Road congestion evaluation method based on new energy automobile network connection big data

Abstract

The invention provides a road congestion evaluation method based on new energy automobile network connection big data, and the method comprises the steps: obtaining the real-time operation data of a new energy automobile, carrying out the preprocessing of the real-time operation data of the new energy automobile, and obtaining a vehicle basic information table; acquiring urban road network data, and analyzing the urban road network data to obtain a road network information table; obtaining a vehicle-road matching relation information table according to the vehicle operation table and the road network information table; obtaining road congestion evaluation information according to the vehicle-road matching relation information table; and obtaining a congestion analysis result according to the road congestion evaluation information. According to the invention, the Internet of Vehicles data and the urban road network data can be obtained, the diversity and real-time performance of the data are ensured, the road congestion condition can be evaluated and predicted more accurately, and more accurate traffic flow prediction and congestion early warning are provided. The evaluation and prediction precision is improved, and the intelligent and informatization level of urban traffic management can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic business evaluation, and in particular to a method for evaluating road congestion based on new energy vehicle network big data. Background Art

[0002] Big data has achieved a lot in traffic management. It can collect and process a large amount of traffic data in real time, including vehicle flow, road conditions, traffic congestion, accident information, etc. It can analyze the real-time traffic flow and traffic congestion on the road, intelligently adjust the timing of traffic lights, and improve road traffic efficiency. At the same time, combined with artificial intelligence algorithms, traffic data can be deeply mined and analyzed to achieve traffic safety risk warning. For example, by analyzing historical accident data and real-time traffic data, it is possible to predict the location and time of an accident, and take corresponding measures in time to ensure traffic safety.

[0003] In the transportation industry, there are many methods for evaluating transportation services. For example, map manufacturers collect user data information through map navigation data, road management departments collect vehicle passing information through gantries, toll gate RFID and other locations, and operating vehicle management departments collect operating vehicle operation information through after-sales equipment. These solutions can help the construction of transportation informatization to a certain extent, but there are problems such as low road coverage, only data can be collected at fixed points, and after-sales equipment is manually disassembled. Summary of the invention

[0004] Based on this, it is necessary to provide a method for road congestion evaluation based on new energy vehicle network big data to address the above technical problems.

[0005] A method for evaluating road congestion based on new energy vehicle network big data includes the following steps:

[0006] Acquire the real-time operation data of the new energy vehicle, pre-process the real-time operation data of the new energy vehicle, and obtain a vehicle basic information table; wherein the vehicle basic information table includes: vehicle ID, vehicle model, vehicle type and coordinate system;

[0007] Acquire urban road network data, parse and process the urban road network data, and obtain a road network information table; wherein the road network information table includes: section ID, section name, name of the road to which it belongs, road ID, road grade, section length, one-way street sign, section sign point sequence number, sign point latitude and longitude, section start number, section end node number, city and district;

[0008] A vehicle-road matching relationship information table is obtained according to the vehicle operation table and the road network information table; wherein the vehicle-road matching relationship information table includes: a relationship between a vehicle driving position and a road network;

[0009] Obtaining road congestion evaluation information according to the vehicle-road matching relationship information table;

[0010] A congestion analysis result is obtained according to the road congestion evaluation information.

[0011] In one embodiment, before obtaining the congestion analysis result according to the road congestion evaluation information, the method further includes:

[0012] The future road speed is obtained according to the vehicle-road matching relationship information table, and the future road congestion evaluation information is obtained according to the future.

[0013] In one embodiment, obtaining the future road speed according to the vehicle-road matching relationship information table, and obtaining the future road congestion evaluation information according to the future includes:

[0014] Establish vehicle prediction autoregressive difference moving average model;

[0015] Acquire the historical vehicle speed of the road according to the vehicle-road matching relationship information table, and obtain the future vehicle speed of the road according to the historical vehicle speed of the road through a vehicle prediction autoregressive difference moving average model;

[0016] Calculating the future average speed and the future quantile speed according to the future road speed;

[0017] According to the future average vehicle speed and the future quantile vehicle speed, the future road congestion evaluation information is obtained according to a preset traffic operation status level classification table.

[0018] In one embodiment, real-time operation data of new energy vehicles is obtained, and the real-time operation data of new energy vehicles is preprocessed to obtain a vehicle basic information table including:

[0019] The real-time operation data of new energy vehicles is obtained, and data is extracted and cleaned for the real-time operation data of new energy vehicles, and matched with administrative division boundaries to obtain a target city vehicle driving data list; wherein the target city vehicle driving data list includes: vehicle ID, timestamp, vehicle driving latitude and longitude, vehicle speed and vehicle cumulative mileage;

[0020] The basic vehicle information is collected and managed through the target city vehicle driving data list to obtain a vehicle basic information table.

