Vehicle navigation analysis method and system based on multi-modal road network data

Abstract

The invention discloses a vehicle navigation analysis method and system based on multi-modal road network data, and the method comprises the steps: obtaining and preprocessing multi-source road network data, the multi-source road network data comprises traffic road network data and civil navigation data, the traffic road network data comprises vector data of national roads, provincial roads, county roads, rural roads and town roads, and the vector data comprises vector data of national roads, provincial roads, county roads and town roads; the civil navigation data comprises a road topological structure and related bridge and tunnel attribute data; carrying out multi-source data fusion, fusing the traffic road network data and the civil navigation data through buffer analysis and geometric feature matching, and generating a fused comprehensive road network data set; and setting a path planning model, and training the path planning model by taking the comprehensive road network data set as a training set so as to complete path planning.

Description

Technical Field

[0001] The present invention belongs to the technical field of road network data processing and vehicle navigation, and more specifically, relates to a vehicle navigation analysis method and system based on multimodal road network data. Background Art

[0002] Vehicle navigation technology has become highly mature and has been widely used in daily life and industrial applications. The following is the current status of vehicle navigation and its main features:

[0003] 1. Global Navigation Satellite System (GNSS) Popularization

[0004] GPS and BeiDou are the main global navigation satellite systems, providing positioning and navigation services worldwide.

[0005] Most navigation devices and smartphones support multiple GNSS systems to improve positioning accuracy and reliability.

[0006] 2. High-precision maps

[0007] HD Maps: Especially in the field of autonomous driving, HD maps have centimeter-level accuracy and provide detailed three-dimensional information of the road, such as lane lines, traffic signs, and signal light locations.

[0008] Dynamic map updates: Modern navigation systems are able to update road information such as traffic jams, accidents, road construction, etc. in real time to provide the best route.

[0009] 3. Real-time traffic information

[0010] Navigation systems can calculate the optimal driving route under current conditions by integrating real-time traffic data, which usually comes from traffic sensors, vehicle systems, data collection from mobile devices, and real-time information on social media.

[0011] However, existing navigation software is prone to navigation errors due to untimely data updates or a single data source. Summary of the invention

[0012] In order to solve the above technical problems, the present invention proposes a vehicle navigation analysis method based on multimodal road network data, comprising:

[0013] Acquire and preprocess multi-source road network data, wherein the multi-source road network data includes traffic road network data and civil navigation data, wherein the traffic road network data includes vector data of national roads, provincial roads, county roads, township roads and town roads, and the civil navigation data includes road topological structure and its related bridge and tunnel attribute data;

[0014] Carry out multi-source data fusion, integrate traffic network data with civil navigation data through buffer zone analysis and geometric feature matching, and generate a fused comprehensive road network data set;

[0015] A path planning model is set, and the comprehensive road network data set is used as a training set to train the path planning model, thereby completing path planning.

[0016] Furthermore, the path planning model includes:

[0017]

[0018] in, is the vehicle navigation index, T total is the total travel time index, μ is the adjustment factor of the travel probability, P pass (s, t) is the passing probability at position s at time t.

[0019] Furthermore, P pass (s, t) is the probability of passing at position s at time t, including:

[0020]

[0021] Where n is the number of roads, bridges or tunnels, σ is the Sigmoid function, and α i (t) is the first adjustment factor for the i-th road, bridge or tunnel, β i (t) is the second adjustment factor for the i-th road, bridge or tunnel, A ri (s, t) is the attribute value of the i-th road, bridge or tunnel at position s at time t. The attribute values ​​of the road, bridge or tunnel include the maximum load weight, height limit or width. vi is the i-th characteristic parameter of the vehicle, and the characteristic parameters include: vehicle weight, vehicle height, or vehicle width, δ is the buffer zone adjustment factor, B(s) is the buffer zone parameter at position s, ζ is the traffic flow adjustment factor, and κ(s, t) is the traffic flow at position s at time t.

[0022] Furthermore, the total travel time index T total include:

[0023]

[0024] Where L is the total length of the route, V opt (s, t) is the optimal speed at position s at time t, ρ is the second adjustment factor of the total travel time index, τ is the first adjustment factor of the total travel time index, ω is the changing frequency of traffic signals, and ξ is the third adjustment factor of the total travel time index.

[0025] Further, obtain the minimized vehicle navigation index After that, the vehicle navigation index will be minimized The corresponding traffic network data and civil navigation data are displayed on the user terminal in the form of navigation.

