A highway data management method based on a data middle platform

Abstract

This invention discloses a highway data management method based on a data platform, belonging to the field of monitoring data processing technology. Specifically, it includes: forming a highway infrastructure inventory catalog through multi-dimensional classification and dynamically updating it using IoT technology; encoding and preprocessing infrastructure attribute data to construct a digital attribute dataset and storing it in the data platform; extracting features and analyzing patterns of vehicle routes using spatiotemporal analysis strategies, and combining real-time traffic data to perform short-term and long-term route predictions using predictive models; automatically generating optimal traffic planning schemes based on the prediction results, and virtually verifying and optimizing them through simulation technology, thereby improving the efficiency and intelligence level of highway traffic management.

Description

Technical Field

[0001] This invention belongs to the field of monitoring data processing technology, specifically a highway data management method based on a data platform. Background Technology

[0002] With the rapid development of highways, the amount of data generated on highways is growing rapidly, including toll data, monitoring data, vehicle data, etc. Traditional data management methods suffer from problems such as data dispersion, low processing efficiency, and difficulty in forming an effective data infrastructure. Therefore, an efficient data management method is needed to achieve comprehensive management and efficient utilization of highway data.

[0003] For example, Chinese patent CN114566058B discloses a method and system for managing highway operation and maintenance monitoring data, including: receiving monitoring data uploaded by monitoring equipment; automatically filtering the monitoring data to obtain normal monitoring data, abnormal monitoring data, congestion monitoring data, and blank monitoring data; deleting blank monitoring data; and storing the normal monitoring data, abnormal monitoring data, and congestion monitoring data into a normal database, an abnormal database, and a congestion database, respectively. The blank monitoring data in this technical solution has virtually no reference value and will not be used for evidence in the future. Directly deleting blank monitoring data reduces the space occupied by useless data. Furthermore, classifying and storing normal monitoring data, abnormal monitoring data, and congestion monitoring data makes it quick and convenient to retrieve monitoring data as evidence later, thus improving the management efficiency of highway operation and maintenance.

[0004] For example, Chinese patent CN112948639B discloses a unified storage management method and system for highway data platforms, including: constructing a descriptor code sequence based on highway data; determining a first cutoff condition, a second cutoff condition, a step size, and a compression count based on the importance of the descriptor code sequence; setting a first sliding window and a second sliding window to slide on the descriptor code sequence, with the two windows adjacent but not overlapping; and storing the obtained compressed and encrypted descriptor code sequence in the unified storage unit of the highway data platform when the determined conditions are met. This technical solution achieves unified storage of highway data, improving the transmission efficiency of highway data, the space utilization of the storage system, and the privacy protection performance of the data.

[0005] The existing technologies described above all suffer from the following problems: although monitoring data is categorized and stored, they do not involve in-depth analysis or prediction of the data. This means that potential traffic problems or bottlenecks cannot be proactively identified; they mainly focus on data processing and storage, without addressing applications in traffic planning and management; and they lack real-time and dynamic capabilities. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this invention proposes a highway data management method based on a data platform. This method involves creating a highway infrastructure inventory catalog through multi-dimensional classification and dynamically updating it using IoT technology. Infrastructure attribute data is encoded and preprocessed to construct a digital attribute dataset, which is then stored in the data platform. A spatiotemporal analysis strategy is used to extract features and analyze patterns in vehicle routes. Combined with real-time traffic data, a predictive model is employed to predict short-term and long-term routes. Based on the prediction results, an optimal traffic planning scheme is automatically generated and virtually verified and optimized using simulation technology, thereby improving the efficiency and intelligence level of highway traffic management.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] A highway data management method based on a data middle platform includes:

[0009] Step S1: Utilize IoT sensors to intelligently collect highway infrastructure data, form an initial infrastructure list, classify highway infrastructure in multiple dimensions according to different application needs and the form of facility value, form a highway infrastructure list catalog, and dynamically update the highway infrastructure list catalog through IoT.

[0010] Step S2: Based on the different types and characteristics of highway infrastructure, each attribute data of each type of highway infrastructure is encoded to form a digital representation attribute dataset of highway infrastructure. At the same time, the digital representation attribute data of highway infrastructure is preprocessed and the preprocessed digital representation attribute data of highway infrastructure is stored in the data warehouse of the data platform.

[0011] Step S3: Use a spatiotemporal analysis strategy to analyze vehicle travel routes on the preprocessed digital representation attribute data of highway infrastructure stored in the data warehouse, obtain the characteristics and patterns of travel routes, and combine real-time traffic data streams to use prediction models to make short-term and long-term predictions of travel routes.

