Heterogeneous energy station spatio-temporal data fusion method and system for expressway network

Abstract

The invention provides an expressway network-oriented heterogeneous energy station spatio-temporal data fusion method, and belongs to the field of traffic transportation. The problems that a collaborative completion mechanism of multi-source heterogeneous data is lacked and deep analysis of road features such as driving directions and lane distribution is lacked are solved. The method comprises the following steps: acquiring GIS road layer data of a target area, and extracting a coordinate point set of a highway section; inputting the coordinate point set into a map navigation interface, and obtaining continuous path navigation data to complement a highway network; integrating multi-channel energy station data; based on a driving direction identification algorithm, determining the orientation relation of each energy station in the highway network; and establishing a competition relation analysis model containing a space-time weight factor according to the orientation relation, wherein the model fuses station spacing, traffic flow distribution and energy demand trend parameters. The method is mainly used in the commercial analysis field.

Description

Technical Field

[0001] The present invention belongs to the field of transportation, and in particular relates to a spatiotemporal data fusion method for heterogeneous energy sites in a highway network. Background Art

[0002] With the development of intelligent transportation systems, the integrity of highway network data has become a crucial foundation for optimizing energy site layouts. Currently, the industry primarily relies on road network layer data provided by geographic information systems (GIS) to construct basic road models. However, this approach suffers from significant flaws in practical applications. First, existing GIS data depicts some highways with gaps and discontinuities, particularly at key nodes such as the junctions between ring roads and main roads and at interprovincial borders. This results in the generated digital road network failing to accurately reflect the actual physical topology. Second, while mainstream map service platforms offer highly accurate navigation path data, their interface designs are oriented towards path planning and lack access to complete road vector data, making it difficult for commercial organizations to directly extract continuous road network information.

[0003] At the energy site data acquisition level, existing technical solutions have a significant data island phenomenon. Oil companies and gas station operators collect site operation data through self-established Internet of Things systems, but such data only contains the spatiotemporal information of their own sites (such as refueling volume and passenger flow trends), and lack a global grasp of the distribution situation of competing sites. Although third-party data suppliers can provide some commercial site data, they have not yet established a spatial mapping relationship with the highway network, resulting in an inability to effectively analyze the competitive radiation range between sites. More prominently, existing data processing methods have technical bottlenecks in the integration of spatiotemporal dimensions: traditional GIS spatial analysis methods can only achieve static point matching, and fail to combine key factors such as road driving direction and dynamic changes in traffic flow, resulting in significant deviations from the generated competitive relationship model and the real business scenario.

[0004] The core contradictions that need to be addressed in the current technology are reflected in three aspects: (1) The lack of a collaborative complement mechanism for multi-source heterogeneous data makes it impossible to build a complete highway digital twin; (2) The spatial relationship modeling of energy sites is single-dimensional, lacking in-depth analysis of road characteristics such as driving direction and lane distribution; (3) Business analysis models fail to effectively integrate time series data with spatial topology, resulting in limited accuracy in competitive situation prediction. These problems seriously restrict energy companies' ability to make precise marketing decisions and optimize site layouts in highway scenarios. Summary of the Invention

[0005] In view of this, the present invention aims to propose a spatiotemporal data fusion method for heterogeneous energy sites in highway networks to solve the problems of the lack of a collaborative completion mechanism for multi-source heterogeneous data and the lack of in-depth analysis of road characteristics such as driving direction and lane distribution.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] A method for spatiotemporal data fusion of heterogeneous energy sites on a highway network, the method comprising:

[0008] Step S1: Obtain GIS road layer data of the target area and extract the coordinate point set of the highway section;

[0009] Step S2: input the coordinate point set into a map navigation interface to obtain continuous path navigation data to complete the highway network;

[0010] Step S3: Integrate multi-channel energy site data;

[0011] Step S4: Determine the positional relationship of each energy station in the highway network based on the driving direction recognition algorithm;

[0012] Step S5: establishing a competition relationship analysis model including a spatiotemporal weight factor based on the location relationship, wherein the model integrates station spacing, vehicle flow distribution, and energy demand trend parameters.

