CN116432095A - Road disease prediction method, device, electronic equipment and storage medium - Google Patents
Road disease prediction method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116432095A CN116432095A CN202211739057.4A CN202211739057A CN116432095A CN 116432095 A CN116432095 A CN 116432095A CN 202211739057 A CN202211739057 A CN 202211739057A CN 116432095 A CN116432095 A CN 116432095A
- Authority
- CN
- China
- Prior art keywords
- road
- data
- influence
- matrix
- disease
- 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
- 201000010099 disease Diseases 0.000 title claims abstract description 178
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 178
- 238000000034 method Methods 0.000 title claims abstract description 38
- 239000011159 matrix material Substances 0.000 claims description 195
- 238000004590 computer program Methods 0.000 claims description 11
- 238000011946 reduction process Methods 0.000 claims 2
- 238000012423 maintenance Methods 0.000 abstract description 5
- 230000002035 prolonged effect Effects 0.000 abstract description 4
- 230000007547 defect Effects 0.000 description 10
- 230000035772 mutation Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000000513 principal component analysis Methods 0.000 description 3
- 239000010426 asphalt Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000004568 cement Substances 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000002591 computed tomography Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The embodiment of the invention provides a road disease prediction method, which is used for acquiring historical driving vehicle data and historical road environment data of each road section; determining a road disease influence factor according to the historical driving vehicle data and the historical road environment data; and predicting the road diseases of the target road section according to the road disease influence factors to obtain a road disease prediction result of the target road section. The road disease influence factors are determined according to the historical driving vehicle data and the historical road environment data of each road section, the road disease of the target road section is predicted according to the road disease influence factors, and what road disease can appear on the target road section can be predicted in advance, so that a relevant management department can conduct targeted maintenance work on the target road section, and the service life of the target road section can be prolonged.
Description
Technical Field
The invention relates to the field of smart cities, in particular to a road disease prediction method, a device, electronic equipment and a storage medium.
Background
Road CT is a way to scan a road and identify road diseases by scanning images, so as to obtain the condition of the road internal diseases, however, road CT scans the existing diseases in the road, and cannot predict the road diseases which occur later, and thus cannot carry out targeted maintenance on the road in advance to prolong the service life of the road.
Disclosure of Invention
The embodiment of the invention provides a road disease prediction method, which aims to solve the problem that the road disease which can occur later cannot be predicted by only scanning the existing disease in the road in the prior art. The road disease influence factors are determined according to the historical driving vehicle data and the historical road environment data of each road section, the road disease of the target road section is predicted according to the road disease influence factors, and what road disease can appear on the target road section can be predicted in advance, so that a relevant management department can conduct targeted maintenance work on the target road section, and the service life of the target road section can be prolonged.
In a first aspect, an embodiment of the present invention provides a road disease prediction method, including:
acquiring historical driving vehicle data and historical road environment data of each road section;
determining a road disease influence factor according to the historical driving vehicle data and the historical road environment data;
and predicting the road diseases of the target road section according to the road disease influence factors to obtain a road disease prediction result of the target road section.
Optionally, the determining the road disease influence factor according to the historical driving vehicle data and the historical road environment data includes:
determining influence data of road diseases according to the historical driving vehicle data and the historical road environment data, wherein the influence data comprises a first number of data dimensions;
performing dimension reduction processing on the influence data to obtain sample dimension reduction data, wherein the sample dimension reduction data comprises a second number of data dimensions, and the second number is smaller than the first number;
and determining a road disease influence factor based on the sample dimension reduction data.
Optionally, the performing dimension reduction processing on the influence data to obtain sample dimension reduction data, where the sample dimension reduction data includes a second number of data dimensions, and the method includes:
determining a first influence matrix according to the influence data, wherein the first influence matrix comprises a first number of data dimensions;
performing dimension reduction on the first influence matrix to obtain a second influence matrix;
the sample dimension reduction data is determined based on the first impact matrix and the second impact matrix.
Optionally, the performing the dimension reduction processing on the first influence matrix to obtain a second influence matrix includes:
determining a covariance matrix of the first influence matrix;
and performing dimension reduction processing on the first influence matrix based on the covariance matrix of the first influence matrix to obtain a second influence matrix.
