CN118233949A - Building network signal coverage assessment method, device, equipment and medium - Google Patents
Building network signal coverage assessment method, device, equipment and medium Download PDFInfo
- Publication number
- CN118233949A CN118233949A CN202410469279.1A CN202410469279A CN118233949A CN 118233949 A CN118233949 A CN 118233949A CN 202410469279 A CN202410469279 A CN 202410469279A CN 118233949 A CN118233949 A CN 118233949A
- Authority
- CN
- China
- Prior art keywords
- information
- network signal
- building
- height
- network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims description 27
- 230000008447 perception Effects 0.000 claims abstract description 70
- 238000005070 sampling Methods 0.000 claims abstract description 54
- 238000007781 pre-processing Methods 0.000 claims abstract description 17
- 238000011156 evaluation Methods 0.000 claims abstract description 13
- 238000004891 communication Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 42
- 210000002569 neuron Anatomy 0.000 claims description 18
- 238000012360 testing method Methods 0.000 claims description 14
- 230000002776 aggregation Effects 0.000 claims description 10
- 238000004220 aggregation Methods 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 5
- 238000013480 data collection Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/22—Traffic simulation tools or models
- H04W16/225—Traffic simulation tools or models for indoor or short range network
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of network communication, in particular to a building network signal coverage evaluation method, a device, equipment and a medium, which are used for acquiring target building layer information and network signal perception data of all sampling points in a set area; preprocessing network signal perception data based on target building layer information; extracting network environment information from the preprocessed network signal perception data, and inputting a trained height identification model to obtain height information corresponding to each sampling point; extracting network signal information from the preprocessed network signal perception data, and carrying out layered network signal coverage analysis on the target building based on the height information. And the height information is obtained through the height identification model, and the data sub-building collection and the data sub-floor collection are carried out, so that the network signal coverage evaluation of each floor in each building is realized, the network signal coverage problem area is accurately positioned, and the data support is provided for the indoor distribution planning of the 5G network.
Description
Technical Field
The application relates to the technical field of network communication, in particular to a building network signal coverage assessment method, device, equipment and medium.
Background
At present, good coverage of 5G signals exists in personnel concentration areas, key areas, traffic roads and the like, but the coverage of the building depth is insufficient, and in order to locate the building coverage problem, the existing building 5G signal coverage evaluation analysis mainly comprises the following 3 modes:
(1) 5G coverage analysis based on GPS altitude. However, the altitude error based on the GPS is about 10m, the partial area error can reach tens of meters, the accuracy of the 5G coverage layering result based on the data is low, and the actual height of the user cannot be truly reflected;
(2) 5G overlay analysis based on MR data TA+AOA. However, the method for estimating the distance between the base station and the UE according to the TA and obtaining the approximate position information of the user terminal according to the AOA information has the advantages that the positioning accuracy is greatly affected by the environment, the positioning is accurate in open areas, the positioning accuracy is poor in areas with more buildings, and the error range of the positioning accuracy is about 40 meters;
(3) Based on manual building 5G coverage assessment. However, the manual census has large workload, low efficiency and low cost, the general census efficiency is 5 buildings/day, and a large amount of personnel, test equipment, test vehicles and the like are required to be input for completing a large number of building census; and the general survey is mainly a sampling test of part of floors, generally high, medium and bottom floors, and the coverage condition of the building cannot be comprehensively and generally surveyed.
Disclosure of Invention
In order to overcome the defects in the prior art, the application aims to provide a building network signal coverage assessment method, device, equipment and medium, which can obtain more accurate positioning information through a constructed height identification model so as to carry out coverage assessment of network signals on building layering and provide support for accurate positioning of building coverage problems.
In a first aspect, the present application provides a building network signal coverage assessment method, including the steps of:
Acquiring network signal perception data of all sampling points in a set area and target building layer information; the set area comprises a coverage area of a target building, and the network signal perception data comprises network signal information and network environment information;
preprocessing the network signal perception data based on the target building layer information;
extracting the network environment information from the preprocessed network signal perception data, and inputting the network environment information into a trained height identification model to obtain height information corresponding to each sampling point;
Extracting the network signal information from the preprocessed network signal perception data, and carrying out layered network signal coverage analysis on the target building based on the obtained height information.
