Road marking control methods and devices

Abstract

This application provides a road marking control method and apparatus, relating to the field of industrial data processing, and solves the technical problems of low efficiency and insufficient quality stability in existing road marking technologies. The method includes: acquiring standard data for various types of roads and historical road marking operation data; constructing an intelligent decision-making model based on the standard data and historical operation data using machine learning algorithms, and training the intelligent decision-making model; the intelligent decision-making model is used to establish a mapping relationship between different road types, different regions, and corresponding optimal marking schemes; receiving type information and region information of the road to be marked, inputting the type information and region information into the trained intelligent decision-making model to output the corresponding optimal marking scheme, and transmitting the optimal marking scheme to the marking equipment to control the marking equipment to perform the marking operation. This application is used in the road marking construction process.

Description

Technical Field

[0001] This application relates to the field of industrial data processing, and in particular to a road marking control method and apparatus. Background Technology

[0002] In the construction and maintenance system of transportation infrastructure, road marking is a crucial link in ensuring orderly traffic operation and improving traffic safety. With the continuous expansion of various transportation networks in my country, including urban roads, highways, and rural roads, the functional requirements for road marking vary significantly across different scenarios. For example, urban roads need to guide complex traffic flows, highways need to ensure accurate marking for long-distance travel, and rural roads need to balance cost with basic traffic guidance functions. The quality and efficiency of road marking directly affect the travel experience of traffic participants and the safety of road operations. Therefore, how to achieve efficient and accurate marking in diverse road scenarios has become an important research direction in the field of road construction and maintenance.

[0003] Existing road marking technologies mostly employ traditional operating methods, such as manually adjusting equipment parameters to adapt to different road marking standards. Given the current demands for diverse scenario adaptation, efficient construction, and high-quality operation in transportation infrastructure construction, existing technologies generally suffer from low operational efficiency and insufficient stability in marking quality. This makes it difficult to fully meet the comprehensive requirements of road marking operations in terms of efficiency, accuracy, and reliability, thus hindering the overall progress of road construction and maintenance. Summary of the Invention

[0004] This application provides a road marking control method and device, which solves the technical problems of low efficiency and insufficient quality stability in existing road marking technologies.

[0005] To achieve the above objectives, this application adopts the following technical solution: Firstly, a road marking control method is provided, comprising: acquiring standard data of road marking for various types of roads and historical road marking operation data; the standard data of road marking includes the marking requirements of various types of roads in different areas, and the historical road marking operation data includes the road type, area, construction parameters, and marking effect data of historical construction; based on the standard data of road marking and the historical road marking operation data, a machine learning algorithm is used to construct an intelligent decision-making model, and the intelligent decision-making model is trained; the intelligent decision-making model is used to establish a mapping relationship between different road types, different areas, and corresponding optimal marking schemes, and the optimal marking schemes include marking color, width, spacing, and paint type; receiving the type information and area information of the road to be marked, inputting the type information and area information into the trained intelligent decision-making model to output the corresponding optimal marking scheme, and transmitting the optimal marking scheme to the marking equipment to control the marking equipment to perform the marking operation.

[0006] Based on the above technical solution, this application acquires standard road marking data and historical operation data, employs machine learning algorithms to construct and train an intelligent decision-making model, and achieves automatic matching between the road information to be marked and the optimal marking scheme, and directly controls the operation of the marking equipment. Compared with the traditional method of manually adjusting parameters, this application further reduces the equipment parameter debugging time and improves construction efficiency; at the same time, it avoids human parameter setting errors, thereby further improving the pass rate of marking quality, effectively meeting the marking standard requirements of different types and regions of roads, and solving the technical problems of low efficiency and insufficient quality stability in existing road marking technologies.

[0007] In conjunction with the first aspect mentioned above, in one possible implementation, the method further includes: establishing a road marking association database, which is used to acquire road planning data, road design standard data, and real-time feedback data during the road marking construction process. The real-time feedback data includes the operating status parameters of the marking equipment, the actual amount of paint used, and the marking quality inspection data; when the deviation between a newly added record in the road marking association database or the real-time feedback data and a preset standard value is detected to be greater than or equal to a preset deviation threshold, an incremental data acquisition operation is triggered to extract incremental data from the road marking association database; the incremental data includes at least one of newly added road planning data, updated road design standard data, and real-time feedback data with a deviation greater than or equal to the preset deviation threshold; the extracted incremental data, marking standard data, and historical road marking operation data are fused to form an updated dataset; a distributed computing framework is used to optimize and train the intelligent decision-making model, the updated dataset is input into the intelligent decision-making model, and the model parameters are adjusted to adapt the intelligent decision-making model to the updated road planning data, road design standard data, and real-time feedback data.

[0008] In conjunction with the first aspect mentioned above, in one possible implementation, the line marking device is equipped with a positioning fusion module and a terrain scanning module: the positioning fusion module includes a satellite positioning submodule and an inertial navigation submodule. The satellite positioning submodule is used to acquire line marking position information under standard operating conditions, and the inertial navigation submodule is used to calculate the line marking position information of the line marking device by measuring the acceleration and angular velocity of the line marking device when the signal strength acquired by the satellite positioning submodule is lower than a preset signal threshold; the terrain scanning module includes a lidar submodule, which is used to scan the terrain of the area to be marked and acquire three-dimensional terrain data; the positioning fusion module is also used to fuse the line marking position information output by the inertial navigation submodule or the satellite positioning submodule with the three-dimensional terrain data acquired by the lidar submodule, and plan the line marking path based on the fused data.

[0009] In conjunction with the first aspect mentioned above, in one possible implementation, the marking equipment is equipped with a multi-sensor redundant monitoring module: the multi-sensor redundant monitoring module includes at least two sensor sub-modules of the same type, the sensor sub-modules are correspondingly set at the key components of the marking equipment, the key components include motors, nozzles and transmission devices, and the types of sensor sub-modules include temperature sensor sub-modules, vibration sensor sub-modules, speed sensor sub-modules and pressure sensor sub-modules; at least two sensor sub-modules of the same type are used to simultaneously collect the operating status parameters of the corresponding key components.

[0010] In conjunction with the first aspect mentioned above, in one possible implementation, the method further includes: acquiring operating status parameters collected by at least two sensor sub-modules of the same type; constructing a fault prediction model based on the operating status parameters and historical fault records of the marking equipment; predicting the fault prediction result of the marking equipment based on the fault prediction model; the fault prediction result includes the probability of a fault occurring in the future time period, the fault type, and the fault time.

[0011] In conjunction with the first aspect mentioned above, in one possible implementation, the method further includes: obtaining the fault prediction results of each marking device output by the fault prediction model, and the construction operation data of each marking device; the construction operation data includes the service life of the marking device and the current construction task priority data; and performing weight allocation and comprehensive scoring on the fault prediction results of each marking device and the construction operation data of each marking device based on the analytic hierarchy process to generate maintenance priority data for each marking device.

[0012] In conjunction with the first aspect mentioned above, in one possible implementation, the multi-sensor redundant monitoring module is further configured with an intelligent filtering submodule; the intelligent filtering submodule is used to process the operating status parameters collected by the sensor submodule using a moving average filtering algorithm and / or a Kalman filtering algorithm to remove random noise signals from the operating status parameters.