[0021] In one embodiment, obtaining urban road network data, parsing and processing the urban road network data, and obtaining a road network information table includes:

[0022] Acquire urban road network data, parse and process the urban road network data, and insert identification points based on the distances of road identification points to obtain a road network information table.

[0023] In one embodiment, obtaining the vehicle-road matching relationship information table according to the vehicle operation table and the road network information table includes:

[0024] Obtaining an initial vehicle-road matching result relationship information table according to the vehicle operation table and the road network information table;

[0025] Deduplication processing is performed on the vehicle-road initial matching result relationship information table to obtain an optimized vehicle-road initial matching relationship information table;

[0026] According to the optimized vehicle-road initial matching relationship information table, the matching accuracy is improved through a graph shortest path search algorithm to obtain a vehicle-road matching relationship information table.

[0027] In one embodiment, obtaining the vehicle-road initial matching result relationship information table according to the vehicle operation table and the road network information table includes:

[0028] The vehicle running longitude and latitude are obtained through the vehicle running table, and the vehicle running longitude and latitude are matched with the honeycomb polygon algorithm H3 to obtain the vehicle running H3 grid:

[0029] vehicle{longitude,latitude}→H3 index

[0030] Among them, vehicle{} represents the vehicle, longitude represents the longitude of the vehicle, latitude represents the latitude of the vehicle, and H3index represents the hexagonal code of the vehicle;

[0031] The longitude and latitude of the identification point are obtained through the road network information table, and the longitude and latitude of the identification point are matched with the honeycomb polygon algorithm H3 to obtain the identification point H3 grid:

[0032] path{longitude ′ ,latitude ′}→H3 index ′

[0033] Among them, path{} represents the identification point, longitude ′ Indicates the longitude of the identification point, latitude ′ Indicates the latitude of the marker point, and H3 index indicates the hexagonal code of the marker point;

[0034] The vehicle travel H3 grid and the identification point H3 grid are matched to obtain the vehicle-road initial matching result relationship information table:

[0035] vehicle{longitude,latitude}→path{longitude ′ ,latitude ′}

[0036] Among them, vehicle{} represents the vehicle, longitude represents the longitude of the vehicle, latitude represents the latitude of the vehicle, path{} represents the identification point, longitude ′ Indicates the longitude of the identification point, latitude ′ Indicates the latitude of the marker point.

[0037] In one embodiment, deduplication processing is performed on the vehicle-road initial matching result relationship information table to obtain an optimized vehicle-road initial matching relationship information table, which includes:

[0038] Get the serial number list corresponding to all driving points of the vehicle in the Ith period and the I+1th period of the preset specific road section:

[0039] serial={serial 1 ,serial 2 ,serial 3 ,…,serial n}

[0040] Among them, serial represents a serial number list, serial n Indicates the sequence number corresponding to the nth driving point;

[0041] The sequence number difference is calculated based on the sequence number list:

[0042]

[0043] in, Indicates the serial number difference, serial t+1 Indicates the serial number at time t+1, serial t Indicates the sequence number at time t;

[0044] According to the sequence number difference, data is deleted according to the preset deduplication requirement to obtain an optimized vehicle-road initial matching relationship information table.

[0045] In one embodiment, the matching accuracy is improved by using a graph shortest path search algorithm according to the optimized vehicle-road initial matching relationship information table, and the vehicle-road matching relationship information table obtained includes:

[0046] Establishing a road network data directed graph according to the optimized vehicle-road initial matching relationship information table;

[0047] Obtaining a matching starting point and a matching end point of a vehicle driving trajectory according to the road network data directed graph;

[0048] The shortest path between the starting point and the ending point is established according to the matching starting point and the matching ending point through a graph shortest path search algorithm to obtain a vehicle-road matching relationship information table.

[0049] In one embodiment, obtaining the road congestion evaluation information according to the vehicle-road matching relationship information table includes:

[0050] According to the vehicle-road matching relationship information table, the driving time is divided into several time periods according to the preset time window;

[0051] Obtaining the vehicle speed within a time period, and calculating the average vehicle speed and the quantile vehicle speed according to the vehicle speed;

[0052] According to the average vehicle speed and the quantile vehicle speed, the traffic operation status level classification table is used to classify the traffic congestion in the future, so as to obtain the evaluation information of the road congestion in the future.

[0053] Compared with the prior art, the advantages and beneficial effects of the present invention are: the present invention can obtain vehicle network data and urban road network data, ensure the diversity and real-time nature of the data, help to more accurately evaluate and predict road congestion, and provide more accurate traffic flow prediction and congestion warning. It can recommend the best driving route based on the user's travel habits and real-time traffic conditions, and provide real-time road condition information and predicted arrival time.