In some embodiments, the network signal perception data further comprises coordinate information of each sampling point, and the target building layer information comprises the number and boundary information of each building.
In some embodiments, the preprocessing the network signal awareness data based on the target building layer information includes the steps of:
Extracting coordinate information of each sampling point from the acquired network signal perception data;
Extracting boundary information of each building from the target building layer information;
And eliminating network signal perception data corresponding to sampling points arranged outside the building based on the coordinate information and the boundary information, and carrying out data aggregation according to the building number.
In some embodiments, the network environment information includes time information, air pressure information, temperature information, terminal manufacturer information and terminal model information, the altitude identification model is constructed based on a BP neural network, the BP neural network includes an input layer, an output layer and an hidden layer disposed between the input layer and the output layer, the hidden layer includes ten neurons, and the input layer includes five neurons, which respectively represent the time information, the air pressure information, the temperature information, the terminal manufacturer information and the terminal model information; the output information includes a neuron representing altitude information.
In some embodiments, the height identification model is trained by the following steps:
Network environment information and corresponding height information acquired by using terminals of different manufacturers and different models in selected different positions, different heights and different types of buildings are used as data sets, and the data sets are divided into training sets and testing sets according to set proportions;
Training a pre-constructed height identification model based on the training set, adjusting parameters of the height identification model according to errors between output results of the height identification model and real height information, and performing iterative training until the parameters of the height identification model are converged to obtain a height identification model to be tested;
And evaluating the to-be-tested height identification model based on the test set, and determining the to-be-tested height identification model as a trained height identification model if an evaluation result reaches a set threshold value.
In some embodiments, the hierarchical network signal coverage analysis of the target building based on the obtained altitude information includes the steps of:
Based on the obtained height information, carrying out data aggregation on the preprocessed network signal perception data according to the defined floors;
And carrying out network signal coverage analysis by utilizing the network signal perception data corresponding to each floor of each building.
In some embodiments, each building is floor-defined by an actual floor height, each building is floor-defined by a set miss height, or each building is floor-defined by a set high, medium, or low level.
In a second aspect, a building network signal coverage assessment apparatus includes:
The acquisition module is used for acquiring network signal perception data of all sampling points in the target building layer information and the set area; the set area comprises a coverage area of a target building, and the network signal perception data comprises network signal information and network environment information;
The preprocessing module is used for preprocessing the network signal perception data based on the target building layer information;
the identification module is used for extracting the network environment information from the preprocessed network signal perception data, inputting the network environment information into a trained height identification model and obtaining the height information corresponding to each sampling point;
and the analysis module is used for extracting the network signal information from the preprocessed network signal perception data and carrying out layered network signal coverage analysis on the target building based on the obtained height information.
In a third aspect, the present application provides an electronic device comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory in communication via the bus when the electronic device is running, the machine-readable instructions when executed by the processor performing the steps of the building network signal coverage assessment method according to any of the first aspects.
In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the building network signal coverage assessment method according to any of the first aspects.
According to the building network signal coverage evaluation method, device, equipment and medium, target building layer information and network signal perception data of all sampling points in a set area are obtained; the set area comprises a coverage area of a target building, and the network signal perception data comprises network signal information and network environment information; preprocessing the network signal perception data based on the target building layer information; extracting the network environment information from the preprocessed network signal perception data, and inputting the network environment information into a trained height identification model to obtain height information corresponding to each sampling point; extracting the network signal information from the preprocessed network signal perception data, and carrying out layered network signal coverage analysis on the target building based on the obtained height information. The height information obtained through the constructed height identification model is more accurate, and the building can be layered in various modes, so that the coverage evaluation of network signals is carried out on the building layering, and support is provided for the accurate positioning of building coverage problems.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows a flow chart of a building network signal coverage assessment method according to an embodiment of the present application;
FIG. 2 illustrates a flow chart of preprocessing the network signal awareness data based on the target building level information in accordance with an embodiment of the present application;
FIG. 3 shows a schematic GIS distribution diagram of sampling points according to an embodiment of the present application;
FIG. 4 is a MAP layer diagram of a target building according to an embodiment of the present application;
FIG. 5 is a schematic diagram showing the results of building data collection according to an embodiment of the present application;
FIG. 6 illustrates a flow chart of training a highly identified model in accordance with an embodiment of the present application;
fig. 7 shows a schematic structural diagram of a BP neural network according to an embodiment of the present application;
FIG. 8 shows a flow chart of a hierarchical network signal coverage analysis of the target building based on the altitude information obtained in accordance with an embodiment of the present application;
FIG. 9 shows a block diagram of a training device provided by an embodiment of the present application;
fig. 10 shows a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for the purpose of illustration and description only and are not intended to limit the scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. A flowchart, as used in this disclosure, illustrates operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be implemented out of order and that steps without logical context may be performed in reverse order or concurrently. Moreover, one or more other operations may be added to or removed from the flow diagrams by those skilled in the art under the direction of the present disclosure.