[0013] In conjunction with the first aspect mentioned above, in one possible implementation, an image acquisition module is configured on the line-drawing device; the image acquisition module is used to acquire image data of the lined area in real time; the method further includes: acquiring the image data of the lined area acquired by the image acquisition module, and performing image recognition on the image data of the lined area to generate line-drawing data; the line-drawing data includes the line width, straightness, color uniformity, and edge clarity of the line; and performing quality assessment based on the line-drawing data to generate a line-drawing quality assessment result.

[0014] Secondly, a road marking control device is provided, comprising: a communication unit and a processing unit; the communication unit is used to acquire standard data of road marking for various types of roads and historical road marking operation data; the standard data of road marking includes the marking requirements corresponding to different types of roads in different areas, and the historical road marking operation data includes the road type, area, construction parameters, and marking effect data of historical construction; the processing unit is used to construct an intelligent decision-making model based on the standard data of road marking and the historical road marking operation data, using machine learning algorithms, and to train the intelligent decision-making model; the intelligent decision-making model is used to establish a mapping relationship between different road types, different areas, and corresponding optimal marking schemes, and the optimal marking schemes include marking color, width, spacing, and paint type; the communication unit is used to receive the type information and area information of the road to be marked, input the type information and area information into the trained intelligent decision-making model to output the corresponding optimal marking scheme, and transmit the optimal marking scheme to the marking equipment to control the marking equipment to perform the marking operation.

[0015] In conjunction with the second aspect above, in one possible implementation, the processing unit is used to: establish a road marking association database, which is used to acquire road planning data, road design standard data, and real-time feedback data during the road marking construction process. The real-time feedback data includes the operating status parameters of the marking equipment, the actual amount of paint used, and the marking quality inspection data; when the deviation between the newly added record in the road marking association database or the real-time feedback data and the preset standard value is greater than or equal to a preset deviation threshold, an incremental data acquisition operation is triggered to extract incremental data from the road marking association database; the incremental data includes at least one of the newly added road planning data, updated road design standard data, and real-time feedback data with a deviation greater than or equal to the preset deviation threshold; the extracted incremental data, marking standard data, and historical road marking operation data are fused to form an updated dataset; a distributed computing framework is used to optimize and train the intelligent decision-making model, the updated dataset is input into the intelligent decision-making model, and the model parameters are adjusted to adapt the intelligent decision-making model to the updated road planning data, road design standard data, and real-time feedback data.

[0016] In conjunction with the second aspect mentioned above, in one possible implementation, the line marking device is equipped with a positioning fusion module and a terrain scanning module: the positioning fusion module includes a satellite positioning submodule and an inertial navigation submodule. The satellite positioning submodule is used to acquire line marking position information under standard operating conditions, and the inertial navigation submodule is used to calculate the line marking position information of the line marking device by measuring the acceleration and angular velocity of the line marking device when the signal strength acquired by the satellite positioning submodule is lower than a preset signal threshold; the terrain scanning module includes a lidar submodule, which is used to scan the terrain of the area to be marked and acquire three-dimensional terrain data; the positioning fusion module is also used to fuse the line marking position information output by the inertial navigation submodule or the satellite positioning submodule with the three-dimensional terrain data acquired by the lidar submodule, and plan the line marking path based on the fused data.

[0017] In conjunction with the second aspect above, in one possible implementation, the marking equipment is equipped with a multi-sensor redundant monitoring module: the multi-sensor redundant monitoring module includes at least two sensor sub-modules of the same type, the sensor sub-modules are correspondingly set at the key components of the marking equipment, the key components include motors, nozzles and transmission devices, and the types of sensor sub-modules include temperature sensor sub-modules, vibration sensor sub-modules, speed sensor sub-modules and pressure sensor sub-modules; at least two sensor sub-modules of the same type are used to simultaneously collect the operating status parameters of the corresponding key components.

[0018] In conjunction with the second aspect above, in one possible implementation, the communication unit is used to: acquire operating status parameters collected by at least two sensor submodules of the same type; the processing unit is used to: construct a fault prediction model based on the operating status parameters and the historical fault records of the marking equipment; predict the fault prediction result of the marking equipment based on the fault prediction model; the fault prediction result includes the probability of a fault occurring in the future time period, the fault type, and the fault time.

[0019] In conjunction with the second aspect above, in one possible implementation, the communication unit is used to: acquire the fault prediction results of each marking device output by the fault prediction model, and the construction operation data of each marking device; the construction operation data includes the service life of the marking device and the current construction task priority data; the processing unit is used to: perform weight allocation and comprehensive scoring on the fault prediction results of each marking device and the construction operation data of each marking device based on the analytic hierarchy process, and generate maintenance priority data for each marking device.

[0020] In conjunction with the second aspect above, in one possible implementation, the multi-sensor redundant monitoring module is further configured with an intelligent filtering submodule; the intelligent filtering submodule is used to process the operating status parameters collected by the sensor submodule using a moving average filtering algorithm and / or a Kalman filtering algorithm to remove random noise signals from the operating status parameters.

[0021] In conjunction with the second aspect above, in one possible implementation, the line-marking device is equipped with an image acquisition module; the image acquisition module is used to acquire image data of the marked area in real time; the communication unit is used to: acquire the image data of the marked area acquired by the image acquisition module; the processing unit is used to: perform image recognition on the image data of the marked area to generate line-marking data; the line-marking data includes the line width, straightness, color uniformity, and edge sharpness of the line; and perform quality assessment based on the line-marking data to generate a line-marking quality assessment result.

[0022] Thirdly, this application provides a road marking control device, comprising: a processor and a storage medium; the storage medium includes instructions, and the processor is configured to execute the instructions to implement the method described in any of the above embodiments. This road marking control device may be an electronic device or a chip within an electronic device.

[0023] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a road marking control device, cause the road marking control device to perform the method described in any of the above embodiments.

[0024] Fifthly, this application provides a computer program product containing instructions that, when run on a road marking control device, cause the road marking control device to perform the method described in any of the above embodiments.

[0025] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0026] Figure 1 A system architecture diagram of a road marking control system provided in this application embodiment; Figure 2 A schematic flowchart illustrating a road marking control method provided in an embodiment of this application; Figure 3 A flowchart illustrating another road marking control method provided in this application embodiment; Figure 4 A flowchart illustrating another road marking control method provided in this application embodiment; Figure 5 A flowchart illustrating another road marking control method provided in this application embodiment; Figure 6 A flowchart illustrating another road marking control method provided in this application embodiment; Figure 7 This is a schematic diagram of the structure of a road marking control device provided in an embodiment of this application; Figure 8 This is a schematic diagram of the hardware structure of a road marking control device provided in an embodiment of this application. Detailed Implementation

[0027] In the description of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. The "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" means one or more, and "multiple" means two or more. The terms "first," "second," etc., do not limit the quantity or order of execution, and "first," "second," etc., do not necessarily imply differences.

[0028] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0029] Road marking is a crucial step in road construction and maintenance, as its quality directly affects traffic order and safety. With the continuous advancement of transportation infrastructure construction in my country, various types of roads, such as urban roads, highways, and rural roads, are emerging, and the requirements for road marking vary significantly across different regions and road types.