[0012] Step S4: Based on the analysis of the characteristics and patterns of the driving routes, combined with short-term and long-term forecast results, automatically generate and recommend traffic planning schemes, and introduce simulation technology to virtually verify the recommended traffic planning schemes. Based on the verification results, optimize the optimal traffic planning scheme, and deploy and implement the optimized traffic planning scheme.

[0013] Specifically, the encoding steps in step S2 include:

[0014] S2.1: Obtain the list of highway infrastructure, and based on the list of highway infrastructure, use IoT sensors to obtain the infrastructure classification results and identify the attributes of each type of infrastructure;

[0015] S2.2: Based on the infrastructure classification and attribute identification results, calculate the relative proportion of each attribute among all attributes using the relative proportion method. And based on the calculated attribute ratio P i Weights W are assigned to the attributes under each category. i =P i / 100, based on the infrastructure classification and attribute weight allocation results, dynamic coding rules are formulated, where P i s represents the proportion of the i-th attribute. i L represents the importance of the i-th attribute. i B represents the measurability of the i-th attribute. i R represents the variability of the i-th attribute. i W represents the relevance of the i-th attribute. i This represents the weight value of the i-th attribute;

[0016] S2.3: According to the dynamic coding rules, the coding algorithm is used to encode each attribute data of each type of highway infrastructure: code = title + location + b1 + b2 + ... + check. If there is data that does not conform to the coding rules, the automatic correction algorithm is used to correct it or it is marked as abnormal data. Here, code represents the coding result, title represents the prefix, location represents the location identifier, b1 and b2 represent the attribute identifiers, and check represents the check code.

[0017] S2.4: Integrate the encoded attribute data into a dataset to form a digital representation attribute dataset for highway infrastructure, and store it in the data warehouse of the data platform.

[0018] Specifically, the automatic correction algorithm in S2.3 includes the following steps for correction:

[0019] S2.31: Obtain infrastructure classification results and dynamic coding rules, and filter out infrastructure classification results that do not conform to the dynamic coding rules through string matching, format validation, and data type checking operations;

[0020] S2.32: Design a correction strategy based on the data type and degree of non-compliance with the rules. The correction strategy includes filling in the default value for missing data, reforming the data for data with incorrect format, and truncating or rounding the data for data that is out of range.

[0021] S2.33: Apply correction strategies to correct data that does not conform to the rules, including string replacement, numerical calculation, and type conversion;

[0022] S2.34: After correction, check again whether the infrastructure classification results conform to the coding rules. If they still do not conform, mark them as abnormal data or perform manual intervention.

[0023] Specifically, step S3 includes the following steps:

[0024] S3.1: Extract digital representation attribute data of highway infrastructure from the data warehouse of the data platform and collect real-time traffic data streams. The extracted digital representation attribute data of highway infrastructure includes road network data and vehicle driving records. The real-time traffic data streams include vehicle location, speed, and direction.

[0025] S3.2: Use the Euclidean distance calculation method to map the location information in the vehicle driving record onto the road network data, and connect the points in the vehicle driving record into a continuous trajectory based on the timestamp and location information to obtain trajectory data, where each trajectory contains the vehicle's location information in the time series;

[0026] S3.3: Use trajectory clustering methods to analyze the trajectory data, identify the driving routes, and extract their features and patterns;

[0027] S3.4: Load the pre-built time series analysis and prediction model, and use real-time traffic data stream data to train and validate the pre-built time series analysis and prediction model based on the characteristics and patterns of the driving route;

[0028] S3.5: Use the trained time series analysis prediction model to make short-term and long-term predictions of the driving route, evaluate the time series analysis prediction model based on the prediction results, and draw a driving volume trend map and a driving route map based on the prediction results.

[0029] Specifically, the specific steps of S3.3 include:

[0030] S3.31: Acquire trajectory data and perform preprocessing;

[0031] S3.32: Set the distance threshold h and the time period Δt, and initialize a variable to record the starting point of the current segment;

[0032] S3.33: Traverse the continuous trajectory data in chronological order. For each trajectory point, calculate the Euclidean distance d between it and the end point of the current segment within the time interval Δt.

[0033] If d≤h, then add the trajectory point to the current segment;

[0034] If d > h, then the current segment ends and the trajectory point is used as the starting point of the new segment. At the same time, each trajectory segment is stored in a pre-created array to obtain the segmented trajectory data.

[0035] S3.34: Use clustering strategies to cluster the segmented trajectories, and analyze the clustered driving routes to extract their features and patterns.