In addition, the described embodiments are only some, but not all, embodiments of the application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present application.
It should be noted that the term "comprising" will be used in embodiments of the application to indicate the presence of the features stated hereafter, but not to exclude the addition of other features.
In view of the problems of low accuracy, large error and difficult positioning of 5G network coverage problem areas in the prior art of user positioning in a building, the application provides a building network signal coverage evaluation method, which can obtain more accurate positioning information through a constructed height identification model so as to evaluate the coverage of network signals in building layering and provide support for the accurate positioning of building coverage problems.
In an embodiment, referring to fig. 1 of the specification, the method for evaluating coverage of building network signals provided by the application includes the following steps:
S1, acquiring network signal perception data of all sampling points in a set area and target building layer information; the set area comprises a coverage area of a target building, and the network signal perception data comprises network signal information and network environment information;
s2, preprocessing the network signal perception data based on the target building layer information;
S3, extracting the network environment information from the preprocessed network signal perception data, and inputting the network environment information into a trained height identification model to obtain height information corresponding to each sampling point;
And S4, extracting the network signal information from the preprocessed network signal perception data, and carrying out layered network signal coverage analysis on the target building based on the obtained height information.
Specifically, in step S1, the target building may be all buildings in a delimited area (for example, a district, an industrial park), and the space between the buildings is not limited to one building. In the present application, therefore, it is necessary to use target building layer information, which may be acquired through a related platform, for example, through ArcGIS, and includes the number and boundary information of each building, and other parameters, which may be overall building information, level information of the building, etc.;
The network signal perception data originate from sampling points (can be mobile phones of all users in a set area), and because the object for network signal coverage analysis is a target building, the set area necessarily comprises the coverage area of the target building (the coverage area of all buildings and the interval area among all buildings); the network signal perception data comprises network signal information and network environment information, wherein the network signal information is mainly used for carrying out network signal coverage analysis, the network environment information is mainly used for identifying the height information of sampling points, and the network signal information comprises key information such as a base station ID, CELLID, RSRP, PCI; the network environment information includes time information, air pressure information, temperature information, terminal manufacturer information, and terminal model information.
In the application, in order to carry out network signal coverage analysis on each building in the target building in the follow-up process, the collected network signal perception data is required to be subjected to data division building collection. Specifically, referring to fig. 2 of the specification, the preprocessing the network signal perceived data based on the target building layer information includes the following steps:
S201, extracting coordinate information of each sampling point from the acquired network signal perception data;
S202, extracting boundary information of each building from the target building layer information;
and S203, eliminating network signal perception data corresponding to sampling points arranged outside the building based on the coordinate information and the boundary information, and carrying out data aggregation according to building numbers.
The network signal perception data comprises network signal information and network environment information, and coordinate information or longitude and latitude information of sampling points. In step S101, coordinate information or longitude and latitude information of each sampling point is extracted from the collected network signal sensing data, so as to generate a GIS (geographic information system ) distribution map of the original sampling point, where a GIS distribution diagram of the sampling point can be referred to fig. 3 in the specification; in step S102, boundary information of each building is extracted from the target building layer information to generate a MAP layer of the target building, wherein the MAP layer schematic diagram of the target building can be referred to fig. 4 in the specification; referring to fig. 5 of the specification, in step S103, in order to perform building data collection on the collected network signal sensing data, the target building layer information and the network signal sensing data are combined based on the coordinate information and the boundary information to implement building data collection. For example, fitting the generated GIS distribution diagram of the original sampling points and the MAP layer diagram of the target building under the same coordinate system, marking the sampling points in each building boundary as building indoor sampling points according to each building boundary, marking the sampling points outside each building boundary as outdoor sampling points, removing network signal perception data corresponding to the outdoor sampling points, only retaining the network signal perception data corresponding to the indoor sampling points, and carrying out aggregation according to building numbers.
