Track and meteorological data fusion analysis method and system

Abstract

The invention provides a trajectory and meteorological data fusion analysis method and system, and the method comprises the steps: fusing trajectory data and meteorological data based on a road network topological structure, selecting the meteorological data with the highest credible probability under the condition of multi-source meteorological data, and carrying out the precise average speed analysis and correlation analysis based on road segment segmentation. And data support is provided for order sending and path planning of salesmen such as couriers or take-out personnel.

Description

Technical Field

[0001] The present application belongs to the field of data analysis technology, and in particular relates to a method and system for fusion analysis of trajectory and meteorological data. Background Art

[0002] While the characteristics of urban transportation vary depending on population size, primary industries, and geographic location, they all share key similarities: passenger transport is the primary focus of urban transportation, commuting is the primary demand during peak hours, and urban traffic volume is directly related to each city's transportation service levels, policies, and management. With the continuous increase in my country's motor vehicle ownership, urban traffic congestion is becoming increasingly serious. Micro-level traffic management and control are effective solutions to this problem, and identifying frequently congested sections and times is fundamental to this management and control.

[0003] The road network is a complex system, and the state of vehicles on the road is affected by a variety of factors, including weather, road conditions, and vehicle status, exhibiting certain correlations across time and space. Time series refers to a set of data that is arranged sequentially over time. For example, the traffic volume in the previous period is correlated with the traffic volume in previous periods, forming a regular sequence of traffic volume data.

[0004] With the advancement of the internet and the increasing demand for convenience, China's e-commerce and food delivery industries have experienced explosive growth. The analysis of road navigation trajectory data is crucial for both e-commerce and food delivery drivers. Currently, both e-commerce and food delivery platforms collect driver trajectory data in real time, generating massive amounts of data. However, the analysis of this data is currently inaccurate and cannot effectively support the business.

[0005] Therefore, there is an urgent need for a new data analysis method that can provide more accurate and objective data navigation support for e-commerce, food delivery and other platforms.

[0006] The above statements are only used to provide background technical information related to this application. Unless otherwise indicated herein, the contents described in this section are not prior art for the contents of other parts of this application. Summary of the Invention

[0007] The present invention proposes a method and system for fusion analysis of trajectory and meteorological data. By fusing trajectory data with meteorological data based on the road network topology, the meteorological data with the highest probability of credibility is selected from multiple sources of meteorological data. Accurate average speed analysis and correlation analysis are then performed based on road segmentation. This provides data support for sales personnel, such as couriers or food delivery drivers, in dispatching orders and planning routes.

[0008] In addition, this application also achieves: 1) replacing coarse-grained regional statistics with segment-level secondary indexing, improving road network indexing efficiency and achieving accurate analysis of the road network; 2) optimizing the accuracy of meteorological data selection through a trusted probability model, solving the problem of multi-source meteorological data conflicts; 3) supporting route optimization decisions by integrating the impact of meteorological conditions on delivery speed.

[0009] In the specific takeaway scenario, this application achieves accurate analysis of the deliveryman's trajectory and integration and correlation analysis with meteorological data and time data by matching the deliveryman's trajectory based on road sections and integrating data from surrounding weather stations. The algorithm can perform distributed computing and process massive trajectory data, thereby achieving accurate analysis of the impact of meteorological conditions on the average speed of deliverymen in different road sections, and providing data support for subsequent deliverymen's route planning and overall scheduling plans under different meteorological conditions.

[0010] According to a first aspect of an embodiment of the present application, a method for fusion analysis of trajectory and meteorological data is provided, comprising the following steps: Based on the road network topology, the target area is gridded and a secondary index is established. The road sections are segmented and associated with the road network. The weather stations in the target area are matched and associated with the road sections to obtain the road network grid index, road section association library, and weather station association library. According to the road network grid index and the road section association library, the target person's trajectory data is matched with the road network section, the trajectory point-road section association relationship and offset distance are obtained, and the road section path event is generated; According to the weather station association database, weather station data with high credibility probability are selected and fused with path events to obtain weather fusion data; Based on meteorological fusion data, the correlation between road speed and meteorological factors is analyzed using the Pearson coefficient.

[0011] In some embodiments of the present application, the target area is gridded based on the road network topology and a secondary index is established, and the road segments are segmented and associated with the road network, including: Divide the target area road network into segments of preset lengths and create a secondary index containing the coordinates of the geometric center points of the road segments and their offset distances; Based on kilometer-level grid division, a cross-correlation relationship between grids and road sections is established, and the grids and road sections with cross-correlation are indexed to obtain a road network grid index and a road section association library.