[0013] Furthermore, a preferred embodiment is proposed, wherein step S2 specifically includes:

[0014] Step S21: Divide the expressway sections according to administrative boundaries;

[0015] Step S22: Select N evenly distributed reference points on each road section as navigation start and end points;

[0016] Step S23: calling the draggable path planning interface to generate continuous road topology data.

[0017] Furthermore, a preferred method is proposed, in which the N evenly distributed reference points are selected to meet the following conditions: the distance between adjacent reference points does not exceed a preset threshold value L, and the value of L is negatively correlated with the road grade.

[0018] Furthermore, a preferred embodiment is proposed, wherein the driving direction recognition algorithm in step S4 includes:

[0019] Step S41: Calculate the main driving direction based on the road vector direction angle;

[0020] Step S42: Establish a site location determination rule set, including:

[0021] The right site priority matching rule; the same-direction traffic distribution rule; the opposite-direction site association rule.

[0022] Furthermore, a preferred method is proposed, wherein the S42 further includes: dynamically adjusting the orientation determination threshold according to real-time traffic flow data; and correcting the orientation relationship of mountainous road sections using three-dimensional space projection.

[0023] Furthermore, a preferred method is proposed, in which the traffic flow distribution in step S5 is obtained based on the actual traffic flow data of the key monitoring points and the established traffic flow attenuation model based on the normal distribution.

[0024] Based on the same inventive concept, the present invention further proposes a spatiotemporal data fusion system for heterogeneous energy sites on a highway network. The system is implemented based on any of the above methods, and includes:

[0025] Road network completion module, used to perform fusion processing of GIS data and navigation data;

[0026] Multi-source data integration module, used to connect enterprise databases and third-party data interfaces;

[0027] Spatial relationship analysis module, used for direction identification and establishment of topological relationships;

[0028] Business modeling module for time series analysis and competitive index calculation.

[0029] Furthermore, a preferred embodiment is proposed, wherein the road network completion module includes:

[0030] Path verification unit, used to detect the connectivity of road topology;

[0031] An exception handling unit is configured to automatically generate an alternative route request when a path break is detected.

[0032] Based on the same inventive concept, the present invention also proposes a computer device, including a memory and a processor, wherein a computer program is stored in the memory. When the processor runs the computer program stored in the memory, the processor executes a spatiotemporal data fusion method for heterogeneous energy sites for a highway network according to any of the above items.

[0033] Based on the same inventive concept, the present invention also proposes a computer-readable storage medium, which stores a computer program. When the computer program is run by a processor, it executes the steps of a spatiotemporal data fusion method for heterogeneous energy sites for highway networks as described in any one of the above.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] 1. This invention effectively solves the road discontinuity problem of traditional GIS layers by integrating GIS benchmarks with navigation path data. Experimental data shows that in applications involving interprovincial border sections, the accuracy of road continuity has increased from 72% to 98%.

[0036] 2. This invention successfully breaks down industry data barriers by building a multi-dimensional integration model of enterprise collaboration data, third-party business data, and spatial matching data. In a pilot application in East China, site data coverage increased from 45% for a single enterprise to 93% for the entire region, and data update timeliness was reduced to one-third of the original timeliness.

[0037] 3. This invention significantly improves the accuracy of station location determination by combining an innovative driving direction recognition algorithm with 3D spatial projection correction technology. Particularly at multi-ramp intersections, it can accurately distinguish the spatial topological relationships of competing stations in the same or opposite directions, significantly reducing errors compared to traditional GIS buffer analysis methods.

[0038] 4. This invention proposes a traffic attenuation model based on a normal distribution, integrated with real-time monitoring data, to keep the error rate of station traffic estimation within ±8%. Furthermore, by integrating spatiotemporal weight parameters to construct a comprehensive competition index model, it effectively predicts passenger flow diversion and provides a quantitative decision-making basis for station layout optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which constitute part of the present invention, are provided to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are provided to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0040] Figure 1 This is a flow chart of a spatiotemporal data fusion method for heterogeneous energy sites in a highway network according to the present invention;

[0041] Figure 2 This is a framework diagram of the spatiotemporal data fusion of energy sites described in the present invention. DETAILED DESCRIPTION

[0042] The following will clearly and completely explain the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. It should be noted that the embodiments of the present invention and the features therein can be combined with each other without conflict, and the embodiments described are only part of the embodiments of the present invention, not all of the embodiments.