[0030] However, existing road marking technologies still face numerous unresolved issues: Firstly, when dealing with different types and regions of road marking standards, current methods largely rely on manual adjustment of equipment parameters, which is not only time-consuming and labor-intensive but also prone to inconsistent marking quality due to human error. Secondly, the maintenance of marking equipment primarily employs a pattern of periodic inspections or repairs after malfunctions, lacking precise monitoring of equipment operating status and fault prediction, easily leading to delays in construction schedules due to sudden equipment failures. Simultaneously, scattered marking operation data has not been effectively integrated and utilized, making it difficult to support the optimization of marking schemes and road planning decisions. Furthermore, in special scenarios such as tunnels and densely populated high-rise areas, traditional positioning technologies are susceptible to interference, resulting in marking position deviations, and lack the ability to perceive micro-topography, affecting the fit between the markings and the surrounding environment. These problems collectively render the efficiency, quality, and adaptability of existing road marking technologies unable to meet the current development needs of road construction.

[0031] In view of this, this application provides a road marking control method. By acquiring marking standard data and historical operation data, a machine learning algorithm is used to construct and train an intelligent decision-making model, which realizes the automatic matching of the road information to be marked with the optimal marking scheme and directly controls the operation of the marking equipment. Compared with the traditional method of manually adjusting parameters, this application further reduces the equipment parameter debugging time and improves construction efficiency; at the same time, it avoids human parameter setting errors (such as mistakenly setting the highway marking width to the urban road width), thereby further improving the marking quality pass rate, effectively meeting the marking standard requirements of different types and regions of roads, and solving the technical problems of low efficiency and insufficient quality stability in existing road marking technologies.

[0032] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0033] Figure 1 This is an architectural diagram of a road marking control system provided in an embodiment of this application. Figure 1 As shown, the road marking control system includes a road marking control device 101 and a marking device 102. The number of road marking control devices 101 and marking devices 102 can be one or more; this application does not limit the number of road marking control devices 101 and marking devices 102.

[0034] In some embodiments, the road marking control device 101 is a server, including: The processor can be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program in this application.

[0035] A transceiver can be any type of transceiver used to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0036] Memory can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions, electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed discs, laser discs, optical discs, digital universal discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory can exist independently and be connected to the processor via communication lines. Memory can also be integrated with the processor.

[0037] In some embodiments, the road marking control device 101 includes an intelligent decision-making module, an equipment status monitoring and predictive maintenance module, and a data center and management module.

[0038] The intelligent decision-making module is used for data collection, model building, and optimization.

[0039] For data collection, the intelligent decision-making module can establish an automatic data update mechanism that connects in real-time with the databases of road construction and management departments. For example, by leveraging network communication technology, it can periodically or in real-time acquire the latest road planning documents, design standards, and feedback data from actual construction. This data covers the specific marking requirements for different types of roads (urban roads, highways, rural roads, etc.) in different areas. Simultaneously, it collects historical operational data, including past marking process parameters, paint types used, construction environmental conditions, and final marking effect evaluations for various types of roads, constructing a vast and dynamically updated industrial big data dataset.

[0040] For model building and optimization, the intelligent decision-making module can construct intelligent decision-making models based on collected data and using machine learning algorithms. First, the data is preprocessed. A data standardization module converts data of different formats and standards into a format suitable for model processing. For example, data on road widths and traffic flow from different regions are normalized according to a unified unit of measurement and range. Then, deep learning algorithms, such as neural networks, are used to train the model, allowing it to learn the mapping relationship between different road conditions and the optimal lane marking scheme. During training, the model's parameters are continuously adjusted to improve its accuracy and generalization ability. When inputting information such as road type and region, the model can quickly output the optimal lane marking scheme, including detailed parameters such as lane color, width, spacing, paint type, and construction speed.

[0041] The equipment condition monitoring and predictive maintenance module is used for sensor data acquisition, fault prediction, and maintenance planning.

[0042] For example, this application can install various types of sensors on key components of the marking device 102, such as the motor, nozzle, and transmission device. For instance, temperature sensors, speed sensors, and vibration sensors can be installed on the motor to monitor its operating parameters in real time; pressure sensors can be installed at the nozzle to monitor the paint spraying pressure. A multi-sensor redundancy design is adopted. Taking the temperature sensor as an example, multiple temperature sensors are installed at different locations on the motor. When one sensor malfunctions or displays abnormal data, the other sensors can continue to provide accurate temperature data. Simultaneously, each sensor is equipped with intelligent filtering and anti-interference algorithms to process the collected data in real time, removing noise and interference signals and improving data accuracy.

[0043] The equipment condition monitoring and predictive maintenance module can acquire real-time equipment operating status data collected by sensors. Utilizing big data analytics, combined with historical operating data and fault records, it establishes equipment fault prediction models. For example, through long-term analysis of motor temperature, speed, and vibration data, it determines the variation patterns of these parameters under normal and fault conditions. When monitored parameters deviate from normal ranges, the model predicts the possible fault type and timing based on a preset algorithm. Simultaneously, a construction equipment management cloud platform is built, integrating multiple marking devices (102) into a unified management system. The platform centrally analyzes the operating status data of all equipment, employing operations research and optimization algorithms to comprehensively consider factors such as equipment lifespan, fault risk, and maintenance costs to formulate an overall maintenance plan. This plan rationally allocates maintenance resources, such as assigning maintenance personnel, determining maintenance times, and replacing parts, enabling collaborative maintenance and scheduling of multiple devices.

[0044] The data center and management module is used for data collection, integration, and analysis.

[0045] For example, the data center and management module can establish a data center to collect real-time data from various marking devices 102 based on network communication technology. This includes equipment operating status data, construction parameter data, marking effect data, and road planning and design standard data and historical operation data obtained by the intelligent decision-making module. Data standardization processing technology is used to uniformly process the collected data of different formats and sources to meet the storage and analysis requirements of the data center. For example, temperature data collected by different devices can be uniformly converted to degrees Celsius, and time data of different formats can be uniformly converted to a standard time format.

[0046] Subsequently, big data analytics is used to deeply mine and analyze the integrated data. For example, by statistically analyzing the wear and tear of road markings in different regions and on different types of roads, key factors affecting the durability of road markings are identified, providing a basis for paint selection and construction process optimization. By analyzing the operational data of different construction teams, efficient construction methods and processes are summarized, forming a construction guide for all construction teams to refer to. At the same time, the analysis results are fed back to the intelligent decision-making module to further optimize the intelligent decision-making model and improve the accuracy and adaptability of the marking scheme; and to the equipment condition monitoring and predictive maintenance module to provide more comprehensive data support for the formulation of equipment maintenance plans.

[0047] In some embodiments, the line marking device 102 includes a location and terrain sensing module for location positioning and terrain sensing.

[0048] For example, the marking device 102 can be equipped with a high-precision global positioning system (GPS) and an inertial navigation system (INS). Under normal conditions, GPS acquires the device's geographical location information in real time, providing an accurate position reference for marking operations. When the device enters special scenarios such as tunnels or densely populated areas where GPS signals may be blocked, the INS measures the device's acceleration and angular velocity, and uses integral calculations to deduce the device's position, velocity, and attitude information, ensuring uninterrupted position tracking of the marking device. Simultaneously, a data fusion algorithm is employed to fuse the position information provided by GPS and INS in real time, improving the accuracy and reliability of positioning. For example, using a Kalman filter algorithm, the error characteristics of both GPS and INS data are comprehensively considered, and the data from both are weighted and fused to obtain more accurate device position information.

