic attribute information; obtaining design drawing images of sites and cells covering the place to be located, identifying devices in the design drawing images based on a device recognition model, identifying device text information in the design drawing images based on a device text recognition model, and identifying a matching relationship between a device and device text information based on a matching relationship model; obtaining three-dimensional position information of each device based on the three-dimensional position information of the place to be located, and devices and device text information having a matching relationship.

[0105] A person of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various media that can store program codes.

[0106] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0107] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A communication network device positioning method, characterized in that: include: Acquire two-dimensional position information and basic attribute information of the place to be located, and acquire three-dimensional position information of the place to be located according to the two-dimensional position information and basic attribute information; Acquire a design drawing image of a site and a cell covering the location to be located, identify a device in the design drawing image based on a device recognition model, identify device text information in the design drawing image based on a device text recognition model, and identify a matching relationship between the device and the device text information based on a matching relationship model; According to the three-dimensional position information of the place to be located, and the devices and device text information having a matching relationship, the three-dimensional position information of each device is obtained; The device recognition model, the device text recognition model and the matching relationship model are trained and acquired based on the design drawing image samples, the annotations of the devices in the design drawing image samples, the annotations of the device text information, and the annotations of the matching relationship between the devices and the device text information in the design drawing image samples; The device text information includes the device number, device name, the coordinates of the device in the design drawing, the floor where the device is located, and the cable routing path and length between devices.

2. The communication network device positioning method according to claim 1, characterized in that: The steps of obtaining the two-dimensional location information of the place to be located include: Obtaining the identifier of the place to be located through a web crawler or a public API; According to the identifier of the place to be located, the two-dimensional boundary coordinates of the place to be located are parsed; wherein the identifier of the place to be located and the boundary coordinates are pre-associated and stored; The two-dimensional boundary coordinates are converted into longitude and latitude formats, and the two-dimensional boundary coordinates in longitude and latitude formats are used as the two-dimensional position information of the place to be located.

3. The communication network device positioning method according to claim 2, characterized in that: When the place to be located is a building, the basic attribute information includes the number of floors of the building and the height of each floor.

4. The communication network device positioning method according to claim 3, characterized in that: The step of acquiring the three-dimensional position information of the place to be located according to the two-dimensional position information and the basic attribute information comprises: Calculating the reference coordinates of the place to be located according to the two-dimensional position information of the place to be located; According to the basic attribute information of the place to be located, the two-dimensional position information and the reference coordinates are expanded into three-dimensional position information of the place to be located.

5. The communication network device positioning method according to claim 4, characterized in that: The reference coordinates of the place to be located are calculated according to the two-dimensional position information of the place to be located by the following formula: ； ； Among them, (Gx, Gy) is the reference coordinates of the location to be located in the latitude and longitude format, (x i ,y i ) is the two-dimensional boundary coordinate in the format of longitude and latitude of the i-th two-dimensional location information of the place to be located, (x i+1 ,y i+1 ) is the i+1th two-dimensional boundary coordinate in the longitude and latitude format in the two-dimensional position information of the place to be located.

6. The method for locating a communication network device according to any one of claims 1 to 5, characterized in that: The device recognition model and the device text recognition model are a combination algorithm of an image feature extraction algorithm and an image recognition algorithm; Wherein, the image feature extraction algorithm includes SIFT algorithm and SURF algorithm; The image recognition algorithm includes a DPM algorithm, an LDA linear discriminant algorithm and a convolutional neural network algorithm; The matching relationship model is a support vector machine or a Fast R-CNN algorithm.

7. The communication network device positioning method according to any one of claims 1 to 5, characterized in that: Before identifying the device in the design drawing image based on the device identification model, identifying the device text information in the design drawing image based on the device text recognition model, and identifying the matching relationship between the device and the device text information based on the matching relationship model, the following further comprises: Acquire multiple combinations of device recognition models, device text recognition models, and matching relationship models; wherein at least one model is different between any two combinations; Evaluate the output results of each combination to obtain the comprehensive performance of each combination; A combination with the best comprehensive performance is selected to use the selected combination to identify the device, device text information, and the matching relationship between the device and the device text information in the design drawing image.

8. The communication network device positioning method according to claim 4, characterized in that: According to the three-dimensional position information of the place to be located, and the devices and device text information having a matching relationship, the step of obtaining the three-dimensional position information of each device includes: According to the floor where the device is located and the three-dimensional position information of the place to be located, obtaining the height where the device is located; Calculate the distance between the device and the reference axis formed by the three-dimensional position information extended from the reference coordinates according to the coordinates of the device in the design drawing, the cable routing path and length between the devices; Acquire the longitude and latitude of the device according to the distance and the longitude and latitude of the reference coordinates; The longitude, latitude and altitude of the device are used as the three-dimensional position information of the device.

9. A communication network device positioning device, characterized in that: include: An acquisition module, used to acquire two-dimensional position information and basic attribute information of the place to be located, and acquire three-dimensional position information of the place to be located according to the two-dimensional position information and basic attribute information; an identification module, used to obtain a design drawing image of a site and a cell covering the location to be located, identify a device in the design drawing image based on a device identification model, identify device text information in the design drawing image based on a device text recognition model, and identify a matching relationship between the device and the device text information based on a matching relationship model; A positioning module, used for acquiring the three-dimensional position information of each of the devices according to the three-dimensional position information of the place to be positioned, and the devices and device text information having a matching relationship; The device recognition model, the device text recognition model and the matching relationship model are trained and acquired based on the design drawing image samples, the annotations of the devices in the design drawing image samples, the annotations of the device text information, and the annotations of the matching relationship between the devices and the device text information in the design drawing image samples; The device text information includes the device number, device name, the coordinates of the device in the design drawing, the floor where the device is located, and the cable routing path and length between devices.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the communication network device positioning method according to any one of claims 1 to 8 are implemented.

Images