[0036] Specifically, the specific steps of the clustering strategy in S3.34 include:

[0037] A1: Obtain the segmented trajectory data X = {x1, ..., x...} n Set parameters ε and minimum number of points q, and initialize an empty set C, where x j ,j∈[1,n] represents the j-th segment of trajectory data, and n represents the number of segments of trajectory data;

[0038] A2: For each object x j Check object x j Has it already been visited?

[0039] If object x j If it has not been visited, mark it as visited and create a new cluster.

[0040] A3: Find object x j All objects in the ε-neighborhood;

[0041] If N ε If x ≥ q, then x j Marked as a core object, where N ε Represents object x j The number of objects in the ε-neighborhood;

[0042] And for object x j For each object in the ε-neighborhood of x, if x j If it has not yet been assigned to any cluster, add it to the cluster. middle;

[0043] A4: Perform a traversal, for clusters For each object in the cluster, find the objects in its ε-neighborhood and add the objects that meet the criteria to the cluster. In, until no new objects can be added to the cluster. until;

[0044] A5: Cluster Add the clustering result set C, iterate and repeat until all objects in X have been visited, and then output the clustering result set C.

[0045] Specifically, step S4 includes the following steps:

[0046] S4.1: Obtain the characteristics and patterns of the driving route, and the short-term and long-term prediction results of the driving route;

[0047] S4.2: Based on the short-term and long-term forecasts of the driving route, identify potential traffic bottlenecks and congestion points, and formulate a traffic planning scheme, which includes intersection control measures and traffic diversion strategies.

[0048] S4.3: Use MATSim traffic simulation software to virtually verify the generated traffic planning scheme, and optimize and adjust the traffic planning scheme based on the simulation verification results;

[0049] S4.4: Recommend the optimal traffic planning scheme to the traffic management department.

[0050] Specifically, the features extracted in S3.34 include the starting point, ending point, and key areas along the route, and the extracted patterns include the time pattern and frequency of the journey.

[0051] An electronic device includes a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of a highway data management method based on a data platform.

[0052] A computer-readable storage medium having computer instructions stored thereon, which, when executed, perform the steps of a highway data management method based on a data middle platform.

[0053] Compared with the prior art, the beneficial effects of the present invention are:

[0054] 1. This invention proposes a highway data management method based on a data platform. It intelligently collects highway infrastructure data through IoT sensors, performs multi-dimensional classification and dynamic updates of the infrastructure, realizes digital management and real-time monitoring of highway infrastructure, and improves the efficiency and accuracy of infrastructure management.

[0055] 2. This invention proposes a highway data management method based on a data platform. It utilizes spatiotemporal analysis strategies and prediction models to make short-term and long-term predictions of driving routes. Combined with the analysis of the characteristics and patterns of driving routes, it automatically generates and recommends traffic planning schemes. The schemes are then virtually verified and optimized using simulation technology. This process not only improves the pertinence and scientific nature of traffic planning but also effectively alleviates traffic congestion and improves road traffic efficiency. At the same time, the introduction of simulation technology makes the verification and optimization of traffic planning schemes more convenient and efficient. Attached Figure Description

[0056] Figure 1 This is a schematic diagram of a highway data management method based on a data middle platform according to the present invention;

[0057] Figure 2 This is a flowchart illustrating the principle of a highway data management method based on a data middle platform according to the present invention.

[0058] Figure 3 This is a schematic diagram of vehicle travel routes for a highway data management method based on a data middle platform according to the present invention.

[0059] Figure 4 This is a flowchart illustrating the vehicle route prediction process of a highway data management method based on a data middle platform according to the present invention.

[0060] Figure 5 This is an architecture diagram of a highway data management system based on a data middle platform according to the present invention. Detailed Implementation

[0061] Example 1

[0062] Please see Figure 1 and Figure 2 The present invention provides an embodiment of a highway data management method based on a data platform, comprising the following steps:

[0063] Step S1: Utilize IoT sensors to intelligently collect highway infrastructure data, form an initial infrastructure list, classify highway infrastructure in multiple dimensions according to different application needs and the form of facility value, form a highway infrastructure list catalog, and dynamically update the highway infrastructure list catalog through IoT.

[0064] Furthermore, the specific steps of step S1 include:

[0065] (1) Deploy IoT sensors, such as temperature sensors, humidity sensors, pressure sensors, and RFID tag readers, along highways and at key facility locations to ensure that the sensors can accurately and in real time collect highway infrastructure data.