[0049] Furthermore, this application can also install a lidar on the line marking device 102. The lidar emits a laser beam at a certain frequency and receives the reflected laser signal. By measuring the flight time of the laser beam, the distance between the device and surrounding objects is calculated, thereby scanning the micro-topography of the marked area in real time and obtaining high-precision three-dimensional terrain data. The terrain data obtained by the lidar is combined with the location information fused from GPS and INS. Using this data, a specialized algorithm is used to accurately plan the line marking path, ensuring that the line perfectly matches the surrounding environment. For example, when marking roads in mountainous areas, the height and angle of the line are adjusted based on the terrain undulation data obtained by the lidar, so that the line can better adapt to changes in terrain, not only improving the aesthetics of the road but also better meeting actual traffic needs, ensuring traffic safety and smooth flow.

[0050] It should be noted that the various embodiments of this application can be referenced or learned from each other. For example, the same or similar steps, method embodiments, system embodiments and device embodiments can be referenced from each other without limitation.

[0051] Figure 2 A flowchart illustrating a road marking control method provided in an embodiment of this application. Figure 2 As shown, the method includes the following steps: Step 201: Obtain standard data for road marking and historical data for road marking operations.

[0052] The road marking standard data includes the marking requirements for various types of roads in different areas, while the road marking historical operation data includes the road type, area, construction parameters, and marking effect data of the historical construction.

[0053] For example, standard road marking data can come from official specifications of road construction and management departments, such as the requirements for the width of road markings on urban main roads, the function of different marking colors and line types, and the reflectivity of road markings on highways; historical road marking operation data can come from the historical construction records of construction units, such as construction date, road latitude and longitude, equipment model used, marking width / color / spacing, paint usage and acceptance reports, etc.

[0054] In some embodiments, this application may also standardize the acquired road marking standard data and historical road marking operation data. For example, for road width data, if there are records in meters and feet, they are uniformly converted to meters; for traffic flow data, data from different statistical periods are normalized to the same standard period to ensure data consistency and comparability for subsequent model processing.

[0055] For example, for collected road width data, if it is recorded in different units such as meters or feet, a unit conversion formula is used to convert it to metric units. For traffic flow data, if the statistical time periods are inconsistent, such as some using 5-minute periods and others using 1-hour periods, it is normalized to use 1-hour as the standard statistical time period. Specifically, if the traffic flow of a certain road segment in 5 minutes is n, then the traffic flow in 1 hour is 12n. For categorical data, such as road type and region, one-hot encoding is used to convert it into a binary vector form that is easy for computers to process, so that subsequent model processing can proceed.

[0056] Step 202: Based on the standard data of road marking and the historical operation data of road marking, a machine learning algorithm is used to build an intelligent decision-making model and train the intelligent decision-making model.

[0057] Among them, the intelligent decision-making model is used to establish the mapping relationship between different road types, different areas and the corresponding optimal marking scheme. The optimal marking scheme includes marking color, width, spacing and paint type.

[0058] For example, this application can build an intelligent decision-making model using machine learning frameworks (such as TensorFlow or PyTorch). The model structure can adopt a multi-layer neural network, where the input layer receives encoded feature information such as road type and region, the intermediate hidden layers learn the inherent patterns in the data through complex connections and weight adjustments between neurons, and the output layer outputs the parameters of the best matching line marking scheme, such as line color, width, spacing, and paint type.

[0059] The machine learning algorithms used can include multilayer perceptrons (MLPs) and random forests. This embodiment uses a multilayer perceptron as an example. When constructing the intelligent decision-making model, the number of input layer nodes can be determined based on the number of encoded features such as road types and regions. For example, if there are 5 road types and 10 region information after one-hot encoding, the number of input layer nodes is 15. Three hidden layers can be set in the middle, with 128, 64, and 32 nodes in each hidden layer, respectively. Connection weights are established by connecting each pair of nodes to learn the intrinsic features in the data. The number of output layer nodes corresponds to various parameters of the line marking scheme, such as line color (assuming 3 colors are encoded, then 3 nodes), width (1 node), spacing (1 node), and paint type (assuming 5 paint types are encoded, then 5 nodes), etc. The total number of output layer nodes can be determined according to actual needs.

[0060] During training, standard road marking data and historical road marking operation data were divided into training and validation sets. Optimization algorithms such as gradient descent were used to continuously adjust the model's weight parameters, minimizing the error between the model's predictions on the training set and the actual road marking schemes. Simultaneously, the model's generalization ability was evaluated using the validation set to prevent overfitting. Through multiple rounds of iterative training, the model achieved high accuracy and stability.

[0061] For example, the collected standard road marking data and historical road marking operation data are divided into training and validation sets in a 7:3 ratio. During training, a stochastic gradient descent optimization algorithm is used, with a learning rate of 0.001 and a batch size of 32. The mean squared error loss function is chosen to measure the error between the model's prediction and the actual road marking parameters. In each training round, the model performs forward propagation on the samples in the training set to calculate the predicted values, then calculates the gradient of the loss function with respect to the model weights using backpropagation, and updates the weights using stochastic gradient descent to continuously reduce the loss value. Simultaneously, the model's performance is evaluated on the validation set, observing the changes in the loss value. If the validation set loss value does not decrease for 10 consecutive rounds, the model is considered overfitted, training is stopped, and the model parameters are reverted to the optimal values ​​from the previous round. After multiple rounds of iterative training, the model achieves high accuracy and stability on both the training and validation sets.

[0062] Step 203: Receive the type information and area information of the road to be marked, input the type information and area information into the trained intelligent decision model to output the corresponding best marking scheme, and transmit the best marking scheme to the marking equipment to control the marking equipment to perform the marking operation.

[0063] The information of the road to be marked can be entered by the operator through the touch screen of the marking equipment, or uploaded to the intelligent decision-making unit through a mobile terminal APP; the best marking scheme is transmitted to the control unit of the marking equipment through serial communication or 5G module, and the control unit drives the nozzle, traveling mechanism and other components to operate according to the scheme parameters.

[0064] For example, when faced with a new road marking task, the operator inputs relevant information such as road type and region through the system interface. This information is first encoded using the same methods as the training data and then fed into the trained intelligent decision-making model. Based on the learned patterns and rules, the model internally calculates the optimal marking scheme parameters that match the road conditions through matrix operations and activation function transformations.

[0065] Based on the above technical solution, this application acquires standard road marking data and historical operation data, employs machine learning algorithms to construct and train an intelligent decision-making model, and achieves automatic matching between the road information to be marked and the optimal marking scheme, and directly controls the operation of the marking equipment. Compared with the traditional method of manually adjusting parameters, this application further reduces the equipment parameter debugging time and improves construction efficiency; at the same time, it avoids human parameter setting errors, thereby further improving the pass rate of marking quality, effectively meeting the marking standard requirements of different types and regions of roads, and solving the technical problems of low efficiency and insufficient quality stability in existing road marking technologies.

[0066] As one possible embodiment of this application, combined with Figure 2 ,like Figure 3 As shown, the method also includes the following steps.

[0067] Step 301: Establish a road marking association database.

[0068] The road marking association database is used to obtain real-time road planning data, road design standard data, and real-time feedback data during the road marking construction process. The real-time feedback data includes the operating status parameters of the marking equipment, the actual amount of paint used, and the marking quality inspection data.

[0069] For example, the road marking control device can establish a real-time connection with the road marking associated database through a network interface, and obtain the latest road planning data, design standard data, and real-time feedback data during the road marking construction process according to a predetermined time interval or event triggering mechanism.

[0070] Step 302: When the deviation between the newly added record in the road marking association database or the real-time feedback data and the preset standard value is greater than or equal to the preset deviation threshold, the incremental data acquisition operation is triggered to extract incremental data from the road marking association database.