Optionally, the performing the dimension reduction processing on the first influence matrix based on the covariance matrix of the first influence matrix to obtain a second influence matrix includes:
calculating a covariance matrix of the first influence matrix;
calculating eigenvalues of the covariance matrix and eigenvectors corresponding to the eigenvalues;
and obtaining the intermediate matrix according to a second number of the eigenvectors with the largest eigenvalues, and determining a second influence matrix according to the first influence matrix and the intermediate matrix.
Optionally, the obtaining the intermediate matrix according to the second number of feature vectors with the largest feature value, and determining a second influence matrix according to the first influence matrix and the intermediate matrix, includes:
multiplying the first influence matrix with the intermediate matrix to obtain a second influence matrix.
Optionally, the predicting the road disease of the target road section according to the road disease influence factor to obtain a road disease prediction result of the target road section includes:
acquiring driving vehicle data and road environment data of the target road section;
determining a target influence matrix of the target road section according to the road disease influence factor;
and predicting the road disease of the target road section based on the target influence matrix to obtain a road disease prediction result of the target road section.
In a second aspect, an embodiment of the present invention provides a road disease prediction apparatus, the apparatus including:
the acquisition module is used for acquiring historical driving vehicle data and historical road environment data of each road section;
the determining module is used for determining road disease influence factors according to the historical driving vehicle data and the historical road environment data;
and the prediction module is used for predicting the road diseases of the target road section according to the road disease influence factors to obtain a road disease prediction result of the target road section.
In a third aspect, an embodiment of the present invention provides an electronic device, including: the road disease prediction method comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the steps in the road disease prediction method provided by the embodiment of the invention are realized when the processor executes the computer program.
In a fourth aspect, embodiments of the present invention provide a computer readable storage medium having a computer program stored thereon, which when executed by a processor, implements the steps of the road disease prediction method provided by the embodiments of the present invention.
In the embodiment of the invention, historical driving vehicle data and historical road environment data of each road section are obtained; determining a road disease influence factor according to the historical driving vehicle data and the historical road environment data; and predicting the road diseases of the target road section according to the road disease influence factors to obtain a road disease prediction result of the target road section. The road disease influence factors are determined according to the historical driving vehicle data and the historical road environment data of each road section, the road disease of the target road section is predicted according to the road disease influence factors, and what road disease can appear on the target road section can be predicted in advance, so that a relevant management department can conduct targeted maintenance work on the target road section, and the service life of the target road section can be prolonged.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a road disease prediction method provided by an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a road disease prediction apparatus according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, fig. 1 is a flowchart of a road disease prediction method according to an embodiment of the present invention, as shown in fig. 1, the road disease prediction method includes the following steps:
101. historical driving vehicle data and historical road environment data of each road section are obtained.
In the embodiment of the present invention, each of the above-described road segments refers to a plurality of sample road segments including a road segment in which a road defect has occurred and a road segment in which a road defect has not occurred.
The above-described history running vehicle data may be data related to the running vehicle such as the type of the running vehicle, the size of the running vehicle, the speed of the running vehicle, the number of the running vehicles, and the like. The historical driving vehicle data can be determined through image data collected by the traffic cameras arranged on each road section, specifically, the traffic cameras are arranged on each road section, traffic images of corresponding road sections are collected through the traffic cameras, vehicle identification is carried out on the traffic images, driving vehicle data of corresponding road sections are obtained, and the driving vehicle data are stored in the server for multiplexing.
The historical road environment data may be weather data, road humidity data, road temperature data, road scanning data, road disease data, and the like. The weather data can be acquired according to a weather department where a road is located, the road scanning data can be acquired according to data scanned by a road scanning vehicle, the road disease data can be acquired according to the road scanning data, and the road disease data can also be acquired through records of road inspection staff.
102. And determining the road disease influence factor according to the historical driving vehicle data and the historical road environment data.