It should be noted that, in the present application, only the network signal perceived data corresponding to the reserved indoor sampling points is subjected to subsequent analysis. In an embodiment, the sample data (network signal sensing data corresponding to the indoor sampling point) of each building is taken as a set M, for example, the sample data of the building aggregate with the number 1 is M1, the sample data of the building aggregate with the number 2 is M2 … …, and the sample data of the building aggregate with the number n is Mn.
After the collected network signal perception data are collected according to the building boundary, the height information of each sampling point is required to be determined so as to realize three-dimensional coverage analysis of the building. In step S3, in order to solve the problems of low positioning accuracy and low efficiency existing in the 5G coverage analysis based on the altitude of the GPS, the 5G coverage analysis based on the MR data ta+aoa and the manual building 5G coverage assessment in the prior art, the application determines the altitude information of each sampling point by constructing a altitude identification model.
Specifically, referring to fig. 6 of the specification, a highly identified model is trained by:
p1, network environment information and corresponding height information acquired by terminals of different manufacturers and different models in selected different positions, different heights and different types of buildings are used as data sets, and the data sets are divided into training sets and test sets according to set proportions;
P2, training a pre-constructed height identification model based on the training set, adjusting parameters of the height identification model according to errors between output results of the height identification model and real height information, and performing iterative training until the parameters of the height identification model are converged to obtain a height identification model to be tested;
and P3, evaluating the to-be-tested height recognition model based on the test set, and determining the to-be-tested height recognition model as a trained height recognition model if an evaluation result reaches a set threshold value.
That is, in the present application, the height identification model is constructed based on the network environment information of five dimensions of time information, air pressure information, temperature information, terminal manufacturer information and terminal model information, and accurate height information is obtained through training and verification of the model.
In step P1, a data acquisition process is performed. To ensure that the acquired network environment information dataset encompasses a variety of conditions to increase robustness of the model, avoid overstretching or overstretching the dataset to certain categories or regions; in order to ensure the balance of the sample number of each category in the data set, the phenomenon that the model learns the categories insufficiently due to the fact that the sample number of certain categories is too small is avoided; in order to ensure the representativeness and diversity of training data, buildings with different positions, different heights and different types (different types such as office buildings, residential buildings, markets, hospitals and the like) are selected as the collecting buildings, and terminals (such as mobile phones) with different types are utilized to collect time information, air pressure information, temperature information, terminal manufacturer information and terminal model information as sample data, so that the model is more stable and reliable in practical application; and after the data acquisition is finished, the corresponding height information is marked to obtain a final data set, and the data set is divided into a training set and a testing set according to a set proportion for training and verification of a subsequent model.
In an embodiment, 80% of data is used as a training set and 20% of data is used as a test set, referring to fig. 7 of the specification, the height identification model is constructed based on a BP neural network, the BP neural network comprises an input layer, an output layer and an implicit layer arranged between the input layer and the output layer, the input layer comprises five neurons respectively representing the time information X 1, the air pressure information X 2, the temperature information X 3, the terminal manufacturer information X 4 and the terminal model information X 5; the output information includes a neuron representing altitude information Y; when determining the number of neurons of the hidden layer, considering that the purpose of the number of neurons of the hidden layer is to balance the fitting capacity and generalization capacity of the neural network, too few neurons may cause under-fitting, and the model cannot capture complex patterns in data; while too many neurons may lead to overfitting, the model performs well on the training set, but has poor generalization ability on new data, so in the present application, the design of hidden layer node numbers refers to the following:
Wherein: n is the number of nodes of the hidden layer neuron; n i is the number of neurons in the input layer; n 0 is the number of neurons of the output layer; a is a constant between 1 and 10, and n is defined as 10 in combination with practical results.