[0071] The incremental data includes at least one of the following: newly added road planning data, updated road design standard data, and real-time feedback data with deviations greater than or equal to a preset deviation threshold.

[0072] The preset deviation threshold can be set according to actual needs. For example, the deviation threshold between the actual amount of paint used and the standard amount (such as 100 kg / km) can be set to ±10%. That is, when the actual amount used is ≥110 kg / km or ≤90 kg / km, incremental acquisition is triggered. New records include road planning entries newly added to the database.

[0073] Step 303: Merge the extracted incremental data, marking standard data, and historical road marking operation data to form an updated dataset.

[0074] For new road design standard data, this application can accurately insert it into the original standard dataset according to the data category and characteristics; for real-time feedback data during construction, such as the performance data of new coatings in actual use, it can be integrated with the coating performance part of historical operation data to ensure the integrity and consistency of the data.

[0075] For example, for acquired road planning data and road design standard data, the primary keys of the data (such as road number, project ID, etc.) are matched with the standard data in the existing industrial big data. If data records with the same primary key exist, the corresponding fields are updated; if it is a new record, it is directly inserted into the standard dataset. For real-time feedback data during construction, it is merged with the corresponding parts of historical operation data according to data type (such as equipment operating parameters, paint usage data, quality inspection data, etc.). For example, new motor temperature data is integrated with historical motor temperature data records, and the data statistical characteristics (such as mean, standard deviation, etc.) are updated for subsequent analysis.

[0076] Step 304: Optimize and train the intelligent decision-making model using a distributed computing framework. Input the updated dataset into the intelligent decision-making model and adjust the model parameters to adapt the intelligent decision-making model to the updated road planning data, road design standard data, and real-time feedback data.

[0077] For example, a distributed computing framework is used to optimize the intelligent decision-making model. The updated industrial big data is partitioned according to data characteristics and model training requirements, and distributed across multiple computing nodes. A random forest algorithm is used to optimize the model. The random forest algorithm improves the model's accuracy and generalization ability by constructing multiple decision trees and voting or averaging the prediction results of these trees. Simultaneously, the model's parameters are tuned, such as trying different combinations of parameters like the number of decision trees and maximum depth using a grid search algorithm. The model's performance is evaluated on a validation set, and the optimal parameter combination is selected. During the optimization process, parallel computing capabilities are utilized to accelerate model training and optimization, reducing the time spent processing massive amounts of data.

[0078] For example, when faced with a road marking task again, the optimized model can process the input road information more quickly and accurately. For instance, this application can employ a caching mechanism during the model prediction phase to cache the marking schemes corresponding to frequently queried road types and regions. When a new task request is received, it first checks if a matching scheme exists in the cache; if so, it directly returns the cached result, greatly improving real-time decision-making speed. Simultaneously, based on real-time acquired road construction and maintenance data, the model can promptly adjust the marking scheme to adapt to new scenarios and requirements, further improving the adaptability and efficiency of the road marking control method. This solves the problems of data timeliness and model computational efficiency, enhancing the system's ability to cope with the constantly changing road construction environment.

[0079] Based on the above technical solution, this application can achieve real-time data acquisition by establishing a road marking association database, triggering incremental data updates and merging them to form a new dataset, and using a distributed framework to optimize the intelligent decision-making model. This solution solves the problems of "data lag and poor adaptability" in traditional models, ensuring that the model always makes decisions based on the latest road planning, design standards, and construction feedback data. At the same time, distributed computing further shortens the model training time and improves the model optimization efficiency.

[0080] As one possible embodiment of this application, the line marking device is equipped with a positioning fusion module and a terrain scanning module.

[0081] In some embodiments, the positioning fusion module includes a satellite positioning submodule and an inertial navigation submodule.

[0082] The satellite positioning submodule is used to acquire the line marking position information under standard working conditions, while the inertial navigation submodule is used to calculate the line marking position information of the line marking device by measuring the acceleration and angular velocity of the line marking device when the signal strength acquired by the satellite positioning submodule is lower than the preset signal threshold.

[0083] For example, the satellite positioning submodule can be a GPS receiver, the inertial navigation submodule can be an inertial measurement unit (IMU), and the positioning fusion module and the terrain scanning module can be connected to the control unit of the marking device through a controller area network (CAN) bus to transmit data in real time.

[0084] During the operation of the line marking equipment, sensor data (such as GPS signal strength, ambient light intensity, and surrounding obstacle detection) and map information are used to determine in real time whether the line marking equipment has entered a special scene, such as a tunnel or a densely populated area of ​​tall buildings. Once a special scene is detected, the initialization program of the backup positioning system (i.e., the inertial navigation submodule) is immediately started to prepare for positioning after the satellite positioning signal is lost.

[0085] For example, the initialization process of the inertial navigation submodule includes calibrating the accelerometer and gyroscope. By reading the calibration parameter table built into the marking device, parameters such as the zero bias and scale factor of the accelerometer and gyroscope are corrected to ensure the accuracy of the measurement data. Simultaneously, the initial position, velocity, and attitude information of the current marking device are acquired as initial values ​​for subsequent calculations by the inertial navigation submodule. These initial values ​​can be obtained from the last valid satellite positioning data and the attitude sensors of the marking device (such as an electronic compass and tilt sensor).

[0086] When satellite positioning signals are weakened or lost due to obstruction, the inertial navigation submodule begins to operate independently. Accelerometers measure the acceleration of the device along three axes (X, Y, Z), and gyroscopes measure the angular velocity of the device along three axes. Through integration, acceleration is integrated over time to obtain velocity, and velocity is integrated over time to obtain displacement, thus calculating the device's position change in three-dimensional space. Simultaneously, using the angular velocity information measured by the gyroscope, attitude calculation algorithms (such as the quaternion method) are used to calculate the device's attitude changes, obtaining attitude information such as the heading angle, pitch angle, and roll angle.

[0087] In some embodiments, the terrain scanning module includes a lidar submodule, which is used to scan the terrain of the area to be marked and acquire three-dimensional terrain data.

[0088] The lidar submodule generates three-dimensional point cloud data by emitting laser beams and receiving reflected signals to measure the distance between the device and the ground and obstacles.

[0089] In some embodiments, the positioning fusion module is further configured to fuse the line drawing position information output by the inertial navigation submodule or the line drawing position information output by the satellite positioning submodule with the three-dimensional terrain data acquired by the lidar submodule, and plan the line drawing path based on the fused data.

[0090] This application utilizes a data fusion algorithm to fuse the position information provided by the inertial navigation submodule with the last valid satellite positioning data. For example, an extended Kalman filter algorithm is used to estimate and correct the errors between the inertial navigation submodule and the satellite positioning data, ensuring that the positioning information maintains high accuracy and continuity even during periods of satellite positioning signal interruption.

[0091] Based on the above technical solution, this application can achieve continuous positioning across all scenarios through a positioning fusion module, and combine it with a LiDAR submodule to acquire three-dimensional terrain data, which is then fused to plan the marking path. This solution solves the positioning deviation problem caused by weak satellite positioning signals in special scenarios; at the same time, combining terrain scanning with LiDAR for data fusion makes the markings more consistent with the road surface terrain, which not only improves the quality of road markings, but also avoids vehicle bumps caused by uneven markings, ensuring traffic safety.