[0066] (2) Through Internet of Things (IoT) technology, the highway infrastructure data collected by sensors is transmitted to the data center. Data analysis algorithms and intelligent recognition technology are used to process and analyze the collected highway infrastructure data to form an initial facility list.

[0067] The highway infrastructure data includes, but is not limited to, road structure data, bridge and tunnel data, traffic facility data, and monitoring equipment data.

[0068] (3) Investigate the facilities and equipment along the expressway, clarify their application needs and the form of facility value, and conduct a preliminary assessment of the facilities and equipment to determine key indicators such as their importance, frequency of use, and maintenance costs.

[0069] (4) Based on the characteristics of facilities and equipment such as type, function, and location, construct a multi-dimensional classification system, set classification standards, and ensure the accuracy and consistency of classification;

[0070] The classification criteria include infrastructure type, such as road facilities, bridge facilities, and tunnel facilities; functional use, such as traffic services, safety services, and maintenance services; and geographical location, such as road sections and areas.

[0071] At the same time, the classification criteria should clearly define the specific division methods and basis for each classification dimension to ensure the accuracy and consistency of the classification. For example, in terms of infrastructure type, it can be classified according to the components of the expressway, such as roads, bridges, and tunnels; in terms of function and purpose, it can be classified according to the role of the infrastructure in the operation of the expressway, such as traffic, service, and safety.

[0072] (5) Based on the multidimensional classification system, compile a list of highway infrastructure according to the classification standards. The list should include detailed information such as the name, model, quantity, location, and value of the facilities and equipment, and should clearly show the infrastructure categories and specific contents under each classification dimension.

[0073] (6) Deploy IoT sensors, RFID tags and other equipment at key facilities and equipment along the highway to establish an IoT data transmission network and ensure that data can be transmitted to the data center in real time and accurately;

[0074] (7) Design a dynamic update mechanism for the infrastructure inventory catalog, including data update frequency and update method;

[0075] (8) Set trigger conditions, such as changes in the status of facilities and equipment, or updates to maintenance records, to automatically trigger the update process.

[0076] Step S2: Based on the different types and characteristics of highway infrastructure, each attribute data of each type of highway infrastructure is encoded to form a digital representation attribute dataset of highway infrastructure. At the same time, the digital representation attribute data of highway infrastructure is preprocessed and the preprocessed digital representation attribute data of highway infrastructure is stored in the data warehouse of the data platform.

[0077] Step S3: Use a spatiotemporal analysis strategy to analyze vehicle travel routes on the preprocessed digital representation attribute data of highway infrastructure stored in the data warehouse, obtain the characteristics and patterns of travel routes, and combine real-time traffic data streams to use prediction models to make short-term and long-term predictions of travel routes.

[0078] Step S4: Based on the analysis of the characteristics and patterns of the driving routes, combined with short-term and long-term forecast results, automatically generate and recommend traffic planning schemes, and introduce simulation technology to virtually verify the recommended traffic planning schemes. Based on the verification results, optimize the optimal traffic planning scheme, and deploy and implement the optimized traffic planning scheme.

[0079] In summary, it is important to understand that the entire process managed in a data platform-based highway data management method includes the acquisition, encoding, judgment, analysis, optimization, and implementation of highway data.

[0080] The specific steps of encoding in step S2 include:

[0081] S2.1: Obtain the list of highway infrastructure, and based on the list of highway infrastructure, use IoT sensors to obtain the infrastructure classification results and identify the attributes of each type of infrastructure, such as size, material, structure, service life, maintenance records, and economic value.

[0082] S2.2: Based on the infrastructure classification and attribute identification results, calculate the relative proportion of each attribute among all attributes using the relative proportion method. And based on the calculated attribute ratio P i Weights W are assigned to the attributes under each category. i =P i / 100, based on the infrastructure classification and attribute weight allocation results, dynamic coding rules are formulated, where P i s represents the proportion of the i-th attribute. i L represents the importance of the i-th attribute. i B represents the measurability of the i-th attribute. i R represents the variability of the i-th attribute. i W represents the relevance of the i-th attribute. i This represents the weight value of the i-th attribute;

[0083] S2.3: According to the dynamic coding rules, the coding algorithm is used to encode each attribute data of each type of highway infrastructure: code = title + location + b1 + b2 + ... + check. If there is data that does not conform to the coding rules, the automatic correction algorithm is used to correct it or it is marked as abnormal data. Here, code represents the coding result, title represents the prefix, location represents the location identifier, b1 and b2 represent the attribute identifiers, and check represents the check code.

[0084] S2.4: Integrate the encoded attribute data into a dataset to form a digital representation attribute dataset for highway infrastructure, and store it in the data warehouse of the data platform.