In the embodiment of the invention, the influence data of the road diseases can be determined for the historical driving vehicle data and the historical road environment data, and the road disease influence factors are determined according to the influence data of the road diseases. Specifically, the dimension reduction processing may be performed on the influence data of the road disease to obtain the road disease influence factor, and the dimension reduction processing may be a plurality of influence factors having the greatest influence on the road disease among all the influence factors. By performing dimension reduction processing on the influence data, dimension reduction data with lower data dimension can be obtained. For example, the road damage influence data is a type of a traveling vehicle, a size of the traveling vehicle, a speed of the traveling vehicle, the number of the traveling vehicles, weather data, road humidity data, road temperature data, etc., and the road damage influence factor may be the size of the traveling vehicle, the speed of the traveling vehicle, the road temperature data.
103. And predicting the road diseases of the target road section according to the road disease influence factors to obtain a road disease prediction result of the target road section.
After the road disease influence factors are obtained, the data corresponding to the road disease influence factors can be screened from the data of the target road section through the road disease influence factors, and the road disease of the target road section is predicted according to the screened data, so that a road disease prediction result of the target road section is obtained. For example, the road influencing factors are the size of the running vehicle, the speed of the running vehicle and the road temperature data, and the size of the running vehicle, the speed of the running vehicle and the road temperature data can be screened out from the data of the target road section, and the type of road diseases which can occur in the target road section can be predicted according to the size of the running vehicle, the speed of the running vehicle and the road temperature data.
Specifically, after the data corresponding to the road disease influencing factor is screened out, the data corresponding to the road disease influencing factor can be input into a trained time sequence model for prediction processing, and the time sequence model outputs and obtains the road disease prediction result of the target road section.
In the embodiment of the invention, historical driving vehicle data and historical road environment data of each road section are obtained; determining a road disease influence factor according to the historical driving vehicle data and the historical road environment data; and predicting the road diseases of the target road section according to the road disease influence factors to obtain a road disease prediction result of the target road section. The road disease influence factors are determined according to the historical driving vehicle data and the historical road environment data of each road section, the road disease of the target road section is predicted according to the road disease influence factors, and what road disease can appear on the target road section can be predicted in advance, so that a relevant management department can conduct targeted maintenance work on the target road section, and the service life of the target road section can be prolonged.
Optionally, in the step of determining the road disease influence factor according to the historical driving vehicle data and the historical road environment data, the influence data of the road disease may be determined according to the historical driving vehicle data and the historical road environment data, where the influence data includes a first number of data dimensions; performing dimension reduction processing on the influence data to obtain sample dimension reduction data, wherein the sample dimension reduction data comprises a second number of data dimensions, and the second number is smaller than the first number; and determining the road disease influence factor based on the sample dimension reduction data.
In the embodiment of the invention, each road section comprises a road section with road disease and a road section without road disease, and after the historical driving vehicle data and the historical road environment data of each road section are obtained, the historical driving vehicle data and the historical road environment data of each road section are sorted to obtain the influence data of the road disease. The above-mentioned influence data of road diseases are used for explaining that the data has more or less influence relation with the generation of road diseases. The above-mentioned road damage influence data may be the type of the traveling vehicle, the size of the traveling vehicle, the speed of the traveling vehicle, the number of the traveling vehicles, weather data, road humidity data, road temperature data, etc., and the road damage influence factor may be the size of the traveling vehicle, the speed of the traveling vehicle, the road temperature data. The road defects mainly comprise road defects corresponding to asphalt pavements, road defects corresponding to cement pavements and road defects corresponding to facilities along the lines, wherein the types of the road defects corresponding to the asphalt pavements can comprise pits, cracks, block cracks, cracks (transverse cracks, longitudinal cracks and irregular oblique lines), sinkers, ruts, road frame differences, sundries, ponding and the like; the types of road diseases corresponding to the cement pavement can comprise panel breakage, pits, plate angle breakage, line breakage and the like; types of roadway damage corresponding to the line-along facilities may include guardrail damage, road frame differences, manhole cover damage, and the like.