[0092] As one possible embodiment of this application, a multi-sensor redundant monitoring module is configured on the marking device.

[0093] In some embodiments, the multi-sensor redundancy monitoring module includes at least two sensor sub-modules of the same type, and the sensor sub-modules are respectively disposed at key components of the marking device.

[0094] Key components include motors, nozzles, and transmission devices. Sensor sub-modules include temperature sensor sub-modules, vibration sensor sub-modules, speed sensor sub-modules, and pressure sensor sub-modules.

[0095] In some embodiments, at least two sensor submodules of the same type are used to simultaneously collect the operating status parameters of corresponding key components.

[0096] In some embodiments, the multi-sensor redundancy monitoring module is further configured with an intelligent filtering submodule. The intelligent filtering submodule is used to process the operating status parameters collected by the sensor submodule using a moving average filtering algorithm and / or a Kalman filtering algorithm to remove random noise signals from the operating status parameters.

[0097] It should be noted that installing multiple sensors of the same or complementary types can form a multi-sensor redundancy design. For example, by simultaneously installing two temperature sensors and two vibration sensors on a motor, when one sensor fails or displays abnormal data, the other sensors can continue to provide accurate monitoring data. Furthermore, this application incorporates intelligent filtering and anti-interference algorithms to perform real-time preprocessing on the collected data. This improves the accuracy of data acquisition by removing noise and correcting deviations, providing reliable data support for subsequent fault prediction.

[0098] As one possible embodiment of this application, combined with Figure 2 ,like Figure 4 As shown, the method also includes the following steps.

[0099] Step 401: Obtain the operating status parameters collected by at least two sensor submodules of the same type.

[0100] For example, operating status parameters may include parameters such as motor temperature, speed, and vibration.

[0101] Step 402: Based on the operating status parameters and the historical fault records of the marking equipment, construct a fault prediction model.

[0102] For example, historical fault records include the motor temperature at the time of the fault (e.g., motor bearing damage at 95°C) and vibration frequency (e.g., transmission gear wear at 300Hz). The fault prediction model can use a long short-term memory (LSTM) network algorithm, inputting the operating status parameters of the past hour (e.g., temperature, vibration, speed), and outputting the fault probability (e.g., 85%), fault type (e.g., motor bearing wear), and fault time (e.g., the next 12 hours) for the next 24 hours.

[0103] Step 403: Predict the fault prediction results of the marking equipment based on the fault prediction model.

[0104] The fault prediction results include the probability of a fault occurring in the future, the type of fault, and the time of the fault.

[0105] This fault prediction model learns from historical operating data and fault records of the equipment to identify patterns of correlation between equipment operating status and potential faults. For example, by analyzing the changing trends of parameters such as motor temperature, speed, and vibration, it can predict the types and timing of potential motor faults.

[0106] Based on the above technical solution, this application can construct a fault prediction model by collecting the operating status parameters of the sensor sub-modules configured on the marking equipment, thereby predicting faults through the fault prediction model, reducing the risk of faults in the marking equipment, and ensuring stable construction of the marking operation.

[0107] As one possible embodiment of this application, combined with Figure 4 ,like Figure 5 As shown, the method also includes the following steps.

[0108] Step 501: Obtain the fault prediction results of each marking device output by the fault prediction model, as well as the construction operation data of each marking device.

[0109] The construction operation data includes the service life of the marking equipment and the current construction task priority data.

[0110] Step 502: Based on the analytic hierarchy process (AHP), the fault prediction results of each marking device and the construction operation data of each marking device are weighted and comprehensively scored to generate maintenance priority data for each marking device.

[0111] For example, the weights of the analytic hierarchy process can be set as follows: failure probability (weight 0.4), failure severity (weight 0.3), construction task priority (weight 0.2), and equipment service life (weight 0.1). The comprehensive score can be determined by weighted calculation, for example, comprehensive score = failure probability × 0.4 + failure severity score × 0.3 + task priority score × 0.2 + (1 / service life) × 0.1. The higher the comprehensive score, the higher the corresponding maintenance priority.

[0112] Based on the above technical solution, this application can perform maintenance assessments on each lane marking device using fault prediction results and construction operation data, determine the maintenance priority of each device, rationally allocate maintenance resources, achieve collaborative maintenance and scheduling of multiple devices, improve overall equipment utilization, and ensure the continuity and efficiency of road marking construction. As one possible embodiment of this application, the marking device is equipped with an image acquisition module, which is used to acquire image data of the marked area in real time, combined with... Figure 2 ,like Figure 6 As shown, the method also includes the following steps.

[0113] Step 601: Obtain image data of the marked area collected by the image acquisition module, and perform image recognition on the image data of the marked area to generate marked data.

[0114] The line data includes the line width, straightness, color uniformity, and edge sharpness.

[0115] For example, the image acquisition module can use an industrial camera (1920×1080 resolution, 30fps), installed at the rear of the marking equipment (1.5m above the ground, facing the marked area), equipped with a supplementary light (adapted to low-light environments such as nighttime and tunnels) to ensure clear image capture of marking details. During nighttime construction, the supplementary light of the image acquisition module automatically turns on, and the camera acquires one frame of the marked area every second, ensuring that the edges, colors, and contrast with the road surface of the markings can be clearly distinguished in the image, without blurring or overexposure.

[0116] Image recognition can employ object detection algorithms. First, the scribbled areas in the sample image (such as road lines of different colors) are labeled. The model is then trained to recognize the scribbled contours. Then, contour analysis is used to calculate the line width (such as measuring the distance between the left and right edges of the contour) and straightness (such as the deviation of the contour from the standard straight line). Color histogram analysis is used to analyze color uniformity (such as the standard deviation of RGB values ​​≤ 10) and edge sharpness is used to calculate edge clarity (such as gradient value ≥ 50).

[0117] Step 602: Perform a quality assessment based on the line drawing data and generate the line drawing quality assessment results.

[0118] The quality assessment result of the line marking can be obtained by weighted calculation based on the deviation values ​​of each standard item in the quality assessment standard.

[0119] Based on the above technical solution, this application can acquire line marking images in real time through an image acquisition module, and identify line marking data and evaluate quality by combining image recognition algorithms, thereby realizing real-time monitoring of line marking quality (changing from traditional post-acceptance to in-process adjustment), saving paint costs and construction time, and further improving the overall line marking quality.

[0120] The above primarily describes the solutions of the embodiments of this application from the perspective of device implementation. It is understood that each device, such as a road marking control device, includes at least one of the hardware structure and software module corresponding to each function in order to achieve the above-mentioned functions. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0121] This application embodiment can divide the road marking control device into functional units according to the above method example. For example, each function can be divided into separate functional units, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0122] When using integrated units, Figure 7A possible structural schematic diagram of the road marking control device (referred to as road marking control device 70) involved in the above embodiments is shown. The road marking control device 70 includes a processing unit 701 and a communication unit 702, and may also include a storage unit 703. Figure 7 The structural diagram shown can be used to illustrate the structure of the road marking control device involved in the above embodiments.

[0123] when Figure 7 The schematic diagram shown illustrates the structure of the road marking control device involved in the above embodiments. The processing unit 701 is used to control and manage the operation of the road marking control device, the communication unit 702 is used for the road marking control device to communicate with other devices, and the storage unit 703 is used to store the program code and data of the road marking control device.