[0085] The specific steps of the automatic correction algorithm in S2.3 include:

[0086] S2.31: Obtain infrastructure classification results and dynamic coding rules, and filter out infrastructure classification results that do not conform to the dynamic coding rules through string matching, format validation, and data type checking operations;

[0087] S2.32: Design a correction strategy based on the data type and degree of non-compliance with the rules. The correction strategy includes filling in the default value for missing data, reforming the data for data with incorrect format, and truncating or rounding the data for data that is out of range.

[0088] S2.33: Apply correction strategies to correct data that does not conform to the rules, including string replacement, numerical calculation, and type conversion;

[0089] S2.34: After correction, check again whether the infrastructure classification results conform to the coding rules. If they still do not conform, mark them as abnormal data or perform manual intervention.

[0090] Example 2

[0091] Please see Figures 3-4 In this embodiment, step S3 specifically includes the following steps:

[0092] S3.1: Extract digital representation attribute data of highway infrastructure from the data warehouse of the data platform and collect real-time traffic data streams. The extracted digital representation attribute data of highway infrastructure includes road network data and vehicle driving records. The real-time traffic data streams include vehicle location, speed, and direction.

[0093] S3.2: Use the Euclidean distance calculation method to map the location information in the vehicle driving record onto the road network data, and connect the points in the vehicle driving record into a continuous trajectory based on the timestamp and location information to obtain trajectory data, where each trajectory contains the vehicle's location information in the time series;

[0094] Furthermore, the specific steps for mapping the location information in vehicle driving records to road network data using the Euclidean distance calculation method include:

[0095] (1) Obtain road network data and vehicle driving records;

[0096] (2) Using the Euclidean distance calculation method, the distance between each location point in the vehicle's driving trajectory and each point on the road network data is calculated. The Euclidean distance calculation method is existing technology in this field and is not an inventive solution of this application. It will not be described in detail here.

[0097] (3) Based on the distance calculation results, map each location point in the vehicle's driving trajectory to the nearest road network data point. The point with the smallest distance is selected as the mapping result by comparing the distance between each location point and each point in the road network data.

[0098] (4) Post-process the mapping results, such as smoothing and removing redundant points, to improve the accuracy and reliability of the mapping results.

[0099] S3.3: Use trajectory clustering methods to analyze the trajectory data, identify the driving routes, and extract their features and patterns;

[0100] S3.4: Load the pre-built time series analysis and prediction model, and train and validate the pre-built time series analysis and prediction model using real-time traffic data stream data according to the characteristics and patterns of the driving route. The time series analysis and prediction model is the prior art in this field and is not an inventive solution of this application, so it will not be described in detail here.

[0101] S3.5: Use the trained time series analysis prediction model to make short-term and long-term predictions of the driving route, evaluate the time series analysis prediction model based on the prediction results, and draw a driving volume trend map and a driving route map based on the prediction results.

[0102] In this invention, the short-term forecast is set to 1 week, and the long-term forecast is set to 2 years.

[0103] Furthermore, the specific steps of S3.5 include:

[0104] (1) Collect driving history data, including driving volume, time, starting point and ending point, and preprocess the data, such as cleaning, deduplication and normalization.

[0105] (2) Load the pre-trained time series analysis and prediction model;

[0106] (3) Use the trained model to make short-term and long-term predictions of the driving route and output the prediction results, including driving volume, driving time and driving route.

[0107] (4) Based on the comparison between the prediction results and the actual driving data, the mean square error is used to evaluate the prediction accuracy of the model. The mean square error is the prior art in this field and is not an inventive solution of this application. It will not be described in detail here.

[0108] (5) Use the visualization tool Matplotlib to draw a traffic volume trend graph to show the trend of traffic volume over time. The Matplotlib graph drawing is a prior art in this field and is not an inventive solution of this application. It will not be described in detail here.

[0109] (6) Draw a route map based on the prediction results, showing the starting point, ending point and main path of the journey.

[0110] The specific steps in S3.3 include:

[0111] S3.31: Acquire trajectory data and perform preprocessing;

[0112] S3.32: Set the distance threshold h and the time period Δt, and initialize a variable to record the starting point of the current segment;

[0113] S3.33: Traverse the continuous trajectory data in chronological order. For each trajectory point, calculate the Euclidean distance d between it and the end point of the current segment within the time interval Δt.

[0114] If d≤h, then add the trajectory point to the current segment;

[0115] If d > h, then the current segment ends and the trajectory point is used as the starting point of the new segment. At the same time, each trajectory segment is stored in a pre-created array to obtain the segmented trajectory data.