The impact data of the road disease has a first number of data dimensions, which can be understood as having a first number of candidate impact factors of the road disease. After the influence data of the road diseases are obtained, the influence data of the road diseases can be subjected to dimension reduction processing to obtain sample header dimension reduction data, wherein the sample dimension reduction data has a second number of data dimensions, and the second number of data dimensions can be understood as having a second number of road disease influence factors.
The dimension reduction processing may be performed by a dimension reduction method such as a principal component analysis algorithm (Principal Component Analysis, PCA) or a linear discriminant analysis algorithm (Discriminant Analysis, LDA). After the sample dimension reduction data is obtained, the road disease influence factors can be determined according to the data dimension in the sample dimension reduction data, and each data dimension corresponds to one road disease influence factor.
Optionally, in the step of performing dimension reduction processing on the influence data to obtain sample dimension reduction data, where the sample dimension reduction data includes a second number of data dimensions, a first influence matrix may be determined according to the influence data, where the first influence matrix includes the first number of data dimensions; performing dimension reduction processing on the first influence matrix to obtain a second influence matrix; sample dimension reduction data is determined based on the first impact matrix and the second impact matrix.
In the embodiment of the invention, the number of all road segments is n, and the first number is m, so that the influence data of m data dimensions corresponding to n road segments can be constructed into an n×m first influence matrix, wherein in the first influence matrix, each column corresponds to one road disease candidate influence factor, and each row corresponds to the influence data of one road segment.
And performing dimension reduction processing on the first influence matrix through a principal component analysis algorithm or a linear discriminant analysis algorithm to obtain a second influence matrix, wherein the second influence matrix is n multiplied by k, and k is a second quantity, namely the data dimension representing sample dimension reduction data is k. The k may be preset. In the second influence matrix, the first column corresponds to a road disease influence factor, and the first row corresponds to influence data of a road section.
Optionally, in the step of performing dimension reduction processing on the first influence matrix to obtain the second influence matrix, a covariance matrix of the first influence matrix may be determined; and performing dimension reduction processing on the first influence matrix based on the covariance matrix of the first influence matrix to obtain a second influence matrix.
In the embodiment of the invention, for a first influence matrix, calculating an average value of each column of performance index data, subtracting the average value from each column of performance index data to obtain a standard deviation corresponding to each performance index data, obtaining covariance corresponding to each performance index data by squaring the standard deviation, and obtaining an n multiplied by m covariance matrix according to the covariance.
The covariance matrix is extracted to obtain the mutation information of the performance index data, so that the covariance matrix is subjected to dimension reduction processing through the mutation information, the sample dimension reduction data with higher mutation degree can be extracted, and the high influence of the sample dimension reduction data on road diseases is ensured.
Optionally, in the step of performing dimension reduction processing on the first influence matrix based on the covariance matrix of the first influence matrix to obtain the second influence matrix, the covariance matrix of the first influence matrix may be calculated; calculating eigenvalues of the covariance matrix and eigenvectors corresponding to the eigenvalues; and obtaining an intermediate matrix according to a second number of eigenvectors with the largest eigenvalues, and determining a second influence matrix according to the first influence matrix and the intermediate matrix.
In the embodiment of the invention, after obtaining the covariance matrix of the first influence matrix, obtaining the eigenvalue and the corresponding eigenvector of the covariance matrix; sorting the feature vectors according to the feature values; and reserving the eigenvectors with the largest first k eigenvalues to obtain an m multiplied by k intermediate matrix. And determining a second influence matrix according to the first influence matrix and the intermediate matrix. The degree of mutation of the performance index data is determined through the characteristic value, so that a sample dimension reduction data with higher degree of mutation can be selected, and the high influence of the sample dimension reduction data on road diseases is ensured.
Each column in the intermediate matrix corresponds to a road disease influence factor, and each row corresponds to a characteristic vector.
Optionally, in the step of predicting the road defect of the target road segment according to the road defect influence factor to obtain the road defect prediction result of the target road segment, the first influence matrix may be multiplied by the intermediate matrix to obtain the second influence matrix.