[0124] For example, the communication unit 702 is used to acquire standard data for road marking of various types and historical data for road marking operations. The standard data for road marking includes the marking requirements for various types of roads in different areas, and the historical data for road marking operations includes the road type, area, construction parameters and marking effect data of the roads constructed in the past.

[0125] The processing unit 701 is used to construct an intelligent decision-making model based on the standard data of road marking and the historical operation data of road marking, and to train the intelligent decision-making model. The intelligent decision-making model is used to establish the mapping relationship between different road types, different areas and the corresponding optimal marking scheme. The optimal marking scheme includes the marking color, width, spacing and paint type.

[0126] The communication unit 702 is used to receive the type information and area information of the road to be marked, input the type information and area information into the trained intelligent decision model to output the corresponding optimal marking scheme, and transmit the optimal marking scheme to the marking device to control the marking device to perform the marking operation.

[0127] In one possible implementation, the processing unit 701 is used to: establish a road marking association database, which is used to acquire road planning data, road design standard data, and real-time feedback data during the road marking construction process. The real-time feedback data includes the operating status parameters of the marking equipment, the actual amount of paint used, and the marking quality inspection data; when the deviation between the newly added record in the road marking association database or the real-time feedback data and the preset standard value is greater than or equal to a preset deviation threshold, an incremental data acquisition operation is triggered to extract incremental data from the road marking association database; the incremental data includes at least one of the newly added road planning data, updated road design standard data, and real-time feedback data with a deviation greater than or equal to the preset deviation threshold; the extracted incremental data, the marking standard data, and the historical road marking operation data are fused to form an updated dataset; a distributed computing framework is used to optimize and train the intelligent decision-making model, the updated dataset is input into the intelligent decision-making model, and the model parameters are adjusted to adapt the intelligent decision-making model to the updated road planning data, road design standard data, and real-time feedback data.

[0128] In one possible implementation, the line marking device is equipped with a positioning fusion module and a terrain scanning module: the positioning fusion module includes a satellite positioning submodule and an inertial navigation submodule. The satellite positioning submodule is used to acquire line marking position information under standard operating conditions, and the inertial navigation submodule is used to calculate the line marking position information of the line marking device by measuring the acceleration and angular velocity of the line marking device when the signal strength acquired by the satellite positioning submodule is lower than a preset signal threshold; the terrain scanning module includes a lidar submodule, which is used to scan the terrain of the area to be marked and acquire three-dimensional terrain data; the positioning fusion module is also used to fuse the line marking position information output by the inertial navigation submodule or the satellite positioning submodule with the three-dimensional terrain data acquired by the lidar submodule, and plan the line marking path based on the fused data.

[0129] In one possible implementation, the marking equipment is equipped with a multi-sensor redundant monitoring module: the multi-sensor redundant monitoring module includes at least two sensor sub-modules of the same type, the sensor sub-modules are correspondingly set at the key components of the marking equipment, the key components include motors, nozzles and transmission devices, and the types of sensor sub-modules include temperature sensor sub-modules, vibration sensor sub-modules, speed sensor sub-modules and pressure sensor sub-modules; at least two sensor sub-modules of the same type are used to simultaneously collect the operating status parameters of the corresponding key components.

[0130] In one possible implementation, the communication unit 702 is used to: acquire operating status parameters collected by at least two sensor submodules of the same type; the processing unit 701 is used to: construct a fault prediction model based on the operating status parameters and the historical fault records of the marking equipment; predict the fault prediction result of the marking equipment based on the fault prediction model; the fault prediction result includes the probability of a fault occurring in the future time period, the fault type, and the fault time.

[0131] In one possible implementation, the communication unit 702 is used to: acquire the fault prediction results of each marking device output by the fault prediction model, and the construction operation data of each marking device; the construction operation data includes the service life of the marking device and the current construction task priority data; the processing unit 701 is used to: perform weight allocation and comprehensive scoring on the fault prediction results of each marking device and the construction operation data of each marking device based on the analytic hierarchy process, and generate maintenance priority data for each marking device.

[0132] In one possible implementation, the multi-sensor redundant monitoring module is also configured with an intelligent filtering submodule; the intelligent filtering submodule is used to process the operating status parameters collected by the sensor submodule using a moving average filtering algorithm and / or a Kalman filtering algorithm to remove random noise signals from the operating status parameters.

[0133] In one possible implementation, an image acquisition module is configured on the line-marking device; the image acquisition module is used to acquire image data of the marked area in real time; the communication unit 702 is used to: acquire the image data of the marked area acquired by the image acquisition module; the processing unit 701 is used to: perform image recognition on the image data of the marked area to generate line-marking data; the line-marking data includes the line width, straightness, color uniformity and edge clarity of the line; and perform quality assessment based on the line-marking data to generate a line-marking quality assessment result.

[0134] The processing unit 701 can be a processor or a controller, and the communication unit 702 can be a communication interface, transceiver, transceiver circuit, transceiver device, etc. The term "communication interface" is a general term and may include one or more interfaces. The storage unit 703 can be a memory. When the road marking control device 70 is a chip, the processing unit 701 can be a processor or a controller, and the communication unit 702 can be an input interface and / or an output interface, pins, or circuits, etc. The storage unit 703 can be a storage unit within the chip (e.g., a register, cache, etc.) or a storage unit located outside the chip (e.g., read-only memory (ROM), random access memory (RAM, etc.).

[0135] The communication unit can also be called a transceiver unit. The antenna and control circuit with transceiver functions in the road marking control device 70 can be considered as the communication unit 702 of the road marking control device 70, and the processor with processing functions can be considered as the processing unit 701 of the road marking control device 70. Optionally, the device in the communication unit 702 that implements the receiving function can be considered as a communication unit, which is used to execute the receiving steps in the embodiments of this application. The communication unit can be a receiver, a receiver circuit, etc. The device in the communication unit 702 that implements the transmitting function can be considered as a transmitting unit, which is used to execute the transmitting steps in the embodiments of this application. The transmitting unit can be a transmitter, a transmitter, a transmitting circuit, etc.

[0136] Figure 7 If the integrated units in the process are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. Storage media for storing computer software products include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0137] Figure 7 The units in the process can also be called modules; for example, a processing unit can be called a processing module.

[0138] This application also provides a hardware structure diagram of a road marking control device (referred to as road marking control device 80), see [link to diagram]. Figure 8 The road marking control device 80 includes a processor 801, and optionally, a memory 802 connected to the processor 801.

[0139] In the first possible implementation, see Figure 8 The road marking control device 80 also includes a transceiver 803. The processor 801, memory 802, and transceiver 803 are connected via a bus. The transceiver 803 is used to communicate with other devices or communication networks. Optionally, the transceiver 803 may include a transmitter and a receiver. The device in the transceiver 803 that implements the receiving function can be considered as a receiver, which is used to perform the receiving steps in the embodiments of this application. The device in the transceiver 803 that implements the transmitting function can be considered as a transmitter, which is used to perform the transmitting steps in the embodiments of this application.

[0140] Based on the first possible implementation method Figure 8 The structural diagram shown can be used to illustrate the structure of the road marking control device involved in the above embodiments.

[0141] in, Figure 8 The diagram can also illustrate the system chip in the road marking control device. In this case, the actions performed by the aforementioned road marking control device can be implemented by this system chip; the specific actions performed can be found above and will not be repeated here.

[0142] In implementation, each step of the method provided in this embodiment can be completed by integrated logic circuits in the processor or by instructions in software form. The steps of the method disclosed in the embodiments of this application can be directly manifested as being executed by a hardware processor, or being executed by a combination of hardware and software modules in the processor.