[0012] In some embodiments of the present application, the weather stations in the target area are matched and associated with road sections, including: The correlation degree k between the weather station and the road section is calculated based on the location and effective radius of the weather station. The formula is: ; ; If > r or , then k = 0; If < r and , then + ; Where and are the distances from the meteorological station to both ends of the road section; r is the effective radius of the meteorological station; According to the correlation degree k between the meteorological station and the road section, the road section is associated with at least one meteorological station to obtain a meteorological station association library.

[0013] ​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​For the path event time t0, calculate the credibility probability pᵢ of the associated weather station data: ; ; Among them, ω1, ω2 are weight coefficients; m is the effective meteorological time; The weather station data with the highest credibility probability of the associated weather station is selected and fused with the route events to obtain the route events including the weather data.

[0016] In some embodiments of the present application, after generating a road segment path event, the method further includes: If there are n path events within the entire path time range, the average speed v of the path is calculated based on the path events. The formula is: V = ; Among them, t1 is the entry time and t2 is the end time.

[0017] In some embodiments of the present application, the correlation between the road speed and the meteorological factors is analyzed by the Pearson coefficient, including: For different road sections, there are N pieces of historical data; meteorological factors include temperature, precipitation and wind speed; Calculate the correlation coefficient r between the average speed and meteorological factors using the formula: r = Cov(X, Y) / (σX * σY); Cov (X,Y)= Σ[(x-x̅) * (y-y̅)] / N; Where X is the average speed; Y is the meteorological factor; σX and σY are the standard deviations of X and Y; x̅ is the average of multiple average speed records; y̅ is the average of multiple meteorological factor records; When r is close to 1, it indicates a positive correlation, and when r is close to -1, it indicates a negative correlation.

[0018] According to a second aspect of an embodiment of the present application, a trajectory and meteorological data fusion analysis system is provided, comprising: The road network preprocessing module is used to grid the target area based on the road network topology and establish a secondary index, segment the road sections and associate them with the road network, match and associate the weather stations in the target area with the road sections, and obtain the road network grid index, road section association library, and weather station association library; The road network matching module is used to match the target person's trajectory data with the road network segments according to the road network grid index and the road segment association library, obtain the trajectory point-road segment association relationship and offset distance, and generate the road segment path event; The data fusion module is used to select weather station data with high credibility probability and fuse them with path events according to the weather station association database to obtain weather fusion data; The correlation analysis module is used to analyze the correlation between road speed and meteorological factors based on meteorological fusion data through the Pearson coefficient.

[0019] According to a third aspect of an embodiment of the present application, a trajectory and meteorological data fusion analysis device is provided, including: a storage unit for storing executable instructions; and a processing unit for connecting to the memory to execute the executable instructions to complete a trajectory and meteorological data fusion analysis method.

[0020] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored; the computer program is executed by a processor to implement a method for fusion analysis of trajectory and meteorological data.

[0021] By adopting the trajectory and meteorological data fusion analysis method and system of this application, the deliveryman's trajectory is matched based on road sections and integrated with the surrounding meteorological station data, which enables accurate trajectory analysis and fusion and correlation analysis with meteorological data and time data. The algorithm can perform distributed computing and process massive trajectory data, providing data support for sales personnel such as couriers or deliverymen to dispatch orders and plan routes.

[0022] In addition, this application also achieves: 1) replacing coarse-grained regional statistics with segment-level secondary indexing, improving road network indexing efficiency and achieving accurate analysis of the road network; 2) optimizing the accuracy of meteorological data selection through a trusted probability model, solving the problem of multi-source meteorological data conflicts; 3) accurately supporting route optimization decisions by integrating the impact of meteorological conditions on delivery speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 : shows a schematic diagram of the steps of the trajectory and meteorological data fusion analysis method according to an embodiment of the present application; Figure 2 : shows a schematic diagram of the steps of road network preprocessing according to an embodiment of the present application; Figure 3 : shows a schematic diagram of the process flow of road network preprocessing according to an embodiment of the present application; Figure 4 : A schematic diagram of the steps of road network matching according to an embodiment of the present application is shown; Figure 5 : shows a schematic diagram of the process of road network matching according to an embodiment of the present application; Figure 6 : shows a flow chart of generating pathway events according to an embodiment of the present application; Figure 7 : shows a schematic diagram of the steps of data fusion according to an embodiment of the present application; Figure 8 : shows a schematic diagram of data fusion according to an embodiment of the present application; Figure 9 : A schematic diagram of the steps of association analysis according to an embodiment of the present application is shown; Figure 10 : shows a structural schematic diagram of a trajectory and meteorological data fusion analysis system according to an embodiment of the present application; Figure 11 Schematic diagram of the structure of the trajectory and meteorological data fusion analysis device according to an embodiment of the present application is shown in FIG. DETAILED DESCRIPTION

[0024] Regarding this application, with the advancement of the internet and the demand for more convenient living, the domestic e-commerce and food delivery industries have experienced explosive growth. The analysis of road navigation trajectory data is crucial for e-commerce and food delivery drivers. Currently, both e-commerce and food delivery platforms collect driver trajectory data in real time, generating a massive amount of trajectory data. However, the analysis of this data is currently limited to regional and hotspot statistics, resulting in inaccurate analysis and lack of integration with meteorological data, which in turn fails to provide strong support for the business.