In step P2, during the forward propagation of training the pre-constructed altitude identification model by using the training set, there is a link to compare whether the pre-constructed altitude identification model is satisfied with the expected result, in which an error is generated between the actual output result and the expected output result, that is, an error between the output result of the altitude identification model and the actual altitude information, and in order to reduce the error, an objective function is required to be set to optimize the error, that is, a loss function, and in an embodiment, the loss function uses an average absolute error MAE (mean absolute error average absolute error) as follows:
Wherein y i is the output result of the height identification model, Is the true height information of the label. And the set maximum training times is 20000 times, when the training times reach 20000 times, the training is stopped, the training stopping error threshold is set to 0.00065, and the learning rate is set to 0.3. And the weight parameter/>, between the input layer and the hidden layer, is obtained through the network training of the training set Bias term parameter/>, between input layer and hidden layerWeight parameter/>, between hidden layer and output layerBias term parameter/>, between hidden layer and output layerFour model parameters.
And after training, comparing the training result with the original data, calculating an average absolute error value MAE, if the MAE is less than or equal to 0.00065 of the training error threshold, passing the training, if the MAE is more than 0.00065, not passing the training, returning to a network training stage, and after modifying parameters, retraining until the MAE meets the 0.00065 threshold.
In the step P3, the test set is input into a to-be-tested height identification model, the output height result and the marked real height result are compared and checked, the result checking error value parameter is set as F, the absolute value of the error value F is counted respectively, the proportion of the height error less than or equal to 3 meters, namely the proportion of the absolute value F less than or equal to 3 is calculated (note: 3m is an adjustable value in the threshold range, such as 5m or 2m can be adjusted according to the requirement), and if the checking result accuracy reaches 99.50%, the BP neural network model is judged to be free of problems. If the accuracy is low, the BP neural network model is judged to be problematic, a data acquisition stage is required to be returned, and a larger sample size is acquired for model training until the accuracy reaches the standard.
In step S3, the network environment information is extracted from the preprocessed network signal sensing data, where the network environment information includes time information, air pressure information, temperature information, terminal manufacturer information and terminal model information, the five-dimensional network environment information is input into the trained height recognition model, and the height information corresponding to each sampling point is obtained through the output of the height recognition model.
When the network signal coverage analysis is carried out on the target building, the data floor-dividing collection is further needed in order to achieve the effect of three-dimensional coverage analysis. Referring to fig. 8 of the specification, in step S4, the hierarchical network signal coverage analysis of the target building based on the obtained height information includes the following steps:
s401, carrying out data collection on the preprocessed network signal perception data according to the defined floors based on the obtained height information;
s402, network signal coverage analysis is carried out by utilizing the network signal perception data corresponding to each floor of each building.
In step S401, when each building is subjected to floor planning, the following layering scheme may be adopted:
(1) Layered according to actual building. Layering the preprocessed network signal perception data according to the height according to the building floor height, for example: the actual layer height is 3.5m, and layering is carried out according to 3.5 m;
(2) Layered according to the "high, medium, low" layers. According to analysis requirements, the sampling points in the building are halved into high, medium and low floors, for example, 30 floors of the building are arranged, and 1-10 floors are the low floors; 11-20 layers are middle layers; the 21-30 layers are high layers;
(3) Layered according to a specified height. In order to adapt to the user demands in more scenes, in the aspect of 5G coverage layering of buildings, the application supports height information calculated according to a model, and building layering is carried out according to the user demands, for example: layering may be performed at 5m, 10m, or other specified heights.
In an embodiment, the building parameter may be set to L, the number of floors is set to c, if the number of floors c of the building x is 6, the reference numerals of each floor are Lx-1, lx-2, … … Lx-6, and for the data in the sampling point set Mx of the building x, the data in the set is divided into one set for each floor according to the calculated height H, that is: m x-1、Mx-2……Mx-c. For example, if the number of floors of the building 5 is 6, the sampling points of the building 5 need to be collected M5, and the sampling points need to be collected into a data set of 6 floors such as M 5-1、M5-2、……M5-6 according to the building hierarchy.
In step S402, the network signal information of each floor of each building is analyzed. For example, the RSRP averaging method is used to analyze the problem of abnormal network coverage of each floor of each building, which should be a technical means known to those skilled in the art and will not be described herein.