[0026] The present invention also proposes a vehicle navigation analysis system based on multimodal road network data, comprising:

[0027] A data acquisition module is used to acquire and preprocess multi-source road network data, wherein the multi-source road network data includes traffic road network data and civil navigation data, wherein the traffic road network data includes vector data of national roads, provincial roads, county roads, township roads and town roads, and the civil navigation data includes road topological structure and its related bridge and tunnel attribute data;

[0028] The data fusion module is used to fuse multi-source data. It fuses traffic network data with civil navigation data through buffer zone analysis and geometric feature matching to generate a fused comprehensive road network data set.

[0029] The path planning module is used to set a path planning model and use the comprehensive road network data set as a training set to train the path planning model, thereby completing path planning.

[0030] Furthermore, the path planning model includes:

[0031]

[0032] in, is the vehicle navigation index, T total is the total travel time index, μ is the adjustment factor of the travel probability, P pass (s, t) is the passing probability at position s at time t.

[0033] Furthermore, P pass (s, t) is the probability of passing at position s at time t, including:

[0034]

[0035] Where n is the number of roads, bridges or tunnels, σ is the Sigmoid function, and α i (t) is the first adjustment factor for the i-th road, bridge or tunnel, β i (t) is the second adjustment factor for the i-th road, bridge or tunnel, A ri (s, t) is the attribute value of the i-th road, bridge or tunnel at position s at time t. The attribute values ​​of the road, bridge or tunnel include the maximum load weight, height limit or width. viis the i-th characteristic parameter of the vehicle, and the characteristic parameters include: vehicle weight, vehicle height, or vehicle width, δ is the buffer zone adjustment factor, B(s) is the buffer zone parameter at position s, ζ is the traffic flow adjustment factor, and к(s,t) is the traffic flow at position s at time t.

[0036] Furthermore, the total travel time index T total include:

[0037]

[0038] Where L is the total length of the route, V opt (s, t) is the optimal speed at position s at time t, ρ is the second adjustment factor of the total travel time index, τ is the first adjustment factor of the total travel time index, ω is the changing frequency of traffic signals, and ξ is the third adjustment factor of the total travel time index.

[0039] Further, obtain the minimized vehicle navigation index After that, the vehicle navigation index will be minimized The corresponding traffic network data and civil navigation data are displayed on the user terminal in the form of navigation.

[0040] In general, the above technical solution conceived by the present invention has the following beneficial effects compared with the prior art:

[0041] The present invention has achieved data fusion results of special vehicle path planning and navigation functions based on the fusion data of traffic road network and navigation road network, basic image map tile data processing results for mobile terminal map quick browsing and query functions, standardization results of various data of traffic atlas database, and pilot construction results of paper version of traffic atlas (electronic picture format). BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flow chart of the method of embodiment 1 of the present invention;

[0043] Figure 2 It is a structural diagram of the system of embodiment 2 of the present invention. DETAILED DESCRIPTION

[0044] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0045] The method provided by the present invention can be implemented in the following terminal environment, and the terminal may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, and the instruction is loaded and executed by the processor to implement the method described in the following embodiment.

[0046] The processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts in the entire terminal, and executes various functions of the terminal and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and calling data stored in the storage medium.

[0047] The storage medium may include a random access memory (RAM) or a read-only memory (ROM). The storage medium may be used to store instructions, programs, codes, code sets or instructions.

[0048] The display screen is used to display the user interface of each application.

[0049] In addition, those skilled in the art can understand that the structure of the above terminal does not constitute a limitation on the terminal, and the terminal may include more or fewer components, or combine certain components, or arrange the components differently. For example, the terminal also includes components such as a radio frequency circuit, an input unit, a sensor, an audio circuit, and a power supply, which will not be described in detail here.

[0050] Example 1

[0051] like Figure 1 As shown, an embodiment of the present invention provides a vehicle navigation analysis method based on multimodal road network data, comprising:

[0052] Step 101, acquiring and preprocessing multi-source road network data, wherein the multi-source road network data includes traffic road network data and civil navigation data, wherein the traffic road network data includes vector data of national roads, provincial roads, county roads, township roads and town roads, and the civil navigation data includes road topological structure and its related bridge and tunnel attribute data;

[0053] The spatial analysis function of vector data makes it widely used in various industries such as construction planning, resource management, and environmental analysis. Through multi-source data fusion, the data dimension can be effectively improved. Dimension improvement can increase the attribute information of the object, which is more conducive to the description of certain spatial relationships. The theory and method of multi-source vector spatial data fusion is a powerful tool to solve the above problems. It can process the consistency of spatial benchmarks, mathematical foundations, scales, contents, and spatial relationships of multi-source vector spatial data to ensure data consistency.

[0054] There are two types of road network data in traffic resource data: one is dedicated road network data, which is vector data with characteristics such as road grade; the other is civil road network data, which has a road network topology structure and can realize path planning and vehicle navigation. The difference between the two types of data sources is that traffic road network data is only spatial vector data without road topology attributes; while civil road network data, such as navigation topology data, can be used to realize navigation and path planning functions. This project needs to use civil road network navigation topology data combined with traffic road network data to carry out data fusion to realize the project vehicle path planning and navigation functions.

[0055] This embodiment is based on the analysis of the spatial geometric relationship of geographic information. The tool software used is the PGsql database. The full name of PGsql is postgresql. It is a very mature, open source, powerful relational database. Generally speaking, the database supports SQL complex syntax and implements left-join query, right-join query, function, trigger, constraint and other functions. The GIS function for processing spatial data provided by PGsql is used to achieve efficient and optimized implementation of data fusion.

[0056] Geographic information spatial geometric relationship analysis mainly includes proximity analysis, overlay analysis, network analysis, etc. Buffer analysis is a type of proximity analysis. The buffer is to identify the influence of a certain geographic entity or spatial object on its surrounding objects by establishing a strip area with a certain width around it. The buffer is used as an independent data layer for overlay analysis, which can be applied to the spatial analysis of roads and bridges, providing a scientific basis for certain application purposes.

[0057] Data fusion is based on line feature matching, and adopts a buffer overlap-based approach, that is, a buffer is established based on matching line segments, and the length of the line segment to be matched entering the buffer range is used to determine whether the two are entities with the same name. The buffer growth method is used to match the road network. In terms of the selection of basic matching units, the "node-arc segment" method is used for matching. At the same time, based on the global consistency matching idea, according to the road network structure, the road data is divided into separate matches based on road grades. At the same time, drawing on the mathematical optimization problem of global optimization, the distance and topological structure are used to measure the similarity between targets, optimize the road network matching problem, and integrate the road grade, road base width, bridge deck width, design load grade, technical condition assessment grade, all bridges and tunnels of the arc segment and other information related to the special road network into the civil road network data, which enhances the attribute information characteristics of the software's topological network data.

[0058] The radius of the buffer zone is confirmed:

[0059] 1) The civil navigation data is superimposed with the special data sets (national and provincial roads, county roads), 100 line segments are randomly sampled, and buffer analysis is performed through postgis. Based on the civil navigation data, buffers are established for the line segments, starting points, center points, and end points. The intersection of the three buffers is calculated, and the matching rate is calculated at 20 meters, 30 meters, 40 meters, 50 meters, 60 meters, and 70 meters respectively. After analysis, it is found that the optimal distance for the buffer zone of national and provincial roads is 50 meters, and the optimal distance for the buffer zone of county roads is 20 meters;

[0060] 2) The civil navigation data is superimposed with different special data sets (national and provincial highway bridges, rural bridges), and a buffer zone is established for the line segments. The matching rates are calculated at 20 meters, 30 meters, 40 meters, 50 meters, 60 meters, and 70 meters respectively. After analysis, it is found that the optimal distance for the buffer zone of national and provincial highway bridges is 50 meters, and the optimal distance for the buffer zone of rural bridges is 20 meters.

[0061] Step 102, performing multi-source data fusion, fusing the traffic network data with the civil navigation data through buffer zone analysis and geometric feature matching, and generating a fused comprehensive road network data set;

[0062] Fusion processing flow:

[0063] The algorithm for matching entities with the same name based on the geometric features of geographic elements is the most basic and most commonly used algorithm among all matching algorithms. The principle of using geometric features to match entities with the same name is to measure the similarity of one or several geometric features of geographic elements and use a preset threshold to determine whether they belong to geographic elements with the same name. The differences between different methods are mainly reflected in the selection of geometric features and matching units and the way to judge the similarity.

[0064] Road data fusion process:

[0065] The road network data of the same road is divided into several arcs. After data analysis, it is found that the arcs of dedicated road network data are longer than those of civil navigation data. In order to improve the accuracy of matching, four methods are used to match the arcs, and the intersection of the matching results is calculated.

[0066] (1) For different road levels, different buffer zones are established to traverse and match dedicated road network data and obtain the value A;

[0067] (2) Using the starting point of the civil navigation data line segment as a buffer, traverse and match the dedicated road network data and obtain the value B;

[0068] (3) Using the center point of the civil navigation data line segment as a buffer zone, traverse and match the dedicated road network data and obtain the value C;

[0069] (4) Matching the dedicated road network data with the end point of the civil navigation data segment as a buffer zone and obtaining a value D;

[0070] The values ​​obtained by the four types of analysis methods are intersected to obtain the final matching data, and the corresponding data details of the dedicated road network are extracted and updated to the navigation data set.

[0071] Bridge data fusion process:

[0072] For bridges, based on civil navigation data, the correspondence between line segments and bridge points is queried. Through function processing, multiple bridge points corresponding to the civil navigation line segments are stored in the format of "a, b, c..." to complete the fusion of civil navigation data bridge information.

[0073] Tunnel data fusion process:

[0074] For tunnels, based on civil navigation data, the correspondence between line segments and tunnel points is queried. Through function processing, multiple bridge points corresponding to civil navigation line segments are stored in the format of "a, b, c..." to complete the integration of civil navigation data tunnel information. The specific process is the same as that of bridges, so it will not be described here.

[0075] Implementation process of the road network data fusion pilot:

[0076] Data preparation:

[0077] The dedicated national road network data consists of the national highway "ROAD_GD", provincial highway "ROAD_SD", county highway "ROAD_X", township highway "ROAD_Y_par1, ROAD_Y_par2", town highway "ROAD_Z", rural highway "ROAD_Y_par1, ROAD_Y_par2, ROAD_Y_par3, ROAD_Y_par4, ROAD_Y_par5, ROAD_Y_par6" line datasets and the national and provincial highway bridges "QLP_GSD", rural bridges "QLP_NCGL", national and provincial highway tunnels "SDP_GSD" and rural tunnels "SDP_NCGL" point datasets.

[0078] The original file of civil data is MIF file. Through the project import function, MIF file is converted into udbx file, and topology preprocessing is performed. After preprocessing, two-dimensional network topology relationship is constructed to generate navigation data set. The navigation data table is named NetWork, which has 67 data attributes such as map sheet number.

[0079] Road network data coordinate system confirmation:

[0080] It is necessary to confirm that the coordinate systems of the traffic network data and the navigation data set are consistent. If they are inconsistent, the coordinate system conversion function in the project software is needed to convert the coordinate systems of the two to the same coordinate system to achieve data accuracy. The coordinate systems of the special data and civil navigation data in this project are both WGS84, so the coordinate system of the final fused map data is WGS84.

[0081] Road network data attribute reconstruction:

[0082] In order to meet the needs of data fusion, it is necessary to reconstruct the table structure of the civil road network data set and the traffic road network data set.

[0083] Dedicated road network data attribute reconstruction:

[0084] The road data in the road network includes national roads, provincial roads, county roads, township roads and town roads. The methods of reconstructing road data attributes are basically the same. This article takes the national road as an example to describe the attribute reconstruction.

[0085] The reconstruction of traffic network data mainly involves adding attribute fields and assigning attributes using corresponding algorithms. The attribute fields added to the dedicated road network data are arc start node (serial number 39), center point (serial number 40) and arc end node (serial number 41); the type is wide character and the length is set to 255. Taking the dedicated national highway attribute table ROAD_GD as an example, the attribute structure after reconstruction is shown in the following table:

[0086] National Highway Table Reconstruction Structure Table

[0087]

[0088]

[0089]

[0090] Civilian navigation road network data attribute reconstruction:

[0091] The reconstruction of the road network data table for civil navigation is divided into three parts, namely, adding road attribute content, adding bridge attribute content and adding tunnel attribute content.

[0092] The additional fields related to roads are the arc start node start_center, the center point center and the arc end node end_center; the dedicated road name road_name, the dedicated road grade dldj, the dedicated road surface net width lmjk, the dedicated route number lxbh and the dedicated arc id.

[0093] The bridge data in the road network include national and provincial highway bridges and rural bridges. The reconstruction of bridge data attributes is to add attribute fields in the civil navigation dataset, namely, national and provincial highway bridge name qlmc, national and provincial highway bridge code qlbm, national and provincial highway bridge deck net width qmjk, design load level code sjhzdjdm, technical condition assessment level jszkpddj, bridge id: jtb_smid, and belonging dataset qlsssjj (1: national and provincial highway bridge dataset; 2: rural bridge dataset; 3: national and provincial highway tunnel dataset; 4: rural tunnel dataset).