[0025] The present invention proposes a method and system for fusion analysis of trajectory and meteorological data. By matching the deliveryman's trajectory based on road sections and integrating data from surrounding meteorological stations, accurate analysis of the deliveryman's trajectory and fusion and correlation analysis with meteorological data and time data can be achieved. The algorithm can perform distributed computing and process massive trajectory data, providing data support for deliveryman dispatching and route planning.

[0026] It includes gridding the target area and establishing a secondary index based on the road network topology, segmenting the road sections and associating them with the road network, matching and associating the meteorological stations in the target area with the road sections to obtain the road network grid index, the road section association library and the meteorological station association library; according to the road network grid index and the road section association library, matching the target personnel trajectory data with the road network sections to obtain the trajectory point-road section association relationship and the offset distance, and generating the road section path events; according to the meteorological station association library, selecting the meteorological station data with a high credibility probability to fuse with the path events to obtain meteorological fusion data; based on the meteorological fusion data, analyzing the correlation between the road section speed and meteorological factors through the Pearson coefficient.

[0027] This application also achieves: 1) replacing coarse-grained regional statistics with a segment-level secondary index, improving road network indexing efficiency and enabling precise road network analysis; 2) optimizing the accuracy of meteorological data selection through a trusted probability model, resolving conflicts in multi-source meteorological data; and 3) supporting route optimization decisions by integrating the impact of weather on delivery speed. This addresses the current issue of trajectory analysis being inaccurate and unable to effectively support business operations without integrating weather data for analysis.

[0028] In order to make the technical solutions and advantages of the embodiments of the present application more clearly understood, the exemplary embodiments of the present application are further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, and are not an exhaustive list of all the embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other unless they conflict.

[0029] Example 1 Figure 1 : shows a schematic diagram of the steps of the trajectory and meteorological data fusion analysis method according to an embodiment of the present application; like Figure 1 As shown, a trajectory and meteorological data fusion analysis method of the present application includes the following steps: S1: Grid the target area based on the road network topology and establish a secondary index. Then, segment the road sections and associate them with the road network. Match and associate the weather stations in the target area with the road sections to obtain the road network grid index, road section association library, and weather station association library. S2: According to the road network grid index and the road segment association library, the target person's trajectory data is matched with the road network segment to obtain the trajectory point-road segment association relationship and offset distance, and generate the road segment path event; S3: According to the weather station association database, weather station data with high credibility probability are selected and fused with pathway events to obtain weather fusion data; S4: Based on meteorological fusion data, the correlation between road speed and meteorological factors is analyzed using the Pearson coefficient.

[0030] The embodiment of the present application replaces coarse-grained regional statistics with a segment-level secondary index, thereby improving the efficiency of road network indexing and achieving accurate analysis of the road network; and accurately supports path optimization decisions by integrating the impact of weather on delivery speed.

[0031] In addition, this application realizes the precise analysis of the deliveryman's trajectory and the fusion and correlation analysis with meteorological data and time data by matching the deliveryman's trajectory based on road segments and integrating the data of surrounding weather stations. The algorithm can perform distributed computing and process massive trajectory data, thereby achieving precise analysis of the impact of the average speed of deliverymen on different road segments under meteorological conditions, providing data support for subsequent path planning and overall scheduling of deliverymen under different meteorological conditions.

[0032] First, data collection is carried out, including the collection of trajectory data and meteorological data. For real-time data in this application, real-time trajectory data and meteorological data are docked from the business platform and meteorological platform through the KAFKA message queue. In the takeaway platform, the trajectory data includes the deliveryman number, location, and timestamp, and the meteorological data includes temperature, humidity, precipitation, wind speed, wind direction, and timestamp.

[0033] Next, road network preprocessing is performed based on the road network topology. The area is gridified, and the road segments are segmented. On this basis, the weather stations are matched and associated with the road segments.

[0034] Figure 2 The schematic diagram of the steps of road network preprocessing according to an embodiment of this application is shown; ​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​is the distance from the meteorological station to both ends of the road section; r is the effective radius of the meteorological station; S14: According to the correlation degree k between the meteorological station and the road section, the road section is associated with at least one meteorological station to obtain a meteorological station association library.

[0036] Figure 3 : shows a schematic diagram of the process flow of road network preprocessing according to an embodiment of the present application; like Figure 3 As shown in the figure, after the road network topology data is initialized, regional gridding is first performed; then the road network is segmented, and longer road sections, such as 300 meters, are divided and associated with grids to establish a secondary index of the road network. On this basis, kilometer-level grid processing is performed, and the road sections that intersect with the grid are indexed.

[0037] The original topological structure of the road network is (V, E), where V is the intersection geometry and E is the set of roads. After segmentation, Eij is the jth section of road Ei. The section structure is represented by the set of center points (p1, p2...pn), with the coordinates of p1 being (x1, y1), and so on.

[0038] Grid Gmn is the grid within the region, m,n is the grid number, the top left grid number is 0,0, the coordinates of the top left corner of the region are (x0, y0), and so on. Usually 1km*1km is used as the grid size, and the road sections that intersect with the grid will establish an association relationship. The intersection relationship confirmation process is as follows: If there is a central point O(Xi, Yi) on a certain road section that satisfies: Xi>x0+1000*(m-1), and Xi <x0+1000*m; Yi>y0+1000*(n-1), and Yi <y0+1000*n; Then there is an intersection relationship between the road section and the grid Gm,n. During data preprocessing, all road sections associated with the grid will be associated and the association relationship will be stored.

[0039] During data preprocessing, the offset distance of the center point p of each road section relative to the starting point of the road section is calculated at the same time , the formula is as follows: ; Then, the weather station road segment matching association is performed.

[0040] Weather station data includes static data and dynamic data. Static data includes the location of the weather station, effective spatial range, and effective time range; dynamic data includes temperature, humidity, precipitation, wind speed, wind direction, station number, release time and other meteorological data.

[0041] Match weather stations according to the location of the weather stations and the effective spatial range, and establish virtual weather stations for each road section. Therefore, one road section can correspond to multiple virtual weather stations. During the subsequent fusion process, a credibility probability judgment will be performed to select a credible weather data source for data fusion.

[0042] The determination of the association relationship between the weather station and the road section is as follows: Let the coordinates of the weather station be ([ , ), the effective radius of the data be r, and the coordinates of the starting point and the ending point of the road section be ([ , ), ([ , ), respectively. Then the calculation formula for the association degree k between this weather station and a certain flight segment is: ;

[0043] If > r or , then k = 0; If < r and , then + ; After matching, one road section can be associated with multiple weather stations with different k values.

[0044] Figure 4 shows a schematic diagram of the steps of road network matching according to an embodiment of the present application; As [[ID=4৮]] Figure 4 shown, when the road network matching module is in S2, according to the road network grid index and the road section association library, the target personnel trajectory data is matched with the road network road sections to obtain the trajectory point-road section association relationship and the offset distance, and generate road section passing events, including the following steps: S21: Search the road network grid index and the road section association library according to the trajectory points of the trajectory data, match the road section and calculate the trajectory point offset distance; obtain the target personnel trajectory data through the Kafka message queue; S22: Improve the trajectory point events at the endpoints of adjacent road sections according to the trajectory point offset distance, and determine a series of trajectory point events of the target personnel trajectory data; the trajectory point events include the trajectory point position and the trajectory time; In the embodiment of the present application, interpolation method is preferably used to calculate the specific time of entering and leaving the road section to improve the trajectory point events at the endpoints of adjacent road sections.

[0045] S23: Generate passing events corresponding to the target personnel trajectory data, including the road section ID, the entering time, and the leaving time, through a series of trajectory point arrays.

[0046] The step S21 of calculating the trajectory point offset distance specifically includes the following steps: S211: Assume that the trajectory point is a(x0, y0), and the centerline points of the two closest road segments in the grid where the trajectory point a(x0, y0) is located are p1(x1, y1) and p2(x2, y2); S212: Calculate the offset distance of trajectory point a(x0,y0) using the perpendicular line method , the formula is: ; When t<0, ; When t>0, ; in, is the base point offset.

[0047] Figure 5 : shows a schematic diagram of the process of road network matching according to an embodiment of the present application; In specific implementation, based on the delivery driver's real-time trajectory, the trajectory point a(x0, y0) is matched to the road section. First, the grid where the trajectory point is located is found, and its associated road section is obtained. The centerline points p1(x1, y1) and p2(x2, y2) of the two nearest road sections are obtained. The offset distance of a is obtained through the perpendicular line as follows, and the corresponding association relationship is stored.

[0048] like Figure 5 As shown in the figure, the processing flow is as follows: receiving the delivery driver's real-time trajectory point a(x0,y0) as input; grid indexing: calling the pre-established grid road network indexing system; grid positioning: determining the grid area to which the trajectory point belongs based on the coordinates; path acquisition: retrieving all candidate paths (road sections) associated with the grid; key point positioning: finding the two closest centerline reference points (p1, p2) on the candidate path; offset calculation: calculating the vertical offset distance from the trajectory point to the path through a geometric algorithm; data storage: saving the mapping relationship between the trajectory point and the road section and the offset data.

[0049] In specific implementation, route events are generated based on segment matching. The segment route events include the following fields: deliveryman number, segment ID, segment length, start time, and end time.

[0050] Figure 6 : shows a flow chart of generating pathway events according to an embodiment of the present application; like Figure 6As shown, the process includes: 1) start, perform initialization processing; 2) match the trajectory point to the road segment, match the current trajectory point to the corresponding road segment (for example, through a spatial matching algorithm); 3) move to the next trajectory point to read the next trajectory point in the trajectory sequence and continue processing; 4) determine whether the road segment has changed, check whether the road segment matched by the current trajectory point is the same as the road segment of the previous trajectory point, and if it is the same road segment, continue to match the road segment and process the next trajectory point; if it is not the same road segment, trigger the event generation process; 5) event generation process: when the road segment changes, calculate the time of leaving the road segment and record the time of leaving the previous road segment (usually using the timestamp of the previous trajectory point); write the previous route event, generate a complete "leave the road segment" event record and store it; generate a new route event and create an "enter the road segment" event record for the current road segment; 6) loop control repeats the above steps until all trajectory points are processed ("trajectory loop end"), ending the termination process.

[0051] Among them, when the event generation process records the time of "leaving the road section" or "entering the road section", due to the long time interval between the trajectory points, when the delivery person enters the next road section, he or she has usually passed the starting point or end point. Therefore, it is necessary to additionally calculate the time it takes to pass the starting point and end point.

[0052] The embodiment of the present application preferably uses the interpolation method to calculate the specific time of entering and leaving the road section.

[0053] Assume that the previous trajectory point is (a1, t1), the next trajectory point is (a2, t2), and the road segment dividing point is a. The time t between the end of the previous road segment and the beginning of the new road segment is as follows: According to the above offset distance calculation formula, we can get the offset distance l1 of the starting point of the road section corresponding to a1, and the offset distance l2 of the starting point of the road section corresponding to a2; The distance between the road segment dividing point a and the starting point of the road segment is l. If a1, a2 and point a match different road segments, the distances are concatenated.

[0054] Get the route time of the road dividing point a for: ; Through the above calculations, the specific time when the delivery person passes the starting and ending points of the road section is recorded. This time is more complete and accurate than the trajectory report time, and can enable more precise trajectory analysis.

[0055] Figure 7 : shows a schematic diagram of the steps of data fusion according to an embodiment of the present application; like Figure 7 As shown, in S3, weather station data with high credibility probability are selected for fusion with pathway events, which specifically includes the following steps: S31: Calculate the credibility probability pᵢ of the associated weather station data for the path event time t0: ; ; Among them, ω1, ω2 are weight coefficients; m is the effective meteorological time; S32: Select the weather station data with the highest credibility probability of the associated weather station and fuse them with the route event to obtain the route event including the weather data.

[0056] In the preferred implementation, after generating the road segment event, the average speed of the road segment is also calculated. The deliveryman trajectory feature mainly analyzes the delivery speed of the deliveryman on different road segments. The specific process of the deliveryman's average speed through the road segment is as follows: There are n path events within the entire path time range of a road segment. The path event array is (road segment ID, road segment length l, entry time t1, end time t2). The average speed v of the road segment is calculated based on the path events. The formula is: V = .

[0057] Figure 8 : shows a schematic diagram of data fusion according to an embodiment of the present application; The delivery speed of food delivery drivers is greatly affected by the weather, and different road sections may be covered by multiple weather stations. The data release frequency of different weather stations is different. Therefore, it is necessary to calculate the credibility probability of meteorological data from different sources based on the meteorological station correlation calculated by preprocessing and the release time of specific meteorological data, and select meteorological data with high credibility probability for fusion.

[0058] like Figure 8 As shown in the figure, the processing flow is as follows: 1) Start and initialize the data fusion process; 2) Loop through each route event and traverse each stored route event (such as entering / leaving a road section event); 3) Find the weather station associated with the road section and query the associated weather monitoring station based on the road section where the current route event is located; 4) Determine the number of associated weather stations and check the number of associated weather stations. If it is not a single weather station, directly obtain the latest data of the weather station; if it is multiple weather stations, obtain the latest data of all associated weather stations, and then calculate the weather data with the highest credible probability (select the optimal data through a weighted algorithm); 5) Data fusion, bind the selected / calculated weather data (such as temperature, precipitation) to the current route event; 6) Loop control repeats the above steps until all route events are processed, and 7) End the data fusion process.