[0054] The road congestion evaluation and prediction method based on the big data of new energy vehicle network has the advantages of data acquisition diversity and real-time, multi-source data fusion analysis, and improved evaluation and prediction accuracy, which helps to improve the intelligence and informatization level of urban traffic management. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A schematic diagram of a process of a method for evaluating road congestion based on new energy vehicle network big data in one embodiment;

[0056] Figure 2 A schematic diagram of road marking point numbering in one embodiment;

[0057] Figure 3 A schematic diagram of hierarchical division in an embodiment;

[0058] Figure 4 Schematic diagram of the relationship between vehicle position and H3 matching in one embodiment. DETAILED DESCRIPTION

[0059] Before describing the specific embodiments of the present invention, the overall concept of the present invention is described as follows:

[0060] The present invention is mainly developed for the process of traffic management. The current traffic evaluation scheme can help the construction of traffic informatization to a certain extent, but it still has problems such as low road coverage, data can only be collected at fixed points, and post-installed equipment is manually disassembled.

[0061] Therefore, the present invention proposes a method for evaluating road congestion based on the big data of new energy vehicle network connection. First, the new energy vehicle network data and the urban road network data are obtained, and the vehicle-road matching relationship information table is obtained according to the new energy vehicle network data and the urban road network data. Then, the vehicle speed of each time slice of the road section is obtained according to the vehicle-road matching relationship information table, and the road congestion is further judged. Then, based on the vehicle speed of each time slice of the road section, the future road speed and congestion are predicted through the autoregressive difference moving average model.

[0062] After introducing the overall concept of the present invention, in order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below through specific implementation methods in conjunction with the accompanying drawings.

[0063] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in one or more embodiments of this specification should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in one or more embodiments of this specification do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0064] In one embodiment, Figure 1 As shown, a method for evaluating road congestion based on new energy vehicle network big data is provided, comprising the following steps:

[0065] Step S101, acquiring real-time operation data of new energy vehicles, preprocessing the real-time operation data of new energy vehicles, and obtaining a vehicle basic information table; wherein the vehicle basic information table includes: vehicle ID, vehicle model, vehicle type and coordinate system.

[0066] On this basis, the real-time operation data of the new energy vehicle is obtained, and the real-time operation data of the new energy vehicle is preprocessed to obtain the vehicle basic information table including:

[0067] Acquire the real-time operation data of new energy vehicles, extract and clean the real-time operation data of new energy vehicles, and match it with the administrative division boundaries to obtain a target city vehicle driving data list; wherein the target city vehicle driving data list includes: vehicle ID, timestamp, vehicle driving latitude and longitude, vehicle speed and vehicle cumulative mileage;

[0068] The basic vehicle information is collected and managed through the target city vehicle driving data list to obtain a vehicle basic information table.

[0069] Specifically, the real-time operation data of new energy vehicles is collected from the new energy vehicle Internet of Vehicles platform through the data collection program, and the message data stream is formed through decompression and decryption processes, and further data extraction and cleaning are carried out, and the data is matched with the administrative division boundaries to obtain the target city vehicle driving data list; through the collection and management of vehicle basic information, the vehicle basic information table is obtained. The vehicle driving data list includes vehicle id, timestamp, vehicle driving latitude and longitude, vehicle speed, and vehicle cumulative mileage; the vehicle basic information table includes vehicle id, vehicle model, vehicle type, and coordinate system.

[0070] Step S102, obtain urban road network data, parse and process the urban road network data, and obtain a road network information table; wherein the road network information table includes: section ID, section name, name of the road to which it belongs, road ID, road grade, section length, one-way street sign, section identification point sequence number, identification point longitude and latitude, section start number, section end node number, city and district / county.

[0071] On this basis, the urban road network data is obtained, and the urban road network data is parsed and processed to obtain a road network information table including:

[0072] Acquire urban road network data, parse and process the urban road network data, and insert identification points based on the distances of road identification points to obtain a road network information table.

[0073] Specifically, the urban road network data and traffic zone vector data files are parsed and processed, including format conversion, key indicator extraction, coordinate list conversion, road direction verification and other processes, and identification points are further inserted based on the distance of road identification points to obtain a road network information table.

[0074] The road network information table includes the road section ID, road section name, road name, road ID, road grade, road section length, one-way street sign, road section identification point sequence number, identification point latitude and longitude, road section start node number, road section end node number, city, and district / county.

[0075] Step S103, obtaining a vehicle-road matching relationship information table according to the vehicle operation table and the road network information table; wherein the vehicle-road matching relationship information table includes: the relationship between the vehicle driving position and the road network.

[0076] Specifically, the vehicle operation table of the new energy vehicle operation data and the road network information table of the urban road network data are matched with the spatial grid respectively, and duplicate data and useless data are cleared to obtain a vehicle-road matching relationship information table.

[0077] On this basis, the vehicle-road matching relationship information table obtained according to the vehicle operation table and the road network information table includes:

[0078] Obtaining a vehicle-road initial matching result relationship information table according to the vehicle operation table and the road network information table;

[0079] Deduplication processing is performed on the vehicle-road initial matching result relationship information table to obtain an optimized vehicle-road initial matching relationship information table;

[0080] According to the optimized vehicle-road initial matching relationship information table, the matching accuracy is improved through a graph shortest path search algorithm to obtain a vehicle-road matching relationship information table.

[0081] Specifically, firstly, the vehicle operation table of the new energy vehicle operation data and the road network information table of the urban road network data are matched with the spatial grid respectively to obtain an initial vehicle-road matching relationship information table indicating the vehicle-road initial matching relationship information.

[0082] Then, the road direction is determined based on the sequence relationship of the road key points to optimize the initial vehicle-road matching relationship information table, and the optimized vehicle-road initial matching relationship information table is obtained.

[0083] Finally, the vehicle-road matching relationship information table is further optimized according to the graph shortest path search algorithm to further improve the matching accuracy and obtain the vehicle-road matching relationship information table.

[0084] On this basis, the vehicle-road initial matching result relationship information table is obtained according to the vehicle operation table and the road network information table, including:

[0085] The vehicle running longitude and latitude are obtained through the vehicle running table, and the vehicle running longitude and latitude are matched with the honeycomb polygon algorithm H3 to obtain the vehicle running H3 grid:

[0086] vehicle{longitude,latitude}→H3 index

[0087] Among them, vehicle{} represents the vehicle, longitude represents the longitude of the vehicle, latitude represents the latitude of the vehicle, and H3index represents the hexagonal code of the vehicle;

[0088] The longitude and latitude of the identification point are obtained through the road network information table, and the longitude and latitude of the identification point are matched with the honeycomb polygon algorithm H3 to obtain the identification point H3 grid:

[0089] path{longitude ′ ,latitude ′}→H3 index ′

[0090] Among them, path{} represents the identification point, longitude ′ Indicates the longitude of the identification point, latitude ′ Indicates the latitude of the marker point, and H3 index indicates the hexagonal code of the marker point;

[0091] The vehicle travel H3 grid and the identification point H3 grid are matched to obtain the vehicle-road initial matching result relationship information table:

[0092] vehicle{longitude,latitude}→path{longitude ′ ,latitude ′}

[0093] Among them, vehicle{} represents the vehicle, longitude represents the longitude of the vehicle, latitude represents the latitude of the vehicle, path{} represents the identification point, longitude ′ Indicates the longitude of the identification point, latitude ′ Indicates the latitude of the marker point.

[0094] Specifically, the road section identification point number is as follows: Figure 2 As shown, the vehicle driving longitude and latitude in the vehicle driving data list are matched with the cellular polygon algorithm H3, the relationship between the vehicle driving position and the gateway is established, and the vehicle driving H3 grid where the vehicle driving position is located is obtained:

[0095] vehicle{longitude,latitude}→H3 index

[0096] Level selection level = 12, H3 level division is as follows Figure 3 shown.

[0097] Match the longitude and latitude of the road section identification point in the road network information table with the honeycomb polygon algorithm H3, establish the relationship between the road network and the grid, and obtain the identification point H3 grid where the road network identification point is located:

[0098] path{longitude ′,latitude ′}→H3 index ′

[0099] Furthermore, the vehicle travel H3 grid is matched with the identification point H3 grid, and the relationship between the vehicle travel position and the road network is preliminarily obtained, forming a vehicle-road initial matching result relationship information table representing the vehicle-road initial matching result relationship information:

[0100] vehicle{longitude,latitude}→path{longitude ′ ,latitude ′}

[0101] On this basis, the vehicle-road initial matching result relationship information table is deduplicated to obtain an optimized vehicle-road initial matching relationship information table including:

[0102] Get the serial number list corresponding to all driving points of the vehicle in the Ith period and the I+1th period of the preset specific road section:

[0103] serial={serial 1 ,serial 2 ,serial 3 ,…,serial n}

[0104] Among them, serial represents a serial number list, serial n Indicates the sequence number corresponding to the nth driving point;

[0105] The sequence number difference is calculated based on the sequence number list:

[0106]

[0107] in, Indicates the serial number difference, serial t+1 Indicates the serial number at time t+1, serial t Indicates the sequence number at time t;

[0108] According to the sequence number difference, data is deleted according to the preset deduplication requirement to obtain an optimized vehicle-road initial matching relationship information table.