According to the building network signal coverage assessment method, network environment information of five dimensions including time information, air pressure information, temperature information, terminal manufacturer information and terminal model information is used as input, height information of sampling points is used as output to construct a height identification model, accurate height information is obtained through model training and verification, building layer information and network signal perception data are combined, after data building aggregation and data building layer aggregation are carried out, network signal coverage assessment is carried out on each floor in each building, and therefore a network signal coverage problem area is accurately located, and data support is provided for indoor distribution planning of a 5G network.
As shown in fig. 9 of the specification, the embodiment of the present application further provides a building network signal coverage assessment device, including:
The acquisition module 901 is used for acquiring target building layer information and network signal perception data of all sampling points in a set area; the set area comprises a coverage area of a target building, and the network signal perception data comprises network signal information and network environment information;
A preprocessing module 902, configured to preprocess the network signal sensing data based on the target building layer information;
The recognition module 903 is configured to extract the network environment information from the preprocessed network signal perceived data, and input the network environment information into a trained height recognition model to obtain height information corresponding to each sampling point;
the analysis module 904 is configured to extract the network signal information from the preprocessed network signal perception data, and perform hierarchical network signal coverage analysis on the target building based on the obtained altitude information.
In some embodiments, the network signal perception data further comprises coordinate information of each sampling point, and the target building layer information comprises the number and boundary information of each building.
In some embodiments, the preprocessing module 902 preprocesses the network signal awareness data based on the target building layer information, including: extracting coordinate information of each sampling point from the acquired network signal perception data; extracting boundary information of each building from the target building layer information; and eliminating network signal perception data corresponding to sampling points arranged outside the building based on the coordinate information and the boundary information, and carrying out data aggregation according to the building number.
In some embodiments, the network environment information includes time information, air pressure information, temperature information, terminal manufacturer information, and terminal model information, the altitude identification model is constructed based on a BP neural network, the BP neural network includes an input layer, an output layer, and an hidden layer disposed between the input layer and the output layer, the hidden layer includes ten neurons, the input layer includes five neurons, and the time information, the air pressure information, the temperature information, the terminal manufacturer information, and the terminal model information are respectively represented; the output information includes a neuron representing altitude information.
In some embodiments, the device includes a training module, configured to take network environment information and corresponding height information collected by terminals of different manufacturers and different models in selected different locations, different heights, and different types of buildings as a dataset, and divide the dataset into a training set and a testing set according to a set proportion; training a pre-constructed height identification model based on the training set, adjusting parameters of the height identification model according to errors between output results of the height identification model and real height information, and performing iterative training until the parameters of the height identification model are converged to obtain a height identification model to be tested; and evaluating the to-be-tested height identification model based on the test set, and determining the to-be-tested height identification model as a trained height identification model if an evaluation result reaches a set threshold value.
In some embodiments, the analysis module 904 performs a hierarchical network signal coverage analysis of the target building based on the obtained altitude information, including: based on the obtained height information, carrying out data aggregation on the preprocessed network signal perception data according to the defined floors; and carrying out network signal coverage analysis by utilizing the network signal perception data corresponding to each floor of each building. Wherein, each building is delimited according to the actual floor height, each building is delimited according to the set miss height, or each building is delimited according to the set high, medium and low levels.
According to the building network signal coverage evaluation device provided by the application, the acquisition module is used for acquiring target building layer information and network signal perception data of all sampling points in a set area; the set area comprises a coverage area of a target building, and the network signal perception data comprises network signal information and network environment information; preprocessing the network signal perception data based on the target building layer information through a preprocessing module; extracting the network environment information from the preprocessed network signal perception data through an identification module, and inputting the network environment information into a trained height identification model to obtain height information corresponding to each sampling point; and extracting the network signal information from the preprocessed network signal perception data through an analysis module, and carrying out layered network signal coverage analysis on the target building based on the obtained height information. The height information obtained through the constructed height identification model is more accurate, and the building can be layered in various modes, so that the coverage evaluation of network signals is carried out on the building layering, and support is provided for the accurate positioning of building coverage problems.