[0043] Implementation method 1, see Figure 1 This embodiment describes a method for spatiotemporal data fusion of heterogeneous energy sites on a highway network, the method comprising:

[0044] Step S1: Obtain GIS road layer data of the target area and extract the coordinate point set of the highway section;

[0045] Step S2: input the coordinate point set into a map navigation interface to obtain continuous path navigation data to complete the highway network;

[0046] Step S3: Integrate multi-channel energy site data, including: spatiotemporal data of sites provided by cooperative enterprises, spatiotemporal data of competing sites purchased from third parties, and potential site location data matched by GIS spatial functions;

[0047] Step S4: Determine the positional relationship of each energy station in the highway network based on the driving direction recognition algorithm;

[0048] Step S5: establishing a competition relationship analysis model including a spatiotemporal weight factor based on the location relationship, wherein the model integrates station spacing, vehicle flow distribution, and energy demand trend parameters.

[0049] The competitive relationship analysis model includes:

[0050] A: The competitor stands on the same side / opposite side of the target station.

[0051] B: The competing station is upstream / downstream of the target station.

[0052] C: The difference between the total score of the competing stations and the engineering environment score of the target station.

[0053] D: The difference between the total score of the competing sites and the business environment score of the target site.

[0054] Score = A*weight a% + B*weight b% + C*weight c% + D*weight d%

[0055] The method proposed in this implementation effectively integrates data from different sources and types (such as GIS road layer data, route navigation data, and energy site data). By establishing a spatiotemporal data fusion mechanism, it addresses the data gaps caused by the lack of collaborative data completion mechanisms in traditional methods. This is particularly effective in the context of complex highway networks, effectively improving the comprehensiveness and integrity of data.

[0056] By introducing a driving direction recognition algorithm that takes into account road characteristics such as the actual driving direction and lane distribution of highway sections, the accuracy of data fusion can be improved while also enabling precise judgment of the relative positions of different stations within the road network and traffic flow characteristics. This measure helps better reflect the relationship between energy station distribution and traffic flow, thereby optimizing the allocation of energy resources.

[0057] Furthermore, in the method described in this embodiment, the location relationship analysis model incorporates spatiotemporal weighting factors, taking into account the impact of multiple parameters (such as station spacing, traffic flow distribution, and energy demand trends) on energy station layout. This enables dynamic adjustment of station distribution based on actual road conditions and energy demand, improving the efficiency and reliability of overall energy supply.

[0058] A competitive relationship analysis model provides an in-depth analysis of the relationships between different energy sites. This not only provides optimized matching solutions between sites, but also dynamically adjusts resource allocation based on traffic volume and demand. This capability is particularly useful in highway networks with high traffic volume fluctuations, enabling timely response to energy demand and avoiding resource waste and shortages.

[0059] Implementation 2: This implementation further defines the spatiotemporal data fusion method for heterogeneous energy sites in a highway network described in Implementation 1. Step S2 specifically includes:

[0060] Step S21: Divide the expressway sections according to administrative boundaries;

[0061] Step S22: Select N evenly distributed reference points on each road section as navigation start and end points;

[0062] Step S23: calling the draggable path planning interface to generate continuous road topology data.

[0063] In this implementation, by dividing highway sections according to administrative boundaries, more precise regional resource analysis and optimization can be performed. This helps align the highway network with the needs and management structures of local administrative regions, facilitating the integration and analysis of energy demand, traffic flow, and other relevant data across different regions. Particularly in multi-provincial and multi-municipal highway networks, dividing by administrative boundaries ensures a more targeted assessment of each region's needs.

[0064] N evenly distributed reference points are selected as the navigation start and end points on each road section to avoid path planning deviations caused by the selection of a single location, ensure the comprehensiveness and uniformity of road data, and help reduce the impact of unbalanced traffic flow.

[0065] Implementation method three. This implementation method is a further limitation of the spatiotemporal data fusion method for heterogeneous energy sites in highway networks described in implementation method one. The N evenly distributed reference points are selected to meet the following requirements: the distance between adjacent reference points does not exceed the preset threshold L, and the value of L is negatively correlated with the road grade.