[0059] The credible probability calculation process is as follows: First, calculate the Euclidean distance di of different data sources, and then calculate the credibility probability pi based on the Euclidean distance; Assume that the time when the deliveryman passes through a certain road section is t0, and the road section is associated with two weather stations, and the correlation degrees are , , within the effective meteorological time m range (generally 1 hour), there are multiple dynamic data, namely (weather station 1, and (Weather Station 2, ), then the corresponding Euclidean distance di is calculated as: ; The calculation formula of credible probability pi is: ; in and It is a weight configuration, which can be configured according to different scenarios to adjust the time and space priority. The default value can be 0.5.

[0060] If there are multiple dynamic data of the same type, the one with the larger Euclidean distance is selected and fused with the traffic flow characteristic data. After fusing different data, the final data format is (start time t1, end time t2, road section index i, traffic flow speed v, temperature t, precipitation r, wind direction w, wind speed).

[0061] Finally, based on the final fusion data, correlation analysis can be used to analyze the factors affecting water transport flow. Correlation analysis uses the Pearson coefficient formula to calculate the correlation relationship between different factors.

[0062] Figure 9 : A schematic diagram of the steps of association analysis according to an embodiment of the present application is shown; like Figure 9 As shown, in the correlation analysis in S4, the correlation between the road speed and the meteorological factors is analyzed by the Pearson coefficient, which includes the following steps: S41: For different road sections, there are N pieces of historical data; meteorological factors include temperature, precipitation and wind speed; S42: Calculate the correlation coefficient r between the average speed and meteorological factors. The formula is: r = Cov(X, Y) / (σX * σY); Cov (X,Y)= Σ[(x-x̅) * (y-y̅)] / N; Where X is the average speed; Y is the meteorological factor; σX and σY are the standard deviations of X and Y; x̅ is the average of multiple average speed records; y̅ is the average of multiple meteorological factor records; When r is close to 1, it indicates a positive correlation, and when r is close to -1, it indicates a negative correlation.

[0063] The trajectory and meteorological data fusion analysis method of this application is adopted. By fusing trajectory data and meteorological data based on the road network topology structure, the meteorological data with the highest probability of credibility is selected in the case of multi-source meteorological data, and accurate average speed analysis and correlation analysis are performed based on road segmentation, providing data support for sales personnel such as couriers or deliverymen to dispatch orders and plan routes.

[0064] In addition, this application also achieves: 1) replacing coarse-grained regional statistics with segment-level secondary indexing, improving road network indexing efficiency and achieving accurate analysis of the road network; 2) optimizing the accuracy of meteorological data selection through a trusted probability model, solving the problem of multi-source meteorological data conflicts; 3) supporting route optimization decisions by integrating the impact of meteorological conditions on delivery speed.

[0065] Example 2 This embodiment provides a trajectory and meteorological data fusion analysis system. For details not disclosed in the trajectory and meteorological data fusion analysis system of this embodiment, please refer to the specific implementation content of the trajectory and meteorological data fusion analysis method in other embodiments.

[0066] Figure 10 Schematic diagram of the structure of a trajectory and meteorological data fusion analysis system according to an embodiment of the present application is shown in FIG.

[0067] like Figure 10 As shown, a trajectory and meteorological data fusion analysis system according to an embodiment of the present application includes: The road network preprocessing module 10 is used to grid the target area based on the road network topology and establish a secondary index, and to segment the road sections and associate them with the road network. The weather stations in the target area are matched and associated with the road sections to obtain a road network grid index, a road section association library, and a weather station association library. The road network matching module 20 is used to match the target person's trajectory data with the road network segments according to the road network grid index and the road segment association library, obtain the trajectory point-road segment association relationship and offset distance, and generate the road segment path event; The data fusion module 30 is used to select weather station data with high credibility probability and fuse them with path events according to the weather station association database to obtain weather fusion data; The correlation analysis module 40 is used to analyze the correlation between the road speed and the meteorological factors through the Pearson coefficient based on the meteorological fusion data.

[0068] In specific implementation, the structure of this technical solution includes trajectory, meteorological data acquisition module, road network preprocessing module, road network matching module, feature extraction module, data fusion module, and association analysis module.

[0069] The road network matching module and data fusion module can use Spark computing for distributed processing, using the Spark engine to execute road network matching and data fusion. Other modules use Kafka message queues to obtain trajectory and meteorological data streams for real-time data access.

[0070] The correlation analysis module outputs the Pearson correlation coefficient r between the road speed and the meteorological factors.

[0071] The distributed computing architecture of this application supports Spark distributed processing through modular design (network matching, data fusion, etc.), thereby improving the throughput capacity of massive data.