Based on the same concept of the present application, as shown in fig. 10 of the specification, an embodiment of the present application provides a structure of an electronic device 1000, where the electronic device 1000 includes: at least one processor 1001, at least one network interface 1004 or other user interface 1003, memory 1005, at least one communication bus 1002. The communication bus 1002 is used to enable connected communication between these components. The electronic device 1000 optionally includes a user interface 1003 including a display (e.g., touch screen, LCD, CRT, holographic imaging (Holographic) or projection (Projector), etc.), keyboard, or pointing device (e.g., mouse, trackball, touch pad, touch screen, etc.).
Memory 1005 may include read only memory and random access memory, and provides instructions and data to the processor 1001. A portion of the memory 1005 may also include non-volatile random access memory (NVRAM).
In some implementations, the memory 1005 stores the following elements, executable modules or data structures, or a subset thereof, or an extended set thereof:
an operating system 10051 containing various system programs for implementing various basic services and handling hardware-based tasks;
The application module 10052 contains various application programs, such as a desktop (desktop), a media player (MEDIA PLAYER), a Browser (Browser), etc., for implementing various application services.
In the embodiment of the present application, the processor 1001 is configured to execute steps in a building network signal coverage evaluation method by calling a program or instructions stored in the memory 1005, so as to obtain more accurate positioning information through a built height identification model, to evaluate the coverage of the network signal on the building hierarchy, and to provide support for the accurate positioning of the building coverage problem.
The application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs steps as in a building network signal coverage assessment method.
In particular, the storage medium can be a general-purpose storage medium, such as a mobile disk, a hard disk, or the like, on which a computer program is executed that is capable of performing the above-described building network signal coverage assessment method.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments provided in the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Finally, it should be noted that: the above examples are only specific embodiments of the present application for illustrating the technical solution of the present application, but not for limiting the scope of the present application, and although the present application has been described in detail with reference to the foregoing examples, it will be understood by those skilled in the art that the present application is not limited thereto: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the corresponding technical solutions. Are intended to be encompassed within the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (10)
1. A building network signal coverage assessment method, comprising the steps of:
Acquiring network signal perception data of all sampling points in a set area and target building layer information; the set area comprises a coverage area of a target building, and the network signal perception data comprises network signal information and network environment information;
preprocessing the network signal perception data based on the target building layer information;
extracting the network environment information from the preprocessed network signal perception data, and inputting the network environment information into a trained height identification model to obtain height information corresponding to each sampling point;
Extracting the network signal information from the preprocessed network signal perception data, and carrying out layered network signal coverage analysis on the target building based on the obtained height information.
2. The building network signal coverage assessment method according to claim 1, wherein the network signal perception data further comprises coordinate information of each sampling point, and the target building layer information comprises numbers and boundary information of each building.
3. The building network signal coverage assessment method according to claim 2, wherein the preprocessing of the network signal perceived data based on the target building layer information comprises the steps of:
Extracting coordinate information of each sampling point from the acquired network signal perception data;
Extracting boundary information of each building from the target building layer information;
And eliminating network signal perception data corresponding to sampling points arranged outside the building based on the coordinate information and the boundary information, and carrying out data aggregation according to the building number.
4. The building network signal coverage assessment method according to claim 1, wherein the network environment information includes time information, air pressure information, temperature information, terminal manufacturer information, and terminal model information, the height identification model is constructed based on a BP neural network including an input layer, an output layer, and an hidden layer provided between the input layer and the output layer, the hidden layer including ten neurons, the input layer including five neurons representing the time information, the air pressure information, the temperature information, the terminal manufacturer information, and the terminal model information, respectively; the output information includes a neuron representing altitude information.
5. The building network signal coverage assessment method of claim 4, wherein training the altitude identification model comprises the steps of:
Network environment information and corresponding height information acquired by using terminals of different manufacturers and different models in selected different positions, different heights and different types of buildings are used as data sets, and the data sets are divided into training sets and testing sets according to set proportions;
Training a pre-constructed height identification model based on the training set, adjusting parameters of the height identification model according to errors between output results of the height identification model and real height information, and performing iterative training until the parameters of the height identification model are converged to obtain a height identification model to be tested;
And evaluating the to-be-tested height identification model based on the test set, and determining the to-be-tested height identification model as a trained height identification model if an evaluation result reaches a set threshold value.