[0109] Specifically, the matching result relationship of the vehicle-road initial matching result relationship information table is a one-to-many relationship between the vehicle driving position and the road network, and a deduplication operation needs to be performed on multiple consecutive points driving on the same road section.

[0110] Get the vehicle V on the road section L at time t i+1 of and t iList of serial numbers corresponding to all trajectory points of all driving within the range:

[0111] serial={serial 1 ,serial 2 ,serial 3 ,…,serial n}

[0112] like Figure 4 As shown, the time t i+1 The point and t i Subtract the serial numbers of the same section of points:

[0113]

[0114] According to the direction of vehicle movement, the specific deduplication requirement is: Indicates that the vehicle is driving in the opposite direction, and the relevant points are deleted from the matching relationship list; if If it is normal data, the relevant results are retained in the matching relationship list to obtain the optimized vehicle-road initial matching relationship information table.

[0115] On this basis, the matching accuracy is improved by using the graph shortest path search algorithm according to the optimized vehicle-road initial matching relationship information table, and the vehicle-road matching relationship information table obtained includes:

[0116] Establishing a road network data directed graph according to the optimized vehicle-road initial matching relationship information table;

[0117] Obtaining a matching starting point and a matching end point of a vehicle driving trajectory according to the road network data directed graph;

[0118] The shortest path between the starting point and the ending point is established according to the matching starting point and the matching ending point through a graph shortest path search algorithm to obtain a vehicle-road matching relationship information table.

[0119] Specifically, extract the road segment ID, the starting node number of the road segment, the ending node number of the road segment, and the length of the road segment from the road network information table to establish a directed graph of road network data:

[0120] G=(V,E)

[0121] Among them, the starting node of the segment is the starting point of the directed edge, the ending node of the segment is the ending point of the directed edge, and the length of the segment is the length of the directed edge.

[0122] For a vehicle’s driving trajectory, find the unique matching point P 1 and P 2 , with P 1 The starting node number of the road segment corresponding to the point is used as the starting point (matching starting point), with P2 The end node of the corresponding road segment is used as the end point (matching end point), and the shortest path between the start point and the end point is established through the following steps:

[0123] initialization:

[0124] Set the starting point: Select the starting point s in the graph as the source point for calculating the shortest path to all other points;

[0125] Initialize the distance table: for each vertex v in the graph, set a distance value dist v , represents the current shortest path length from s to v. Initially, dist v Set to 0, for all other vertices v, dist v Set to infinity (∞), indicating that these points are temporarily unreachable;

[0126] Set the visited set: Create an empty set visited to store the vertices for which the shortest path has been found;

[0127] Algorithm process:

[0128] Select the vertex with the shortest distance: Select the vertex u with the shortest distance from the unvisited vertices and add it to the set visited;

[0129] Update the distance of adjacent points: For each adjacent point v of vertex u, calculate the length of the path from u to v (i.e., dist u + weight of the edge from u to v), if this value is less than dist v , then update dist v For this smaller value;

[0130] Repeat the above two steps until the visited set contains all the vertices in the graph.

[0131] Step S104, obtaining road congestion evaluation information according to the vehicle-road matching relationship information table.

[0132] Specifically, the vehicle speed at each time slice of the road section is calculated, and the road congestion situation is further determined to obtain road congestion evaluation information.

[0133] On this basis, the road congestion evaluation information obtained according to the vehicle-road matching relationship information table includes:

[0134] According to the vehicle-road matching relationship information table, the driving time is divided into several time periods according to the preset time window;

[0135] Obtaining the vehicle speed within a time period, and calculating the average vehicle speed and the quantile vehicle speed according to the vehicle speed;

[0136] According to the average vehicle speed and the quantile vehicle speed, the traffic operation status level classification table is used to classify the traffic congestion in the future, so as to obtain the evaluation information of the road congestion in the future.

[0137] Specifically, according to the vehicle-road matching relationship information table, the preset time window size of the target analysis is set to T, and the time is divided into sequences:

[0138] T={t 1 ,t 2 ,t 3 ,…,t n}

[0139] At time t i and t i+1 All vehicles falling into a certain road section are taken as target samples, and the corresponding vehicle speed list is obtained:

[0140] V={v 1 ,v 2 ,v 3 ,…,v n}

[0141] For the original vehicle speed, calculate the corresponding average speed and α quantile speed:

[0142] P{V≥v α}=α

[0143] Compare the average speed and the α-quantile speed with the preset traffic operation status classification table in Table 1 below to obtain the time t i and t i+1 The traffic congestion level of road L in the corresponding time window.

[0144]

[0145] Table 1 Preset traffic operation status classification table

[0146] On this basis, before obtaining the congestion analysis result according to the road congestion evaluation information, the method further includes:

[0147] The future road speed is obtained according to the vehicle-road matching relationship information table, and the future road congestion evaluation information is obtained according to the future.

[0148] Specifically, based on the historical speed information of the road, the future road speed and congestion are predicted. Road congestion has obvious time series characteristics, and the future speed can be predicted based on the historical speed of the road.

[0149] On this basis, the future road speed is obtained according to the vehicle-road matching relationship information table, and the future road congestion evaluation information obtained according to the future includes:

[0150] Establish vehicle prediction autoregressive difference moving average model;

[0151] Acquire the historical vehicle speed of the road according to the vehicle-road matching relationship information table, and obtain the future vehicle speed of the road according to the historical vehicle speed of the road through a vehicle prediction autoregressive difference moving average model;

[0152] Calculating the future average speed and the future quantile speed according to the future road speed;

[0153] According to the future average vehicle speed and the future quantile vehicle speed, the future road congestion evaluation information is obtained according to a preset traffic operation status level classification table.

[0154] Specifically, a vehicle prediction autoregressive difference moving average model is established, using the autoregressive difference moving average model, namely the ARIMA (p, d, q) model, where p is the lagged value of the observation value, that is, the observation value is a linear combination of the previous p values, d is the model difference order, and q is the number of white noises backtracking the current value;

[0155] The general formula of the model is:

[0156]

[0157] Where: Y t is the time series of the target analysis; arrive is the parameter of the AR model, which is used to describe the relationship between the current value and the values ​​at p time points in the past; θ 1 to θ q is the parameter of the MA model, which is used to describe the relationship between the error between the current value and the value at the past q time points; ε t is the error term at time point t; c is a constant term.

[0158] The modeling is done through the following steps:

[0159] S1: Import the vehicle speed information of the road section in each period of the past month and divide it into training set and test set;

[0160] S2: Stationarity test, using ADF to test whether the time series has a unit root, that is, based on the following three scenarios, if the significance p value is <0.05, it is significant at the level, indicating that it is a stationary time series;

[0161] Formula 1:

[0162] Formula 2

[0163] Formula 3:

[0164] Where ΔX t Represents X t The first-order difference value of , δ represents the parameter to be estimated, X t-1 represents the observed value (time series) at time point t-1, ΔX t-i represents the first-order difference value at time point ti, m represents the model difference order, α represents the constant term, βt represents the time trend term, ε t represents the random disturbance term;

[0165] S3: White noise detection of skip sequences;

[0166] S4: If the stationary difference test of S2 shows a unit root, that is, the time series is non-stationary, the fluctuation of the data is eliminated by difference, where:

[0167] First-order difference formula

[0168] Second-order difference formula

[0169] in, Represents Y t The first-order difference value, Y t Indicates that there is a unit root at time point t in the time series, Y t-1 It indicates that there is a time series with unit root at time point t-1, Represents Y t The second-order difference value, Y t-2 Indicates that there is a unit root at time point t-2 in the time series.

[0170] After the difference, the stationarity test is continued, and so on, until the entire sequence becomes a stationary sequence. The number of differences corresponds to the order d of the ARIMAX (p, d, q) model, and is brought into the subsequent modeling;

[0171] S5: By analyzing the time series autocorrelation function ACF and partial autocorrelation function PACF, the model type and its corresponding parameters are determined;

[0172] The autocorrelation coefficient ACF is used to describe the correlation between the data in different periods, that is, the impact of the historical road speed on the current speed:

[0173]

[0174] Among them, Cov(X t, X t+k ) represents the covariance of the observations at time point t and time point t+k, Var(X t ) represents the time series X t The variance of

[0175] The partial correlation coefficient PACF removes the indirect effect of the intermediate variable when calculating the correlation:

[0176]

[0177] Among them, Cov represents covariance, X t represents the observed value at time point t, X t-1 represents the observed value at time point t-1, X t-(k+1) represents the observed value at time point t-(k+1), E represents the expectation, and Var represents the variance;

[0178] S6: Based on S5, the initial p and q are determined, and the ARIMAX (p, d, q) model is established. Based on the set 95% confidence interval and the test set data, the future data, i.e., the future vehicle speed, is predicted and compared with the real data in a visual way;

[0179] S57: Model optimization, by traversing various combinations of p and q, using the Bayesian Information Criterion BIC to evaluate the model. The smaller the BIC value, the better the model.

[0180] The formula for BIC is as follows:

[0181] BIC = ln(n)*k = 2ln(L)

[0182] Where n represents the number of observed data, k represents the number of estimated parameters in the model, and L represents the maximum log-likelihood of the model fit;

[0183] S58: Based on the optimal combination of p and q, the optimal ARIMAX (p, d, q) model is obtained, and the prediction result of the future road speed is obtained.