[0094] The newly added attribute fields of the civil navigation dataset are tunnel name sdmc, tunnel code sdbm, tunnel clear width sdjk, tunnel clear height sdjg, overall technical condition assessment ztjszkpd, tunnel id: jtb_sdid, and the dataset to which it belongs qlsssjj (1: national and provincial highway bridge dataset; 2: rural bridge dataset; 3: national and provincial highway tunnel dataset; 4: rural tunnel dataset). The reconstructed attribute structure is shown in the following table:

[0095] Network reconstruction structure table

[0096]

[0097]

[0098]

[0099]

[0100] Data fusion processing:

[0101] Road network data assignment:

[0102] Assignment of the extended fields of traffic network and civil navigation data, since the location information of the road network data is spatial vector data content, the project uses GIS software to calculate and assign values. The implementation method is to use the program to read the geographic information of each arc of the road network, call the function to obtain the longitude and latitude information of the arc, calculate and assign values ​​to the newly created three attribute fields (start_center, center point center and arc end node end_center).

[0103] Civilian navigation road network data assignment:

[0104] Navigation arc data assignment:

[0105] The assignment of the extended fields of civil navigation data is consistent with that of the traffic road network. Since the location information of the road network data is spatial vector data content, the project calculates and assigns values ​​through GIS software. The implementation method is to use the program to read the geographic information of each arc segment of the road network, call the function to obtain the longitude and latitude information of the arc segment, and calculate and assign values ​​to the newly created three attribute fields (start_center, center point center and arc segment end node end_center).

[0106] Road data assignment:

[0107] Data fusion is carried out according to the spatial function characteristics of POSTGIS, based on civil navigation data, and according to the road level corresponding to FUNCCLASS, special data is queried, and buffers are established for line segments, starting points, center points, and end points. The intersection of the three buffers is calculated to obtain the corresponding special data information; the fusion of the special data primary key (jtb-smid), road name (roadname), road level (dldj), road width (dlkd), and route number (lxbh) attributes is completed;

[0108] Data analysis is performed on the fused line data set. For the unfused data, a buffer is only established for the line segments to obtain dedicated corresponding data information, further improving the data fusion rate.

[0109] Bridge data assignment:

[0110] For bridges, based on civil navigation data, the correspondence between line segments and bridge points is queried. Through function processing, multiple bridge points corresponding to civil navigation line segments are stored in the format of "a, b, c...", and the special data bridge name (qlmc), bridge code (qlbm), bridge deck clear width (qmjk), special bridge primary key (jtb_qlid), bridge data set (qlsssjj), technical condition assessment level (jszkpddjdm), and design load level (sjhzdjdm) are completed.

[0111] Tunnel data assignment:

[0112] For tunnels, based on civil navigation data, the correspondence between line segments and tunnel points is queried. Through function processing, multiple bridge points corresponding to civil navigation line segments are stored in the format of "a, b, c...", and the dedicated data tunnel name (sdmc), tunnel code (sdbm), tunnel clear width (sdjk), tunnel clear height (sdjg), dedicated bridge primary key (jtb_sdid), tunnel data set (qlsssjj), technical status assessment level (jszkpddjdm), and design load level (sjhzdjdm) are completed.

[0113] Step 103, setting a path planning model, and using the comprehensive road network data set as a training set to train the path planning model, thereby completing path planning.

[0114] Specifically, the path planning model includes:

[0115]

[0116] in, is the vehicle navigation index, T total is the total travel time index, μ is the adjustment factor of the travel probability, P pass (s,t) is the passing probability at position s at time t.

[0117] Specifically, P pass (s, t) is the probability of passing at position s at time t, including:

[0118]

[0119] Where n is the number of roads, bridges or tunnels, σ is the Sigmoid function, and α i (t) is the first adjustment factor for the i-th road, bridge or tunnel, β i (t) is the second adjustment factor for the i-th road, bridge or tunnel, A ri (s, t) is the attribute value of the i-th road, bridge or tunnel at position s at time t. The attribute values ​​of the road, bridge or tunnel include the maximum load weight, height limit or width. vi is the i-th characteristic parameter of the vehicle, and the characteristic parameters include: vehicle weight, vehicle height, or vehicle width, δ is the buffer zone adjustment factor, B(s) is the buffer zone parameter at position s, ζ is the traffic flow adjustment factor, and κ(s, t) is the traffic flow at position s at time t.