6. A building network signal coverage assessment method according to claim 3, characterized in that said hierarchical network signal coverage analysis of said target building based on said obtained height information comprises the steps of:
Based on the obtained height information, carrying out data aggregation on the preprocessed network signal perception data according to the defined floors;
And carrying out network signal coverage analysis by utilizing the network signal perception data corresponding to each floor of each building.
7. The building network signal coverage assessment method according to claim 6, wherein each building is floor-defined according to an actual floor height, each building is floor-defined according to a set missing height, or each building is floor-defined according to a set high-medium-low level.
8. A building network signal coverage assessment device, comprising:
The acquisition module is used for acquiring network signal perception data of all sampling points in the target building layer information and the set area; the set area comprises a coverage area of a target building, and the network signal perception data comprises network signal information and network environment information;
The preprocessing module is used for preprocessing the network signal perception data based on the target building layer information;
the identification module is used for extracting the network environment information from the preprocessed network signal perception data, inputting the network environment information into a trained height identification model and obtaining the height information corresponding to each sampling point;
and the analysis module is used for extracting the network signal information from the preprocessed network signal perception data and carrying out layered network signal coverage analysis on the target building based on the obtained height information.
9. An electronic device comprising a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor in communication with the memory via the bus when the electronic device is in operation, the machine-readable instructions when executed by the processor performing the steps of the building network signal coverage assessment method of any one of claims 1 to 7.
10. A storage medium storing program instructions executable by a processor for performing the steps of the building network signal coverage assessment method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410469279.1A CN118233949A (en) | 2024-04-18 | 2024-04-18 | Building network signal coverage assessment method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410469279.1A CN118233949A (en) | 2024-04-18 | 2024-04-18 | Building network signal coverage assessment method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118233949A true CN118233949A (en) | 2024-06-21 |
Family
ID=91505990
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410469279.1A Pending CN118233949A (en) | 2024-04-18 | 2024-04-18 | Building network signal coverage assessment method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118233949A (en) |
-
2024
- 2024-04-18 CN CN202410469279.1A patent/CN118233949A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | Modified data-driven framework for housing market segmentation | |
| CN109493119B (en) | POI data-based urban business center identification method and system | |
| CN110956412B (en) | Flood dynamic assessment method, device, medium and equipment based on real-scene model | |
| US11676375B2 (en) | System and process for integrative computational soil mapping | |
| US10984518B2 (en) | Methods and systems for assessing the quality of geospatial data | |
| CN110852243B (en) | Road intersection detection method and device based on improved YOLOv3 | |
| CN109543907B (en) | Complex terrain wind resource assessment method and device | |
| CN104573387A (en) | Noise map drawing method and device | |
| CN117035511A (en) | Gas pipeline accident risk assessment method, equipment, device and medium | |
| Rodrigues et al. | Extracting 3D maps from crowdsourced GNSS skyview data | |
| CN110716998A (en) | Method for spatializing fine-scale population data | |
| CN113901348A (en) | Oncomelania snail distribution influence factor identification and prediction method based on mathematical model | |
| CN108734393A (en) | Matching process, user equipment, storage medium and the device of information of real estate | |
| Lin et al. | Enhancing Urban Land Use Identification Using Urban Morphology | |
| Cui et al. | Research on the driving forces of urban hot spots based on exploratory analysis and binary logistic regression model | |
| CN118233949A (en) | Building network signal coverage assessment method, device, equipment and medium | |
| CN116630111A (en) | Data processing method and system in urban green space optimization based on big data | |
| CN108133234B (en) | Sparse subset selection algorithm-based community detection method, device and equipment | |
| CN116307857A (en) | Built-up area environment evaluation method based on remote sensing image scene understanding | |
| CN115689106A (en) | Method, device and equipment for quantitatively identifying regional space structure of complex network view angle | |
| CN115879594A (en) | Urban settlement population distribution trend prediction method based on geographic detector | |
| CN111461163B (en) | Urban interior PM2.5 concentration simulation and population exposure evaluation method and device | |
| Feng et al. | GridDER: grid detection and evaluation in R | |
| CN113971348A (en) | Source end power short-term prediction method based on comprehensive energy system | |
| Mao et al. | Population spatialization at building scale based on residential population index—A case study of Qingdao city |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |