Resource scheduling method and system for road maintenance informatization management

Abstract

The invention discloses a resource scheduling method and system for road maintenance informatization management, and relates to the technical field of road maintenance, and the method comprises the steps: obtaining historical road surface detection data of a selected road section in a set time period; obtaining respective weight values of the abnormal data in the selected road section in a set time period, obtaining the abnormal data after weighting, carrying out modeling analysis based on the abnormal data and the intact data, obtaining a time mapping relation between the abnormal data and the intact data, and establishing an abnormal data prediction model; and extracting length features about cracks, smoothness and pit slot defects in the to-be-maintained road surface image, obtaining a prediction result of road abnormity through the abnormal data prediction model, and selecting a resource scheduling scheme through the prediction result. According to the method, the prediction result is generated and the resource scheduling scheme is selected through the real-time image and abnormal data prediction model, the hysteresis problem of problem discovery and processing is solved, and the road maintenance effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of highway maintenance, and in particular to a resource scheduling method and system for highway maintenance information management. Background Art

[0002] With the acceleration of urbanization and the continuous increase in traffic volume, the importance of highway maintenance and upkeep is becoming increasingly prominent as an important infrastructure. Pavement cracks not only affect driving comfort, but may also cause more serious road damage, thus threatening driving safety. Therefore, timely and effective detection and evaluation of pavement crack conditions are crucial for the rational planning of highway maintenance plans.

[0003] Traditional highway maintenance methods mainly rely on manual inspections and empirical judgments, which are inefficient and subjective, and cannot meet the needs of modern highway management. In recent years, with the development of information technologies such as the Internet of Things and big data analysis, the application of intelligent detection and management has gradually become popular, improving the efficiency and accuracy of highway maintenance work.

[0004] However, the existing intelligent detection and management still have some shortcomings. Based on the regular inspection and maintenance cycle, there is no accurate data as a basis, and it is difficult to make scientific resource allocation and decision-making. This means that there is a certain lag in the discovery and handling of problems, resulting in a lack of accurate and reasonable scientific analysis and decision-making process in the highway maintenance process, and the maintenance effect is poor. Summary of the invention

[0005] The purpose of the present invention is to provide a resource scheduling method and system for highway maintenance information management in view of the above-mentioned deficiencies in the prior art, so as to solve the problem that there is a certain lag in the discovery and processing of problems in the prior art, resulting in a lack of accurate and reasonable scientific analysis and decision-making process in the highway maintenance process, and poor maintenance effect.

[0006] The present invention specifically provides the following technical solutions:

[0007] A resource scheduling method for highway maintenance information management includes the following steps:

[0008] Obtain historical road surface detection data of the selected road section within a set time period; the historical road surface detection data includes abnormal data and intact data of the road surface, the abnormal data is the length of the road surface with cracks, flatness and pothole defects, and the intact data is the length of the road surface without defects;

[0009] Obtain the weight values ​​of cracks, flatness and pothole defects in the selected road section within a set time period, obtain abnormal data after weighting different weight values, and perform modeling analysis based on abnormal data and intact data, obtain the time mapping relationship between abnormal data and intact data in historical highway pavement detection data, and establish an abnormal data prediction model for highway pavement through the time mapping relationship;

[0010] Length features of cracks, flatness and pothole defects in the road pavement image to be maintained are extracted, and the length features are input into an abnormal data prediction model to obtain prediction results of highway abnormal data, and a resource scheduling plan is selected based on the prediction results.

[0011] Preferably, the modeling and analysis based on the abnormal data and the intact data to obtain the time mapping relationship between the abnormal data and the intact data in the historical highway pavement detection data includes:

[0012] Clean the historical highway pavement inspection data, remove duplicate values, process missing values, and integrate the data;

[0013] Extracting length features of cracks, flatness and pothole defects and intact data features from the historical highway pavement inspection data after data integration, mapping the intact data features and the length features of cracks, flatness and pothole defects into the same feature space, obtaining a correlation function with time as a variable, and performing parameter estimation on the correlation function by the least squares method to obtain an optimal parameter value;

[0014] The time mapping relationship between intact data and length characteristics of cracks, flatness and pothole defects in historical highway pavement inspection data is obtained through a correlation function with optimal parameter values.

[0015] Preferably, the performing parameter estimation on the correlation function by the least square method to obtain the optimal parameter value comprises:

[0016] When estimating parameters, setting an objective function, wherein the objective function is the residual sum of squares between historical highway pavement detection data and predicted data;

[0017] The gradient descent method is used to obtain the minimum value of the residual sum of squares, and the minimum value of the residual sum of squares is used as the optimal parameter value.

[0018] Preferably, the method of using the gradient descent method to obtain the minimum value of the residual sum of squares includes:

[0019] Get the minimum value of the residual sum of squares. The specific expression is:

[0020]

[0021] Among them, RSS is the residual sum of squares, n is the number of data points, i is the i-th data point, and y i is the actual observed value, is the predicted value, usually expressed as:

[0022]

[0023] Among them, β0 is the intercept, β1 is the slope, and x i is the independent variable;

[0024] The partial derivative of β0 and β1 is calculated to obtain the gradient of RSS under the current parameter value, and the gradient is updated through the update rule to obtain β0 and β1 that minimize RSS. The minimum value of the residual sum of squares is obtained through β0 and β1 that minimize RSS.

[0025] Preferably, the extracting of length features of cracks, flatness and pothole defects in the road surface image to be maintained includes:

[0026] Inputting the road surface image of the highway to be maintained into a trained neural network model, sliding the convolution kernel of the convolution layer on the highway image to extract local features of the road surface image of the highway to be maintained, and downsampling the local features through a pooling layer;

[0027] By stacking multiple convolutional layers and pooling layers, the pavement image of the highway to be maintained is repeatedly processed to obtain the length features of cracks, flatness and pothole defects in the pavement image of the highway to be maintained.

[0028] Preferably, the step of obtaining the weight values ​​of the length characteristics of cracks, flatness and pothole defects in the selected road section within the set time period, and weighting different weight values ​​to obtain abnormal data includes:

[0029] All parameters to be considered are selected based on historical highway pavement inspection data over a period of time; the parameters include length characteristics of cracks, flatness and pothole defects;

[0030] The subjective weight is obtained by the influence of the selected parameters on highway operation, and the eigenvalues ​​and eigenvectors of the selected parameters are obtained through principal component analysis, and the comprehensive score coefficients of the eigenvalues ​​and eigenvectors are obtained. The weight value of each parameter is obtained through the comprehensive score coefficient of each parameter.

[0031] Preferably, the resource scheduling scheme includes planning schemes for human resources, material resources and time resources.

[0032] The present invention provides a resource scheduling system for highway maintenance information management, comprising:

[0033] The acquisition module is used to obtain historical road surface detection data of the selected road section within a set time period; the historical road surface detection data includes abnormal data and intact data of the road surface, the abnormal data is the length of the road surface with cracks, flatness and pothole defects, and the intact data is the length of the road surface without defects;

[0034] A model building module is used to obtain the weight values ​​of cracks, flatness and pothole defects in the selected road section within a set time period, obtain abnormal data after weighting different weight values, and perform modeling analysis based on abnormal data and intact data, obtain the time mapping relationship between abnormal data and intact data in historical highway pavement detection data, and establish an abnormal data prediction model for highway pavement through the time mapping relationship;

[0035] The resource scheduling module is used to extract the length features of cracks, flatness and pothole defects in the road surface image to be maintained, and input the length features into the abnormal data prediction model to obtain the prediction results of the highway abnormal data, and select the resource scheduling plan according to the prediction results.

[0036] The present invention provides a computer device, including a memory and a processor, wherein a program is stored in the memory, and when the program is executed by the processor, the processor executes the steps of the above-mentioned resource scheduling method for highway maintenance information management.

[0037] The present invention provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the resource scheduling method for highway maintenance information management are implemented.

[0038] Compared with the prior art, the present invention has the following significant advantages:

[0039] The present invention targets images of highway maintenance sections and combines them with historical highway pavement detection data. First, the length characteristics of cracks, flatness and pothole defects under different weights are fitted to the historical highway pavement detection data, thereby constructing a time mapping relationship between intact data and the length characteristics of cracks, flatness and pothole defects and an abnormal data prediction model, thereby providing a prediction model for highway detection, facilitating subsequent accurate guidance of highway maintenance, extracting features from the highway pavement image at the current moment, providing direct input data for the abnormal data prediction model, selecting a resource scheduling plan through the prediction results generated by the real-time image and the abnormal data prediction model, and solving the lag problem of problem discovery and processing, thereby achieving accurate, reasonable and scientific analysis and decision-making based on current highway information, and improving the effect of highway maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1This is an overall flow chart of a resource scheduling method for highway maintenance information management according to the present invention;

[0041] Figure 2 A diagram showing the construction process of the abnormal data prediction model in the present invention;

[0042] Figure 3 This is a diagram of the processing of a highway image by a neural network in the present invention;

[0043] Figure 4 It is a specific flow chart of the model fitting in the present invention. DETAILED DESCRIPTION

[0044] The following is a clear and complete description of the technical solutions of the embodiments of the present invention in conjunction with the drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0045] Based on the existing technology, the current resource scheduling methods in the field of highway maintenance often rely on manual experience and subjective judgment. The traditional resource scheduling methods are mainly based on the experience and subjective judgment of maintenance personnel. This method is easily affected by personal subjective opinions and experience, resulting in the allocation and utilization of resources being not scientific and accurate enough. Different maintenance personnel may have different judgment criteria, resulting in inconsistency in resource scheduling. The traditional resource scheduling methods lack sufficient data support and cannot fully understand the actual situation and needs of highway maintenance. Without accurate data as a basis, it is difficult to make scientific resource allocation and decision-making. The traditional resource scheduling methods are usually based on the cycle of regular inspections and maintenance, which means that there is a certain lag in the discovery and handling of problems. Resource scheduling is often carried out after the problem occurs, which may lead to further deterioration of the problem and affect the safety and comfort of the highway. The traditional resource scheduling methods often do not use optimization algorithms to optimize resource allocation and utilization. They lack scientific algorithm support and cannot achieve the optimal scheduling plan under limited resource conditions, resulting in insufficient resource utilization and low efficiency.

[0046] like Figure 1 As shown, the present invention provides a resource scheduling method for highway maintenance information management, which specifically includes the following steps:

[0047] Step S1: Acquire historical road surface detection data of the selected road section within a set time period; wherein the historical road surface detection data includes abnormal data and intact data of the road surface, the abnormal data is the length of the road surface with cracks, flatness and pothole defects, and the intact data is the length of the road surface without defects.

[0048] The historical highway pavement inspection data includes the length characteristics of pavement cracks, flatness, and pothole defects. The details are shown in Table 1:

[0049] Table 1 Highway maintenance quality inspection record

[0050]

[0051] This record contains abnormal data reported by a brand new highway during each annual inspection.

[0052] Step S2: Obtain the weight values ​​of cracks, flatness and pothole defects in the selected road section within the set time period, obtain abnormal data after weighting different weight values, and perform modeling analysis based on abnormal data and intact data, obtain the time mapping relationship between abnormal data and intact data in historical highway pavement detection data, and establish an abnormal data prediction model for highway pavement through the time mapping relationship.

[0053] The time-based abnormal data prediction model analyzes time through parameter estimation and curve fitting methods, finds out the trend characteristics and assumes that this trend can continue in the future, so as to make predictions for future data. The trend characteristics of the analysis object can be intuitively shown through the time model diagram.

[0054] Obtain the weight values ​​of the length characteristics of cracks, flatness and pothole defects in the selected road section within the set time period, and obtain abnormal data after weighting different weight values, including:

[0055] All parameters to be considered are selected based on historical highway pavement inspection data over a period of time; the parameters include length characteristics of cracks, flatness and pothole defects.

[0056] The subjective weight is obtained by the influence of the selected parameters on highway operation, and the eigenvalues ​​and eigenvectors of the selected parameters are obtained through principal component analysis, and the comprehensive score coefficients of the eigenvalues ​​and eigenvectors are obtained. The weight value of each parameter is obtained through the comprehensive score coefficient of each parameter.

[0057] Building an abnormal data prediction model includes the following steps:

[0058] Data preparation: Data cleaning is performed on historical highway pavement inspection data, duplicate values ​​are removed, missing values ​​are processed, and data integration is performed. If necessary, data is processed by difference, logarithmic transformation, etc. to meet the requirements of the model.

[0059] Model selection: Select a suitable model based on the characteristics and requirements of the data, and consider factors such as the stationarity, seasonality, and trend of the data.

[0060] Parameter estimation: The length characteristics of cracks, flatness and pothole defects and the intact data characteristics are extracted from the historical highway pavement inspection data after data integration, and the length characteristics of cracks, flatness and pothole defects and the intact data characteristics are used to map the intact data and the length characteristics of cracks, flatness and pothole defects into the same feature space to obtain the correlation function with time as the variable, and the parameters of the correlation function are estimated by the least squares method to obtain the optimal parameter value.

[0061] The time mapping relationship between intact data and length characteristics of cracks, flatness and pothole defects in historical highway pavement inspection data is obtained through a correlation function with optimal parameter values.

[0062] Model verification: Perform necessary tests on the fitted model to prove the validity and accuracy of the model, including white noise test of residual sequence, significance test of parameters, etc. If the model does not meet the requirements, it may be necessary to reselect the model or adjust the parameters.

[0063] Use the fitted model to predict the future values ​​of the time series data, determine the prediction interval and confidence level, and evaluate the reliability of the prediction results.

[0064] Among them, the least squares method estimates the parameters of the relevant function and obtains the optimal parameter value, including:

[0065] Assume that the correlation function is a linear function, y = ax + b, a and b are the parameters to be estimated, y is normal data, and x is abnormal data. When estimating parameters, set the objective function, where the objective function is the residual sum of squares between normal data and predicted data. The objective function can be expressed as:

[0066]

[0067] Where n is the number of data points, y i and x i is the observed data, i is the number of observation points, S is the objective function, that is, the residual sum of squares RSS (Residual Sum of Squares), the gradient descent method is used to obtain the minimum value of the residual sum of squares, and the minimum value of the residual sum of squares is taken as the optimal parameter value, specifically:

[0068]

[0069] Among them, RSS is the residual sum of squares, n is the number of data points, i is the i-th data point, and y i is the actual observed value, is the predicted value, usually expressed as:

[0070]

[0071] Among them, β0 is the intercept, β1 is the slope, and x i is the independent variable.

[0072] The partial derivative of β0 and β1 is calculated to obtain the gradient of RSS under the current parameter value, and the gradient is updated through the update rule to obtain β0 and β1 that minimize RSS. The minimum value of the residual sum of squares is obtained through β0 and β1 that minimize RSS.

[0073] Once you have estimates for the parameters, you can use these values ​​to build a model and verify the model's accuracy. This usually involves calculating the differences between the model's predictions and the actual observed values ​​and assessing whether these differences are within an acceptable range.

[0074] Step S3: extract the length features of cracks, flatness and pothole defects in the road surface image to be maintained, input the length features into the abnormal data prediction model, obtain the prediction results of the highway abnormal data, and select the resource scheduling plan based on the prediction results.

[0075] Extracting the length features of cracks, flatness and pothole defects in the road pavement image to be maintained includes the following steps:

[0076] The pavement image of the highway to be maintained is input into the trained neural network model, and the convolution kernel of the convolution layer slides on the highway image to extract the local features of the pavement image of the highway to be maintained, and the local features are downsampled through the pooling layer.

[0077] The convolution layer is the core component of CNN, which extracts features from the image through convolution operations. When extracting local features of a highway image, element-wise multiplication is performed with the local area of ​​the image, and the results are summed to form an element of the output feature map. This process is repeated over the entire area of ​​the image to generate a complete feature map. The convolution kernel can capture local dependencies and spatial hierarchical structures in the image. As the network level deepens, the convolution layer can further combine these simple features to extract more complex features. The pooling layer is usually located after the convolution layer to reduce the spatial dimension of the feature map, which helps reduce the amount of computation and the risk of overfitting while maintaining the spatial hierarchy of the features. Commonly used pooling operations include maximum pooling and average pooling.

[0078] After the convolution layer, a nonlinear activation function is set, such as ReLU (rectifier linear unit), which increases the nonlinear ability of the network and enables CNN to learn more complex features.

[0079] By stacking multiple convolutional layers and pooling layers, the pavement image of the highway to be maintained is repeatedly processed to obtain the length features of cracks, flatness and pothole defects in the pavement image of the highway to be maintained.

[0080] Resource scheduling plans include planning plans for human resources, material resources, and time resources. When formulating a scheduling plan, it is usually necessary to consider multiple factors to ensure the effectiveness and rationality of the plan. These factors include: Resource availability: It is necessary to understand the quantity, type, performance, etc. of resources to determine which resources can be used to complete the task. Task priority: Different tasks may have different priorities, and resources need to be allocated based on the urgency and importance of the task. Running time and resource consumption: It is necessary to estimate the running time and resource consumption of the task in order to reasonably allocate resources and avoid resource waste. Task constraints: Possible task constraints, such as time windows, resource dependencies, etc., need to be considered when formulating the plan.

[0081] Based on the above method, the present invention provides a resource scheduling system for highway maintenance information management, including: a collection module, a model building module and a resource scheduling module.

[0082] Among them, the acquisition module is used to obtain the historical highway pavement detection data of the selected section within a set time period; the historical highway pavement detection data includes abnormal data and intact data of the highway pavement, the abnormal data is the length of the highway pavement with cracks, flatness and pothole defects, and the intact data is the length of the highway pavement without defects; the model building module is used to obtain the respective weight values ​​of cracks, flatness and pothole defects in the selected section within the set time period, obtain the abnormal data after weighting different weight values, and perform modeling analysis based on the abnormal data and intact data, obtain the time mapping relationship between the abnormal data and the intact data in the historical highway pavement detection data, and establish an abnormal data prediction model for the highway pavement through the time mapping relationship; the resource scheduling module is used to extract the length features of cracks, flatness and pothole defects in the image of the highway pavement to be maintained, and input the length features into the abnormal data prediction model to obtain the prediction results of the highway abnormal data, and select the resource scheduling plan according to the prediction results.

[0083] The present invention also provides a computer device, including a memory and a processor, wherein a program is stored in the memory, and when the program is executed by the processor, the processor executes the steps of a resource scheduling method for highway maintenance information management.

[0084] In accordance with the disclosed embodiments, a computing device may communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth communications, etc.), or with any device (e.g., routers, modems, etc.) that enables a computing device to communicate with one or more other computing devices.

[0085] The present invention also provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of a resource scheduling method for highway maintenance information management are implemented.

[0086] According to the disclosed embodiments, the storage medium may be a non-volatile computer-readable storage medium, such as but not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, the storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0087] The above content is a further detailed description of the present invention in combination with a specific preferred embodiment. For technicians in the technical field to which the present invention belongs, several simple deductions or substitutions can be made without departing from the concept of the present invention, which should be regarded as belonging to the protection scope of the present invention.

Claims

1. A resource scheduling method for highway maintenance information management, characterized in that: include: Obtain historical highway pavement detection data for the selected road section within a set time period; The historical road surface inspection data includes abnormal data and intact data of the road surface. The abnormal data refers to the length of the road surface with cracks, flatness and pothole defects, and the intact data refers to the length of the road surface without defects. Obtain the weight values ​​of cracks, flatness and pothole defects in the selected road section within a set time period, obtain abnormal data after weighting different weight values, and perform modeling analysis based on abnormal data and intact data, obtain the time mapping relationship between abnormal data and intact data in historical highway pavement detection data, and establish an abnormal data prediction model for highway pavement through the time mapping relationship; Length features of cracks, flatness and pothole defects in the road pavement image to be maintained are extracted, and the length features are input into an abnormal data prediction model to obtain prediction results of highway abnormal data, and a resource scheduling plan is selected based on the prediction results.

2. A resource scheduling method for highway maintenance information management as claimed in claim 1, characterized in that: The modeling and analysis based on abnormal data and intact data to obtain the time mapping relationship between abnormal data and intact data in the historical highway pavement detection data includes: Clean the historical highway pavement inspection data, remove duplicate values, process missing values, and integrate the data; Extracting length features of cracks, flatness and pothole defects and intact data features from the historical highway pavement inspection data after data integration, mapping the intact data features and the length features of cracks, flatness and pothole defects into the same feature space, obtaining a correlation function with time as a variable, and performing parameter estimation on the correlation function by the least squares method to obtain an optimal parameter value; The time mapping relationship between intact data and length characteristics of cracks, flatness and pothole defects in historical highway pavement inspection data is obtained through a correlation function with optimal parameter values.

3. A resource scheduling method for highway maintenance information management as claimed in claim 2, characterized in that: The method of performing parameter estimation on the correlation function by the least square method to obtain the optimal parameter value comprises: When estimating parameters, setting an objective function, wherein the objective function is the residual sum of squares between historical highway pavement detection data and predicted data; The gradient descent method is used to obtain the minimum value of the residual sum of squares, and the minimum value of the residual sum of squares is used as the optimal parameter value.

4. A resource scheduling method for highway maintenance information management as claimed in claim 3, characterized in that: The method of using the gradient descent method to obtain the minimum value of the residual sum of squares includes: Get the minimum value of the residual sum of squares. The specific expression is: Among them, RSS is the residual sum of squares, n is the number of data points, i is the i-th data point, and y i is the actual observed value, is the predicted value, usually expressed as: Where β0 is the intercept, β1 is the slope, and x i is the independent variable; The partial derivative of β0 and β1 is calculated to obtain the gradient of RSS under the current parameter value, and the gradient is updated through the update rule to obtain β0 and β1 that minimize RSS. The minimum value of the residual sum of squares is obtained through β0 and β1 that minimize RSS.

5. A resource scheduling method for highway maintenance information management as claimed in claim 1, characterized in that: The method of extracting length features of cracks, flatness and pothole defects in the road surface image to be maintained includes: Inputting the road surface image of the highway to be maintained into a trained neural network model, sliding the convolution kernel of the convolution layer on the highway image to extract local features of the road surface image of the highway to be maintained, and downsampling the local features through a pooling layer; By stacking multiple convolutional layers and pooling layers, the pavement image of the highway to be maintained is repeatedly processed to obtain the length features of cracks, flatness and pothole defects in the pavement image of the highway to be maintained.

6. A resource scheduling method for highway maintenance information management as claimed in claim 1, characterized in that: The method of obtaining the weight values ​​of the length characteristics of cracks, flatness and pothole defects in the selected road section within the set time period, and obtaining abnormal data after weighting different weight values, includes: All parameters to be considered are selected based on historical highway pavement inspection data over a period of time; the parameters include length characteristics of cracks, flatness and pothole defects; The subjective weight is obtained by the influence of the selected parameters on highway operation, and the eigenvalues ​​and eigenvectors of the selected parameters are obtained through principal component analysis, and the comprehensive score coefficients of the eigenvalues ​​and eigenvectors are obtained. The weight value of each parameter is obtained through the comprehensive score coefficient of each parameter.

7. A resource scheduling method for highway maintenance information management as claimed in claim 1, characterized in that: The resource scheduling scheme includes planning schemes for human resources, material resources and time resources.

8. A resource scheduling system for highway maintenance information management, characterized in that: include: A collection module, used to obtain historical highway pavement detection data of a selected road section within a set time period; The historical road surface inspection data includes abnormal data and intact data of the road surface. The abnormal data refers to the length of the road surface with cracks, flatness and pothole defects, and the intact data refers to the length of the road surface without defects. A model building module is used to obtain the weight values ​​of cracks, flatness and pothole defects in the selected road section within a set time period, obtain abnormal data after weighting different weight values, and perform modeling analysis based on abnormal data and intact data, obtain the time mapping relationship between abnormal data and intact data in historical highway pavement detection data, and establish an abnormal data prediction model for highway pavement through the time mapping relationship; The resource scheduling module is used to extract the length features of cracks, flatness and pothole defects in the road surface image to be maintained, and input the length features into the abnormal data prediction model to obtain the prediction results of the highway abnormal data, and select the resource scheduling plan according to the prediction results.

9. A computer device, characterized in that: It includes a memory and a processor, wherein a program is stored in the memory, and when the program is executed by the processor, the processor executes the steps of a resource scheduling method for highway maintenance information management as described in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a resource scheduling method for highway maintenance information management described in any one of claims 1 to 7 are implemented.

Images