[0116] S3.34: Use clustering strategies to cluster the segmented trajectories, and analyze the clustered driving routes to extract their features and patterns.

[0117] The features extracted in S3.34 include the starting point, ending point, and key areas along the route, and the patterns extracted include the time pattern and frequency of the journey.

[0118] The specific steps of the clustering strategy in S3.34 include:

[0119] A1: Obtain the segmented trajectory data X = {x1, ..., x...} n Set parameters ε and minimum number of points q, and initialize an empty set C, where x j ,j∈[1,n] represents the j-th segment of trajectory data, and n represents the number of segments of trajectory data;

[0120] A2: For each object x j Check object x j Has it already been visited?

[0121] If object x j If it has not been visited, mark it as visited and create a new cluster.

[0122] A3: Find object x j All objects in the ε-neighborhood;

[0123] If N ε If x ≥ q, then x j Marked as a core object, where N ε Represents object x j The number of objects in the ε-neighborhood;

[0124] And for object x j For each object in the ε-neighborhood of x, if x j If it has not yet been assigned to any cluster, add it to the cluster. middle;

[0125] A4: Perform a traversal, for clusters For each object in the cluster, find the objects in its ε-neighborhood and add the objects that meet the criteria to the cluster. In, until no new objects can be added to the cluster. until;

[0126] A5: Cluster Add the clustering result set C, iterate and repeat until all objects in X have been visited, and then output the clustering result set C.

[0127] The specific steps of step S4 include:

[0128] S4.1: Obtain the characteristics and patterns of the driving route, and the short-term and long-term prediction results of the driving route;

[0129] S4.2: Based on the short-term and long-term forecasts of the driving route, identify potential traffic bottlenecks and congestion points, such as key intersections and highway entrances, and formulate traffic planning schemes. The traffic planning schemes include intersection control measures and diversion strategies. The intersection control measures include traffic light control and lane adjustment, and the diversion strategies include setting up temporary lanes and guiding vehicles to detour.

[0130] When identifying potential traffic bottlenecks and congestion points, the focus is mainly on outliers in the prediction results, such as sudden increases in traffic flow or decreases in vehicle speed. These may be potential traffic bottlenecks and congestion points. Then, by combining the characteristics and patterns of the driving route with real-time traffic data, potential traffic bottlenecks and congestion points can be determined. In particular, key areas such as critical intersections, highway entrances, and transportation hubs on the driving route are more prone to traffic congestion.

[0131] S4.3: Using MATSim traffic simulation software, the generated traffic planning scheme is virtually verified, and the traffic planning scheme is optimized and adjusted based on the simulation verification results, including adjusting the traffic light cycle and optimizing the lane layout. Here, MATSim traffic simulation is prior art in this field and is not an inventive solution of this application, so it will not be described in detail here.

[0132] S4.4: Recommend the optimal traffic planning scheme to the traffic management department.

[0133] Example 3

[0134] Please see Figure 5 A highway data management system based on a data middle platform includes:

[0135] Infrastructure inventory management module, data processing module, forecasting module, and solution generation module;

[0136] The infrastructure inventory management module is used to classify facilities and equipment along highways in multiple dimensions, and to compile and dynamically update the highway infrastructure inventory.

[0137] The data processing module is used to encode the different types of characteristics of highway infrastructure, form a digital attribute dataset, and perform preprocessing.

[0138] The prediction module is used to perform vehicle route analysis on highway infrastructure data using spatiotemporal analysis strategies, and to make short-term and long-term predictions.

[0139] The scheme generation module is used to automatically generate and recommend the optimal traffic planning scheme based on the characteristics and patterns of the driving route, and to perform virtual verification and optimization.

[0140] The infrastructure inventory management module includes: a classification unit, an inventory compilation unit, and a dynamic update unit;

[0141] The classification unit is used to classify highway-side facilities and equipment in multiple dimensions according to different application needs and the form of facility value manifestation;

[0142] The inventory compilation unit is used to compile a catalog of highway infrastructure.

[0143] The dynamic update unit is used to update the highway infrastructure inventory catalog in real time or periodically via the Internet of Things.

[0144] The data processing module includes: an encoding unit, a preprocessing unit, and a data storage unit;

[0145] Encoding units are used to encode each attribute data for each type of highway infrastructure;

[0146] The preprocessing unit is used to preprocess the digital representation attribute data of highway infrastructure, such as cleaning, formatting, and conversion.

[0147] The data storage unit is used to store the pre-processed data in the data warehouse of the data platform.