In the embodiment of the invention, after the first influence matrix and the intermediate matrix are obtained, matrix calculation is performed on the first influence matrix and the intermediate matrix to obtain the second influence matrix. Specifically, assuming that the first influence matrix is h=n×m and the intermediate influence matrix d=m×k, the second influence matrix g=hd=n×k. Thus, the first influence matrix can be reduced from m dimension to k dimension, and the data dimension with small influence on road diseases is removed.
And performing dimension reduction processing through matrix multiplication to obtain sample dimension reduction data with higher variability, and ensuring high influence of the sample dimension reduction data on road diseases.
After the second influence matrix is obtained, the data dimension corresponding to each column in the second influence matrix can be determined as the corresponding road disease influence factor.
Optionally, in the step of predicting the road damage of the target road section according to the road damage influencing factor to obtain the road damage prediction result of the target road section, the driving vehicle data and the road environment data of the target road section may be obtained; determining a target influence matrix of a target road section according to the road disease influence factors; and predicting the road diseases of the target road section based on the target influence matrix to obtain a road disease prediction result of the target road section.
In the embodiment of the present invention, the data related to the traveling vehicles, such as the type of the traveling vehicle, the size of the traveling vehicle, the speed of the traveling vehicle, the number of the traveling vehicles, and the like, are the traveling vehicle data of the target road section. The driving vehicle data of the target road section can be determined by image data collected by a traffic camera arranged on the target road section. Specifically, a traffic camera is arranged in the target road section, traffic images of the target road section are collected through the traffic camera, vehicle identification is carried out on the traffic images, driving vehicle data of the target road section are obtained, and the driving vehicle data are stored in a server for multiplexing.
The road environment data may be weather data, road humidity data, road temperature data, road scan data, road disease data, etc. of the target link. The weather data can be acquired according to a weather department where the target road is located, the road scanning data can be acquired according to data obtained when the road scanning vehicle scans the target road, the road disease data can be acquired according to road scanning data of the target road section, and the road disease data can also be acquired through records of road inspection staff of the target road section.
After the driving vehicle data and the road environment data of the target road section are obtained, data related to the road disease factors are screened out, and a target influence matrix of G=1×k×T is constructed, wherein k in the target influence matrix represents k road disease influence factors, and T represents the time dimension. And inputting the target influence matrix into a time sequence model for prediction to obtain a road disease prediction result of the target road section.
The timing model may be a cyclic neural network RNN or long and short memory network LSTM based timing model. When training a time sequence model, a data set and an initial time sequence model can be obtained, wherein the data set comprises a sample influence matrix and a real disease label, the sample influence matrix and a target influence matrix are obtained through the same processing method, the sample influence matrix is input into the initial time sequence model to obtain a sample disease prediction result, error loss between the sample disease prediction result and the real disease label is calculated, the minimum error loss is used as an optimization target, parameter adjustment is carried out on the initial time sequence model, the parameter adjustment process is iterated until the iteration times reach the preset times, or the initial time sequence model converges at the position of minimizing the error loss, training is stopped, and the trained time sequence model is obtained.
After the trained time sequence model is obtained, the target influence matrix is input into the trained time sequence model, and the road disease prediction result of the target road section is output through the trained time sequence model. The road disease prediction result of the upper judge comprises the type of the road disease and the occurrence time of the road disease.
It should be noted that, the road disease prediction method provided by the embodiment of the invention can be applied to devices such as an intelligent camera, an intelligent mobile phone, a computer, a server and the like which can perform the road disease prediction method.
Optionally, referring to fig. 2, fig. 2 is a schematic structural diagram of a road disease prediction device according to an embodiment of the present invention, as shown in fig. 2, where the device includes:
an acquisition module 201, configured to acquire historical driving vehicle data and historical road environment data of each road section;
a determining module 202, configured to determine a road disease impact factor according to the historical driving vehicle data and the historical road environment data;
and the prediction module 203 is configured to predict the road damage of the target road segment according to the road damage influencing factor, so as to obtain a road damage prediction result of the target road segment.