[0120] Specifically, the total travel time index T total include:

[0121]

[0122] Where L is the total length of the route, V opt (s, t) is the optimal speed at position s at time t, ρ is the second adjustment factor of the total travel time index, τ is the first adjustment factor of the total travel time index, ω is the changing frequency of traffic signals, and ξ is the third adjustment factor of the total travel time index.

[0123] Specifically, obtain the minimized vehicle navigation index After that, the vehicle navigation index will be minimized The corresponding traffic network data and civil navigation data are displayed on the user terminal in the form of navigation.

[0124] Example 2

[0125] like Figure 2 As shown, an embodiment of the present invention further provides a vehicle navigation analysis system based on multimodal road network data, comprising:

[0126] A data acquisition module is used to acquire and preprocess multi-source road network data, wherein the multi-source road network data includes traffic road network data and civil navigation data, wherein the traffic road network data includes vector data of national roads, provincial roads, county roads, township roads and town roads, and the civil navigation data includes road topological structure and its related bridge and tunnel attribute data;

[0127] The data fusion module is used to fuse multi-source data. It fuses traffic network data with civil navigation data through buffer zone analysis and geometric feature matching to generate a fused comprehensive road network data set.

[0128] The path planning module is used to set a path planning model and use the comprehensive road network data set as a training set to train the path planning model, thereby completing path planning.

[0129] Specifically, the path planning model includes:

[0130]

[0131] in, is the vehicle navigation index, T total is the total travel time index, μ is the adjustment factor of the travel probability, P pass (s, t) is the passing probability at position a at time r.

[0132] Specifically, P pass (s, t) is the probability of passing at position s at time t, including:

[0133]

[0134] Where n is the number of roads, bridges or tunnels, σ is the Sigmoid function, and α i (t) is the first adjustment factor for the i-th road, bridge or tunnel, β i (t) is the second adjustment factor for the i-th section of road, bridge or tunnel, A ri (s, t) is the attribute value of the i-th road, bridge or tunnel at position s at time t. The attribute values ​​of the road, bridge or tunnel include the maximum load weight, height limit or width. viis the i-th characteristic parameter of the vehicle, and the characteristic parameters include: vehicle weight, vehicle height, or vehicle width, δ is the buffer zone adjustment factor, B(s) is the buffer zone parameter at position s, ζ is the traffic flow adjustment factor, and κ(s, t) is the traffic flow at position s at time t.

[0135] Specifically, the total travel time index T toal include:

[0136]

[0137] Where L is the total length of the route, V opt (s, t) is the optimal speed at position a at time t, ρ is the second adjustment factor of the total travel time index, τ is the first adjustment factor of the total travel time index, ω is the changing frequency of traffic signals, and ξ is the third adjustment factor of the total travel time index.

[0138] Specifically, obtain the minimized vehicle navigation index After that, the vehicle navigation index will be minimized The corresponding traffic network data and civil navigation data are displayed on the user terminal in the form of navigation.

[0139] Example 3

[0140] The embodiment of the present invention further proposes a storage medium storing a plurality of instructions, wherein the instructions are used to implement the vehicle navigation analysis method based on multimodal road network data.

[0141] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0142] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps: Step 101, acquiring and preprocessing multi-source road network data, wherein the multi-source road network data includes traffic road network data and civil navigation data, wherein the traffic road network data includes vector data of national roads, provincial roads, county roads, township roads and town roads, and the civil navigation data includes road topology and its related bridge and tunnel attribute data;

[0143] Step 102, performing multi-source data fusion, fusing the traffic network data with the civil navigation data through buffer zone analysis and geometric feature matching, and generating a fused comprehensive road network data set;

[0144] Step 103, setting a path planning model, and using the comprehensive road network data set as a training set to train the path planning model, thereby completing path planning.

[0145] Specifically, the path planning model includes:

[0146]

[0147] in, is the vehicle navigation index, T total is the total travel time index, μ is the adjustment factor of the travel probability, P pass (s, t) is the passing probability at position s at time t.

[0148] Specifically, P pass (s, t) is the probability of passing at position s at time t, including:

[0149]

[0150] Where n is the number of roads, bridges or tunnels, σ is the Sigmoid function, and α i (t) is the first adjustment factor for the i-th road, bridge or tunnel, β i (t) is the second adjustment factor for the i-th road, bridge or tunnel, A ri (s, t) is the attribute value of the i-th road, bridge or tunnel at position s at time t. The attribute values ​​of the road, bridge or tunnel include the maximum load weight, height limit or width. vi is the i-th characteristic parameter of the vehicle, and the characteristic parameters include: vehicle weight, vehicle height, or vehicle width, δ is the buffer zone adjustment factor, B(s) is the buffer zone parameter at position s, ζ is the traffic flow adjustment factor, and κ(s, t) is the traffic flow at position s at time t.

[0151] Specifically, the total travel time index T total include:

[0152]

[0153] Where L is the total length of the route, V opt (s, t) is the optimal speed at position s at time t, ρ is the second adjustment factor of the total travel time index, τ is the first adjustment factor of the total travel time index, ω is the changing frequency of traffic signals, and ξ is the third adjustment factor of the total travel time index.

[0154] Specifically, obtain the minimized vehicle navigation index After that, the vehicle navigation index will be minimized The corresponding traffic network data and civil navigation data are displayed on the user terminal in the form of navigation.

[0155] Example 4

[0156] An embodiment of the present invention also proposes an electronic device, including a processor and a storage medium connected to the processor, wherein the storage medium stores multiple instructions, and the instructions can be loaded and executed by the processor to enable the processor to execute the vehicle navigation analysis method based on multimodal road network data.

[0157] Specifically, the electronic device of this embodiment may be a computer terminal, and the computer terminal may include: one or more processors, and a storage medium.

[0158] Among them, the storage medium can be used to store software programs and modules, such as a vehicle navigation analysis method based on multimodal road network data in an embodiment of the present invention, and the corresponding program instructions / modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium, that is, realizing the above-mentioned vehicle navigation analysis method based on multimodal road network data. The storage medium may include a high-speed random storage medium, and may also include a non-volatile storage medium, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include a storage medium remotely arranged relative to the processor, and these remote storage media may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0159] The processor can call the information and application program stored in the storage medium through the transmission system to perform the following steps: Step 101, acquiring and preprocessing multi-source road network data, wherein the multi-source road network data includes traffic road network data and civil navigation data, wherein the traffic road network data includes vector data of national roads, provincial roads, county roads, township roads and town roads, and the civil navigation data includes road topological structure and its related bridge and tunnel attribute data;

[0160] Step 102, performing multi-source data fusion, fusing the traffic network data with the civil navigation data through buffer zone analysis and geometric feature matching, and generating a fused comprehensive road network data set;

[0161] Step 103, setting a path planning model, and using the comprehensive road network data set as a training set to train the path planning model, thereby completing path planning.

[0162] Specifically, the path planning model includes:

[0163]

[0164] in, is the vehicle navigation index, T total is the total travel time index, μ is the adjustment factor of the travel probability, P pass(s,t) is the passing probability at position s at time t.

[0165] Specifically, P pass (s, t) is the probability of passing at position s at time t, including:

[0166]

[0167] Where n is the number of roads, bridges or tunnels, σ is the Sigmoid function, and α i (t) is the first adjustment factor for the i-th road, bridge or tunnel, β i (t) is the second adjustment factor for the i-th section of road, bridge or tunnel, A ri (s, t) is the attribute value of the i-th road, bridge or tunnel at position s at time t. The attribute values ​​of the road, bridge or tunnel include the maximum load weight, height limit or width. vi is the i-th characteristic parameter of the vehicle, and the characteristic parameters include: vehicle weight, vehicle height, or vehicle width, δ is the buffer zone adjustment factor, B(s) is the buffer zone parameter at position s, ζ is the traffic flow adjustment factor, and κ(s, t) is the traffic flow at position s at time t.

[0168] Specifically, the total travel time index T total include:

[0169]

[0170] Where L is the total length of the route, V opt (s, t) is the optimal speed at position s at time t, ρ is the second adjustment factor of the total travel time index, τ is the first adjustment factor of the total travel time index, ω is the changing frequency of traffic signals, and ξ is the third adjustment factor of the total travel time index.

[0171] Specifically, obtain the minimized vehicle navigation index After that, the vehicle navigation index will be minimized The corresponding traffic network data and civil navigation data are displayed on the user terminal in the form of navigation.

[0172] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0173] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0174] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0175] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0176] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0177] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only storage medium (ROM, Read-Only Memory), random access storage medium (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0178] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. A vehicle navigation analysis method based on multimodal road network data, characterized in that: include: Acquire and preprocess multi-source road network data, wherein the multi-source road network data includes traffic road network data and civil navigation data, wherein the traffic road network data includes vector data of national roads, provincial roads, county roads, township roads and town roads, and the civil navigation data includes road topological structure and its related bridge and tunnel attribute data; Carry out multi-source data fusion, integrate traffic network data with civil navigation data through buffer zone analysis and geometric feature matching, and generate a fused comprehensive road network data set; A path planning model is set, and the comprehensive road network data set is used as a training set to train the path planning model, thereby completing path planning.