[0072] Therefore, the trajectory and meteorological data fusion analysis system of this application is adopted. By fusing trajectory data and meteorological data based on the road network topology structure, the meteorological data with the highest probability of credibility is selected in the case of multi-source meteorological data, and accurate average speed analysis and correlation analysis are performed based on road segmentation, providing data support for sales personnel such as couriers or deliverymen to dispatch orders and plan routes.

[0073] Example 3 This embodiment provides a trajectory and meteorological data fusion analysis device. For details not disclosed in the trajectory and meteorological data fusion analysis device of this embodiment, please refer to the specific implementation content of the trajectory and meteorological data fusion analysis method or system in other embodiments.

[0074] Figure 11 Schematic diagram of the structure of the trajectory and meteorological data fusion analysis device 400 according to an embodiment of the present application is shown in FIG.

[0075] like Figure 11 As shown, the trajectory and meteorological data fusion analysis device 400 includes: a storage unit 402: for storing executable instructions; and a processing unit 401: for connecting to the storage unit 402 to execute the executable instructions to complete the trajectory and meteorological data fusion analysis method.

[0076] Those skilled in the art will understand that the schematic diagram is merely an example of the trajectory and meteorological data fusion analysis device 400 and does not constitute a limitation on the trajectory and meteorological data fusion analysis device 400. The device may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the trajectory and meteorological data fusion analysis device 400 may also include input and output devices, network access devices, buses, etc.

[0077] The so-called processing unit 401 (Central Processing Unit, CPU) can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor, or the processing unit 401 can also be any conventional processor. The processing unit 401 is the control center of the trajectory and meteorological data fusion analysis device 400, and uses various interfaces and lines to connect the various parts of the entire trajectory and meteorological data fusion analysis device 400.

[0078] Storage unit 402 can be used to store computer-readable instructions. Processing unit 401 implements the various functions of trajectory and meteorological data fusion and analysis device 400 by running or executing the computer-readable instructions or modules stored in storage unit 402 and accessing the data stored in storage unit 402. Storage unit 402 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as sound playback or image playback); the data storage area may store data generated by trajectory and meteorological data fusion and analysis device 400. Furthermore, storage unit 402 may include a hard disk, memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash card, at least one disk storage device, a flash memory device, a read-only memory (ROM), a random access memory (RAM), or other non-volatile or volatile storage devices.

[0079] If the module integrated into the trajectory and meteorological data fusion analysis device 400 is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can also implement all or part of the process of the above-mentioned embodiment method by instructing the relevant hardware through computer-readable instructions. The computer-readable instructions can be stored in a computer-readable storage medium. When executed by a processor, the computer-readable instructions can implement the steps of each of the above-mentioned method embodiments.

[0080] Example 4 This embodiment provides a computer-readable storage medium having a computer program stored thereon; the computer program is executed by a processor to implement the trajectory and meteorological data fusion analysis method in other embodiments.

[0081] The trajectory and meteorological data fusion analysis device and computer-readable storage medium of the present application are adopted, and the trajectory and meteorological data fusion analysis method of the present application is adopted. By fusing the trajectory data and meteorological data based on the road network topology structure, the meteorological data with the highest probability of credibility is selected in the case of multi-source meteorological data, and accurate average speed analysis and correlation analysis are performed based on road segmentation, providing data support for sales personnel such as couriers or deliverymen to dispatch orders and plan routes.

[0082] In addition, this application also achieves: 1) replacing coarse-grained regional statistics with segment-level secondary indexing, improving road network indexing efficiency and achieving accurate analysis of the road network; 2) optimizing the accuracy of meteorological data selection through a trusted probability model, solving the problem of multi-source meteorological data conflicts; 3) supporting route optimization decisions by integrating the impact of meteorological conditions on delivery speed.

[0083] Those skilled in the art will appreciate that the terms used in the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. As used in the present invention and the appended claims, the singular forms "a," "the," and "the" are intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.

[0084] It should be understood that although the terms "first," "second," "third," etc. may be used in the present invention to describe various information, such information should not be limited to these terms. These terms are merely used to distinguish information of the same type from one another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present invention. Depending on the context, the term "if" as used herein may be interpreted as "when," "when," or "in response to determining."

[0085] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0086] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A trajectory and meteorological data fusion analysis method, characterized in that: The following steps are involved: Based on the road network topology, the target area is gridded and a secondary index is established. The road sections are segmented and associated with the road network. The weather stations in the target area are matched and associated with the road sections to obtain the road network grid index, road section association library, and weather station association library. According to the road network grid index and the road segment association library, the target person's trajectory data is matched with the road network segment to obtain the trajectory point-road segment association relationship and the offset distance, and generate the road segment path event; According to the weather station association database, weather station data with high credibility probability is selected and fused with the pathway event to obtain weather fusion data; Based on meteorological fusion data, the correlation between road speed and meteorological factors is analyzed using the Pearson coefficient.