[0184] According to the future road speed, the future average speed and future quantile speed are calculated.

[0185] According to the future average vehicle speed, the future quantile vehicle speed and the preset traffic operation status classification table (Table 1), the future road congestion evaluation information is obtained. The road congestion evaluation information and the future road congestion evaluation information include: road traffic congestion situation, urban road traffic congestion ranking, urban road congestion analysis, urban road source tracing analysis, and key AOI surrounding road congestion situation analysis.

[0186] Step S105, obtaining a congestion analysis result according to the road congestion evaluation information.

[0187] Specifically, a visualization system is built to display the results of digital traffic analysis. A visualization system is built to display road traffic congestion. The core functions include urban road traffic congestion ranking, urban road congestion analysis, urban road source tracing analysis, and key AOI surrounding road congestion situation analysis, etc., to support the development of urban traffic business.

[0188] It should be noted that the method of the embodiment of the present invention can be performed by a single device, such as a computer or a server. The method of this embodiment can also be applied in a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present invention, and the multiple devices will interact with each other to complete the described method.

[0189] It should be noted that some embodiments of the present invention are described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0190] The present invention can obtain vehicle network data and urban road network data, ensuring the diversity and real-time nature of the data, helping to more accurately evaluate and predict road congestion, and provide more accurate traffic flow prediction and congestion warning. It can recommend the best driving route based on the user's travel habits and real-time traffic conditions, and provide real-time road condition information and predicted arrival time.

[0191] The road congestion evaluation and prediction method based on the big data of new energy vehicle network has the advantages of data acquisition diversity and real-time, multi-source data fusion analysis, and improved evaluation and prediction accuracy, which helps to improve the intelligence and informatization level of urban traffic management.

[0192] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention (including the claims) is limited to these examples. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present invention as described above, which are not provided in detail for the sake of simplicity.

[0193] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0194] In addition, when specific details are set forth to describe exemplary embodiments of the present invention, it will be apparent to those skilled in the art that embodiments of the present invention may be implemented without these specific details or when these specific details are varied. Therefore, these descriptions should be considered illustrative rather than restrictive. Although the present invention has been described in conjunction with specific embodiments of the present invention, many replacements, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art based on the foregoing description.

[0195] The embodiments of the present invention are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for evaluating road congestion based on big data of new energy vehicle network, characterized in that: include: Acquire the real-time operation data of the new energy vehicle, pre-process the real-time operation data of the new energy vehicle, and obtain a vehicle basic information table; wherein the vehicle basic information table includes: vehicle ID, vehicle model, vehicle type and coordinate system; Acquire urban road network data, parse and process the urban road network data, and obtain a road network information table; wherein the road network information table includes: section ID, section name, name of the road to which it belongs, road ID, road grade, section length, one-way street sign, section sign point sequence number, sign point latitude and longitude, section start number, section end node number, city and district; A vehicle-road matching relationship information table is obtained according to the vehicle operation table and the road network information table; wherein the vehicle-road matching relationship information table includes: a relationship between a vehicle driving position and a road network; Obtaining road congestion evaluation information according to the vehicle-road matching relationship information table; A congestion analysis result is obtained according to the road congestion evaluation information.

2. According to claim 1, a method for evaluating road congestion based on new energy vehicle network big data is characterized in that: Before obtaining the congestion analysis result according to the road congestion evaluation information, the method further includes: The future road speed is obtained according to the vehicle-road matching relationship information table, and the future road congestion evaluation information is obtained according to the future.

3. According to claim 2, a method for evaluating road congestion based on new energy vehicle network big data is characterized in that: The obtaining of the future road speed according to the vehicle-road matching relationship information table and the obtaining of the future road congestion evaluation information according to the future include: Establish vehicle prediction autoregressive difference moving average model; Acquire the historical vehicle speed of the road according to the vehicle-road matching relationship information table, and obtain the future vehicle speed of the road according to the historical vehicle speed of the road through a vehicle prediction autoregressive difference moving average model; Calculating the future average speed and the future quantile speed according to the future road speed; According to the future average vehicle speed and the future quantile vehicle speed, the future road congestion evaluation information is obtained according to a preset traffic operation status level classification table.

4. According to claim 1, a method for evaluating road congestion based on new energy vehicle network big data is characterized in that: The real-time operation data of the new energy vehicle is obtained, and the real-time operation data of the new energy vehicle is preprocessed to obtain the vehicle basic information table, including: Acquire the real-time operation data of new energy vehicles, extract and clean the real-time operation data of new energy vehicles, and match it with the administrative division boundaries to obtain a target city vehicle driving data list; wherein the target city vehicle driving data list includes: vehicle ID, timestamp, vehicle driving latitude and longitude, vehicle speed and vehicle cumulative mileage; The basic vehicle information is collected and managed through the target city vehicle driving data list to obtain a vehicle basic information table.

5. According to claim 1, a method for evaluating road congestion based on new energy vehicle network big data is characterized in that: The obtaining of the urban road network data and the parsing of the urban road network data to obtain the road network information table include: Acquire urban road network data, parse and process the urban road network data, and insert identification points based on the distances of road identification points to obtain a road network information table.

6. According to claim 1, a method for evaluating road congestion based on new energy vehicle network big data is characterized in that: The obtaining of the vehicle-road matching relationship information table according to the vehicle operation table and the road network information table comprises: Obtaining an initial vehicle-road matching result relationship information table according to the vehicle operation table and the road network information table; Deduplication processing is performed on the vehicle-road initial matching result relationship information table to obtain an optimized vehicle-road initial matching relationship information table; According to the optimized vehicle-road initial matching relationship information table, the matching accuracy is improved through a graph shortest path search algorithm to obtain a vehicle-road matching relationship information table.

7. According to claim 6, a method for evaluating road congestion based on new energy vehicle network big data is characterized in that: The vehicle-road initial matching result relationship information table obtained according to the vehicle operation table and the road network information table includes: The vehicle running longitude and latitude are obtained through the vehicle running table, and the vehicle running longitude and latitude are matched with the honeycomb polygon algorithm H3 to obtain the vehicle running H3 grid: vehicle{longitude,latitude}→H3 index Among them, vehicle{} represents the vehicle, longitude represents the longitude of the vehicle, latitude represents the latitude of the vehicle, and H3 index represents the hexagonal code corresponding to the longitude and latitude of the vehicle; The longitude and latitude of the identification point are obtained through the road network information table, and the longitude and latitude of the identification point are matched with the honeycomb polygon algorithm H3 to obtain the identification point H3 grid: path{longitude ′ ,latitude ′ }→H3 index ′ Among them, path{} represents the identification point, longitude ′ Indicates the longitude of the identification point, latitude ′ Indicates the latitude of the identification point, and H3index indicates the hexagonal code corresponding to the longitude and latitude of the identification point; The vehicle travel H3 grid and the identification point H3 grid are matched to obtain the vehicle-road initial matching result relationship information table: vehicle{longitude,latitude}→path{longitude ′ ,latitude ′ } Among them, vehicle{} represents the vehicle, longitude represents the longitude of the vehicle, latitude represents the latitude of the vehicle, path{} represents the identification point, longitude ′ Indicates the longitude of the identification point, latitude ′ Indicates the latitude of the marker point.

8. According to claim 6, a method for evaluating road congestion based on new energy vehicle network big data is characterized in that: The deduplication processing of the vehicle-road initial matching result relationship information table to obtain the optimized vehicle-road initial matching relationship information table includes: Get the serial number list corresponding to all driving points of the vehicle in the Ith period and the I+1th period of the preset specific road section: serial={serial1,serial2,serial3,…,serial n } Among them, serial represents a serial number list, serial n Indicates the sequence number corresponding to the nth driving point; The sequence number difference is calculated based on the sequence number list: in, Indicates the serial number difference, serial t+1 Indicates the serial number at time t+1, serial t Indicates the sequence number at time t; According to the sequence number difference, data is deleted according to the preset deduplication requirement to obtain an optimized vehicle-road initial matching relationship information table.

9. According to claim 6, a method for evaluating road congestion based on new energy vehicle network big data is characterized in that: The vehicle-road matching relationship information table is obtained by improving the matching accuracy through the graph shortest path search algorithm according to the optimized vehicle-road initial matching relationship information table, and includes: Establishing a road network data directed graph according to the optimized vehicle-road initial matching relationship information table; Obtaining a matching starting point and a matching end point of a vehicle driving trajectory according to the road network data directed graph; The shortest path between the starting point and the ending point is established according to the matching starting point and the matching ending point through a graph shortest path search algorithm to obtain a vehicle-road matching relationship information table.

10. The method for evaluating road congestion based on big data of new energy vehicle network connection according to claim 1, characterized in that: The obtaining of road congestion evaluation information according to the vehicle-road matching relationship information table includes: According to the vehicle-road matching relationship information table, the driving time is divided into several time periods according to the preset time window; Obtaining vehicle speeds within a time period, and calculating average vehicle speeds and quantile vehicle speeds based on the vehicle speeds; According to the average vehicle speed and the quantile vehicle speed, the traffic operation status level classification table is used to classify the traffic congestion in the future, so as to obtain the evaluation information of the road congestion in the future.

Images