[0148] The prediction module includes: a route analysis unit, a prediction model unit, and a result output unit;

[0149] The route analysis unit is used to perform route analysis on data stored in the data warehouse to extract features and patterns.

[0150] The prediction model unit is used to combine real-time traffic data streams and utilize machine learning models to make short-term and long-term predictions of driving routes.

[0151] The results output unit is used to output the prediction results in a visual way for use by subsequent modules.

[0152] The solution generation module includes: a solution generation unit, a recommendation unit, a simulation verification unit, and a solution optimization unit;

[0153] The scheme generation unit is used to automatically generate the optimal traffic planning scheme based on the characteristics and patterns of the driving route;

[0154] The recommendation unit is used to recommend the generated optimal traffic planning scheme to decision-makers or users;

[0155] The simulation verification unit introduces simulation technology to virtually verify the recommended optimal traffic planning scheme;

[0156] The scheme optimization unit is used to adjust and optimize the optimal traffic planning scheme based on the verification results.

[0157] In summary, the infrastructure inventory management module, data processing module, prediction module, scheme generation module, and their constituent units together constitute a complete and efficient highway data management system, which can realize comprehensive management of highway infrastructure, data encoding and processing, spatiotemporal analysis and prediction, and generation and optimization of traffic planning schemes.

[0158] Example 4

[0159] An electronic device includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of a highway data management method based on a data platform. For details, please refer to the above method embodiments, which will not be repeated here.

[0160] A computer-readable storage medium storing computer instructions that, when executed, perform steps of a highway data management method based on a data middle platform, wherein the storage medium may be a volatile or non-volatile computer-readable storage medium.

[0161] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments under the guidance of the present invention without departing from the spirit and scope of the present invention. All of these variations are within the protection scope of the present invention.

Claims

1. A highway data management method based on a data middle platform, characterized in that, include: Step S1: Utilize IoT sensors to intelligently collect highway infrastructure data, form an initial infrastructure list, classify highway infrastructure in multiple dimensions according to different application needs and the form of facility value, form a highway infrastructure list catalog, and dynamically update the highway infrastructure list catalog through IoT. Step S2: Based on the different types and characteristics of highway infrastructure, each attribute data of each type of highway infrastructure is encoded to form a digital representation attribute dataset of highway infrastructure. At the same time, the digital representation attribute data of highway infrastructure is preprocessed and the preprocessed digital representation attribute data of highway infrastructure is stored in the data warehouse of the data platform. Step S3: Use a spatiotemporal analysis strategy to analyze vehicle travel routes on the preprocessed digital representation attribute data of highway infrastructure stored in the data warehouse, obtain the characteristics and patterns of travel routes, and combine real-time traffic data streams to use prediction models to make short-term and long-term predictions of travel routes. Step S4: Based on the analysis of the characteristics and patterns of the driving routes, combined with short-term and long-term forecast results, automatically generate and recommend traffic planning schemes, and introduce simulation technology to virtually verify the recommended traffic planning schemes. Based on the verification results, optimize the traffic planning schemes and deploy and implement the optimized traffic planning schemes. The specific steps of step S3 include: S3.1: Extract digital representation attribute data of highway infrastructure from the data warehouse of the data platform and collect real-time traffic data streams. The extracted digital representation attribute data of highway infrastructure includes road network data and vehicle driving records. The real-time traffic data streams include vehicle location, speed, and direction. S3.2: Use the Euclidean distance calculation method to map the location information in the vehicle driving record onto the road network data, and connect the points in the vehicle driving record into a continuous trajectory based on the timestamp and location information to obtain trajectory data, where each trajectory contains the vehicle's location information in the time series; S3.3: Use trajectory clustering methods to analyze the trajectory data, identify the driving routes, and extract their features and patterns; S3.4: Load the pre-built time series analysis and prediction model, and use real-time traffic data stream data to train and validate the pre-built time series analysis and prediction model based on the characteristics and patterns of the driving route; S3.5: Use the trained time series analysis prediction model to make short-term and long-term predictions of the driving route, evaluate the time series analysis prediction model based on the prediction results, and draw a driving volume trend map and a driving route map based on the prediction results.