[0066] Implementation 4: This implementation further limits the spatiotemporal data fusion method for heterogeneous energy sites on a highway network described in Implementation 1. The driving direction recognition algorithm in step S4 includes:

[0067] Step S41: Calculate the main driving direction based on the road vector direction angle;

[0068] Step S42: Establish a site location determination rule set, including:

[0069] The right site priority matching rule; the same-direction traffic distribution rule; the opposite-direction site association rule.

[0070] In this embodiment, step S41 calculates the main driving direction based on the road vector direction angle. This method can eliminate errors caused by complex road sections in the highway network and ensure the accuracy of the driving direction. In step S42, by setting the right-side station priority matching rule, the vehicle's stop selection can be optimized and the efficiency of energy station utilization can be improved. Especially on highways, right-side stations are usually more convenient, and vehicle drivers can directly enter the station for energy replenishment without changing lanes. The design of the same-direction traffic distribution rules and the opposite-direction station association rules helps to more reasonably distribute and manage the load of the stations, avoid excessive congestion or insufficient energy supply at a certain station, and thus improve the efficiency and service quality of energy stations in the highway network.

[0071] Implementation method five. This implementation method further limits the spatiotemporal data fusion method for heterogeneous energy sites in highway networks described in implementation method one. The S42 also includes: dynamically adjusting the orientation determination threshold according to real-time traffic flow data; and correcting the orientation relationship of mountainous sections using three-dimensional space projection.

[0072] Implementation method six: This implementation method further limits the spatiotemporal data fusion method for heterogeneous energy sites in a highway network described in implementation method one. The traffic flow distribution in step S5 is obtained based on the actual traffic flow data of key monitoring points and the established traffic flow attenuation model based on normal distribution.

[0073] The traffic flow attenuation model based on normal distribution includes:

[0074]

[0075] Where p is the sample proportion, is the confidence interval statistic, and n is the sample size.

[0076] Implementation 7: This implementation describes a spatiotemporal data fusion system for heterogeneous energy sites on a highway network. The system is implemented based on the method described in any one of Implementation 1 to Implementation 6, and includes:

[0077] Road network completion module, used to perform fusion processing of GIS data and navigation data;

[0078] Multi-source data integration module, used to connect enterprise databases and third-party data interfaces;

[0079] Spatial relationship analysis module, used for direction identification and establishment of topological relationships;

[0080] Business modeling module for time series analysis and competitive index calculation.

[0081] Implementation 8: This implementation further defines the spatiotemporal data fusion system for heterogeneous energy sites on a highway network described in Implementation 7. The road network completion module includes:

[0082] Path verification unit, used to detect the connectivity of road topology;

[0083] An exception handling unit is configured to automatically generate an alternative route request when a path break is detected.

[0084] Implementation method nine: A computer device described in this implementation method includes a memory and a processor, wherein a computer program is stored in the memory. When the processor runs the computer program stored in the memory, the processor executes a spatiotemporal data fusion method for heterogeneous energy sites for a highway network according to any one of implementation methods one to six.

[0085] Implementation method ten: A computer-readable storage medium described in this implementation method stores a computer program, and when the computer program is executed by a processor, the steps of a spatiotemporal data fusion method for heterogeneous energy sites for a highway network are executed as described in any one of implementation methods one to six.

[0086] Implementation method 11, see Figure 2 This embodiment provides a specific example of the spatiotemporal data fusion method for heterogeneous energy sites on a highway network described in the first embodiment, and is also used to explain the second to sixth embodiments. Specifically:

[0087] A. Processing highway section data:

[0088] A1: Integrate open source and third-party purchased GIS road data;

[0089] A2: Matching China's national administrative boundary GIS data to determine highway section data within each city;

[0090] A3: Select N relatively evenly distributed points from the highway section data of various cities;

[0091] A4: Use the N selected points as the starting and passing points, and use the "Draggable Driving Route Planning" interface of the AutoNavi open platform to obtain road path data.

[0092] B. Processing gas station data:

[0093] B1: Obtain the gas station data of the partner oil company;

[0094] B2: Match the gas station data within the administrative division.

[0095] C: Processing third-party gas station data:

[0096] C1: third-party gas station data;

[0097] C2: Matches gas station data within administrative divisions.