Optionally, the determining module 202 includes:
a first determining sub-module for determining impact data of road diseases according to the historical driving vehicle data and the historical road environment data, wherein the impact data comprises a first number of data dimensions;
the processing submodule is used for carrying out dimension reduction processing on the influence data to obtain sample dimension reduction data, wherein the sample dimension reduction data comprises a second number of data dimensions, and the second number is smaller than the first number;
and the second determining submodule is used for determining the road disease influence factor based on the sample dimension reduction data.
Optionally, the processing sub-module includes:
a first determining unit configured to determine a first influence matrix according to the influence data, where the first influence matrix includes a first number of data dimensions;
the processing unit is used for performing dimension reduction processing on the first influence matrix to obtain a second influence matrix;
and a second determining unit configured to determine the sample dimension-reduction data based on the first influence matrix and the second influence matrix.
Optionally, the processing unit includes:
a determining subunit configured to determine a covariance matrix of the first influence matrix;
and the processing subunit is used for carrying out dimension reduction processing on the first influence matrix based on the covariance matrix of the first influence matrix to obtain a second influence matrix.
Optionally, the processing subunit is further configured to calculate a covariance matrix of the first influence matrix; calculating eigenvalues of the covariance matrix and eigenvectors corresponding to the eigenvalues; and obtaining the intermediate matrix according to a second number of the eigenvectors with the largest eigenvalues, and determining a second influence matrix according to the first influence matrix and the intermediate matrix.
Optionally, the processing subunit is further configured to multiply the first influence matrix with the intermediate matrix to obtain a second influence matrix.
Optionally, the prediction module 203 includes:
the acquisition sub-module is used for acquiring the driving vehicle data and the road environment data of the target road section;
the third determining submodule is used for determining a target influence matrix of the target road section according to the road disease influence factor;
and the prediction sub-module is used for predicting the road diseases of the target road section based on the target influence matrix to obtain a road disease prediction result of the target road section.
It should be noted that the road disease prediction device provided by the embodiment of the invention can be applied to devices such as an intelligent camera, an intelligent mobile phone, a computer, a server and the like which can perform the road disease prediction method.
The road disease prediction device provided by the embodiment of the invention can realize each process realized by the road disease prediction method in the method embodiment, and can achieve the same beneficial effects. In order to avoid repetition, a description thereof is omitted.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 3, including: a memory 302, a processor 301, and a computer program stored on the memory 302 and executable on the processor 301 for a road fault prediction method, wherein:
the processor 301 is configured to call a computer program stored in the memory 302, and perform the following steps:
acquiring historical driving vehicle data and historical road environment data of each road section;
determining a road disease influence factor according to the historical driving vehicle data and the historical road environment data;
and predicting the road diseases of the target road section according to the road disease influence factors to obtain a road disease prediction result of the target road section.
Optionally, the determining, by the processor 301, the road disease influence factor according to the historical driving vehicle data and the historical road environment data includes:
determining influence data of road diseases according to the historical driving vehicle data and the historical road environment data, wherein the influence data comprises a first number of data dimensions;
performing dimension reduction processing on the influence data to obtain sample dimension reduction data, wherein the sample dimension reduction data comprises a second number of data dimensions, and the second number is smaller than the first number;
and determining a road disease influence factor based on the sample dimension reduction data.
Optionally, the performing, by the processor 301, the dimension reduction processing on the impact data, to obtain sample dimension-reduced data, where the sample dimension-reduced data includes a second number of data dimensions, and includes:
determining a first influence matrix according to the influence data, wherein the first influence matrix comprises a first number of data dimensions;
performing dimension reduction on the first influence matrix to obtain a second influence matrix;
the sample dimension reduction data is determined based on the first impact matrix and the second impact matrix.
Optionally, the performing, by the processor 301, the dimension reduction processing on the first influence matrix to obtain a second influence matrix includes:
determining a covariance matrix of the first influence matrix;
and performing dimension reduction processing on the first influence matrix based on the covariance matrix of the first influence matrix to obtain a second influence matrix.
Optionally, the performing, by the processor 301, the dimension reduction processing on the first influence matrix based on the covariance matrix of the first influence matrix to obtain a second influence matrix includes:
calculating a covariance matrix of the first influence matrix;
calculating eigenvalues of the covariance matrix and eigenvectors corresponding to the eigenvalues;
and obtaining the intermediate matrix according to a second number of the eigenvectors with the largest eigenvalues, and determining a second influence matrix according to the first influence matrix and the intermediate matrix.