2. A vehicle navigation analysis method based on multimodal road network data as claimed in claim 1, characterized in that: The path planning model includes: in, is the vehicle navigation index, T total is the total travel time index, μ is the adjustment factor of the travel probability, P pass (s, t) is the passing probability at position s at time t.

3. A vehicle navigation analysis method based on multimodal road network data as claimed in claim 2, characterized in that: P pass (s, t) is the probability of passing at position s at time t, including: Where n is the number of roads, bridges or tunnels, σ is the Sigmoid function, and α i (t) is the first adjustment factor for the i-th section of road, bridge or tunnel, β i (t) is the second adjustment factor for the i-th road, bridge or tunnel, A ri (s, t) is the attribute value of the i-th road, bridge or tunnel at position s at time t. The attribute values ​​of the road, bridge or tunnel include the maximum load weight, height limit or width. vi is the i-th characteristic parameter of the vehicle, and the characteristic parameters include: vehicle weight, vehicle height, or vehicle width, δ is the buffer zone adjustment factor, B(s) is the buffer zone parameter at position s, ζ is the traffic flow adjustment factor, and κ(s, t) is the traffic flow at position s at time t.

4. The vehicle navigation analysis method based on multimodal road network data as claimed in claim 3, characterized in that: Total driving time index T total include: Where L is the total length of the route, V opt (s, t) is the optimal speed at position s at time t, ρ is the second adjustment factor of the total travel time index, τ is the first adjustment factor of the total travel time index, ω is the changing frequency of traffic signals, and ξ is the third adjustment factor of the total travel time index.

5. The vehicle navigation analysis method based on multimodal road network data according to claim 4, characterized in that: Get the minimized vehicle navigation index After that, the vehicle navigation index will be minimized The corresponding traffic network data and civil navigation data are displayed on the user terminal in the form of navigation.

6. A vehicle navigation analysis system based on multimodal road network data, characterized in that: include: A data acquisition module is used to acquire and preprocess multi-source road network data, wherein the multi-source road network data includes traffic road network data and civil navigation data, wherein the traffic road network data includes vector data of national roads, provincial roads, county roads, township roads and town roads, and the civil navigation data includes road topological structure and its related bridge and tunnel attribute data; The data fusion module is used to fuse multi-source data. It fuses traffic network data with civil navigation data through buffer zone analysis and geometric feature matching to generate a fused comprehensive road network data set. The path planning module is used to set a path planning model and use the comprehensive road network data set as a training set to train the path planning model, thereby completing path planning.

7. A vehicle navigation analysis system based on multimodal road network data as claimed in claim 6, characterized in that: The path planning model includes: in, is the vehicle navigation index, T total is the total travel time index, μ is the adjustment factor of the travel probability, P pass (s, t) is the passing probability at position s at time t.

8. The vehicle navigation analysis system based on multimodal road network data as claimed in claim 7, characterized in that: P pass (s, t) is the probability of passing at position s at time t, including: Where n is the number of roads, bridges or tunnels, σ is the Sigmoid function, and α i (t) is the first adjustment factor for the i-th section of road, bridge or tunnel, β i (t) is the second adjustment factor for the i-th road, bridge or tunnel, A ri (s, t) is the attribute value of the i-th road, bridge or tunnel at position s at time t. The attribute values ​​of the road, bridge or tunnel include the maximum load weight, height limit or width. vi is the i-th characteristic parameter of the vehicle, and the characteristic parameters include: vehicle weight, vehicle height, or vehicle width, δ is the buffer zone adjustment factor, B(s) is the buffer zone parameter at position s, ζ is the traffic flow adjustment factor, and κ(s, t) is the traffic flow at position s at time t.

9. A vehicle navigation analysis system based on multimodal road network data as claimed in claim 8, characterized in that: Total driving time index T total include: Where L is the total length of the route, V opt (s, t) is the optimal speed at position s at time t, ρ is the second adjustment factor of the total travel time index, τ is the first adjustment factor of the total travel time index, ω is the changing frequency of traffic signals, and ξ is the third adjustment factor of the total travel time index.

10. A vehicle navigation analysis system based on multimodal road network data as claimed in claim 9, characterized in that: Get the minimized vehicle navigation index After that, the vehicle navigation index will be minimized The corresponding traffic network data and civil navigation data are displayed on the user terminal in the form of navigation.

Images