[0143] The processor in this application may include, but is not limited to, at least one of the following: a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a microcontroller unit (MCU), or an artificial intelligence processor, etc., which are various computing devices that run software. Each computing device may include one or more cores for executing software instructions to perform calculations or processing. The processor may be a separate semiconductor chip or integrated with other circuits into a single semiconductor chip. For example, it may be integrated with other circuits (such as encoding / decoding circuits, hardware acceleration circuits, or various bus and interface circuits) to form a SoC (System-on-a-Chip), or it may be integrated as a built-in processor within an ASIC. The ASIC with the integrated processor may be packaged separately or together with other circuits. In addition to the cores for executing software instructions to perform calculations or processing, the processor may further include necessary hardware accelerators, such as field-programmable gate arrays (FPGAs), PLDs (programmable logic devices), or logic circuits that implement dedicated logic operations.

[0144] The memory in the embodiments of this application may include at least one of the following types: read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions; random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions; or electrically erasable programmable-only memory (EEPROM). In some scenarios, the memory may also be a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer, but is not limited thereto.

[0145] This application also provides a computer-readable storage medium including instructions that, when run on a computer, cause the computer to perform any of the methods described above.

[0146] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform any of the methods described above.

[0147] This application also provides a chip including a processor and an interface circuit. The interface circuit is coupled to the processor. The processor is used to run computer programs or instructions to implement the above-described method. The interface circuit is used to communicate with other modules outside the chip.

[0148] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks (SSDs)).

[0149] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0150] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. A road marking control method, characterized in that, include: Acquire standard data for road marking and historical road marking operation data for various types of roads; the standard data includes the marking requirements for each type of road in different areas, and the historical road marking operation data includes the road type, area, construction parameters, and marking effect data of the roads constructed in the past. Based on the aforementioned road marking standard data and historical road marking operation data, a machine learning algorithm is used to construct an intelligent decision-making model, and the intelligent decision-making model is trained. The intelligent decision-making model is used to establish a mapping relationship between different road types, different areas and corresponding optimal road marking schemes. The optimal road marking schemes include marking color, width, spacing and paint type. The system receives the type and area information of the road to be marked, inputs the type and area information into the trained intelligent decision model to output the corresponding optimal marking scheme, and transmits the optimal marking scheme to the marking device to control the marking device to perform the marking operation.

2. The road marking control method according to claim 1, characterized in that, The method further includes: A road marking association database is established. The road marking association database is used to obtain road planning data, road design standard data and real-time feedback data during the road marking construction process. The real-time feedback data includes the operating status parameters of the marking equipment, the actual amount of paint used and the marking quality inspection data. When a new record is detected in the road marking association database or when the deviation between the real-time feedback data and the preset standard value is greater than or equal to a preset deviation threshold, an incremental data acquisition operation is triggered to extract incremental data from the road marking association database. The incremental data includes at least one of the following: newly added road planning data, updated road design standard data, and real-time feedback data with a deviation greater than or equal to the preset deviation threshold. The extracted incremental data, marking standard data, and historical road marking operation data are merged to form an updated dataset; The intelligent decision-making model is optimized and trained using a distributed computing framework. The updated dataset is input into the intelligent decision-making model, and the model parameters are adjusted to adapt the intelligent decision-making model to the updated road planning data, road design standard data, and real-time feedback data.

3. The road marking control method according to claim 1, characterized in that, The marking device is equipped with a positioning fusion module and a terrain scanning module: The positioning fusion module includes a satellite positioning submodule and an inertial navigation submodule. The satellite positioning submodule is used to acquire line marking position information under standard working conditions. The inertial navigation submodule is used to calculate the line marking position information of the line marking device by measuring the acceleration and angular velocity of the line marking device when the signal strength acquired by the satellite positioning submodule is lower than a preset signal threshold. The terrain scanning module includes a lidar submodule, which is used to scan the terrain of the area to be marked and obtain three-dimensional terrain data. The positioning fusion module is also used to fuse the line drawing position information output by the inertial navigation submodule or the line drawing position information output by the satellite positioning submodule with the three-dimensional terrain data acquired by the lidar submodule, and plan the line drawing path based on the fused data.

4. The road marking control method according to claim 1, characterized in that, The marking device is equipped with a multi-sensor redundant monitoring module: The multi-sensor redundancy monitoring module includes at least two sensor sub-modules of the same type. The sensor sub-modules are correspondingly set at the key components of the marking device. The key components include a motor, a nozzle, and a transmission device. The types of the sensor sub-modules include temperature sensor sub-modules, vibration sensor sub-modules, speed sensor sub-modules, and pressure sensor sub-modules. The at least two identical sensor submodules are used to simultaneously collect the operating status parameters of the corresponding key components.

5. The road marking control method according to claim 4, characterized in that, The method further includes: Obtain the operating status parameters collected by the at least two sensor submodules of the same type; Based on the operating status parameters and the historical fault records of the marking equipment, a fault prediction model is constructed. The fault prediction model is used to predict the faults of the marking equipment; the fault prediction results include the probability of a fault occurring in the future time period, the fault type, and the fault time.

6. The road marking control method according to claim 5, characterized in that, The method further includes: Obtain the fault prediction results of each marking device output by the fault prediction model, as well as the construction operation data of each marking device; the construction operation data includes the service life of the marking device and the current construction task priority data. Based on the analytic hierarchy process (AHP), the fault prediction results of each marking device and the construction operation data of each marking device are weighted and comprehensively scored to generate maintenance priority data for each marking device.

7. The road marking control method according to claim 4, characterized in that, The multi-sensor redundancy monitoring module is also equipped with an intelligent filtering submodule; the intelligent filtering submodule is used to process the operating status parameters collected by the sensor submodule using a moving average filtering algorithm and / or a Kalman filtering algorithm to remove random noise signals from the operating status parameters.

8. The road marking control method according to any one of claims 1-7, characterized in that, The marking device is equipped with an image acquisition module; The image acquisition module is used to acquire image data of the marked area in real time; the method further includes: The image acquisition module acquires image data of the marked area, and performs image recognition on the image data of the marked area to generate line data; the line data includes the line width, straightness, color uniformity, and edge sharpness of the line. A quality assessment is performed based on the line drawing data to generate a line drawing quality assessment result.

9. A road marking control device, characterized in that, The device includes: a communication unit and a processing unit; The communication unit is used to acquire standard data for road marking of various types and historical data for road marking operations. The standard data for road marking includes the marking requirements for various types of roads in different areas, and the historical data for road marking operations includes the road type, area, construction parameters, and marking effect data of the roads that were marked in the past. The processing unit is used to construct an intelligent decision-making model based on the standard road marking data and historical road marking operation data, using machine learning algorithms, and to train the intelligent decision-making model. The intelligent decision-making model is used to establish a mapping relationship between different road types, different areas and corresponding optimal road marking schemes. The optimal road marking scheme includes marking color, width, spacing and paint type. The communication unit is used to receive type information and area information of the road to be marked, input the type information and area information into the trained intelligent decision model to output the corresponding optimal marking scheme, and transmit the optimal marking scheme to the marking device to control the marking device to perform the marking operation.

10. A road marking control device, characterized in that, include: A processor and a communication interface; the communication interface is coupled to the processor, the processor being used to run computer programs or instructions to implement the road marking control method as described in any one of claims 1-8.

Images