2. The highway data management method based on a data middle platform as described in claim 1, characterized in that, The specific steps of encoding in step S2 include: S2.1: Obtain the list of highway infrastructure, and based on the list of highway infrastructure, use IoT sensors to obtain the infrastructure classification results and identify the attributes of each type of infrastructure; S2.2: Based on the infrastructure classification and attribute identification results, calculate the relative proportion of each attribute among all attributes using the relative proportion method. And based on the calculated attribute ratio Weights are assigned to the attributes under each category. Based on the infrastructure classification and attribute weight allocation results, dynamic coding rules are formulated, among which... This represents the proportion of the i-th attribute. This indicates the importance of the i-th attribute. This indicates the measurability of the i-th attribute. Indicates the variability of the i-th attribute. This represents the relevance of the i-th attribute. This represents the weight value of the i-th attribute; S2.3: In accordance with the dynamic coding rules, use the coding algorithm to encode each attribute data of each type of highway infrastructure. If data that does not conform to the encoding rules is found, an automatic correction algorithm will be used to correct it, or it will be marked as abnormal data. Here, code represents the encoding result, title represents the prefix, and location represents the location identifier. and This represents the attribute identifier; check represents the checksum. S2.4: Integrate the encoded attribute data into a dataset to form a digital representation attribute dataset for highway infrastructure, and store it in the data warehouse of the data platform.

3. The highway data management method based on a data middle platform as described in claim 2, characterized in that, The specific steps of the automatic correction algorithm in S2.3 include: S2.31: Obtain infrastructure classification results and dynamic coding rules, and filter out infrastructure classification results that do not conform to the dynamic coding rules through string matching, format validation, and data type checking operations; S2.32: Design a correction strategy based on the data type and degree of non-compliance with the rules. The correction strategy includes filling in the default value for missing data, reforming the data for data with incorrect format, and truncating or rounding the data for data that is out of range. S2.33: Apply correction strategies to correct data that does not conform to the rules, including string replacement, numerical calculation, and type conversion; S2.34: After correction, check again whether the infrastructure classification results conform to the coding rules. If they still do not conform, mark them as abnormal data or perform manual intervention.

4. The highway data management method based on a data middle platform as described in claim 3, characterized in that, The specific steps of S3.3 include: S3.31: Acquire trajectory data and perform preprocessing; S3.32: Set the distance threshold h and time period And initialize a variable to record the starting point of the current segment; S3.33: Traverse the continuous trajectory data in chronological order. For each trajectory point, within the time period... Within the segment, calculate the Euclidean distance d between it and the end point of the current segment; like If so, then the trajectory point is added to the current segment; like If the current segment ends, the trajectory point is used as the starting point of the new segment. At the same time, each trajectory segment is stored in a pre-created array to obtain the segmented trajectory data. S3.34: Use clustering strategies to cluster the segmented trajectories, and analyze the clustered driving routes to extract their features and patterns.

5. The highway data management method based on a data middle platform as described in claim 4, characterized in that, The specific steps of the clustering strategy in S3.34 include: A1: Obtain the segmented trajectory data Set parameters Find the minimum number of points q, and initialize an empty set C, where, Let j represent the j-th segment of trajectory data, and n represent the number of segments in the trajectory data. A2: For each object , Inspection object Has it already been visited? If the object If it has not been visited, mark it as visited and create a new cluster. ; A3: Search for objects of -All objects in the neighborhood; like Then Marked as a core object, where, Representation Object of - The number of objects in the neighborhood; And for objects of - For each object in the neighborhood, if If it has not yet been assigned to any cluster, add it to the cluster. middle; A4: Perform a traversal, for clusters For each object in the list, find its - Objects in the neighborhood, and add objects that meet the criteria to the cluster. In, until no new objects can be added to the cluster. until; A5: Cluster Add the clustering result set C, iterate and repeat until all objects in X have been visited, and then output the clustering result set C.

6. The highway data management method based on a data middle platform as described in claim 5, characterized in that, The specific steps of step S4 include: S4.1: Obtain the characteristics and patterns of the driving route, and the short-term and long-term prediction results of the driving route; S4.2: Based on the short-term and long-term forecasts of the driving route, identify potential traffic bottlenecks and congestion points, and formulate a traffic planning scheme, which includes intersection control measures and traffic diversion strategies. S4.3: Use MATSim traffic simulation software to virtually verify the generated traffic planning scheme, and optimize and adjust the traffic planning scheme based on the simulation verification results; S4.4: Recommend the optimal traffic planning scheme to the traffic management department.

7. The highway data management method based on a data platform as described in claim 6, characterized in that, The features extracted in S3.34 include the starting point, ending point, and key areas along the route, and the extracted patterns include the time pattern and frequency of the journey.

8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the highway data management method based on a data middle platform as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, It stores computer instructions, which, when executed, perform the steps of the highway data management method based on a data middle platform as described in any one of claims 1-7.

Images