2. The trajectory and meteorological data fusion analysis method according to claim 1 is characterized in that: The target area is gridded based on the road network topology, a secondary index is established, and the road sections are segmented and associated with the road network, including: Divide the target area road network into segments of preset lengths and create a secondary index containing the coordinates of the geometric center points of the road segments and their offset distances; Based on the grid division, the cross-correlation relationship between grids and road sections is established, and the grids and road sections with cross-correlation are indexed to obtain the road network grid index and road section association library.

3. The trajectory and meteorological data fusion analysis method according to claim 1, characterized in that: The step of matching and associating the weather stations in the target area with each other on road sections includes: The correlation degree k between the weather station and the road section is calculated based on the location and effective radius of the weather station. The formula is: ； ； like > r or , then k=0; like < r and ,but + ; in and is the distance from the meteorological station to both ends of the road section; r is the effective radius of the meteorological station; According to the correlation degree k between the meteorological station and the road section, the road section is associated with at least one meteorological station to obtain a meteorological station association library.

4. The trajectory and meteorological data fusion analysis method according to claim 1, characterized in that: The method of matching the target person's trajectory data with the road network sections according to the road network grid index and the road section association library, obtaining the trajectory point-road section association relationship and the offset distance, and generating the road section path event includes: According to the trajectory points, the trajectory data is searched for the road network grid index and the road section association library, matched to the road section and calculated the trajectory point offset distance; According to the trajectory point offset distance, the trajectory point events of the adjacent road segment endpoints are improved to determine a series of trajectory point events of the target person's trajectory data; the trajectory point events include the trajectory point position and trajectory time; A route event including a road segment ID, an entry time, and an exit time corresponding to the target person's trajectory data is generated through the series of trajectory point arrays.

5. The trajectory and meteorological data fusion analysis method according to claim 4 is characterized in that: The calculating of the trajectory point offset distance includes: Let the trajectory point be a(x0,y0), and the centerline points of the two closest road segments in the grid where the trajectory point a(x0,y0) is located are p1(x1,y1) and p2(x2,y2); Calculate the offset distance of trajectory point a(x0,y0) by the perpendicular line method , the formula is: ； When t<0, ; When t>0, ; in, is the base point offset.

6. The trajectory and meteorological data fusion analysis method according to claim 1, characterized in that: The step of selecting weather station data with high credibility probability and fusing it with the pathway event comprises: For the path event time t0, calculate the credibility probability pᵢ of the associated weather station data: ； ； Among them, ω1, ω2 are weight coefficients; m is the effective meteorological time; The weather station data with the highest credibility probability of the associated weather station is selected and fused with the route events to obtain the route events including the weather data.

7. The trajectory and meteorological data fusion analysis method according to claim 1, characterized in that: After the road segment path event is generated, the following steps are also included: If there are n path events within the entire path time range, the average speed v of the path is calculated based on the path events. The formula is: V = ； Among them, t1 is the entry time and t2 is the end time.

8. The trajectory and meteorological data fusion analysis method according to claim 7, characterized in that: The analysis of the correlation between road speed and meteorological factors using the Pearson coefficient includes: For different road sections, N pieces of historical data are provided; the meteorological factors include temperature, precipitation and wind speed; Calculate the correlation coefficient r between the average speed and meteorological factors using the formula: r = Cov(X, Y) / (σX * σY); Cov (X,Y)= Σ[(x-x̅) * (y-y̅)] / N; Where X is the average speed; Y is the meteorological factor; σX and σY are the standard deviations of X and Y; x̅ is the average of multiple average speed records; y̅ is the average of multiple meteorological factor records; When r is close to 1, it indicates a positive correlation, and when r is close to -1, it indicates a negative correlation.

9. A trajectory and meteorological data fusion analysis system, characterized in that: include: The road network preprocessing module is used to grid the target area based on the road network topology and establish a secondary index, segment the road sections and associate them with the road network, match and associate the weather stations in the target area with the road sections, and obtain the road network grid index, road section association library, and weather station association library; A road network matching module is used to match the target person's trajectory data with the road network segments according to the road network grid index and the road segment association library, obtain the trajectory point-road segment association relationship and offset distance, and generate the road segment path event; A data fusion module is used to select weather station data with high credibility probability according to the weather station association database and fuse them with the pathway events to obtain weather fusion data; The correlation analysis module is used to analyze the correlation between road speed and meteorological factors based on meteorological fusion data through the Pearson coefficient.

10. A trajectory and meteorological data fusion analysis device, characterized in that: include: The method comprises: a storage unit for storing executable instructions; and a processing unit for connecting with the storage to execute the executable instructions so as to complete the trajectory and meteorological data fusion analysis method.

Images