Optionally, the obtaining, by the processor 301, the intermediate matrix according to the second number of the feature vectors with the largest feature values, and determining a second influence matrix according to the first influence matrix and the intermediate matrix includes:
multiplying the first influence matrix with the intermediate matrix to obtain a second influence matrix.
Optionally, the predicting, by the processor 301, the road disease of the target road segment according to the road disease affecting factor, to obtain a road disease prediction result of the target road segment includes:
acquiring driving vehicle data and road environment data of the target road section;
determining a target influence matrix of the target road section according to the road disease influence factor;
and predicting the road disease of the target road section based on the target influence matrix to obtain a road disease prediction result of the target road section.
The electronic equipment provided by the embodiment of the invention can realize each process realized by the road disease prediction method in the embodiment of the method, and can achieve the same beneficial effects. In order to avoid repetition, a description thereof is omitted.
The embodiment of the invention also provides a computer readable storage medium, and a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the process of the road disease prediction method provided by the embodiment of the invention is realized, the same technical effect can be achieved, and the repetition is avoided, so that the description is omitted.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disc, a Read-Only memory (RON), a random access memory (Randon Access Nenory, RAN for short), or the like.
The foregoing disclosure is illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.
Claims (10)
1. A road disease prediction method, characterized by comprising the steps of:
acquiring historical driving vehicle data and historical road environment data of each road section;
determining a road disease influence factor according to the historical driving vehicle data and the historical road environment data;
and predicting the road diseases of the target road section according to the road disease influence factors to obtain a road disease prediction result of the target road section.
2. The road disease prediction method according to claim 1, wherein the determining a road disease influence factor from the historical traveling vehicle data and the historical road environment data includes:
determining influence data of road diseases according to the historical driving vehicle data and the historical road environment data, wherein the influence data comprises a first number of data dimensions;
performing dimension reduction processing on the influence data to obtain sample dimension reduction data, wherein the sample dimension reduction data comprises a second number of data dimensions, and the second number is smaller than the first number;
and determining a road disease influence factor based on the sample dimension reduction data.
3. The method of predicting road disease of claim 2, wherein the performing the dimension reduction on the impact data to obtain sample dimension reduction data, the sample dimension reduction data including a second number of data dimensions, comprises:
determining a first influence matrix according to the influence data, wherein the first influence matrix comprises a first number of data dimensions;
performing dimension reduction on the first influence matrix to obtain a second influence matrix;
the sample dimension reduction data is determined based on the first impact matrix and the second impact matrix.
4. The method for predicting road diseases according to claim 3, wherein said performing a dimension reduction process on said first influence matrix to obtain a second influence matrix comprises:
determining a covariance matrix of the first influence matrix;
and performing dimension reduction processing on the first influence matrix based on the covariance matrix of the first influence matrix to obtain a second influence matrix.
5. The method for predicting road diseases according to claim 4, wherein the performing the dimension reduction process on the first influence matrix based on the covariance matrix of the first influence matrix to obtain a second influence matrix comprises:
calculating a covariance matrix of the first influence matrix;
calculating eigenvalues of the covariance matrix and eigenvectors corresponding to the eigenvalues;
and obtaining the intermediate matrix according to a second number of the eigenvectors with the largest eigenvalues, and determining a second influence matrix according to the first influence matrix and the intermediate matrix.
6. The method of predicting road disease of claim 5, wherein the obtaining the intermediate matrix from the second number of eigenvectors having the largest eigenvalues, determining a second influence matrix from the first influence matrix and the intermediate matrix, comprises:
multiplying the first influence matrix with the intermediate matrix to obtain a second influence matrix.
7. The method of claim 6, wherein predicting the road fault of the target link based on the road fault influencing factor to obtain the road fault prediction result of the target link comprises:
acquiring driving vehicle data and road environment data of the target road section;
determining a target influence matrix of the target road section according to the road disease influence factor;
and predicting the road disease of the target road section based on the target influence matrix to obtain a road disease prediction result of the target road section.