[0098] D: Match road sections and gas / refueling station data.

[0099] E. Establish a business analysis model for the competitive relationship between gas / gas stations along the highway:

[0100] Based on historical sales data of gas stations, reductions in fuel vehicle consumption, growth in LNG vehicles, and other data, a business analysis model for the comprehensive competitive relationship between various gas stations is established to effectively predict passenger flow diversion and provide a quantitative decision-making basis for site layout optimization.

[0101] Those skilled in the art will appreciate that embodiments of the present disclosure may be provided as methods, systems, or computer program products. Thus, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0102] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram and the combination of processes and / or blocks in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including the instruction device, which implements the function specified in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0103] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure and are not intended to limit its scope of protection. Although the present disclosure has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that after reading the present disclosure, those skilled in the art can still make various changes, modifications or equivalent substitutions to the specific implementation methods of the invention, but these changes, modifications or equivalent substitutions are all within the scope of protection of the disclosed claims.

Claims

1. A spatiotemporal data fusion method for heterogeneous energy sites in highway networks, characterized by: The method comprises: Step S1: Obtain GIS road layer data of the target area and extract the coordinate point set of the highway section; Step S2: input the coordinate point set into a map navigation interface to obtain continuous path navigation data to complete the highway network; Step S3: Integrate multi-channel energy site data; Step S4: Determine the positional relationship of each energy station in the highway network based on the driving direction recognition algorithm; Step S5: establishing a competition relationship analysis model including a spatiotemporal weight factor based on the location relationship, wherein the model integrates station spacing, vehicle flow distribution, and energy demand trend parameters.

2. The spatiotemporal data fusion method for heterogeneous energy sites in highway networks according to claim 1 is characterized in that: The step S2 specifically includes: Step S21: Divide the expressway sections according to administrative boundaries; Step S22: Select N evenly distributed reference points on each road section as navigation start and end points; Step S23: calling the draggable path planning interface to generate continuous road topology data.

3. The spatiotemporal data fusion method for heterogeneous energy sites in highway networks according to claim 1 is characterized in that: The N evenly distributed reference points are selected to satisfy the following conditions: the distance between adjacent reference points does not exceed a preset threshold value L, and the value of L is negatively correlated with the road grade.

4. The spatiotemporal data fusion method for heterogeneous energy sites in highway networks according to claim 1 is characterized in that: The driving direction recognition algorithm in step S4 includes: Step S41: Calculate the main driving direction based on the road vector direction angle; Step S42: Establish a site location determination rule set, including: The right site priority matching rule; the same-direction traffic distribution rule; the opposite-direction site association rule.

5. The spatiotemporal data fusion method for heterogeneous energy sites in highway networks according to claim 1 is characterized in that: The S42 further includes: dynamically adjusting the orientation determination threshold according to the real-time traffic flow data; and correcting the orientation relationship for mountainous road sections using three-dimensional space projection.

6. The spatiotemporal data fusion method for heterogeneous energy sites in highway networks according to claim 1 is characterized in that: The traffic flow distribution in step S5 is obtained based on the actual traffic flow data of the key monitoring points and the established traffic flow attenuation model based on the normal distribution.

7. A spatiotemporal data fusion system for heterogeneous energy sites in highway networks, characterized by: The system is implemented based on the method according to any one of claims 1 to 6, and includes: Road network completion module, used to perform fusion processing of GIS data and navigation data; Multi-source data integration module, used to connect enterprise databases and third-party data interfaces; Spatial relationship analysis module, used for direction identification and establishment of topological relationships; Business modeling module for time series analysis and competitive index calculation.

8. The spatiotemporal data fusion system for heterogeneous energy sites in highway networks according to claim 7 is characterized in that: The road network completion module includes: Path verification unit, used to detect the connectivity of road topology; An exception handling unit is configured to automatically generate an alternative route request when a path break is detected.

9. A computer device, characterized in that: It includes a memory and a processor, wherein a computer program is stored in the memory. When the processor runs the computer program stored in the memory, the processor executes a spatiotemporal data fusion method for heterogeneous energy sites for highway networks according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of a spatiotemporal data fusion method for heterogeneous energy sites in a highway network according to any one of claims 1 to 6.

Images