8. A road disease prediction apparatus, characterized in that the apparatus comprises:
the acquisition module is used for acquiring historical driving vehicle data and historical road environment data of each road section;
the determining module is used for determining road disease influence factors according to the historical driving vehicle data and the historical road environment data;
and the prediction module is used for predicting the road diseases of the target road section according to the road disease influence factors to obtain a road disease prediction result of the target road section.
9. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the road fault prediction method as claimed in any one of claims 1 to 7 when the computer program is executed.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps in the road disease prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211739057.4A CN116432095A (en) | 2022-12-31 | 2022-12-31 | Road disease prediction method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211739057.4A CN116432095A (en) | 2022-12-31 | 2022-12-31 | Road disease prediction method, device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116432095A true CN116432095A (en) | 2023-07-14 |
Family
ID=87086128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211739057.4A Pending CN116432095A (en) | 2022-12-31 | 2022-12-31 | Road disease prediction method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116432095A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117233752A (en) * | 2023-11-08 | 2023-12-15 | 江苏筑升土木工程科技有限公司 | Road underground disease body water content calculation and analysis method based on radar nondestructive detection |
-
2022
- 2022-12-31 CN CN202211739057.4A patent/CN116432095A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117233752A (en) * | 2023-11-08 | 2023-12-15 | 江苏筑升土木工程科技有限公司 | Road underground disease body water content calculation and analysis method based on radar nondestructive detection |
| CN117233752B (en) * | 2023-11-08 | 2024-01-30 | 江苏筑升土木工程科技有限公司 | Road underground disease body water content calculation and analysis method based on radar nondestructive detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hadjidemetriou et al. | Automated pavement patch detection and quantification using support vector machines | |
| CN112800911B (en) | Pavement damage rapid detection and natural data set construction method | |
| CN111666995B (en) | Vehicle damage assessment method, device, equipment and medium based on deep learning model | |
| Hadjidemetriou et al. | Automated detection of pavement patches utilizing support vector machine classification | |
| CN111143932A (en) | Bridge health state assessment method, device, system and equipment | |
| CN116432095A (en) | Road disease prediction method, device, electronic equipment and storage medium | |
| CN113962960A (en) | Pavement disease detection method based on deep learning | |
| CN111127465A (en) | Automatic generation method and system for bridge detection report | |
| CN113269042A (en) | Intelligent traffic management method and system based on running vehicle violation identification | |
| CN111241994A (en) | Method for extracting remote sensing image rural highway desertification road section for deep learning | |
| Oliveira et al. | Identifying and retrieving distress images from road pavement surveys | |
| Ha et al. | Assessing severity of road cracks using deep learning-based segmentation and detection | |
| CN115995056A (en) | Automatic bridge disease identification method based on deep learning | |
| CN114283383A (en) | Smart city highway maintenance method, computer equipment and medium | |
| CN115170988A (en) | Power grid line fault identification method and system based on deep learning | |
| Hassan et al. | Detecting patches on road pavement images acquired with 3D laser sensors using object detection and deep learning | |
| Katsamenis et al. | A Few-Shot Attention Recurrent Residual U-Net for Crack Segmentation | |
| CN116168356B (en) | Vehicle damage judging method based on computer vision | |
| CN116740495A (en) | Training method and defect detection method for defect detection model of road and bridge tunnel | |
| CN114550460B (en) | Rail transit anomaly detection method and device and storage medium | |
| CN115239689A (en) | Road surface information detection method, road surface information calculation method, road surface information detection system, road surface information detection equipment and computer readable storage medium | |
| CN115294774A (en) | Non-motor vehicle road illegal parking detection method and device based on deep learning | |
| CN114219073A (en) | Method and device for determining attribute information, storage medium and electronic device | |
| Ferrer-Espinoza et al. | Evaluation of the use of Cascade Detection algorithms based on Machine Learning for Crack Detection in asphalt Pavements | |
| CN113191398A (en) | Improved Faster R-CNN-based pavement damage identification method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |